Evolutionary Reinforcement Learning (ERL) is a new learning paradigm that integrates Evolutionary Algorithm (EA) with Reinforcement Learning (RL). Existing ERL methods encounter a problem of poor balance between individual quality and diversity, which causes experience mismatch where delayed experiences generated by the population hinder the training of the RL agent. To address this problem, we propose a Late-start Clustering Evolutionary Reinforcement Learning (LCERL) algorithm to improve individual quality and diversity, thereby enhancing the synergy between the population and the RL agent. First, a late-start strategy is proposed to avoid the detrimental impact of poor experiences generated by the population on the RL agent’s training in the early stage. Second, a double opposite proximal mutation operator is designed and applied to the RL agent to generate high-quality individuals that are comparable to the RL agent. Third, a clustering selection method with an archive is designed to select diverse individuals for experience generation. Experimental results on the MuJoCo benchmark and a real-world energy management problem demonstrate the superior performance and practicability of LCERL.

This paper proposes an evolutionary contribution and problem heuristic information ensemble-based computing resource allocation scheme for cooperative co-evolutionary algorithms. For problem heuristic information, this paper assembles the correlation sensitivity of variables in each subproblem and the dimension ratio of this subproblem; for evolutionary contribution, this paper assembles the historical and the current evolutionary contributions of each subproblem. By assembling these two crucial factors, the devised method computes the selection probability of each subproblem and then randomly picks one subproblem by the roulette wheel selection strategy to undergo optimization in each iteration. In this way, computing resources are preferentially allocated to those subproblems with high complexity manifested by the problem heuristic information and high fitness improvement reflected by the evolutionary contribution. With this method, cooperative co-evolutionary algorithms expectedly fully utilize the computing resources to achieve satisfactory performance in addressing large-scale optimization problems. By combining the devised method with 6 latest decomposition methods along with two evolutionary optimizers, this paper has conducted experiments to compare it with 7 state-of-the-art computing resource allocation methods on two popular suites of large-scale optimization problems. Experimental results have proved that the devised method outperforms the 7 compared methods in helping cooperative co-evolutionary algorithms achieve better performance.

The development of multiagent systems (MASs) has given rise to a new type of traveling salesman problem (TSP), namely the multiagent TSP (MATSP). MATSP aims to find multiple routes with the minimum total cost through the cooperation of intelligent agents. Since the distributed nature of MATSP, it is challenging to solve MATSP effectively in a distributed manner. This article focuses on MATSP and proposes a distributed ant colony system with pheromone transfer (DACS) to solve the problem. First, we formally define MATSP, in which each agent has only partial data and independently makes routing decisions. All agents cooperate to make a consensus on the visiting conflicts caused by the loss of global information. To further consider the balanced workloads of agents, the fairness-aware colored MATSP is further formulated. Second, to solve MATSP in a distributed manner, the proposed DACS allows each agent to run an ant colony optimizer and be responsible for the routing under its jurisdiction. To coordinate these agents to avoid conflicts, a bidding-based cooperation mechanism (BCM) is designed to reach a consensus on the allocation of cities. Agents bid for the accessibilities of cities based on market-based economic theory, owning the ability to adapt to complex environments. Two pheromone transfer strategies are designed to improve efficiency. DACS transfers learned pheromones within the same agent and between different agents. Besides, we conduct extensive experiments in nine datasets to certify the effectiveness of DACS. Experimental results show that DACS is effective and efficient even in complex environments.

The research on home energy management systems (HEMSs) has attracted wide attention because of the development trend of urban smart buildings. However, coordinating various homes is a nontrivial task due to uncertainties regarding renewable energy, user behavior, and the concern of privacy disclosure. The complex properties of household appliances further put forward requirements for the decision-making procedure. To solve these, this article proposes a novel federated transfer framework based on a teacher–student learning paradigm for the energy optimization process. The pretrained model based on an open-source building environment is introduced to assist the learning procedure under a cross-domain adaption mechanism, which avoids the time-consuming learning process from scratch. Considering household appliance discrepancies, a hybrid proximal policy optimization method with discrete-continuous action space is proposed to schedule these devices optimally. Extensive experiments have demonstrated the effectiveness of our proposed method in terms of training performance, cost efficiency, and comfort level.

A significant challenge in fog computing is task allocation, in which computing tasks are assigned to distributed nodes for processing. This problem is NP-hard and involves multiple conflicting objectives. Although some studies have considered these objectives jointly, effectively balancing them while honoring user preferences remains difficult. In this paper, we consider the effect of marginal utility on achieving multi objective balance under user preferences, and formulate a multi objective task allocation problem for fog computing. We introduce a knee-driven set-based level-based learning optimizer (KSLLSO) to find preferred solutions. The knee-point driven strategy identifies regions with high marginal utility, while the set-based operators and level-based learning strategy efficiently search the discrete decision space. Moreover, a constructive solution generation approach and a capacity-guided allocation strategy allow KSLLSO to exploit problem structure and improve optimization performance. Comprehensive experiments comparing KSLLSO with classical and recent methods demonstrate the effectiveness of the proposed approach.

Crowdsourcing leverages the collective intelligence of the crowd to collect data and solve complex computational tasks. Driven by this paradigm, data can now be gathered more efficiently and at larger scales, thereby increasing the need for effective dimensionality reduction, which makes feature selection (FS) essential for efficient learning. In this paper, we refer to the problem in which multiple workers in a crowdsourcing environment collect data and concurrently optimize FS as the crowdsourcing feature selection (CFS) problem. In CFS, workers perform FS on local data and upload candidate feature subsets to complete the outsourced task. Nevertheless, the heterogeneity across multiple data sources hinders the formation of a reliable and high-quality consensus solution. To address this issue, we propose a cooperative learning-based Distributed Evolutionary Algorithm for the CFS problem (DEA-CFS). First, we formulate the CFS problem and define the roles of workers and the server, as well as their interactions in a crowdsourcing environment. Second, on the worker side, we design a distributed cooperative learning strategy that refines local solutions and mitigates data heterogeneity through confidence-aware fitness comparison. Third, on the server side, we introduce an adaptive credibility-based aggregation mechanism that aggregates a robust consensus solution. Extensive experiments on 18 datasets with up to 10,000 features demonstrate the efficiency and effectiveness of DEA-CFS. Specifically, compared to four existing distributed baselines, DEA-CFS achieves a superior average rank of 1.16 and obtains the best performance on 15 of the 18 datasets.

Urban customized bus (UCB) has become an important mode of urban transportation in recent years. To further enhance the applicability of UCB, we develop a UCB model that accommodates flexible pick-ups and drop-offs in this article. In our model, when a bus passes through a station, it can drop off passengers whose destination is exactly this station and pick up new passengers as long as constraints are satisfied. By eliminating fixed boarding and alighting regions that were commonly adopted in prior studies, we can provide travel services for both prebooked and real-time orders across broader temporal and spatial ranges. Under such a scenario, it is more challenging to decide when and where to pick up which passenger with which bus, and which route the bus chooses. To solve these intractable problems, we proposed an approach including passenger assignment and route design. For passenger assignment, we devise an ant colony system (ACS) method and a greedy method to assign prebooked and real-time passengers to buses, respectively. ACS represents the correlation among different passengers numerically through a pheromone matrix and updates it iteratively based on the good results. Therefore, prebooked passengers with higher correlations are more likely to be assigned to the same buses. The greedy method always selects passengers with the highest heuristic value to have a fast response in real-time passenger assignment. For route design, we adapt a Dijkstra-based greedy method to efficiently design routes for each bus in both static and dynamic situations. At last, experiments based on both generated data and real data demonstrate the superiority of the proposed method.

Reinforcement learning (RL) has shown promising performance in tackling robotic manipulation tasks (RMTs), which require learning a prolonged sequence of manipulation actions to control robots efficiently. However, most RL algorithms often suffer from two problems when solving RMTs: inefficient exploration due to the extremely large action space and catastrophic forgetting due to the poor sampling efficiency. To alleviate these problems, this paper introduces an Evolutionary Reinforcement Learning algorithm with parameterized Action Primitives, called ERLAP, which combines the advantages of an evolutionary algorithm (EA) and hierarchical RL (HRL) to solve diverse RMTs. A library of heterogeneous action primitives is constructed in HRL to enhance the exploration efficiency of robots and dual populations with new evolutionary operators are run in EA to optimize these primitive sequences, which can diversify the distribution of replay buffer and avoid catastrophic forgetting. The experiments show that ERLAP outperforms four state-of-the-art RL algorithms in simulated RMTs with dense rewards and can effectively avoid catastrophic forgetting in a set of more challenging simulated RMTs with sparse rewards.

To efficiently tackle problems with multiple conflicting objectives, several Multi-Objective Reinforcement Learning (MORL) algorithms utilize a universal policy network that takes preference weights as input to represent optimal policies for all different preferences. However, it is quite challenging to train such a universal policy as it is easy to forget or fail to learn skills for some preferences. To alleviate this issue, we propose an efficient Population-Based MORL (PB-MORL) method that trains multiple agents with universal policy networks using a shared replay buffer. Each agent is biased towards optimizing specific objectives by applying differentiated weights to the rewards sampled from the buffer. Therefore, the policy of each agent only needs to handle the specific part of the preference space rather than the entire space, simplifying the training task. Meanwhile, the experiences in the common buffer facilitate the information sharing among individuals, which can significantly reduce the number of interaction steps for training multiple agents. Experiments on both continuous and discrete tasks demonstrate the superiority of PB-MORL over several state-of-the-art MORL methods.

Designing effective black‑box optimizers is hampered by limited problem-specific knowledge and manual control that spans months for almost every detail. In this paper, we present DesignX, the first automated algorithm design framework that generates an effective optimizer specific to a given black-box optimization problem within seconds. Rooted in the first principles, we identify two key sub-tasks: 1) algorithm structure generation and 2) hyperparameter control. To enable systematic construction, a comprehensive modular algorithmic space is first built, embracing hundreds of algorithm components collected from decades of research. We then introduce a dual-agent reinforcement learning system that collaborates on structural and parametric design through a novel cooperative training objective, enabling large-scale meta-training across 10k diverse instances. Remarkably, through days of autonomous learning, the DesignX-generated optimizers continuously surpass human-crafted optimizers by orders of magnitude, either on synthetic testbed or on realistic optimization scenarios such as Protein-docking, AutoML and UAV path planning. Further in-depth analysis reveals DesignX's capability to discover non-trivial algorithm patterns beyond expert intuition, which, conversely, provides valuable design insights for the optimization community. We provide DesignX's Python project at~\url{https://github.com/MetaEvo/DesignX}.

Surrogate model-assisted evolutionary algorithm (SAEA) has become a generalized method for expensive optimization problems (EOPs) with high-cost evaluations. However, most existing SAEAs retrain surrogate models frequently during evolutionary iterations. Besides, the quality of sample data directly affects model accuracy, leading to difficulties in finding the optimal solution. To address these challenges, this paper introduces the tree-based broad learning system (TBLS) as the surrogate model into SAEA framework, and a TBLS-assisted optimizer with incremental learning (TBLSO-IF) is proposed. First, an incrementable TBLS is constructed for predicting the quality of the solution, and the model is incrementally updated by expanding the layer nodes when the samples increase. And then effectively avoids the high computational costs of retraining models from scratch and significantly improves the update efficiency of surrogate models. Second, an adaptive sample augmentation (ASA) strategy is designed to generate more samples for updating the TBLS using a variational autoencoder (VAE). Experiments on 15 problems in the CEC2017 benchmark functions show that the proposed TBLSO-IF algorithm is more effective and competitive than the other five state-of-the-art SAEA methods.

Crowdsourcing has become a powerful tool for data collection and problem-solving, harnessing collective intelligence to address complex tasks. Building knowledge bases through such intelligence is gaining attention to enhance cross-domain model performance. As an essential technique for dimensionality reduction, the task of feature selection (FS) also emerges in the context of crowdsourcing, resulting in crowd-sourcing feature selection (CFS). Due to the diversity of workers and the varying quality of data in a crowdsourcing environment, CFS faces challenges such as heterogeneous data reliability and dynamic participation. To tackle these issues, we present Crowd-Fed Evolutionary Transfer Optimization (CFETO), an efficient and crowdsourcing-enhanced framework for feature selection. CFETO comprises a central server and multiple distributed workers: workers perform local data collection and optimization, extracting knowledge from their datasets, while the server integrates this knowledge to build a knowledge base. An evolutionary transfer learning strategy is further employed to harness this knowledge, thereby improving both convergence speed and selection robustness. Experiments on 20 real-world datasets show that CFETO outperforms traditional centralized FS methods approaches, underlining its potential for broader application in complex, distributed crowdsourcing scenarios.

Recent years have witnessed the increasing adoption of unmanned aerial vehicles (UAVs) for power grid inspection, as they gradually replace conventional hazardous manual operations. However, conventional metaheuristics and operations research-based path planning algorithms suffer from long computation times for large-scale problems, thus making them unsuitable for real-time multi-UAV scheduling under flight time and energy consumption uncertainty. To solve the multi-UAV online path planning problem, this paper proposes a multi-agent deep reinforcement learning (MADRL) algorithm that performs online path planning based on real-time environmental and UAV state information, with the goal of minimizing the total travel distance. We employ resource preservation and decision sharing to handle real-time cooperation under travel time uncertainty while preventing resource conflicts. We design a Safety Mask mechanism that constrains dangerous UAV actions to address energy consumption uncertainty. Experiments on instances with 40-400 towers show that our algorithm requires minimal computation time and generates higher-quality solutions compared to other baseline algorithms in large-scale tower scenarios.

The influence maximization (IM) problem in large-scale social networks has attracted great attention. Considering the interactions among multiple online social platforms, the multilayer IM problem poses further challenges ($\rm i.e.,$high-simulation burden and low-optimization quality). To solve these problems, this article proposes a susceptible-exposed-infected1-infected2-infected12-vigilant (SE3IV) model to simulate the information spreading process in multilayer networks. The spreading dynamic is modeled by mean-field equations considering the effect of cross-layer propagation. To optimize the multilayer information maximization modeled by SE3IV, an asynchronous distributed cooperative coevolutionary algorithm (ADCA) is proposed. To improve the efficiency of the algorithm in multilayer networks, the multilayer community detection first decompresses the network into a single layer by dimension-based method. Then, the Louvain method is adopted to decompose the problems into subcomponents with lower dimensionality. The populations with the same size evolve corresponding subcomponents in an asynchronous and distributed way based on the pool model. Besides, an asynchronous communication mechanism is devised to manage the communication among the shared pool. An adaptive seeds regulation strategy is designed to adjust the number of seeds of subcomponents. Numerous experiments on different networks show that ADCA possesses good scalability and efficiency, especially in large-scale networks.

In expensive multi/many-objective optimization problems (EMOPs), the expensive objectives are generally accessed through different simulation tools, leading to different evaluation latencies and unbearable computational time for serial optimization. One promising approach to improve efficiency is to perform simulation and build surrogates separately for each objective in parallel. However, how to improve the model accuracy and select promising candidates without global information are big challenges. To alleviate these problems, this article proposes an asynchronous influence-based SAEA (AIEA) based on the client-server model. Each client approximates an objective and the server takes charge for evolution. To adaptively select promising candidates, the influence degree is introduced in candidate selection, which is calculated in the objective space to judge which candidate has more beneficial influence for evolution. With the selected candidate, the most-uncertain-first strategy is devised in objective selection for asynchronous evaluations and model improvement. To handle incomplete objective values, the nearest neighbor inheritance is adopted for unevaluated objectives. Comprehensive experiments compared with five surrogate-assisted EAs demonstrate the global optimization and scalability of AIEA.

In recent years, black-box distributed optimization (DBO) has been widely studied to solve complex optimization problems in multi-agent systems, such as hyperparameter optimization of distributed machine learning. However, most existing methods use a fixed or diminishing step size to sample and search in the black box optimization space, which makes it challenging to maintain optimization efficiency on different optimization problems. In this work, we propose a multi-agent evolution strategy with cooperative and cumulative step adaptation (). In, each agent executes the algorithm to sample and explores its local objective function, and communicates with other agents to optimize the global objective function cooperatively, which is the sum of local objective functions. To improve the sampling adaptability, we design a cooperative and cumulative step adaptation method (CCSA) consisting of inner adaptation and outer adaptation. By detecting the evolution path of the multi-agent system, CCSA decreases the step size when the evolution directions of agents are conflicting and increases the step size when consistent. In terms of theoretical analysis, we first discuss the working principle of CCSA, and then discuss the system consensus of . In terms of experimental verification, achieves better consensus performance and competitive solution quality compared with state-of-the-art algorithms for DBO.

Distributed optimization has attracted lots of attention in recent years. Thanks to the intrinsic parallelism and great search capacity, evolutionary computation (EC) has the potential for black-box and non-convex distributed optimization. However, due to the decentralization of local objective functions, it is challenging to optimize the global objective function with efficient communication and guaranteed system consensus. To tackle this challenge, we propose a Multi-Agent Swarm Optimization method with adaptive Internal and External learning (MASOIE). In MASOIE, each agent evolves a swarm of particles by internal learning and external learning. Internal learning enables agents to optimize their local objectives, while external learning enables agents to cooperate to achieve a consensus toward the global objective. To improve the consensus ability, we design a special velocity setting of external learning for particle evolution. We provide the theoretical analysis of the system consensus of deterministic MASOIE. To improve communication efficiency, we design an adaptive communication mechanism to adjust the communication interval, enabling agents to explore at the early stage and reach system consensus at the later stage. Empirical studies show that the proposed algorithm achieves stable consensus performance, competitive solution quality and lower communication cost on benchmark functions compared with existing black-box distributed algorithms.

Surrogate-assisted evolutionary algorithms (SAEAs) have achieved effective performance in solving complex data-driven optimization problems. In the Internet of Things environment, the data of many problems are collected and processed in distributed network nodes and cannot be transmitted. As each local node can only access and build surrogate models based on partial data, local models are usually not accurate and even conflicting. To address these challenges, this paper proposes a classifier-ensemble-based surrogate-assisted evolutionary algorithm (CESAEA) with the following features. First, the local nodes in CESAEA train classifiers as surrogate models based on their own data to classify candidates into several levels according to their fitness quality. The classifiers are less sensitive to the partial and biased data than regression models in local nodes. Second, the central node in CESAEA ensembles the local surrogates to form a global classifier with a relaxation condition to guide the evolutionary optimizer to generate promising candidates. The relaxation condition helps to overcome the problem of local model inconsistency. Overall, CESAEA is composed of local classifier construction, global classifier ensemble, classifier-assisted evolutionary optimization and local regression-assisted selection. As only classifiers are allowed to transmit from local nodes to the central node, the mapping relationship between decision vector and objective is hidden and thus data privacy is protected. The experimental results on benchmark functions as well as distributed feature selection problems verify the effectiveness of CESAEA compared to several state-of-the-art approaches.

Neural solvers (NSs) based on the attention mechanism have demonstrated remarkable effectiveness in solving routing problems like traveling salesman problems (TSPs) and vehicle routing problems (VRPs). However, in the generalization process, we find a phenomenon of the dispersion of attention scores in existing NSs, which leads to poor performance. To improve the generalization ability of NSs, this article proposes a distance-aware attention reshaping (DAR) method. Specifically, without increasing any parameter of the neural network (NN), we utilize the distance information between nodes to adjust attention scores. This enables an NS trained on small-scale instances with a certain distribution to make rational choices when solving large-scale problems with different distributions. Its effectiveness is verified both theoretically and empirically. Extensive experiments on the TSP, asymmetric TSP (ATSP), capacitated VRP (CVRP), VRP with time windows (VRPTW), capacitated arc routing problem (CARP), and knapsack problem (KP) demonstrate the advantages of our method. Our code is available at https://github.com/ftwangyang/DAR.

The shared replay buffer is the core of synergy in evolutionary reinforcement learning (ERL). Existing methods overlooked the objective conflict between population evolution in evolutionary algorithm and ERL, leading to poor quality of the replay buffer. In this article, we propose a strategic ERL algorithm with operator selection and experience filter (SERL-OS-EF) to address the objective conflict issue and improve the synergy from three aspects: 1) an operator selection strategy is proposed to enhance the performance of all individuals, thereby fundamentally improving the quality of experiences generated by the population; 2) an experience filter is introduced to filter the experiences obtained from the population, maintaining the long-term high quality of the buffer; and 3) a dynamic mixed sampling strategy is introduced to improve the efficiency of RL agent learning from the buffer. Experiments in four MuJoCo locomotion environments and three Ant-Maze environments with deceptive rewards demonstrate the superiority of the proposed method. In addition, the practical significance of the proposed method is verified on a low-carbon multienergy microgrid (MEMG) energy management task.

Multipoint dynamic aggregation (MPDA) is a multirobot task allocation problem, which requires the collaborative scheduling of multiple robots to complete time-varying tasks distributed on a map. Most existing studies consider the scenarios with homogeneous robots and tasks. To model the application scenarios where different types of robots are required, we propose a heterogeneous MPDA problem, which incorporates different types of robots and tasks with dependency. Correspondingly, a novel metaheuristic algorithm called multistage particle swarm optimization is designed and consists of two parts: 1) a multistage strategy and 2) a specially designed particle swarm optimization (PSO) algorithm. The multistage strategy imposes temporary constraints to force cooperation between robots, which can reduce and smoothen the search space. The proposed PSO contains a mixed updating mechanism consisting of a continuous velocity updating rule and a discrete position updating rule, which is effective for updating the permutation-based solutions of MPDA. The experiments on a newly designed benchmark test set show that the proposed algorithm is more effective and efficient than the state-of-the-art methods.

Crowd management plays a crucial role in improving travel efficiency and reducing potential risks caused by overcrowding in large public places. Crowd control at entrances is a common way in our daily life to avoid overcrowding, but nowadays the control of crowd inflow at the entrances of public places mainly relies on manual operation. In this article, we intend to propose a dynamic crowd inflow control system (DRIFT) to avoid risks of overcrowding and improve the throughput of public places. First, we formulate an optimization problem that maximizes throughput by adjusting the crowd inflow rate of each entrance in the public place. Through mathematical analysis and related proofs, we introduce a baseline for the aforementioned problem that can calculate the upper bound of static inflow rate. With this baseline, we can easily measure the performance of other dynamic inflow control algorithms. Second, we treat the proposed optimization problem as a real-time decision-making problem, and further propose the DRIFT system based on deep reinforcement learning to address it. Specifically, the strategy of DRIFT is a basic actor-critic framework adapting a shared long short term memory (LSTM) layer to extract scene feature information. Third, we train it through proximal policy optimization (PPO) to improve learning performance. The environment for experiments is a crowd simulation model of OpenAI Gym structure based on real scene data from the 1F floor of the Chengdudong Railway Station and Xizhimen Railway Station. In comparison experiments and ablation experiments, the strategy of our DRIFT outperforms all other comparison strategies, including the most recent strategy using reinforcement learning, in term of system crowd throughput and robustness.

Recently, an emerging research direction called Evolutionary Reinforcement Learning (ERL) has been proposed, which combines evolutionary algorithm with reinforcement learning (RL) for tackling the tasks of sequential decision making. However, the recently proposed ERL algorithms often suffer from two challenges: the inaccuracy of policy estimation caused by the overestimation bias in RL and the insufficiency of exploration caused by inefficient mutations. To alleviate these problems, we propose an Evolutionary Reinforcement Learning algorithm enhanced with Truncated variance and Distillation mutation, called ERL-TD. We utilize multiple Q-networks to evaluate state-action pairs, so that multiple networks can provide more accurate evaluations for state-action pairs, in which the variance of evaluations can be adopted to control the overestimation bias in RL. Moreover, we propose a new distillation mutation to provide a promising mutation direction, which is different from traditional mutation generating a large number of random solutions. We evaluate ERL-TD on the continuous control benchmarks from the OpenAI Gym and DeepMind Control Suite. The experiments show that ERL-TD shows excellent performance and outperforms all baseline RL algorithms on the test suites.

The integration of Evolutionary Algorithm (EA) and Reinforcement Learning (RL) has emerged as a promising approach for tackling some challenges in RL, such as sparse rewards, lack of exploration, and brittle convergence properties. However, existing methods often employ actor networks as individuals of EA, which may constrain their exploratory capabilities, as the entire actor population will stop evolution when the critic network in RL falls into local optimal. To alleviate this issue, this paper introduces a Two-stage Evolutionary Reinforcement Learning (TERL) framework that maintains a population containing both actor and critic networks. TERL divides the learning process into two stages. In the initial stage, individuals independently learn actor-critic networks, which are optimized alternatively by RL and Particle Swarm Optimization (PSO). This dual optimization fosters greater exploration, curbing susceptibility to local optima. Shared information from a common replay buffer and PSO algorithm substantially mitigates the computational load of training multiple agents. In the subsequent stage, TERL shifts to a refined exploitation phase. Here, only the best individual undergoes further refinement, while the rest individuals continue PSO-based optimization. This allocates more computational resources to the best individual for yielding superior performance. Empirical assessments, conducted across a range of continuous control problems, validate the efficacy of the proposed TERL paradigm.

The vehicle routing problem with simultaneous pickup-delivery and time windows (VRPPDTW) is applicable to a wide range of practical scenarios within the domains of transportation and logistics. When addressing this complex problem, conventional heuristic algorithms have exhibited limitations in effectiveness, primarily due to the need for expert knowledge in heuristic design, which often prioritizes immediate improvements and leads to convergence towards local optima. To overcome this challenge, we propose a deep Q-network-based iterated local search algorithm (DQN-ILS). This algorithm employs a deep Q-learning network to automatically learn a policy for selecting heuristics to improve the current solution. Simultaneously, an adaptive perturbation strategy is designed to avoid becoming trapped in local optima. In this way, our algorithm can better balance the trade-off between exploration and exploitation when solving VRPPDTW. Experimental studies conducted on a real test suite of large-scale VRPPDTW instances validate the superiority of the proposed DQN-ILS over several recently proposed methods.

Genetic programming (GP) hyper-heuristic method has been extensively studied to solve multiple dynamic job shop scheduling tasks by generating an effective heuristic for each task simultaneously. However, a fundamental question has not been answered. Do we need to customize a specific heuristic for each task? To fill this research gap, we propose to generate a single heuristic for handling multiple tasks. Without designing complex evolution mechanisms, only during the evaluation process of GP, the fitness of a heuristic is evaluated by multiple tasks. Since there are multiple tasks, a heuristic has multiple objective values. A rank aggregation (RA) fitness evaluation strategy is designed to convert multiple objective values of multiple tasks into a fitness value for a single heuristic. To validate the effectiveness of the generated solution and the proposed RA strategy, we design multitask scenarios that encompass tasks with diverse objectives, utilization levels, and maximum operation times. The results demonstrate that the performance of the single heuristic generated in multitask scenarios is comparable to solutions generated by GP using the single-task learning paradigm, meaning that with an appropriate training method, GP can generate a heuristic with good generality.

As electric vehicles become more prevalent, a novel vehicle routing problem (VRP) has emerged, known as the capacitated electric VRP (CEVRP). CEVRP requires determining not only the service order of customers but also the charging plans for vehicles, thereby increasing the complexity of solution construction. In response to this challenge, we propose a bilevel hybrid genetic algorithm (BHGA). BHGA models CEVRP as two levels of subproblem: 1) the upper level capacitated VRP, focusing on the service order and 2) the lower level fixed route vehicle charging problem, focusing on the charging plans. In dealing with the upper level subproblem, the hybrid genetic search algorithm is adopted to construct the routes to visit customers and an advanced screening strategy is proposed to optimize the local search process and effectively guide the evolution of population. For the lower level subproblem, an efficient heuristic method called focus enumeration is designed, which is specifically used to insert charging stations into routes to ensure battery constraint. The collaboration of the advanced screening strategy and the focus enumeration assists in more unified solving of the two subproblems. The experiments show that BHGA significantly surpasses state-of-the-art algorithms on benchmark instances and has successfully updated eleven best known solutions, demonstrating its outstanding performance.

The emergence of the last-mile delivery by unmanned aerial vehicles (UAVs) has gained widespread attention in both scientific and industrial communities in recent years. The problem can be modeled as a mixed linear integer programming problem to minimize the routing cost to serve all customers and the number of UAV launches. Considering the complexity of the multi-depot, multi-UAV, and multi-customer pickup and delivery integrated scheduling problem, this paper proposes a novel two-stage order-aware adaptive iterative local search metaheuristic algorithm to solve this problem. In the first stage, tasks are assigned to different depots, transforming the complex original problem into multiple single depot scheduling problem. In the second stage, an order-aware adaptive iterative local search (OAILS) metaheuristic is designed to optimize the route planning for each depot's UAVs. In AILS, we propose a novel order-based adaptive operator selection named (OAOS) to select the appropriate operator based on the recent performance of operator and the order relationships of operators. Finally, a series of experiments were conducted to verify the effectiveness of the proposed OAOS and OAILS methods.

The Vehicle Routing Problem with Simultaneous Pickup-Delivery and Time Windows (VRPSPDTW) is a highly challenging issue in complex logistics distribution scenarios, requiring an optimal balance between cost and efficiency. Traditional methods often rely on single heuristic or metaheuristic algorithms, which perform not so well when dealing with VRPSPDTW. To overcome this challenge, we propose a deep reinforcement learning-based multi-agent algorithm (DRL-MA) to tackle the VRPSPDTW. Our algorithm includes explorative, exploitative, and perturbative agents, which are responsible for balancing exploration and exploitation. The action space of each agent comprises a combination of neighborhood operators, and then the Deep Q-network (DQN) is used to learn effective neighborhood transition sequences from a long-term perspective, which can effectively explore large and complex solution spaces. The cooperation and competition among agents during the search process offer a more flexible and effective strategy. Experimental studies conducted on a real test suite of large-scale VRPSPDTW instances validate the superiority of our proposed DRL-MA over some state-of-the-art algorithms.

The widespread adoption of social networks facilitates the dissemination of authentic information while also accelerating the spread of misinformation, such as rumors. The propagation of positive information can enhance user awareness and mitigate the hazards of misinformation. The misinformation containment (MC) problem aims to identify a set o$k$nodes that initiate the spread of positive information, maximizing its influence while minimizing the hazards of misinformation. The greedy approach, which employs extensive Monte Carlo simulations to estimate influence, is time-consuming and can only prioritize either propagation or containment, but not both. This paper studies the MC problem under competitive activation models. Based on geometric models of probability, we calculate the approximate probabilities of nodes being activated by positive information and misinformation at various times. Taking into account the two-hop theory, we propose a consistent and efficient computational method to assess node influence distribution from the perspectives of propagation and containment. This method strikes a balance between propagation and containment, surpassing degree centrality, further informing a heuristic solution to the MC problem. The heuristic solution's overall performance surpasses that of greedy approaches, which can only prioritize one aspect. Experiments on real-world networks demonstrate that our approach effectively balances the propagation of positive information and misinformation containment with low time complexity.

Traffic signal control (TSC) problems have received increasing attention with the development of the smart city. Reinforcement learning (RL) models TSC as a Markov decision process and learns the timing relationship of traffic scheduling from massive historical data. Due to the uncertainty and mutability of TSC problems, existing RL methods face bottlenecks in diversity and are easy to be trapped into local optima. To alleviate this predicament, this paper combines evolutionary optimization and RL to propose an evolutionary algorithm-assisted reinforcement learning (EARL-Light) method for TSC problems. EARL-Light is a population-based algorithm, in which one individual represents a policy and a population of individuals are evolved to search for near-optimal policies. The diversified search ability of evolutionary optimization can help the algorithm get rid of local optima for global optimization and the rapid learning based on the gradient of RL can achieve fast convergence. Extensive experiments on seven real-world traffic datasets demonstrates that EARL-Light achieves shorter travel time with fast convergence.

Target tracking has broad applications like disaster relief, and unmanned aerial vehicles (UAVs) have been universally applied in target tracking in recent years. Due to the strong responsiveness to deceptive reward signals and diverse exploration, evolutionary reinforcement learning (ERL) is a more noteworthy option for training UAVs than common reinforcement learning. However, for ERL contains too many neural networks, its training efficiency is not satisfactory enough. To address this shortcoming, this paper proposes an evolutionary reinforcement learning with double replay buffers (ERLDRB) for UAV online target tracking problem. Firstly, considering the energy consumption and the possible delay of feedback signals to the UAV, a more realistic model of UAV online target tracking problem is designed. Then based on the problem formulation, ERLDRB utilizes a double experience replay buffers technique to increase learning efficiency in the training stage, which can better solve real-world UAV online target tracking problem. Simulation results show that ERLDRB outperforms multiple contrasting algorithms on the designed model.

The formation of information cocoons, driven by limited disclosure and individual preferences, has resulted in the polarization of society. However, the underlying mechanisms and pathways to escape these cocoons remain unresolved. This article aims to solve it by developing an adaptive imitation process. In this process, the measurement of information cocoons across the population is based on Shannon’s information entropy, taking into account neighborhood information. Incorporating the Dirac function to formulate information distribution over networks, theoretical results are validated by numerical simulation experiments. Results show that individual backgrounds and preferences are crucial factors in the formation of information cocoons, and the severity of information cocoon production increases with an individual capacity to stick to oneself. Encouraging connections among diverse communities can effectively mitigate the intensity of information cocoons. This research contributes to the advancement of computational communication systems and offers insights toward dismantling informational boundaries.

Traffic assignment problem (TAP) is of great significance for promoting the development of smart city and society. It usually focuses on the deterministic or predictable traffic demand and the vehicle traffic assignment. However, in the real world, traffic demand is usually unpredictable, especially the foot traffic assignment inside buildings such as shopping malls and subway stations. In this work, we consider the dynamic version of TAP, where uncertain commuters keep entering the traffic network constantly. These dynamically arriving commuters bring new challenges to this problem where planning paths for each commuter in advance is incompetent. To address this problem, we propose a genetic programming (GP) hyper-heuristic method to assign uncertain commuters in real-time. Specifically, a low-level heuristic rule called reactive assignment strategy (RAS) is proposed and is evolved by the proposed method. All commuters obey the same strategy to route themselves based on their local observations in a traffic network. Through training based on a designed heuristic template, all commuters will have the ability to find their appropriate paths in real-time to maximize the throughput of the traffic network. This decentralized control mechanism can address dynamically arriving commuters more efficiently than centralized control mechanisms. The experimental results show that our method significantly outperforms the state-of-the-art methods and the evolved RAS has a certain generalization ability.

The rapid development of online social networks (OSNs) has facilitated people to express opinions and share information. To optimize the utility of information dissemination in OSNs, problems such as influence maximization have received increasing attention in recent years. However, not only positive information but also negative information is spreading in OSNs. The dissemination of positive and negative information interacts with each other, making network dissemination analysis and utility optimization more challenging. To this end, we develop a negative–neutral–positive–susceptible (NNPS) model and propose a max–min ant system algorithm with a repetitive influence reduction strategy (MMAS-RIR). First, an NNPS model with a novel heterogenous influence indicator is constructed to simulate the interactive dissemination of positive and negative information. The influence of each user’s neighbors on each user is treated differently, producing heterogenous state transition probabilities for users. Second, we formulate the control of information dissemination as an optimization problem with a designed control scheme. The disruption strategy and counterbalance strategy are automatically implemented on the selected users according to their states in the control scheme. Third, we specially develop a MMAS-RIR algorithm for the formulated problem, where the repetitive influence reduction strategy is used to reduce the influence repeated range of the connected users. Moreover, to improve the exploitation, an adaptive local search is added in MMAS-RIR. Finally, various experiments are conducted to validate the effectiveness of our work.

Emerging infectious diseases pose a growing threat to human society and have sparked extensive public discussions on social media. Although numerous efforts have been made in health data mining on social media, there is a lack of focus on quantitative comparisons across multiple platforms, despite their crucial role in the holistic social communication system. This study addresses this gap by developing a generalized regression model that considers the distinct attributes of social media platforms, including short-text, long-text, and Eastern or Western orientation. Using Monkeypox as an application case, this study examines differences among platforms based on four factors: user characteristics, text topics, text emotion, and text quality. The modeling and regression results reveal significant heterogeneity in public opinion expressions across different platforms, particularly between long-text and short-text platforms. Users on short-text platforms are more exposed to diverse information and tend to be susceptible to emotionally provocative content. On the other hand, users on long-text platforms prefer in-depth discussions and show greater receptivity to content infused with positive emotions. This study reveals the information bias brought by platform differences and contributes to data-driven modeling in social communication systems.

Collective decision-making problems consisting of individual decisions are commonly seen in social applications. In this article, the vehicle energy station distribution problem (VESDP) is considered, which is modeled as a network-based collective decision-making problem fulfilling consumers’ requirements by arranging the distribution of energy stations rationally. This problem involves the game among the government and energy station investors. The government intends to maximize the satisfaction of both gas and electric vehicle (EV) customers through policy guidance, while investors aim to maximize their own profits. To solve this problem, we propose an individual evolutionary game model guided by global evolutionary optimization with the following three features. From the individual perspective, we use a network-based evolutionary game with a confidence mechanism to describe the behavior of investors. From the global perspective, we design a genetic algorithm to find out the global-optimized program, which considers the satisfaction of all customers. To heal the divergence between these two perspectives, we design a policy formulation method for the government to motivate selfish investors to adopt strategies in accordance with the overall interests of all customers by using subsidies and taxation. Experiments are performed on both square grid and real-world networks. Experimental results demonstrate the effectiveness of the proposed model.

Crowd navigation path planning is important in public scenes. Existing strategies are mainly based on manual design, which is not flexible or effective enough. This article proposes an evolutionary framework for automatic crowd navigation path planning in public scenes. The proposed framework contains a new fitness evaluation mechanism that can quantitatively evaluate the quality of a path planning strategy by considering both crowd safety and flow speed. Based on the fitness evaluation mechanism, a framework based on multiobjective differential evolution (DE) is developed to efficiently evolve path planning strategies. Simulation results on two synthetic scenes and a real-world metro station scene show that the proposed framework can provide good path planning strategies.

Binary hashing is an effective approach for content-based image retrieval, and learning binary codes with neural networks has attracted increasing attention in recent years. However, the training of hashing neural networks is difficult due to the binary constraint on hash codes. In addition, neural networks are easily affected by input data with small perturbations. Therefore, a sensitive binary hashing autoencoder (SBHA) is proposed to handle these challenges by introducing stochastic sensitivity for image retrieval. SBHA extracts meaningful features from original inputs and maps them onto a binary space to obtain binary hash codes directly. Different from ordinary autoencoders, SBHA is trained by minimizing the reconstruction error, the stochastic sensitive error, and the binary constraint error simultaneously. SBHA reduces output sensitivity to unseen samples with small perturbations from training samples by minimizing the stochastic sensitive error, which helps to learn more robust features. Moreover, SBHA is trained with a binary constraint and outputs binary codes directly. To tackle the difficulty of optimization with the binary constraint, we train the SBHA with alternating optimization. Experimental results on three benchmark datasets show that SBHA is competitive and significantly outperforms state-of-the-art methods for binary hashing.

Evolutionary algorithms (EAs), such as the genetic algorithm (GA), offer an elegant way to handle combinatorial optimization problems (COPs). However, limited by expertise and resources, most users lack the capability to implement EAs for solving COPs. An intuitive and promising solution is to outsource evolutionary operations to a cloud server, however, it poses privacy concerns. To this end, this article proposes a novel computing paradigm called evolutionary computation as a service (ECaaS), where a cloud server renders evolutionary computation services for users while ensuring their privacy. Following the concept of ECaaS, this article presents privacy-preserving genetic algorithm (PEGA), a privacy-preserving GA designed specifically for COPs. PEGA enables users, regardless of their domain expertise or resource availability, to outsource COPs to the cloud server that holds a competitive GA and approximates the optimal solution while safeguarding privacy. Notably, PEGA features the following characteristics. First, PEGA empowers users without domain expertise or sufficient resources to solve COPs effectively. Second, PEGA protects the privacy of users by preventing the leakage of optimization problem details. Third, PEGA performs comparably to the conventional GA when approximating the optimal solution. To realize its functionality, we implement PEGA falling in a twin-server architecture and evaluate it on two widely known COPs: 1) the traveling Salesman problem (TSP) and 2) the 0/1 knapsack problem (KP). Particularly, we utilize encryption cryptography to protect users' privacy and carefully design a suite of secure computing protocols to support evolutionary operators of GA on encrypted chromosomes. Privacy analysis demonstrates that PEGA successfully preserves the confidentiality of COP contents. Experimental evaluation results on several TSP datasets and KP datasets reveal that PEGA performs equivalently to the conventional GA in approximating the optimal solution.

In high dimensional environment, the interaction among particles significantly affects their movements in searching the vast solution space and thus plays a vital role in assisting particle swarm optimization (PSO) to attain good performance. To this end, this paper designs a random contrastive interaction (RCI) strategy for PSO, resulting in RCI-PSO, to tackle large-scale optimization problems (LSOPs) effectively and efficiently. Unlike existing interaction mechanisms for low-dimensional problems, RCI randomly chooses several different peers from the current swarm to construct a random interaction topology for each particle. Then, it lets the particle interact with the selected peers based on their current evolutionary information instead of their historical evolutionary information. Within the topology, RCI only propagates the evolutionary information of two contrastive dominators with the largest difference in fitness to direct the evolution of the particle. Therefore, particles with no more than two dominators in their topologies are not updated. Furthermore, a dynamic topology size adjustment scheme is devised to gradually enlarge the interaction topology. In this way, the swarm gradually switches from exploring the immense search space dispersedly to exploiting the found optimal regions intensively as the evolution continues. With these two strategies, RCI-PSO expectedly compromises search diversity and search convergence well at the swarm level and the particle level. At last, extensive experiments executed on two public LSOP suites verify that RCI-PSO performs competitively with or even much better than totally 40 state-of-theart large-scale approaches and preserves a good capability and scalability in tackling complex LSOPs.

Density clustering has shown advantages over other types of clustering methods for processing arbitrarily shaped datasets. In recent years, extensive research efforts has been made on the improvements of DBSCAN or the algorithms incorporating the concept of density peaks. However, these previous studies remain the problems of being sensitive to the parameter settings, and some of them will stuck in weak results when encountering the situations of varying-density distributions. To overcome these issues, we propose an evolution framework named EvoS&R that evolves multiple seeds and the corresponding radii for varying-density data clustering. Compared with the traditional methods, EvoS&R handles the parameter tuning and multi-density fitting problems in an integrated and straightforward manner. Note that, however, the underlying task in EvoS&R is a mixed-variable optimization problem that is challenging in nature. We specifically design a hybrid encoding differential evolution algorithm with novel encoding, mutation, etc., to solve the optimization problem efficiently. Extensive experiments on density-based datasets shows that our algorithm outperforms the other state-of-the-arts in most cases, which validates the effectiveness of the proposed method.

Crowdsourcing utilizes the crowd intelligence for pervasive data sensing and processing. When the processing task is a decision-making and optimization problem, the objective is evaluated based on sensed data, which is defined as crowdsourcing-based distributed optimization (CrowdDO). As evolutionary computation (EC) is a powerful technique for black-box and data-driven optimization problems, this paper combines crowdsourcing and EC to propose crowdsourcing-based EC (CrowdEC) for CrowdDO. CrowdEC performs optimization based on a server and a crowd of workers. Once receiving a CrowdDO request, the server posts the problem to workers. Each worker senses its own data and makes local decisions by local EC optimizer. Due to the heterogeneity of worker behaviors and devices, the sensed data are partial with noises, and thus the server needs to coordinate global optimization based on workers information. To avoid the leakage of worker privacy, workers only compare optimization results with adjacent workers and report comparison results to the server. With partial comparison results, the server adopts the competitive ranking to guide workers cooperation and develop the reliability detection to distinguish unreliable workers. A crowdsourcing-based level-based learning swarm optimizer is implemented as an example. Comparison experiments on benchmark testsuites and distributed clustering optimization demonstrate the potential applications of CrowdEC.

The emergence of networked systems in various fields brings many complex distributed optimization problems, where multiple agents in the system need to optimize a global objective cooperatively when they only have local information. In this work, we take advantage of the intrinsic parallelism of evolutionary computation to address network-based distributed optimization. In the proposed multiagent co-evolutionary algorithm, each agent maintains a subpopulation in which individuals represent solutions to the problem. During optimization, agents perform local optimization on their subpopulations and negotiation through communication with their neighbors. In order to help agents optimize the global objective cooperatively, we design a penalty-based objective function for fitness evaluation, which constrains the subpopulation within a small and controllable range. Further, to make the penalty more targeted, a conflict detection method is proposed to examine whether agents are conflicting on a certain shared variable. Finally, in order to help agents negotiate a consensus solution when only the local objective function is known, we retrofit the processes of negotiating shared variables, namely, evaluation, competition, and sharing. The above approaches form a multiagent co-evolutionary framework, enabling agents to cooperatively optimize the global objective in a distributed manner. Empirical studies show that the proposed algorithm achieves comparable solution quality with the holistic algorithm and better performance than existing gradient-free distributed algorithms on gradient-uncomputable problems.

Many real-world combinatorial optimization problems are defined on networks, such as road networks and social networks, etc. Due to the connectivity nature of networks, decision variables in such problems are usually coupled with each other, and the variables are also closely related to the characteristics of the local subnetwork to which they belong. These features pose new challenges to the design of cooperative coevolutionary (CC) algorithms for the large-scale network-based optimization. To improve the scalability, efficiency, and effectiveness of CC, we propose a new approach called parallel cooperative coevolution with overlapping decomposition and local evaluation (CCOL) for large-scale network-based combinatorial optimization. First, CCOL devises the overlapping decomposition to divide a large-scale network-based problem into some overlapping subproblems with lower dimensions. Second, subproblems are optimized in parallel since they can be evaluated by defined local objectives without the context of other subproblems. Meanwhile, an overlapping cooperation strategy is employed to achieve consensus toward the global objective. Finally, as different subproblems may have different scales, a Huffman-tree-based resources assignment strategy is devised. This strategy is able to utilize computing resources in a better way and thus further improve the scalability of the algorithm. To better demonstrate the proposed CCOL, we implement a set-based particle swarm optimization CCOL (CCOL-SPSO) to solve the multidepot vehicle routing problem with time windows as an example. Experimental results in medium and large scale benchmark problems indicate that CCOL is efficient and promising.

Efficient power inspection is crucial for maintaining a stable power system. During an inspection, unmanned aerial vehicles (UAVs) usually need to be recharged due to the wide geographical range of inspection and the limited battery capacity of UAVs. This limitation makes the problem more challenging that requires not only optimizing the task execution order, but also taking the chargings of UAVs into consideration. In order to address this complex problem, this work first formulates the UAV power inspection planning problem with charging stations. After that, we propose a new heuristic navigation model, in which UAVs can follow a heuristic rule to decide where to go next based on both its own information and task-related information. To obtain the heuristic rule, we design a set of features to describe the status of the UAVs and task completion. Then a genetic programming (GP) algorithm is introduced to evolve and get the heuristic rule. Finally, by applying heuristic navigation rule, the UAV navigation model can automatically prioritize task and charging order, and generate UAV flight routes that satisfy all constraints. The experiment results show that our method significantly outperforms the state-of-the-art algorithms.

Identifying influential nodes in social networks is an important problem called the influence maximization (IM) problem. So far, a large number of IM algorithms have been proposed. Among these algorithms, meta-heuristic approaches such as evolutionary algorithms (EAs) can obtain high-quality solutions. But in general, they usually suffer from time efficiency problems and are designed only for a few diffusion models. In this paper, we propose a novel EA combined with the reverse influence sampling (RIS) to solve the IM problem. By introducing the RIS technique, we can evaluate influence spreading efficiently under various diffusion models using hypergraphs. Moreover, the hypergraphs are also used as a kind of high-level heuristic information. To combine the RIS technique with EA, we exploit the idea of RIS to design a surrogate model and decide to address the single-objective IM problem in a multi-objective way. Then we modify the classical NSGA-II algorithm and apply it to this strategy. Our experimental results on million-scale social networks validate the good performance of the proposed approach.

Ridesharing is a popular transportation mode and has become an important part of smart city development, which helps alleviate the pressure of urban travel. The ridesharing problem (RSP) is mainly to match drivers to suitable passengers. In practice, passengers appear dynamically, and the departure and the destination locations of these subsequent orders are unknown, resulting in the dynamic RSP (DRSP). To solve this dynamic optimization problem, this paper develops a new genetic programming hyperheuristic (GPHH) method to evolve order dispatching rules (ODRs), which can guide drivers to match suitable passengers in real time. The proposed GPHH method contains a heuristic template for simulation-based hyper-heuristic optimization. The experiment results show that the proposed GPHH method outperforms the state-of-the-art methods. Further analysis revealed some valuable insights, such as the generalizability of the generated rules and the impact of some features on the results.

Online social networks have greatly facilitated the dissemination of information. The study of influence maximization(IM) in social networks is an important field. IM aims to find a subset of nodes with the maximum spreading influence. However, traditional research on IM ignores the reliability of data. Due to the uncertainty of data, there is a requirement to ensure connections between network nodes in IM are reliable. To solve this problem, this paper proposes a network embedding prediction model to analyze data reliability and an improved ant colony algorithm for IM. First, we predict the true connections between network nodes through the network embedding prediction model. EA - NEcornrnunity network embedding is used to represent the connections obtained from unreliable data by vectors. Based on these vectors, back-propagation neural network predicts the true connectivity relationships. Second, we develop an ant colony algorithm with specially designed heuristics and evaluation function. Heuristics are calculated by the seed set influence evaluation and influence overlap penalty term, which is calculated by cosine similarity based on vectors obtained from the network embedding. Evaluation function also takes these two items into account.

Influence maximization (IM) is a problem of selecting the most influential vertices with a limited budget under a given propagation model. A significant challenge faced by many existing algorithms pertains to their inability to reconcile the competing goals of solution quality and computational efficiency, rendering them unsuitable in large-scale social networks. In this paper, we propose an adaptive community-based influence maximization algorithm, named AComA, to solve the IM problem with a balance of effectiveness and efficiency. First, we introduce a community detection method to divide a large-scale network into several communities. An adaptive indicator is then defined to identify vertices with high propagation values in divided community networks. Based on community detection and the adaptive influence indicator, the number of candidate vertices is reduced, which significantly reduces the search space of the problem. Second, to select the final seed set from these candidate vertices, a genetic algorithm (GA) is introduced. The crossover and mutation operations are modified explicitly to adapt to the IM problem. By extracting information from the local neighborhood and the global community structure, AComA achieves a more accurate measurement of the influence spread for each vertex. The method proposed in this paper is tested on several real-world datasets. The experimental results show that AComA is promising.

Social networks built on real or online provide platforms for people to share and update their opinions. Based on the influence maximization problem, the opinion maximization (OM) problem aims to locate a set of initial nodes to achieve the maximum of total positive opinion dissemination in the social network. However, decision-makers prefer to have multiple optimal or near-optimal solutions at hand, which brings up the multimodal OM problem. In this paper, we firstly define the multimodal OM problem, which aims at providing several promising sets of initial nodes at one time. To solve this problem, we propose a genetic algorithm with a dynamic fitness sharing niching method (GADN). In GADN, we take the dynamic fitness sharing method to divide the population dynamically, design a repair strategy to fill the possible gap in sets after crossover, and take a scalable reproduction to assign reproductive opportunities. Finally, a series of experiments are conducted on multiple social networks. The results show that the proposed GADN outperforms other methods on both opinion and active ratio in most cases.

Surrogate-assisted evolutionary algorithms (SAEAs) have become a popular method to solve data-driven optimization problems (DOPs), which are common in industry. However, with the development of the Internet of Things, data are collected, processed, and stored in a distributed manner, leading a new optimization paradigm for SAEAs. To make SAEAs adapt to these distributed DOPs, this paper employs the edge computing paradigm to develop a platform that provides technical support for SAEAs with distributed structures, named ECdo. Specifically, the platform utilizes KubeEdge, an open-source edge computing framework, to mount the cluster and combines microservice interface design with the containerization strategy to offer a flexible deployment approach for distributed SAEAs. In addition, an efficient and stable internal communication mechanism is designed for the interaction between distributed components within the platform. To demonstrate the application of ECdo, we take the examples of a class of distributed DOPs, in which the objective and constraints are expensive and need to be approximated by accumulated data. These problems are known as distributed and expensive constrained optimization problems (DECOPs). We implement a distributed SAEA on ECdo to address DECOPs in real-world scenarios. Experiments show that the ECdo can provide the expected implementation for distributed SAEAs with good network tolerance under tough network conditions.

Target tracking and path planning using unmanned aerial vehicles (UAVs) have attracted increasing research attention in recent years. The rapid development of communication technology enables the use of multiple UAVs to perform target tracking collaboratively. But it remains challenging to coordinate multiple UAVs in some complicated scenarios, e.g., tracking multiple targets using multiple UAVs. In this paper, we intend to propose a Nash-based evolutionary dynamic optimization algorithm for multi-target tracking using multiple UAVs. Firstly, considering the requirement of balancing the number of UAVs tracking each target, we formulate the tracking problem as a distributed constrained multi-objective dynamic optimization problem using model predictive control (MPC). Secondly, to better track dynamic targets with stochastic behaviors, we design an evolutionary dynamic optimization (EDO) approach to solve the optimization problem. Thirdly, in order to avoid collisions, we combine the EDO approach with Nash optimization. The experimental results show that our approach has better performance than compared algorithms.

Surrogate-assisted evolutionary algorithms (EAs) have been proposed in recent years to solve data-driven optimization problems. Most existing surrogate-assisted EAs are for centralized optimization and do not take into account the challenges brought by the distribution of data at the edge of networks in the era of the Internet of Things. To this end, we propose edge-cloud co-EAs (ECCoEAs) to solve distributed data-driven optimization problems, where data are collected by edge servers. Specifically, we first propose a distributed framework of ECCoEAs, which consists of a communication mechanism, edge model management, and cloud model management. This communication mechanism is to avoid deadlock during the collaboration of edge servers and the cloud server. In edge model management, the edge models are trained based on local historical data and data composed of new solutions generated by co-evolutionary and their real evaluation values. In cloud model management, the black-box prediction functions received from edge models are used to find promising solutions to guide the edge model management. Moreover, two ECCoEAs are implemented, which proves the generality of the framework. To verify the performance of algorithms for distributed data-driven optimization problems, we design a novel benchmark test suite. The performance on the benchmarks and practical distributed clustering problems shows the effectiveness of ECCoEAs.

Centralized particle swarm optimization (PSO) does not fully exploit the potential of distributed or parallel computing and suffers from single-point-of-failure. Particularly, each particle in PSO comprises a potential solution (e.g., traveling route and neural network model parameters) which is essentially viewed as private data. Unfortunately, previously neither centralized nor distributed PSO algorithms fail to protect privacy effectively. Inspired by secure multiparty computation and multiagent system, this article proposes a privacy-preserving multiagent PSO algorithm (called PriMPSO) to protect each particle's data and enable private data sharing in a privacy-preserving manner. The goal of PriMPSO is to protect each particle's data in a distributed computing paradigm via existing PSO algorithms with competitive performance. Specifically, each particle is executed by an independent agent with its own data, and all agents jointly perform global optimization without sacrificing any particle's data. Thorough investigations show that selecting an exemplar from all particles and updating particles through the exemplar are critical operations for PSO algorithms. To this end, this article designs a privacy-preserving exemplar selection algorithm and a privacy-preserving triple computation protocol to select exemplars and update particles, respectively. Strict privacy analyses and extensive experiments on a benchmark and a realistic task confirm that PriMPSO not only protects particles' privacy but also has uniform convergence performance with the existing PSO algorithm in approximating an optimal solution.

Expensive optimization problems (EOPs) are common in industry and surrogate-assisted evolutionary algorithms (SAEAs) have been developed for solving them. However, many EOPs have not only expensive objective but also expensive constraints, which are evaluated through distributed ways. We define this kind of EOPs as distributed expensive constrained optimization problems (DECOPs). The distributed characteristic of DECOPs leads to the asynchronous evaluation of both objective and constraints. Though some researchers have studied the asynchronous evaluation of objectives, the asynchronous evaluation of constraints has not gained much attention. Therefore, this article gives a formal formulation of DECOPs and proposes a distributed evolutionary constrained optimization algorithm with on-demand evaluation (DEAOE). DEAOE can adaptively evolve different constraints in an asynchronous way through the on-demand evaluation strategy. The on-demand evaluation works from two aspects to improve the population convergence and diversity. From the aspect of individual selection, a joint sample selection strategy is adopted to determine which candidates are promising. From the aspect of constraint selection, an infeasible-first evaluation strategy is devised to judge which constraints need to be further evolved. Extensive experiments and analyses on benchmark functions and engineering problems demonstrate that DEAOE has better performance and higher efficiency compared to centralized state-of-the-art SAEAs.

The increasing population density in public places necessitates urgent attention to address safety concerns via effective crowd management. In many congested scenarios such as peak-hour subway stations, the utilization of fences to guide crowd movement has become a widely adopted approach to alleviate congestion. This work presents a method that combines crowd simulation and management, focusing on the optimization of the fence layout for efficient crowd guidance. First, a congestion probability social force model (CP-SFM) is introduced to simulate the irrational pedestrians and to evaluate the efficacy of different fence layouts. Second, based on CP-SFM, we are the first to formulate the fence layout problem as an optimization problem with the objective to minimize the congestion of pedestrians in public places. Third, we further propose an ant colony crowd intervention algorithm (ACCI) to optimize the layout of fences. Lastly, we illustrate the performance of proposed ACCI on 18 scenarios including two real-world subway stations. Compared with other optimization methods, ACCI demonstrates promising performance in avoiding crowd congestion.

As an emerging sensing data collection paradigm, mobile crowdsensing (MCS) enjoys good scalability and low deployment cost but raises privacy concerns. In this paper, we propose a privacy-preserving MCS system calledCrowdFLby seamlessly integrating federated learning (FL) into MCS. At a high level, in order to protect participants’ privacy and fully explore participants’ computing power, participants inCrowdFLlocally process sensing data via FL paradigm and only upload encrypted training models to the server. To this end, we design a secure aggregation algorithm (SecAgg) through the threshold Paillier cryptosystem to aggregate training models in an encrypted form. Also, to stimulate participation, we present a hybrid incentive mechanism combining the reverse Vickrey auction and posted pricing mechanism, which is proved to be truthful and fail. Results of theoretical analysis and experimental evaluation on a practical MCS scenario (human activity recognition) show thatCrowdFLis effective in protecting participants’ privacy and is efficient in operations. In contrast to existing solutions,CrowdFLis 3× faster in model decryption and improves an order of magnitude in model aggregation.

Surrogate-assisted evolutionary algorithms (SAEAs) have become a popular tool to solve expensive optimization problems and have been gradually used to deal with expensive constraints. To handle inequality expensive constraints, existing SAEAs need both the information of constraint violation and satisfaction to construct surrogate models for constraints. However, many problems only feedback whether the candidate solution is feasible or how much degree it violates constraints. There is no detailed information of how much degree the candidate satisfies constraints. The performance of most existing SAEAs decreases a lot in solving expensive constrained optimization problems (ECOPs) with such incomplete constraint information. To solve the problem, this article proposes a hybrid regressor and classifier-assisted evolutionary algorithm (HRCEA). HRCEA adopts a radial basis function regression model to approximate the degree of constraint violation. In order to make a more credible prediction, a logistic regression classifier (LRC) is constructed for the offspring rectification. The classifier works in cooperation with the$\alpha $-cut strategy, in which the high confidence level can significantly improve the prediction reliability. Besides, the LRC is built based on the boundary training data selection strategy, which is devised to select samples around feasible boundaries. This strategy is helpful for the LRC to fit the local feasibility structure. Extensive experiments on commonly used benchmark functions in CEC2006 and CEC 2010 demonstrate that HRCEA has satisfactory performance in found results and execution efficiency when solving ECOPs with incomplete constraint information. Furthermore, HRCEA is utilized to solve ceramic formula design optimization problem, which shows its promising application in real-world optimization problems.

Constraint handling is a core part when using surrogate-assisted evolutionary algorithms (SAEAs) to solve expensive constrained optimization problems (ECOPs). However, most existing SAEAs for ECOPs train a surrogate for each constraint. With the number of constraints increasing, the training burden of surrogates becomes heavy and the efficiency of the algorithm is greatly reduced. To solve this issue, this article proposes an efficient two-stage surrogate-assisted differential evolution (eToSA-DE) algorithm to handle expensive inequality constraints. eToSA-DE trains one surrogate for the degree of constraint violation and the type of the surrogate varies during the evolution process. In the first stage when there are only a few feasible individuals, a Gaussian process regression model is trained to fit the degree of constraint violation. In the second stage when more feasible individuals are accumulated, a support vector machine classification model is trained to classify whether candidates are feasible. Both types of surrogates are constructed by individuals which are chosen by the boundary training data selection strategy. These selected individuals are located around the feasible boundaries and helpful for the surrogate to approximate the feasibility structure. Besides, a feasible exploration strategy is devised to search for promising areas. To alleviate the error caused by the regression model, a nearest neighbor rectification is adopted to modify the prediction results. Extensive experiments on benchmark test functions and two formulated engineering optimization problems demonstrate that the proposed method can get satisfactory optimization results and significantly improve the efficiency of the algorithm.

One essential issue in surrogate-assisted evolutionary algorithms (SAEAs) is how to evaluate solutions and find candidates for evolution, without resorting to the calculation of the computational-expensive real objective function. While most studies use regression models as surrogate models for SAEAs, some recent work propose to use classification models for single-objective expensive optimization, as classification models are more stable and much easier to train with limited available data. However, for multi-objective expensive optimization problems, it is more challenging to classify the solutions into different levels according to their quality, and thus the use of classification-based surrogate models for multi-objective SAEAs has not been explored in-depth. To this end, in this paper we propose a classification-assisted level-based learning swarm optimizer for expensive multi-objective optimization. First, a preference relationship among individuals taking both Pareto dominance and crowding distance into account is defined to divide the whole population into different quality levels. Then, a classification model is trained as the surrogate. In addition, a selection strategy is devised in decision space to acquire solutions on the sparse part on the Pareto front. Experimental results validate the superiority and efficiency of the proposed algorithm on benchmark test functions.

With the rapid development of distributed computing paradigms like edge computing and Internet of Things (IoT), many distributed edge nodes involve in data collection and decision making, resulting in many distributed optimization problems (DOPs). In this paper, we consider the DOPs with the following features. First, decision variables of a problem are naturally distributed in several spatial-distributed edges. Each computing node is responsible for one subproblem, and it can only access its corresponding local data and perform local objective evaluation. Second, some decision variables appear in different groups simultaneously, which are called overlapping variables. Third, the computing nodes can only communicate following a certain network topology. They need to work together to solve the overall problem. Because of its divide-and-conquer nature, cooperative coevolution (CC) has good potential for handling such distributed problems. Therefore, we develop a new distributed CC framework to solve them. First, a new CC architecture based on the ring network without any central node is designed. Second, an asynchronously communication strategy with low communication frequency and volume is proposed. Third, a competitive selection strategy is adopted to achieve consistency in asynchronous evolution. We define a set of distributed benchmark problems and the experimental results validate the effectiveness of the proposed approach.

The energy consumption and environmental pollution caused by fuel vehicles have attracted great attention, and now governments around the world are vigorously promoting the production and use of electric vehicles. Among them, the unreasonable layout of charging piles brings inconvenience to users and seriously restricts the development of electric vehicles. In order to deploy charging plies in the existing parking lots more reasonably, this paper intends to propose a fine-grained layout model based on the Voronoi diagram and further develop an adaptive particle swarm optimization (APSO) approach. First, a point-based method is used to estimate charging demands. Second, combined with the Voronoi diagram, this paper proposes a fine-grained layout model of charging piles in parking lots with the goal of maximizing the social benefit. Third, the APSO is developed to solve the optimization problem. Finally, the performance of the model and the proposed algorithm is analyzed through an example in terms of the satisfaction of user needs, the benefits of parking lots, and the density of the charging piles. The numerical experimental results verify the universality and rationality of the proposed model, and thus the proposed model can provide a certain decision-making basis for theoretical and practical research into the new energy vehicle industry.

Multimodal optimization problems have multiple satisfactory solutions to identify. Most of the existing works conduct the search based on the information of the current population, which can be inefficient. This article proposes a probabilistic niching evolutionary computation framework that guides the future search based on more sufficient historical information, in order to locate diverse and high-quality solutions. A binary space partition tree is built to structurally organize the space visiting information. Based on the tree, a probabilistic niching strategy is defined to reinforce exploration and exploitation by making full use of the structural historical information. The proposed framework is universal for incorporating various baseline niching algorithms. In this article, we integrate the proposed framework with two niching algorithms: 1) a distance-based differential evolution algorithm and 2) a topology-based particle swarm optimization algorithm. The two new algorithms are evaluated on 20 multimodal optimization test functions. The experimental results show that the proposed framework helps the algorithms obtain competitive performance. They outperform a number of state-of-the-art niching algorithms on most of the test functions.

High-dimensional problems are ubiquitous in many fields, yet still remain challenging to be solved. To tackle such problems with high effectiveness and efficiency, this article proposes a simple yet efficient stochastic dominant learning swarm optimizer. Particularly, this optimizer not only compromises swarm diversity and convergence speed properly, but also consumes as little computing time and space as possible to locate the optima. In this optimizer, a particle is updated only when its two exemplars randomly selected from the current swarm are its dominators. In this way, each particle has an implicit probability to directly enter the next generation, making it possible to maintain high swarm diversity. Since each updated particle only learns from its dominators, good convergence is likely to be achieved. To alleviate the sensitivity of this optimizer to newly introduced parameters, an adaptive parameter adjustment strategy is further designed based on the evolutionary information of particles at the individual level. Finally, extensive experiments on two high dimensional benchmark sets substantiate that the devised optimizer achieves competitive or even better performance in terms of solution quality, convergence speed, scalability, and computational cost, compared to several state-of-the-art methods. In particular, experimental results show that the proposed optimizer performs excellently on partially separable problems, especially partially separable multimodal problems, which are very common in real-world applications. In addition, the application to feature selection problems further demonstrates the effectiveness of this optimizer in tackling real-world problems.

Online social media have aroused much research interest in recent years. In contrast to previous work that focused on the detection of emerging topics, this article undertakes the prediction of active users in online social events, which is so far rarely explored. This prediction task is formulated as a binary classification problem that built on real-world tweet streams, taking Ferguson event and New York Chockhold event as examples. Then, a comprehensive user feature system is designed to characterize the events’ online participants, which includes not only basic statistical characteristics and image-pixel-level features, but also some emotional features and personality features. Next, the Weighted Random Forest (Weighted-RF) classifier is adopted to solve the classification problem. Based on the user feature system and the classifier, the experience of a previous event can be archived and applied to the prediction of later similar events. Experimental results show that the Weighted-RF trained by samples of Ferguson event can effectively predict active users in NYC event, with an AUC value around 0.8392. Besides, the image-content based personality model provides a new tool for depicting user portraits, which further contributes to the quantitative analysis of online social events.

Scientific cloud workflows enable the access to distributed computing resources in cloud environments for executing scientific computing applications. In the literature, most workflow scheduling models assume that each workflow task is mapped to only one service instance. But in computation and data-intensive applications, it is common that the computation resources provided by a single service instance are insufficient for some complicated tasks which contain several closely correlated sub-tasks. To manage such complicated workflows, this article devises a novel workflow model with composite tasks (cWFS). The model views a complicated task as a composite task and allows mapping multiple service instances to a composite task. The data transmission among sub-tasks of a composite task can also be addressed by the proposed model. To solve cWFS problem, we devise a nested particle swarm optimization (N-PSO) that utilizes two kinds of populations, i.e., the outer population and inner population. Since N-PSO is a bit time-consuming, we further devise a Fast version of N-PSO (FN-PSO), which can save more than 60 percent of running time compared with N-PSO. The proposed approaches are evaluated on five real-world workflow types. The experimental results verify that the proposed approaches can solve the new workflow model effectively.

With the rapid development of the insurance industry, more diverse insurance products are produced for consumers. Insurance portfolio problems have received increasing attention. While most studies focus on insurance portfolio problem for a single insured, insurance portfolio problems for a specific group of insured are even more intricate but little attention has been paid to. In this article, we propose a group insurance portfolio model for investment allocation of several insurance policies so that the total payout of the whole group can be maximized. The statistical average value of each parameter is considered in the model to approximate the expectation payout of the group insurance portfolio problem. To solve this problem, a coevolutionary estimation of distribution algorithm (EDA) utilizing the divide-and-conquer strategy is proposed. First, as the payout of each insured under a certain portfolio plan can be calculated separately, the proposed approach decomposes the group insurance portfolio problem into several single-insured insurance portfolio problems. In this way, the dimension of the optimization problem becomes lower compared to the original problem. An adaptive EDA is proposed to optimize the portfolio plan of each insured independently. Second, the group insurance portfolio problem remains a nonseparable problem since the investment amount of each insured is limited by the total investable amount of the whole group. A particle swarm optimization algorithm is adopted to cooperate with the EDA to optimize the proportion of allocation to each insured. The proposed algorithm is verified on various scenarios. The experimental results validate that the proposed approach is effective for the group insurance portfolio problem.

Crowdsensing is regarded as a critical component of the Internet of Things (IoT) and has been widely applied in smart city services. Incentive mechanism design, data reliability evaluation, and privacy preservation are the research focuses of crowdsensing. However, most existing incentive mechanisms fail to protect data privacy and evaluate data credibility, simultaneously. Moreover, traditional privacy and reliability-aware incentive schemes are usually challenging to realize real-time reward distribution. To this end, we first point out a single-time slice of failure problem in real-time incentive mechanisms and propose a two-layer truth discovery model (TLTD) to resolve this problem. Then, a reliability-aware real-time incentive mechanism (RRIM) is designed based on the proposed TLTD. In order to evaluate data reliability in a privacy-preserving manner, we build a privacy-preserving truth discovery solution (PriTD) based on secure computation protocols. Finally, our proposed system [privacy and reliability-aware real-time incentive system for crowdsensing (PRICE)] integrating the aforementioned protocols realizes real-time reward distribution, data reliability evaluation, and privacy protection, simultaneously. Theoretical analysis and experimental evaluations on a synthetic and real-world data set demonstrate the feasibility and efficiency of the proposed PRICE.

In many practical applications, it is crucial to perform automatic data clustering without knowing the number of clusters in advance. The evolutionary computation paradigm is good at dealing with this task, but the existing algorithms encounter several deficiencies, such as the encoding redundancy and the cross-dimension learning error. In this article, we propose a novel elastic differential evolution algorithm to solve automatic data clustering. Unlike traditional methods, the proposed algorithm considers each clustering layout as a whole and adapts the cluster number and cluster centroids inherently through the variable-length encoding and the evolution operators. The encoding scheme contains no redundancy. To enable the individuals of different lengths to exchange information properly, we develop a subspace crossover and a two-phase mutation operator. The operators employ the basic method of differential evolution and, in addition, they consider the spatial information of cluster layouts to generate offspring solutions. Particularly, each dimension of the parameter vector interacts with its correlated dimensions, which not only adapts the cluster number but also avoids the cross-dimension learning error. The experimental results show that our algorithm outperforms the state-of-the-art algorithms that it is able to identify the correct number of clusters and obtain a good cluster validation value.

The covariance matrix adaptation evolution strategy (CMA-ES) is a powerful evolutionary algorithm for single-objective real-valued optimization. However, the time and space complexity may preclude its use in high-dimensional decision space. Recent studies suggest that putting sparse or low-rank constraints on the structure of the covariance matrix can improve the efficiency of CMA-ES in handling large-scale problems. Following this idea, this paper proposes a search direction adaptation evolution strategy (SDA-ES) which achieves linear time and space complexity. SDA-ES models the covariance matrix with an identity matrix and multiple search directions, and uses a heuristic to update the search directions in a way similar to the principal component analysis. We also generalize the traditional 1/5th success rule to adapt the mutation strength which exhibits the derandomization property. Numerical comparisons with nine state-of-the-art algorithms are carried out on 31 test problems. The experimental results have shown that SDA-ES is invariant under search-space rotational transformations, and is scalable with respect to the number of variables. It also achieves competitive performance on generic black-box problems, demonstrating its effectiveness in keeping a good tradeoff between solution quality and computational efficiency.

Evacuation path optimization (EPO) is a crucial problem in crowd and disaster management. With the consideration of dynamic evacuee velocity, the EPO problem becomes nondeterministic polynomial-time hard (NP-Hard). Furthermore, since not only one single evacuation path but multiple mutually restricted paths should be found, the crowd evacuation problem becomes even challenging in both solution spatial encoding and optimal solution searching. To address the above challenges, this article puts forward an ant colony evacuation planner (ACEP) with a novel solution construction strategy and an incremental flow assignment (IFA) method. First, different from the traditional ant algorithms, where each ant builds a complete solution independently, ACEP uses the entire colony of ants to simulate the behavior of the crowd during evacuation. In this way, the colony of ants works cooperatively to find a set of evacuation paths simultaneously and thus multiple evacuation paths can be found effectively. Second, in order to reduce the execution time of ACEP, an IFA method is introduced, in which fractions of evacuees are assigned step by step, to imitate the group-based evacuation process in the real world so that the efficiency of ACEP can be further improved. Numerical experiments are conducted on a set of networks with different sizes. The experimental results demonstrate that ACEP is promising.

The resource-constrained project scheduling problem (RCPSP) is a basic problem in project management. The net present value (NPV) of discounted cash flow is used as a criterion to evaluate the financial aspects of RCPSP in many studies. But while most existing studies focused on only the contractor's NPV, this article addresses a practical extension of RCPSP, called the payment scheduling negotiation problem (PSNP), which considers both the interests of the contractor and the client. To maximize NPVs of both sides and achieve a win-win solution, these two participants negotiate together to determine an activity schedule and a payment plan for the project. The challenges arise in three aspects: 1) the client's NPV and the contractor's NPV are two conflicting objectives; 2) both participants have special preferences in decision making; and 3) the RCPSP is nondeterministic polynomial-time hard (NP-Hard). To overcome these challenges, this article proposes a new approach with the following features. First, the problem is reformulated as a biobjective optimization problem with preferences. Second, to address the different preferences of the client and the contractor, a strategy of multilevel region interest is presented. Third, this strategy is integrated in the nondominated sorting genetic algorithm II (NSGA-II) to solve the PSNP efficiently. In the experiment, the proposed algorithm is compared with both the double-level optimization approach and the multiobjective optimization approach. The experimental results validate that the proposed method can focus on searching in the region of interest (ROI) and provide more satisfactory solutions.

The control of virus spreading over complex networks with a limited budget has attracted much attention but remains challenging. This article aims at addressing the combinatorial, discrete resource allocation problems (RAPs) in virus spreading control. To meet the challenges of increasing network scales and improve the solving efficiency, an evolutionary divide-and-conquer algorithm is proposed, namely, a coevolutionary algorithm with network-community-based decomposition (NCD-CEA). It is characterized by the community-based dividing technique and cooperative coevolution conquering thought. First, to reduce the time complexity, NCD-CEA divides a network into multiple communities by a modified community detection method such that the most relevant variables in the solution space are clustered together. The problem and the global swarm are subsequently decomposed into subproblems and subswarms with low-dimensional embeddings. Second, to obtain high-quality solutions, an alternative evolutionary approach is designed by promoting the evolution of subswarms and the global swarm, in turn, with subsolutions evaluated by local fitness functions and global solutions evaluated by a global fitness function. Extensive experiments on different networks show that NCD-CEA has a competitive performance in solving RAPs. This article advances toward controlling virus spreading over large-scale networks.

Surrogate-assisted evolutionary algorithms (SAEAs) have become one popular method to solve complex and computationally expensive optimization problems. However, most existing SAEAs suffer from performance degradation with the dimensionality increasing. To solve this issue, this article proposes a classifier-assisted level-based learning swarm optimizer on the basis of the level-based learning swarm optimizer (LLSO) and the gradient boosting classifier (GBC) to improve the robustness and scalability of SAEAs. Particularly, the level-based learning strategy in LLSO has a tight correspondence with the classification characteristic by setting the number of levels in LLSO to be the same as the number of classes in GBC. Together, the classification results feedback the distribution of promising candidates to accelerate the evolution of the optimizer, while the evolved population helps to improve the accuracy of the classifier. To select informative and valuable candidates for real evaluations, we devise an${L}1$-exploitation strategy to extensively exploit promising areas. Then, the candidate selection is conducted between the predicted${L}1$offspring and the already real-evaluated${L}1$individuals based on their Euclidean distances. Extensive experiments on commonly used benchmark functions demonstrate that the proposed optimizer can achieve competitive or better performance with a very small training dataset compared with three state-of-the-art SAEAs.

The minimum travel distance of task participants is one of the significant optimization objectives of privacy-preserving task assignment in mobile crowdsensing (MCS). However, when the travel distance is minimized, most of the previous schemes only focus on the task participant privacy and disregard the task requester privacy. Moreover, existing solutions usually only support the constraint of a single type, such as equality constraints or range constraints. In this paper, we propose a bilateral privacy-preserving Task Assignment mechanism for MCS (iTAM), which protects not only the task participants privacy but also the task requesters privacy and can minimize the travel distance. Furthermore, iTAM provides both equality and range constraints of task assignment by utilizing the Paillier cryptosystem. To accommodate the multiple relations between the task participants and the task, we propose the single/multiple task participants selection problems for a task requiring task participants to compete and cooperate. Experimental evaluations over synthetic and real-world data illustrate that iTAM is feasible and effective. Compared with the state-of-the-art, iTAM positively solves the optimal problem of travel distance. The complexities of iTAM are$\mathcal {O}(n)$and$\mathcal {O}(n\log n)$for a single and multiple task participants selection problems, respectively.

In multi-view subspace clustering, the low-rankness of the stacked self-representation tensor is widely accepted to capture the high-order cross-view correlation. However, using the nuclear norm as a convex surrogate of the rank function, the self-representation tensor exhibits strong connectivity with dense coefficients. When noise exists in the data, the generated affinity matrix may be unreliable for subspace clustering as it retains the connections across inter-cluster samples due to the lack of sparsity. Since both the connectivity and sparsity of the self-representation coefficients are curial for subspace clustering, we propose a Reliable Multi-View Affinity Learning (RMVAL) method so as to optimize both properties in a single model. Specifically, RMVAL employs the low-rank tensor constraint to yield a well-connected yet dense solution, and purifies the densely connected self-representation tensor by preserving only the connections in local neighborhoods using the$l_1$-norm regularization. This way, the strong connections on the self-representation tensor are retained and the trivial coefficients corresponding to the inter-cluster connections are suppressed, leading to a “clean” self-representation tensor and also a reliable affinity matrix. We propose an efficient algorithm to solve RMVAL using the alternating direction method of multipliers. Extensive experiments on benchmark databases have demonstrated the superiority of RMVAL.

Real-time taxi-passenger matching plays a critical role in modern taxi dispatch systems. Currently, the greedy strategy is widely adopted, which limits the quality of the service (QoS) and the profit of the entire system. There are two crucial tasks in this system: 1) the pairwise prioritization and 2) the matching of taxi-passenger pairs. In this paper, we develop a two-stage taxi-passenger matching system to deal with these two tasks. In the first stage, we design a fuzzy controller to assign a priority score to each taxi-passenger pair in real time. To ensure its performance on providing good QoS and profit, the fuzzy controller is optimized by an offline differential evolution algorithm. New individual representation is designed to optimize the membership functions and fuzzy rule base simultaneously. To accelerate the optimization process, the algorithm is implemented in a parallel way. Then, in the second stage, considering the priority scores as weights in the bipartite graph of taxi and passenger sets, we further apply a polynomial Kuhn-Munkres algorithm to find the maximum weight perfect matching in the bipartite graph. Simulated results validate the effectiveness of the proposed algorithm, which is able to enhance the QoS provided by the taxi system and improve the profit gained by the taxi service company.

The introduction of workflow in cloud computing has afforded a new and efficient way to tackle large-scale applications. As an NP-hard problem, how to schedule cloud workflows effectively and economically with deadline constraints and different kinds of tasks and resources is extraordinarily challenging. To solve this constrained problem, this paper intends to develop an intelligent scheduling system from the perspective of users to reduce expenditure of workflow, subject to the deadline and other execution constraints. A new estimation model of the task execution time is designed according to virtual machine settings in real public clouds and execution data from practical workflows. Based on the new model, an adaptive ant colony optimization algorithm is proposed to meet the quality of service and orchestrate tasks. The adaptiveness of the algorithm is embodied in two aspects. First, an adaptive solution construction method is designed that each solution is built with a dynamically changing resource pool, thus the search space of the algorithm is narrowed down and the execution time is decreased. Second, two heuristics with self-adaptive weight are introduced to adaptively meet different deadline settings. Simulating results on four types of workflows show that the proposed approach is effective and competitive.

Virtual network embedding (VNE) is an important problem in network virtualization for the flexible sharing of network resources. While most existing studies focus on centralized embedding for VNE, distributed embedding is considered more scalable and suitable for large-scale scenarios, but how virtual resources can be mapped to substrate resources effectively and efficiently remains a challenging issue. In this paper, we devise a distributed VNE system with historical archives (HAs) and metaheuristic approaches. First, we introduce metaheuristic approaches to each delegation of the distributed embedding system as the optimizer for VNE. Compared to the heuristic-based greedy algorithms used in existing distributed embedding approaches, which are prone to be trapped in local optima, metaheuristic approaches can provide better embedding performance for these distributed delegations. Second, an archive-based strategy is also introduced in the distributed embedding system to assist the metaheuristic algorithms. The archives are used to record the up-to-date information of frequently repeated tasks. By utilizing such archives as historical memory, metaheuristic algorithms can further improve embedding performance for frequently repeated tasks. Following this idea, we incorporate the set-based particle swarm optimization (PSO) as the optimizer and propose the distributed VNE system with HAs and set-based PSO (HA-VNE-PSO) system to solve the VNE problem in a distributed way. HA-VNE-PSO is empirically validated in scenarios of different scales. The experimental results verify that HA-VNE-PSO can scale well with respect to substrate networks, and the HA strategy is indeed effective in different scenarios.

The control of epidemics taking place in complex networks has been an increasingly active topic in public health management. In this article, we propose an efficient networked epidemic control system, where a modified susceptible-exposed-infected-vigilant (SEIV) model is first built to simulate epidemic spreading. Then, different from existing continuous resource models which abstractly map resources to parameters of epidemic models, a concrete resource description model is built to simulate real-world goods/services and their allocation. Based on the two models, a cost-constraint subset selection problem in epidemic control is identified. To solve the problem, a swarm-based stochastic optimization policy is proposed, where each particle in the swarm can determine its own solutions according to the guidance of its superior peers and historical searching experience of the whole swarm, without extra problem-relative information. Theoretical proof about system equilibrium is provided, which is consistent with experimental observations. The competitive performance of the proposed optimizer is validated by theoretical analysis and comparison experiments. Finally, an application case is provided to illustrate the practicability.

Virtual network embedding (VNE) is the key technology in network virtualization and has been proven NPhard. The purpose of VNE is to find the optimal mapping of virtual nodes and links, and minimize the utilization of resources. However, many particle swarm optimization approaches to VNE separate VNE into two independent subproblems (i.e., node mapping and link mapping) and ignore the coordination between node mapping and link mapping. In this paper, a one-stage and dual-heuristic particle swarm optimization (DH-PSO) is devised to solve VNE. To coordinate node mapping and link mapping, firstly, DH-PSO updates positions of particles step by step, and nodes and links are mapped in one stage. Secondly, DH-PSO devises the dual-heuristic strategy to further improve the optimizing capability. The first heuristic strategy is to construct a candidate set and the second strategy is to find the best solution from the candidate set. Hence, not only the network resources but the network paths are taken into account to construct solutions. DH-PSO can be combined with different two-stage approaches to become one-stage. DH-PSO is experimentally studied on different instances. The experimental results verify that the proposed DH-PSO is promising.

Surrogated assisted evolutionary algorithms are commonly used to solve real-world expensive optimization problems. However, in some situations, no online data is available during the evolution process. In this situation, we have to build surrogate models based on offline historical data, which is known as offline data-driven optimization. Since no new data can be used to improve the surrogate models, offline data-driven optimization remains a challenging problem. In this paper, we propose a Gaussian process assisted offline estimation of multivariate Gaussian distribution algorithm to address the offline data-driven optimization problem. Instead of using surrogate models to predict the fitness values of individuals, we utilize a surrogate model to predict the rankings of individuals based on the frequently used lower confidence bound. In this way, the robustness of the proposed algorithm could be enhanced. Experiments are conducted on five commonly used benchmark problems. The experimental results demonstrate that the proposed offline surrogate model and the multivariate Gaussian estimation of distribution algorithm are able to achieve competitive performance.

The virtual machine (VM) placement problem with the objective to save energy consumption and improve machine utility has been studied extensively in Cloud computing. However, the connection information among VMs during the execution of scientific workflows is seldom considered in existing studies. Therefore, this paper intends to build a novel connection-aware model for VM placement in scientific workflows. Different from existing studies, as the connection information of VMs is considered following the topology of workflows, not only the CPU capacity and memory capacity but also the transmission bandwidth among machines should be considered. An energy- aware, traffic-aware, connection-aware ant colony optimization (ETCACO) approach is developed. The proposed ETCACO combines Ant Colony Optimization (ACO) with a scheduler, namely greedy placeman. Experiments are performed to compare the proposed model with the traditional approach. It is discovered that by taking the connection information into consideration, the proposed approach can reduce energy consumption by 7%.

The allocation of epidemic-control resources has been an increasingly active topic in the physical world. Most existing studies focus on the allocation of abstract and continuous epidemic control resources, and then formulate differentiable convex programming problems. However, real-world resources are usually discrete materials, goods, or services, so that resource allocation problems become non-convex. As a complementary study, this paper builds three discrete resource allocation problems based on an improved Susceptible-Exposed-Infectious- Vigilant (SEIV) spread model: the cost-constraint optimization problem (CCOP), rate-constraint optimization problem (RCOP), and eradication optimization problem (EOP). Then, existing swarm-based metaheuristic algorithms are adapted to effectively solve the problems. Thereinto, the Heuristic Majority-Voting Binary Particle Swarm Optimizer (HMV-BPSO) is present, which introduces a heuristic factor which concerns the probability distribution of resources to guide the evolution of particles and helps improve the performance of original MV-BPSO. Numerical experiments are developed to verify the effectiveness of swarm- based metaheuristic algorithms on epidemic control. Results show that HMV-BPSO can produce higher-quality solutions than other algorithms.

A reliable mobile crowdsensing (MCS) application usually relies on sufficient participants and trustworthy data. However, privacy concerns reduce participants' willingness to participate in sensing tasks. The uncertainty of participant behavior and heterogeneity of sensing devices result in the unreliability of sensing data and further bring unreliable MCS services. Hence, it is crucial to estimate the reliability of sensing data and protect privacy. Unfortunately, most existing privacy-preserving data estimation solutions are designed for single-type data. In practice, however, heterogeneous sensing data are ubiquitous in data integration tasks. To this end, we propose a privacy-preserving reliability estimation solution of heterogeneous data for MCS, called IronM, which is effective for text, number, and multimedia data (e.g., image, audio, and video). Specifically, IronM first formulates the reliability assessment of text, number, and multimedia data as equality and range constraints, and then estimates the reliability of heterogeneous data through our proposed privacy-preserving hybrid constraints assessment mechanism. Privacy analysis demonstrates that IronM can not only evaluate the reliability of heterogeneous data but also protect data confidentiality. The experimental results in real-world datasets show the effectiveness and efficiency of IronM.

The rapid development of online social networks not only enables prompt and convenient dissemination of desirable information but also incurs fast and wide propagation of undesirable information. A common way to control the spread of pollutants is to block some nodes, but such a strategy may affect the service quality of a social network and leads to a high control cost if too many nodes are blocked. This paper considers the node selection problem as a biobjective optimization problem to find a subset of nodes to be blocked so that the effect of the control is maximized while the cost of the control is minimized. To solve this problem, we design an ant colony optimization algorithm with an adaptive dimension size selection under the multiobjective evolutionary algorithm framework based on decomposition (MOEA/D-ADACO). The proposed algorithm divides the biobjective problem into a set of single-objective subproblems and each ant takes charge of optimizing one subproblem. Moreover, two types of pheromone and heuristic information are incorporated into MOEA/D-ADACO, that is, pheromone and heuristic information of dimension size selection and that of node selection. While constructing solutions, the ants first determine the dimension size according to the former type of pheromone and heuristic information. Then, the ants select a specific number of nodes to build solutions according to the latter type of pheromone and heuristic information. Experiments conducted on a set of real-world online social networks confirm that the proposed biobjective optimization model and the developed MOEA/D-ADACO are promising for the pollutant spreading control.

Large-scale optimization with high dimensionality and high computational cost becomes ubiquitous nowadays. To tackle such challenging problems efficiently, devising distributed evolutionary computation algorithms is imperative. To this end, this paper proposes a distributed swarm optimizer based on a special master-slave model. Specifically, in this distributed optimizer, the master is mainly responsible for communication with slaves, while each slave iterates a swarm to traverse the solution space. An asynchronous and adaptive communication strategy based on the request-response mechanism is especially devised to let the slaves communicate with the master efficiently. Particularly, the communication between the master and each slave is adaptively triggered during the iteration. To aid the slaves to search the space efficiently, an elite-guided learning strategy is especially designed via utilizing elite particles in the current swarm and historically best solutions found by different slaves to guide the update of particles. Together, this distributed optimizer asynchronously iterates multiple swarms to collaboratively seek the optimum in parallel. Extensive experiments on a widely used large-scale benchmark set substantiate that the distributed optimizer could: 1) achieve competitive effectiveness in terms of solution quality as compared to the state-of-the-art large-scale methods; 2) accelerate the execution of the algorithm in comparison with the sequential one and obtain almost linear speedup as the number of cores increases; and 3) preserve a good scalability to solve higher dimensional problems.

The subgraph isomorphism problems, which aim to map subgraphs to a given graph, are widely seen in many applications and are usually nondeterministic polynomial-time complete (NP-complete). As a representative extension of the subgraph isomorphism problem, virtual network embedding (VNE) is a key problem in datacenter scheduling and network virtualization. Existing metaheuristic approaches to VNE problems tend to schedule networks as a whole. But when the problem scale grows, the performance of these approaches may degenerate due to the curse of dimensionality. In this article, we intend to propose a divide-and-conquer evolutionary algorithm with overlapping decomposition (ODEA) to solve large-scale VNE problems. First, realizing the fact that the decision variables in graph-based optimization problems like VNE are usually nonseparable, an overlapping decomposition method is introduced by investigating the characteristic of the network structure. In this method, the critical elements which have tight connections to many other nodes can belong to multiple subcomponents. As a result, the decision variables with tight connections can always be evolved together in multiple subcomponents. Second, to combine the subsolutions into a complete feasible solution, a competitive strategy is devised. Through the competition among critical elements, the optimizing information is shared among subcomponents, which can further improve the effectiveness of ODEA. The proposed ODEA can adopt different metaheuristics as the optimizer, and we conduct experiments on both the scenarios with a single virtual network and with a series of online networks. The experimental results verify that ODEA can significantly improve the performance of different metaheuristics in large-scale VNE problems.

The increasing popularity of battery-limited electric vehicles puts forward an important issue of how to charge the vehicles effectively. This problem, commonly referred to as Electric Vehicle Charging Scheduling (EVCS), has been proven to be NP-hard. Most of the existing works formulate the EVCS problem simply as a constrained shortest path finding problem and treat it by discrete optimization. However, other variables such as the charging amount of energy and the charging option at a station need to be considered in practical use. This paper hence formulates the EVCS problem as a hierarchical mixed-variable optimization problem, considering the dependency among the station selection, the charging option at each station and the charging amount settings. To adapt to the new problem model, we specifically design a Mixed-Variable Differentiate Evolution (MVDE) as the scheduling algorithm for our proposed EVCS system. The MVDE contains several specific operators, including a charging station route construction, a hierarchical mixed-variable mutation operator and a constraint-aware evaluation operator. Experimental results validate the effectiveness of our proposed MVDE-based system on both synthetic and real-world transportation networks.

The Reversible lanes optimization problem (RLOP) is a complex optimization problem in traffic management. The objective of this problem is to find an optimal direction assignment of lanes in an urban traffic network, so that the traffic capacity of urban streets could get the utmost promotion. To solve this problem efficiently, we particularly devise a histogram-based estimation of distribution algorithm (HEDA) in this paper. Specifically, during the estimation of the distribution, this algorithm considers different individuals differently based on their contributions. Besides, HEDA also combines both the current and historical population distribution information to generate offspring. Experiments conducted on ten different traffic network instances substantiate that HEDA achieves better performance than the compared method on most instances, especially on large-scale network instances.

Potable water distribution networks (WDNs) are important infrastructures of modern cities. A good design of the network can not only reduce the construction expenditure but also provide reliable service. Nowadays, the scale of the WDN of a city grows dramatically along with the city expansion, which brings heavy pressure to its optimal design. In order to solve the large-scale WDN optimization problem, a cooperative co-evolutionary algorithm is proposed in this paper. First, an iterative trace-based decomposition method is specially designed by utilizing the information of water tracing to divide a large-scale network into small subnetworks. Since little domain knowledge is required, the decomposition method has great adaptability to multiform networks. Meanwhile, during optimization, the proposed algorithm can gradually refine the decomposition to make it more accurate. Second, a new fitness function is devised to handle the pressure constraint of the problem. The function transforms the constraint into a part of the objective to punish the infeasible solutions. Finally, a new suite of benchmark networks are created with both balanced and imbalanced cases. Experimental results on a widely used real network and the benchmark networks show that the proposed algorithm is promising.

Through introducing the divide-and-conquer strategy, cooperative co-evolution (CC) has been successfully employed by many evolutionary algorithms (EAs) to solve large-scale optimization problems. In practice, it is common that different subcomponents of a large-scale problem have imbalanced contributions to the global fitness. Thus, how to utilize such imbalance and concentrate efforts on optimizing important subcomponents becomes an important issue for improving performance of cooperative co-EA, especially in distributed computing environment. In this paper, we propose a two-layer distributed CC (dCC) architecture with adaptive computing resource allocation for large-scale optimization. The first layer is the dCC model which takes charge of calculating the importance of subcomponents and accordingly allocating resources. An effective allocating algorithm is designed which can adaptively allocate computing resources based on a periodic contribution calculating method. The second layer is the pool model which takes charge of making fully utilization of imbalanced resource allocation. Within this layer, two different conformance policies are designed to help optimizers use the assigned computing resources efficiently. Empirical studies show that the two conformance policies and the computing resource allocation algorithm are effective, and the proposed distributed architecture possesses high scalability and efficiency.

Insurance has been increasingly realized as an important way of investment and risk aversion.Fruitful insurance products are launched by insurers, but there is little research on how to make a proper insurance investment plan for a specific policyholder given different kinds of policies.In this paper, we aim to propose a practical approach to multipolicy insurance investment planning with a data-driven model and an estimation of distribution algorithm (EDA).First, by making use of the insurance data accumulated in the modern financial market, an optimization model about how to choose endowment and hospitalization policies is built to maximize the yearly profit of insurance investment.With the model parameters set according to the real data from insurance market, the resulting plan is practical and individualized.Second, as the optimal solution cannot be achieved by mathematical deduction under this datadriven model, an EDA is introduced.To adapt the EDA for the considered problem, the proposed EDA is mixed with both the continuous and discrete probability distribution models to handle different kinds of variables.In addition, an adaptive scheme for choosing suitable distribution models and an efficient constraint handling strategy are proposed.Experiments under different conditions confirm the effectiveness and efficiency of the proposed model and method.

Path planning is one of the most important problems in the development of autonomous underwater vehicles (AUVs). In some common AUV missions, e.g., wreckage search for rescue, an AUV is often required to traverse multiple targets in a complex environment with dense obstacles. In such case, the AUV path planning problem becomes even more challenging. In order to address the problem, this paper develops a two-layer algorithm, namely ACO-A*, by combining the ant colony optimization (ACO) with the A* search. Once a mission with a set of arbitrary targets is assigned, ACO is responsible to determine the traveling order of targets. But, prior to ACO, a cost graph indicating the necessary traveling costs among targets must be quickly established to facilitate traveling order evaluation. For this purpose, a coarse-grained modeling with a representative-based estimation (RBE) strategy is proposed. Following the order obtained by ACO, targets will be traversed one by one and the pairwise path planning to reach each target can be performed during vehicle driving. To deal with the dense obstacles, A* is adopted to plan paths based on a fine-grained modeling and an admissible heuristic function is designed for A* to guarantee its optimality. Experiments on both synthetic and realistic scenarios have been designed to validate the efficiency of the proposed ACO-A*, as well as the effectiveness of RBE and the necessity of A*.

Cross-docks serve as distribution centers where shipments from different vendors are first consolidated according to their destinations, and then delivered to the retailers directly, with little or no storage in between. A critical problem encountered in the operation of cross-docks is the assignment of receiving and shipping doors, which greatly influences the labor or machinery cost of transferring the shipments between inbound and outbound transports. We show that the cross-dock door assignment problem (CDAP) is strictly non-deterministic polynomial-time complete. Although some deterministic algorithms have been reported to handle small-scale problems, the solutions to the middle- and large-scale CDAPs progressed at a slow pace. In this paper, we develop a nature-inspired dual-colony ant algorithm for CDAP, in which the two colonies of ants cooperatively search the optimal assignments of receiving and shipping doors to minimize the transferring costs of shipments. A collaborative local search strategy is designed and incorporated into the algorithm to enhance the search efficiency. Experiments have been conducted on a number of problem instances with different cross-dock sizes and freight flow patterns. The results show that the proposed algorithm is very competitive and can provide better solutions than the state-of-the-art heuristic algorithms.

As you open this January issue of the IEEE Transactions on Neural Networks and Learning Systems (TNNLS), I hope everyone enjoyed a great holiday season and is excited for the new year of 2019. I am very delighted and honored to report several key metrics of IEEE TNNLS to the community.

As the mutation strategy and algorithmic parameters in differential evolution (DE) are sensitive to the problems being solved, a hot research topic is to adaptively control the strategy and parameters according to the requirements of the problem. In the literature, most adaptive DE use either historical experiences of the population or heuristic information of the individuals to promote adaptation. In this paper, we develop a novel variant of adaptive DE, utilizing both the historical experience and heuristic information for the adaptation. In this novel historical and heuristic DE (HHDE), each individual dynamically adjusts its mutation strategy and associated parameters not only by learning from previous successful experience of the whole population, but also according to heuristic information related with its own current state. These help the algorithm select a more suitable mutation strategy and determinate better parameters for each individual in different evolutionary stages. The performance of the proposed HHDE is extensively evaluated on 30 benchmark functions with different dimensions. Experimental results confirm the competitiveness of the proposed algorithm to a number of DE variants.

Nowadays, large-scale optimization problems are ubiquitous in many research fields. To deal with such problems efficiently, this paper proposes a distributed differential evolution with adaptive mergence and split (DDE-AMS) on subpopulations. The novel mergence and split operators are designed to make full use of limited population resource, which is important for large-scale optimization. They are adaptively performed based on the performance of the subpopulations. During the evolution, once a subpopulation finds a promising region, the current worst performing subpopulation will merge into it. If the merged subpopulation could not continuously provide competitive solutions, it will be split in half. In this way, the number of subpopulations is adaptively adjusted and better performing subpopulations obtain more individuals. Thus, population resource can be adaptively arranged for subpopulations during the evolution. Moreover, the proposed algorithm is implemented with a parallel master-slave manner. Extensive experiments are conducted on 20 widely used large-scale benchmark functions. Experimental results demonstrate that the proposed DDE-AMS could achieve competitive or even better performance compared with several state-of-the-art algorithms. The effects of DDE-AMS components, adaptive behavior, scalability, and parameter sensitivity are also studied. Finally, we investigate the speedup ratios of DDE-AMS with different computation resources.

This paper studies a specific class of multiobjective combinatorial optimization problems (MOCOPs), namely the permutation-based MOCOPs. Many commonly seen MOCOPs, e.g., multiobjective traveling salesman problem (MOTSP), multiobjective project scheduling problem (MOPSP), belong to this problem class and they can be very different. However, as the permutation-based MOCOPs share the inherent similarity that the structure of their search space is usually in the shape of a permutation tree, this paper proposes a generic multiobjective set-based particle swarm optimization methodology based on decomposition, termed MS-PSO/D. In order to coordinate with the property of permutation-based MOCOPs, MS-PSO/D utilizes an element-based representation and a constructive approach. Through this, feasible solutions under constraints can be generated step by step following the permutation-tree-shaped structure. And problem-related heuristic information is introduced in the constructive approach for efficiency. In order to address the multiobjective optimization issues, the decomposition strategy is employed, in which the problem is converted into multiple single-objective subproblems according to a set of weight vectors. Besides, a flexible mechanism for diversity control is provided in MS-PSO/D. Extensive experiments have been conducted to study MS-PSO/D on two permutation-based MOCOPs, namely the MOTSP and the MOPSP. Experimental results validate that the proposed methodology is promising.

In pedagogy, teachers usually separate mixed-level students into different levels, treat them differently and teach them in accordance with their cognitive and learning abilities. Inspired from this idea, we consider particles in the swarm as mixed-level students and propose a level-based learning swarm optimizer (LLSO) to settle large-scale optimization, which is still considerably challenging in evolutionary computation. At first, a level-based learning strategy is introduced, which separates particles into a number of levels according to their fitness values and treats particles in different levels differently. Then, a new exemplar selection strategy is designed to randomly select two predominant particles from two different higher levels in the current swarm to guide the learning of particles. The cooperation between these two strategies could afford great diversity enhancement for the optimizer. Further, the exploration and exploitation abilities of the optimizer are analyzed both theoretically and empirically in comparison with two popular particle swarm optimizers. Extensive comparisons with several state-of-the-art algorithms on two widely used sets of large-scale benchmark functions confirm the competitive performance of the proposed optimizer in both solution quality and computational efficiency. Finally, comparison experiments on problems with dimensionality increasing from 200 to 2000 further substantiate the good scalability of the developed optimizer.

With the rapid development of e-commerce, logistics industry becomes a crucial component in the e-commercial ecological chain. Impelled by both economical and environmental benefit, logistics companies demand automated tools more urgently than ever. In this paper, a dynamic logistic dispatching system is proposed. The underlying model of the dispatching system is the dynamic vehicle routing problem which allows new orders being received as the working day progress. With this feature, the system becomes more practical than the systems with traditional static vehicle routing models, but is also more challenging as the vehicles must be scheduled in a dynamic way. The core of the system is a specially designed set-based particle swarm optimization algorithm. According to the characteristic of the problem, a new encoding scheme is defined by set and possibility, and a local refinement method is designed to accelerate the convergence speed of the algorithm. In addition, two more techniques: 1) region partition and 2) archive strategy are incorporated in the dispatching system to reduce the complexity of the problem and to facilitate the optimization process, helping the dispatcher control the vehicles in real time. The proposed system is tested on various benchmarks with different scales. Experimental results show that the proposed dispatching system is effective.

Taxi dispatch is a critical issue for taxi company to consider in modern life. This paper formulates the problem into a taxi-passenger matching model and proposes a parallel ant colony optimization algorithm to optimize the model. As the search space is large, we develop a region-dependent decomposition strategy to divide and conquer the problem. To keep the global performance, a critical region is defined to deal with the communications and interactions between the subregions. The experimental results verify that the proposed algorithm is effective, efficient, and extensible, which outperforms the traditional global perspective greedy algorithm in terms of both accuracy and efficiency.

Virtual network embedding (VNE), which is a significant problem in cloud computing, has gained much attention among many researchers recently. Due to the NP-hardness of VNE, the existing solvers are either inefficient or inaccurate. This paper develops a novel algorithm based on the ant colony system (ACS). To solve the VNE problem, the algorithm structure concentrates on the link mapping from virtual network to substrate network. Particularly, for a specific virtual network request, we first sort the embedding sequence of virtual nodes according to their link resources. Then, ACS is used to embed the virtual nodes onto substrate nodes according the sorted sequence, while the virtual links are mapped via a shortest path strategy for the embedded nodes. For the first time, we propose a link resource heuristic information and incorporate it into the search process of ACS. The link resource heuristic information has two significant effects, one is to make virtual nodes tend to be embedded on the substrate nodes that cost less bandwidth, and the other is to confirm the connectivity of the substrate nodes that embed the virtual nodes. The proposed algorithm improves the optimization performance of VNE when compared with a few existing algorithms, while it substantially reduces the cost of time.

Pedestrian detection plays a pivotal role in various domains but is still a challenging problem nowadays. In this study, we transform the multiple-pedestrian detection problem into a multimodal optimization problem and then utilize a multimodal estimation of distribution algorithm (MEDA) to optimize this problem based on Histograms of Oriented Gradients (HOG) feature and Support Vector Machines (SVM). Specifically, we adopt a three-dimensional vector to represent a rectangular region of an image and also use it to encode individuals. Then, a state-of-the-art multimodal optimization algorithm called MEDA is utilized to evolve the individuals, so that a series of optimal rectangular regions containing pedestrians can be obtained. Experiments conducted on a set of images from one pedestrian dataset called INRIA confirm that in comparison with the classical HOG-SVM method and one state-of-the-art method, the developed algorithm cannot only achieve higher detection accuracy on images containing different numbers of pedestrians, but also can remain high computational efficiency.

The cooperative co-evolution (CC) framework is one of the most efficient methods to solve large scale optimization problems. The traditional CC framework divides decision variables into several mutually-exclusive groups. In this paper, we propose the overlapped cooperative co-evolution (OCC) framework for large scale optimization problems. In OCC framework, the decision variables that have strong impacts on the optimization are overlapped by different groups. First, we devise the delta-disturbance strategy to detect the influential variables. Then the overlapped grouping strategy is proposed to overlap the influential variables. Finally, the OCC framework is proposed to allocate more computation resources to the influential decision variables. To compare the performance of CC and OCC, we combine two frameworks with the random grouping strategy and the differential grouping strategy, and the comparative experiments are conducted on the CEC2010 benchmark functions. The experimental results verify that the proposed OCC framework is promising through comparing with the CC framework.

The virtual networking embedding (VNE) problem is a core issue in network virtualization. This is also a challenging problem as it contains different kinds of constraints, and its complexity becomes even higher in an online VNE problem with thousands of virtual network (VN) requests. In this paper, we proposed an ant colony system based VNE algorithm, called ACS-VNE, for the online VNE problem. The benefits of ACS-VNE are threefold. First, it is an ACS based algorithm so it can take full advantage of the dynamically changing heuristic information and pheromone to improve the quality of a solution. Second, different from previous work that only considers the resource of nodes in node mapping phase, we take the distance message related to links into consideration so that we can reduce the cost of VN requests. The last but not least, the algorithm tries to reduce the cost for every single VN and it helps to increase the possibility of accepting more future VN requests. The proposed method is tested on both the single VN request VNE problem and the online VNE problem. Experimental results show that the proposed algorithm outperforms some previous approaches in terms of average revenue and acceptance ratio, and the results also have a relatively low cost.

The popular performance profiles and data profiles for benchmarking deterministic optimization algorithms are extended to benchmark stochastic algorithms for global optimization problems. A general confidence interval is employed to replace the significance test, which is popular in traditional benchmarking methods but suffering more and more criticisms. Through computing confidence bounds of the general confidence interval and visualizing them with performance profiles and (or) data profiles, our benchmarking method can be used to compare stochastic optimization algorithms by graphs. Compared with traditional benchmarking methods, our method is synthetic statistically and therefore is suitable for large sets of benchmark problems. Compared with some sample-mean-based benchmarking methods, e.g., the method adopted in black-box-optimization-benchmarking workshop/competition, our method considers not only sample means but also sample variances. The most important property of our method is that it is a distribution-free method, i.e., it does not depend on any distribution assumption of the population. This makes it a promising benchmarking method for stochastic optimization algorithms. Some examples are provided to illustrate how to use our method to compare stochastic optimization algorithms.

Large-scale optimization has become a significant yet challenging area in evolutionary computation. To solve this problem, this paper proposes a novel segment-based predominant learning swarm optimizer (SPLSO) swarm optimizer through letting several predominant particles guide the learning of a particle. First, a segment-based learning strategy is proposed to randomly divide the whole dimensions into segments. During update, variables in different segments are evolved by learning from different exemplars while the ones in the same segment are evolved by the same exemplar. Second, to accelerate search speed and enhance search diversity, a predominant learning strategy is also proposed, which lets several predominant particles guide the update of a particle with each predominant particle responsible for one segment of dimensions. By combining these two learning strategies together, SPLSO evolves all dimensions simultaneously and possesses competitive exploration and exploitation abilities. Extensive experiments are conducted on two large-scale benchmark function sets to investigate the influence of each algorithmic component and comparisons with several state-of-the-art meta-heuristic algorithms dealing with large-scale problems demonstrate the competitive efficiency and effectiveness of the proposed optimizer. Further the scalability of the optimizer to solve problems with dimensionality up to 2000 is also verified.

Taking the advantage of estimation of distribution algorithms (EDAs) in preserving high diversity, this paper proposes a multimodal EDA. Integrated with clustering strategies for crowding and speciation, two versions of this algorithm are developed, which operate at the niche level. Then these two algorithms are equipped with three distinctive techniques: 1) a dynamic cluster sizing strategy; 2) an alternative utilization of Gaussian and Cauchy distributions to generate offspring; and 3) an adaptive local search. The dynamic cluster sizing affords a potential balance between exploration and exploitation and reduces the sensitivity to the cluster size in the niching methods. Taking advantages of Gaussian and Cauchy distributions, we generate the offspring at the niche level through alternatively using these two distributions. Such utilization can also potentially offer a balance between exploration and exploitation. Further, solution accuracy is enhanced through a new local search scheme probabilistically conducted around seeds of niches with probabilities determined self-adaptively according to fitness values of these seeds. Extensive experiments conducted on 20 benchmark multimodal problems confirm that both algorithms can achieve competitive performance compared with several state-of-the-art multimodal algorithms, which is supported by nonparametric tests. Especially, the proposed algorithms are very promising for complex problems with many local optima.

The selection of swarm leaders (i.e., the personal best and global best), is important in the design of a multiobjective particle swarm optimization (MOPSO) algorithm. Such leaders are expected to effectively guide the swarm to approach the true Pareto optimal front. In this paper, we present a novel external archive-guided MOPSO algorithm (AgMOPSO), where the leaders for velocity update are all selected from the external archive. In our algorithm, multiobjective optimization problems (MOPs) are transformed into a set of subproblems using a decomposition approach, and then each particle is assigned accordingly to optimize each subproblem. A novel archive-guided velocity update method is designed to guide the swarm for exploration, and the external archive is also evolved using an immune-based evolutionary strategy. These proposed approaches speed up the convergence of AgMOPSO. The experimental results fully demonstrate the superiority of our proposed AgMOPSO in solving most of the test problems adopted, in terms of two commonly used performance measures. Moreover, the effectiveness of our proposed archive-guided velocity update method and immune-based evolutionary strategy is also experimentally validated on more than 30 test MOPs.

Detecting community structure has become one important technique for studying complex networks. Although many community detection algorithms have been proposed, most of them focus on separated communities, where each node can belong to only one community. However, in many real-world networks, communities are often overlapped with each other. Developing overlapping community detection algorithms thus becomes necessary. Along this avenue, this paper proposes a maximal clique based multiobjective evolutionary algorithm (MOEA) for overlapping community detection. In this algorithm, a new representation scheme based on the introduced maximal-clique graph is presented. Since the maximal-clique graph is defined by using a set of maximal cliques of original graph as nodes and two maximal cliques are allowed to share the same nodes of the original graph, overlap is an intrinsic property of the maximal-clique graph. Attributing to this property, the new representation scheme allows MOEAs to handle the overlapping community detection problem in a way similar to that of the separated community detection, such that the optimization problems are simplified. As a result, the proposed algorithm could detect overlapping community structure with higher partition accuracy and lower computational cost when compared with the existing ones. The experiments on both synthetic and real-world networks validate the effectiveness and efficiency of the proposed algorithm.

Seeking multiple optima simultaneously, which multimodal optimization aims at, has attracted increasing attention but remains challenging. Taking advantage of ant colony optimization (ACO) algorithms in preserving high diversity, this paper intends to extend ACO algorithms to deal with multimodal optimization. First, combined with current niching methods, an adaptive multimodal continuous ACO algorithm is introduced. In this algorithm, an adaptive parameter adjustment is developed, which takes the difference among niches into consideration. Second, to accelerate convergence, a differential evolution mutation operator is alternatively utilized to build base vectors for ants to construct new solutions. Then, to enhance the exploitation, a local search scheme based on Gaussian distribution is self-adaptively performed around the seeds of niches. Together, the proposed algorithm affords a good balance between exploration and exploitation. Extensive experiments on 20 widely used benchmark multimodal functions are conducted to investigate the influence of each algorithmic component and results are compared with several state-of-the-art multimodal algorithms and winners of competitions on multimodal optimization. These comparisons demonstrate the competitive efficiency and effectiveness of the proposed algorithm, especially in dealing with complex problems with high numbers of local optima.

In cloud computing, scheduling plays a critical role for quality of service (QoS) and provider efficiency which are generally measured by several metrics and make the scheduling a multiobjective problem (MOP). In this paper, we propose a differential evolution algorithm with double-level archives (DE-DLA) for bi-objective cloud task scheduling. The proposed algorithm is based on the newly-developed framework, multiobjective evolutionary algorithm with double-level archives (MOEA-DLA), and uses differential evolution to implement this framework. Global Archive is used to save Pareto-optimal individuals for the whole problem and Sub-archive is used to save several comparatively good individuals for the corresponding sub-problem formed by decomposition. So the algorithm takes advantages of both whole multiobjective problem optimization and decomposition based optimization. Precedence constraint in user's application is considered in the scheduling model of this paper. To minimize cost and makespan simultaneously, the proposed algorithm tries to find optimal resource allocation and optimal order of task executing. In the experiment, compared with two other algorithms, DE-DLA has shown competitive advantages.

Following the first three industrial revolutions, Industry 4.0 (I4) aims at realizing mass customization at a mass production cost. Currently, however, there is a lack of smart analytics tools for achieving such a goal. This paper investigates this issues and then develops a predictive analytics framework integrating cloud computing, big data analysis, business informatics, communication technologies, and digital industrial production systems. Computational intelligence in the form of a self-organizing map (SOM) is used to manage relevant big data for feeding potential customer needs and wants to smart designs for targeted productivity and customized mass production. The selection of patterns from big data with SOM helps with clustering and with the selection of optimal attributes. A car customization case study shows that the SOM is able to assign new clusters when growing knowledge of customer needs and wants. The self-organizing tool offers a number of features suitable to smart design that is required in realizing Industry 4.0.

This paper presents a random-based dynamic grouping strategy (RDG) for cooperative coevolution to deal with large scale multi-objective optimization problems (MOPs) by decomposing the whole dimension into several groups of variables with an equal size. First, a decomposer pool containing different group sizes is designed. Then, a group size is dynamically selected with probability in the evolution process. The probability of each group size in the pool is computed based on the historical performance measured by C-metric, a common metric in multi-objective optimization. Under the selected group size, random grouping is executed to decompose the whole dimension into groups. Through this, both the group size and the group components are dynamic. Finally, combining RDG with a traditional and famous multi-objective evolutionary algorithm (MOEA) named MOEA/D, we develop MOEA/D-RDG to cope with large scale MOPs. The efficacy of the proposed MOEA/D-RDG is verified on two sets of MOPs (UF1-UF10 and WFG1-WFG9) through comparing with two MOEA/D variants.

Large scale optimization has become an important and challenging area in evolutionary computation. To solve this kind of problems efficiently, this paper proposes a multiple parents guided differential evolution (MPGDE) algorithm. Instead of using only one parent to guide each individual in traditional DE variants, multiple top ranked parents are utilized to direct each individual to search the space. Since the failed parents or trial vectors may also contain useful information, we maintain an archive to preserve these failed individuals and utilize a niching method to update the archive during evolution. Combining the above together, we put forward a new mutation strategy for DE. Cooperated with existing self-adaptive strategies for parameters in DE, MPGDE can afford a good balance between exploration and exploitation, so that promising performance can be obtained. Extensive experiments are conducted on 20 CEC'2010 large scale benchmark functions with 1000 dimensions to verify the efficacy and effectiveness of the developed MPGDE in comparison with several state-of-the-art algorithms dealing with large scale problems.

In recent years, multiobjective immune algorithms (MOIAs) have shown promising performance in solving multiobjective optimization problems (MOPs). However, basic MOIAs only use a single hypermutation operation to evolve individuals, which may induce some difficulties in tackling complicated MOPs. In this paper, we propose a novel hybrid evolutionary framework for MOIAs, in which the cloned individuals are divided into several subpopulations and then evolved using different evolutionary strategies. An example of this hybrid framework is implemented, in which simulated binary crossover and differential evolution with polynomial mutation are adopted. A fine-grained selection mechanism and a novel elitism sharing strategy are also adopted for performance enhancement. Various comparative experiments are conducted on 28 test MOPs and our empirical results validate the effectiveness and competitiveness of our proposed algorithm in solving MOPs of different types.

Operating mode scheduling is crucial for the lifetime of wireless sensor networks (WSNs). However, the growing scale of networks has made such a scheduling problem more challenging, as existing set cover and evolutionary algorithms become unable to provide satisfactory efficiency due to the curse of dimensionality. In this paper, a Kuhn–Munkres (KM) parallel genetic algorithm is developed to solve the set cover problem and is applied to the lifetime maximization of large-scale WSNs. The proposed algorithm schedules the sensors into a number of disjoint complete cover sets and activates them in batch for energy conservation. It uses a divide-and-conquer strategy of dimensionality reduction, and the polynomial KM algorithm a are hence adopted to splice the feasible solutions obtained in each subarea to enhance the search efficiency substantially. To further improve global efficiency, a redundant-trend sensor schedule strategy was developed. Additionally, we meliorate the evaluation function through penalizing incomplete cover sets, which speeds up convergence. Eight types of experiments are conducted on a distributed platform to test and inform the effectiveness of the proposed algorithm. The results show that it offers promising performance in terms of the convergence rate, solution quality, and success rate.

The aim of multimodal optimization is to locate multiple optima of a given problem. Evolutionary algorithms (EAs) are one of the most promising candidates for multimodal optimization. However, due to the use of greedy selection operators, the population of an EA will generally converge to one region of attraction. By incorporating a well-designed selection operator that can facilitate the formation of different species, EAs will be able to allow multiple convergence. Following this research avenue, we propose a novel selection operator, namely, queueing selection (QS) and integrate it with one of the most promising DE variants, called composite differential evolution (CoDE). The integrated algorithm (denoted by CoDE-QS) inherits the strong global search ability of CoDE and is capable of finding and maintaining multiple optima. It has been tested on the CEC2013 benchmark functions. Experimental results show that CoDE-QS is very competitive.

With the proliferation of wireless sensor networks (WSN), the issues about how to schedule all the sensors in order to maximize the system's working time have been in the spotlight. Inspired by the promising performance of ant colony optimization (ACO) in solving combinational optimization problem, we attempt to apply it in prolonging the life time of WSN. In this paper, we propose an improved version of ACO algorithm to get solutions about selecting exact sensors to accomplish the covering task in a reasonable way to preserve more energy to maintain longer active time. The methodology is based on maximizing the disjoint subsets of sensors, in other words, in every time interval, choosing which sensor to sustain active state must be rational in certain extent. With the aid of pheromone and heuristic information, a better solution can be constructed in which pheromone denotes the previous scheduling experience, while heuristic information reflects the desirable device assignment. Orderly sensor selection is designed to construct an advisable subset for coverage task. The proposed method has been successfully applied in solving limited energy assignment problem no matter in homogenous or heterogeneous WSNs. Simulation experiments have shown it has a good performance in addressing relevant issues.

This paper takes the multiobjective traveling salesman problem (MOTSP) as the representative for multiobjective combinatorial problems and develop a set-based comprehensive learning particle swarm optimization (S-CLPSO) with decomposition for solving MOTSP. The main idea is to take advantages of both the multiobjective evolutionary algorithm based on decomposition (MOEA/D) framework and our previously proposed S-CLPSO method for discrete optimization. Consistent to MOEA/D, a multiobjective problem is decomposed into a set of subproblems, each of which is represented as a weight vector and solved by a particle. Thus the objective vector of a solution or the cost vector between two cities will be transformed into real fitness to be used in S-CLPSO for the exemplar construction, the heuristic information generation and the update of pBest. To validate the proposed method, experiments based on TSPLIB benchmark are conducted and the results indicate that the proposed algorithm can improve the solution quality to some degree.

The tightly restricted resource in wireless sensors networks (WSN) makes it challenging to schedule the task assignment for better performance. Binary particle swarm optimizers (BPSO) along with its modified version (MBPSO) have shown promising performance to this problem, but premature convergence remains a key issue. To improve performance of BPSO for task assigning in WSN, this paper first develops various extended BPSOs by using different topologies and the comprehensive learning strategy. An integrated comparison among these candidate approaches and the MBPSO is carried out. In addition, the choice of transfer function highly affects the global optimizing ability of BPSO. Thus the significance of transfer functions with different shapes adopted in BPSO is discussed. Through sufficient simulations and analysis, it is found that the BPSO with the comprehensive learning strategy and a V-shaped transfer function is very promising, especially toward large-scale problems.

Existing multiobjective evolutionary algorithms (MOEAs) tackle a multiobjective problem either as a whole or as several decomposed single-objective sub-problems. Though the problem decomposition approach generally converges faster through optimizing all the sub-problems simultaneously, there are two issues not fully addressed, i.e., distribution of solutions often depends on a priori problem decomposition, and the lack of population diversity among sub-problems. In this paper, a MOEA with double-level archives is developed. The algorithm takes advantages of both the multiobjective-problem-level and the sub-problem-level approaches by introducing two types of archives, i.e., the global archive and the sub-archive. In each generation, self-reproduction with the global archive and cross-reproduction between the global archive and sub-archives both breed new individuals. The global archive and sub-archives communicate through cross-reproduction, and are updated using the reproduced individuals. Such a framework thus retains fast convergence, and at the same time handles solution distribution along Pareto front (PF) with scalability. To test the performance of the proposed algorithm, experiments are conducted on both the widely used benchmarks and a set of truly disconnected problems. The results verify that, compared with state-of-the-art MOEAs, the proposed algorithm offers competitive advantages in distance to the PF, solution coverage, and search speed.

Utilizing cumulative correlation information already existing in an evolutionary process, this paper proposes a predictive approach to the reproduction mechanism of new individuals for differential evolution (DE) algorithms. DE uses a distributed model (DM) to generate new individuals, which is relatively explorative, whilst evolution strategy (ES) uses a centralized model (CM) to generate offspring, which through adaptation retains a convergence momentum. This paper adopts a key feature in the CM of a covariance matrix adaptation ES, the cumulatively learned evolution path (EP), to formulate a new evolutionary algorithm (EA) framework, termed DEEP, standing for DE with an EP. Without mechanistically combining two CM and DM based algorithms together, the DEEP framework offers advantages of both a DM and a CM and hence substantially enhances performance. Under this architecture, a self-adaptation mechanism can be built inherently in a DEEP algorithm, easing the task of predetermining algorithm control parameters. Two DEEP variants are developed and illustrated in the paper. Experiments on the CEC'13 test suites and two practical problems demonstrate that the DEEP algorithms offer promising results, compared with the original DEs and other relevant state-of-the-art EAs.

Cloud computing provides resources as services in pay-as-you-go mode to customers by using virtualization technology. As virtual machine (VM) is hosted on physical server, great energy is consumed by maintaining the servers in data center. More physical servers means more energy consumption and more money cost. Therefore, the VM placement (VMP) problem is significant in cloud computing. This paper proposes an approach based on ant colony optimization (ACO) to solve the VMP problem, named as ACO-VMP, so as to effectively use the physical resources and to reduce the number of running physical servers. The number of physical servers is the same as the number of the VMs at the beginning. Then the ACO approach tries to reduce the physical server one by one. We evaluate the performance of the proposed ACO-VMP approach in solving VMP with the number of VMs being up to 600. Experimental results compared with the ones obtained by the first-fit decreasing (FFD) algorithm show that ACO-VMP can solve VMP more efficiently to reduce the number of physical servers significantly, especially when the number of VMs is large.

The performance of a multimodal evolutionary algorithm is highly sensitive to the setting of population size. This paper introduces a generic archive technique to reduce the importance of properly setting the population size parameter. The proposed archive technique contains two components: subpopulation identification and convergence detection. The first component is used to identify subpopulations in a number of individuals while the second one is used to determine whether a subpopulation is converged. By using the two components, converged subpopulations are identified, and then, individuals in the converged subpopulations are stored in an external archive and re-initialized to search for other optima. We integrate the archive technique with several state-of-the-art PSO-based multimodal algorithms. Experiments are carried out on a recently proposed multimodal problem set to investigate the effect of the archive technique. The experimental results show that the proposed method can reduce the influence of the population size parameter and improve the performance of multimodal algorithms.

The performance of differential evolution (DE) largely depends on its mutation strategy and control parameters. In this paper, we propose an adaptive DE (ADE) algorithm with a new mutation strategy DE/lbest/1 and a two-level adaptive parameter control scheme. The DE/lbest/1 strategy is a variant of the greedy DE/best/1 strategy. However, the population is mutated under the guide of multiple locally best individuals in DE/lbest/1 instead of one globally best individual in DE/best/1. This strategy is beneficial to the balance between fast convergence and population diversity. The two-level adaptive parameter control scheme is implemented mainly in two steps. In the first step, the population-level parameters Fp and CRp for the whole population are adaptively controlled according to the optimization states, namely, the exploration state and the exploitation state in each generation. These optimization states are estimated by measuring the population distribution. Then, the individual-level parameters Fi and CRi for each individual are generated by adjusting the population-level parameters. The adjustment is based on considering the individual's fitness value and its distance from the globally best individual. This way, the parameters can be adapted to not only the overall state of the population but also the characteristics of different individuals. The performance of the proposed ADE is evaluated on a suite of benchmark functions. Experimental results show that ADE generally outperforms four state-of-the-art DE variants on different kinds of optimization problems. The effects of ADE components, parameter properties of ADE, search behavior of ADE, and parameter sensitivity of ADE are also studied. Finally, we investigate the capability of ADE for solving three real-world optimization problems.

In this paper, we propose a novel greedy position update strategy for the ABC algorithm. The greedy position update strategy is implemented mainly in two steps. In the first step, good solutions randomly chosen from the top t solutions in the current population are used to guide the search process of onlooker bees. In the second step, the new parameter t is adaptively adjusted in each iteration of the algorithm. The adjustment is simply based on determining whether the globally best solution is obtained by the employed bees or the onlooker bees. The effect of the proposed greedy position update strategy is evaluated on a set of benchmark functions. Experimental results show that the proposed strategy can significantly improve the performance of the classic ABC algorithm. In addition, ABC using the proposed strategy exhibits very competitive performance when compared with some existing ABC variants.

The TSP problem is considered as classical discrete optimization grouping problem, which is widely used in practice, but it is real a difficult NP problem. Simultaneously differential evolution (DE) algorithm has been proven to be a powerful optimization algorithm. Since the mutation process of DE contains a series of arithmetic operators operating on continuous space, few algorithms based on DE solve this problem nicely and the advantages of DE in continuous space cannot be used to solve TSP. To take full advantages of the strengths of DE, this paper proposes a set-based DE (S-DE) which completely follows the procedure of the original DE. We present a representation scheme to characterize the discrete problem space and by redefining its basic concept and all related operators in mutation, DE can operate directly on the original set space of the discrete optimization problems instead of performing a space transformation. In that way, the searching features of DE in continuous space is kept. In experiment, we test the performance of our proposed S-DE and the results show it is very promising.

Nurse rostering is a non-deterministic polynomial problem with many constraints. In the literature, a number of heuristic approaches have been proposed, but few of them can achieve satisfying performance on both solution quality and search speed. Inspired by the successful experience of ant colony optimization (ACO) on many highly-constrained problems, this paper proposed an ant colony optimization approach termed ACO-NR for solving the nurse rostering problem. First, the search space of the nurse rostering problem is remodeled as a graph, with each solution corresponding to a path on the graph. Then a heuristic function is designed to guide the path construction behavior of ACO-NR. The heuristic information comes not only from the static information defined by the problem-dependent knowledge, but also from the dynamic information generated by the solution construction procedure. A penalty function is defined to help ACO-NR handle problem constraints. Experimental results on 52 benchmark instances show that the proposed ACO-NR can achieve better performance than classic nurse rostering algorithms.

Human being is the most intelligent organism in the world and the brainstorming process popularly used by them has been demonstrated to be a significant and promising way to create great ideas for problem solving. Brain storm optimization (BSO) is a new kind of swarm intelligence algorithm inspired by human being creative problem solving process. BSO transplants the brainstorming process in human being into optimization algorithm design and gains successes. BSO generally uses the grouping, replacing, and creating operators to produce ideas as many as possible to approach the problem solution generation by generation. In these operators, BSO involves mainly three control parameters named: (1) p_replce to control the replacing operator; (2) p_one to control the creating operator to create new ideas between one cluster and two clusters; and (3) p_center (p_one_center and p_two_center) to control using cluster center or random idea to create new idea. In this paper, we make investigations on these parameters to see how they affect the performance of BSO. More importantly, a new BSO variant designed according to the investigation results is proposed and its performance is evaluated.

The optimal selection of parameters for time-delay embedding is crucial to the analysis and the forecasting of chaotic time series. Although various parameter selection techniques have been developed for conventional uniform embedding methods, the study of parameter selection for nonuniform embedding is progressed at a slow pace. In nonuniform embedding, which enables different dimensions to have different time delays, the selection of time delays for different dimensions presents a difficult optimization problem with combinatorial explosion. To solve this problem efficiently, this paper proposes an ant colony optimization (ACO) approach. Taking advantage of the characteristic of incremental solution construction of the ACO, the proposed ACO for nonuniform embedding (ACO-NE) divides the solution construction procedure into two phases, i.e., selection of embedding dimension and selection of time delays. In this way, both the embedding dimension and the time delays can be optimized, along with the search process of the algorithm. To accelerate search speed, we extract useful information from the original time series to define heuristics to guide the search direction of ants. Three geometry- or model-based criteria are used to test the performance of the algorithm. The optimal embeddings found by the algorithm are also applied in time-series forecasting. Experimental results show that the ACO-NE is able to yield good embedding solutions from both the viewpoints of optimization performance and prediction accuracy.

In nature, almost every organism ages and has a limited lifespan. Aging has been explored by biologists to be an important mechanism for maintaining diversity. In a social animal colony, aging makes the old leader of the colony become weak, providing opportunities for the other individuals to challenge the leadership position. Inspired by this natural phenomenon, this paper transplants the aging mechanism to particle swarm optimization (PSO) and proposes a PSO with an aging leader and challengers (ALC-PSO). ALC-PSO is designed to overcome the problem of premature convergence without significantly impairing the fast-converging feature of PSO. It is characterized by assigning the leader of the swarm with a growing age and a lifespan, and allowing the other individuals to challenge the leadership when the leader becomes aged. The lifespan of the leader is adaptively tuned according to the leader's leading power. If a leader shows strong leading power, it lives longer to attract the swarm toward better positions. Otherwise, if a leader fails to improve the swarm and gets old, new particles emerge to challenge and claim the leadership, which brings in diversity. In this way, the concept “aging” in ALC-PSO actually serves as a challenging mechanism for promoting a suitable leader to lead the swarm. The algorithm is experimentally validated on 17 benchmark functions. Its high performance is confirmed by comparing with eight popular PSO variants.

Research into developing effective computer aided techniques for planning software projects is important and challenging for software engineering. Different from projects in other fields, software projects are people-intensive activities and their related resources are mainly human resources. Thus, an adequate model for software project planning has to deal with not only the problem of project task scheduling but also the problem of human resource allocation. But as both of these two problems are difficult, existing models either suffer from a very large search space or have to restrict the flexibility of human resource allocation to simplify the model. To develop a flexible and effective model for software project planning, this paper develops a novel approach with an event-based scheduler (EBS) and an ant colony optimization (ACO) algorithm. The proposed approach represents a plan by a task list and a planned employee allocation matrix. In this way, both the issues of task scheduling and employee allocation can be taken into account. In the EBS, the beginning time of the project, the time when resources are released from finished tasks, and the time when employees join or leave the project are regarded as events. The basic idea of the EBS is to adjust the allocation of employees at events and keep the allocation unchanged at nonevents. With this strategy, the proposed method enables the modeling of resource conflict and task preemption and preserves the flexibility in human resource allocation. To solve the planning problem, an ACO algorithm is further designed. Experimental results on 83 instances demonstrate that the proposed method is very promising.

Adapting genetic operators and parameter settings during the optimization process can improve the overall performance of evolutionary algorithms (EAs). In this paper, a novel maturity-based adaptation strategy for EAs is proposed. During the search process, a maturity degree of the population is calculated based on both the population distribution in the search space and that in the fitness space. According to the maturity degree, four evolution states of EAs are defined by a set of thresholds. As both the convergence of the genotypes (reflected by the geographical distance among the individuals) and that of the phenotypes (shown by the differentiation over individuals' fitness values) are taken into consideration, the estimation of the evolution state is very comprehensive. Then, a set of adaptation rules is applied to adapt the parameters and operators of EAs according to the maturity degree and evolution state. Implemented on genetic algorithm (GA), the probabilities of crossover and mutation are tuned to fulfill the current evolution requirement of the population. Meanwhile, a novel allele gene-based mutation scheme and the traditional mutation are alternately executed. Experimental results on eight benchmark functions show that the proposed maturity-based adaptation strategy can bring significant improvements in search speed, solution accuracy and robustness.

This paper addresses a complicated problem in project management termed the payment scheduling negotiation problem. The problem is a practical extension of the classical multi-mode resource constrained project scheduling problem and it considers the financial aspects of both the project client and contractor in a contracting project. The client and contractor negotiate with each other to determine an optimal payment schedule and an activity schedule so as to maximize their net present values (NPVs). As the NPV of the client and the NPV of the contractor are conflicting objectives, this paper first formulates the PSNP as a bi-objective optimization problem. To solve this problem effectively, a non-dominated sorting genetic algorithm II (NSGA-II) approach is proposed. In the negotiation, the client and contractor may have two preferences: the ideal NPVs for the client and the contractor, and the optimization degree of the activity schedule. In order to tackle these preferences, this paper further introduces a new dominance relation named the extended r-dominance relation. The er-dominance relation extends the r-dominance relation and is able to deal with multiple preferences described by aspiration functions. Experimental results show that by incorporating the NSGA-II with the er-dominance, the proposed approach is promising for the PSNP.

Cloud computing has emerged as a powerful computing paradigm that enables users to access computing services anywhere on demand. It provides a flexible way to implement computation-intensive workflow applications on a pay-per-use basis. Since users are more concerned on the satisfaction of Quality of Service (QoS) in cloud systems, the cloud workflow scheduling problem that addresses different QoS requirements of users has become an important and challenging problem for workflow management in cloud computing. In this paper, we tackle a cloud workflow scheduling problem which enables users to define various QoS constraints like the deadline constraint, the budget constraint, and the reliability constraint. It also enables users to specify one preferred QoS parameter as the optimization objective. A set-based PSO (S-PSO) approach is proposed for this scheduling problem. As the allocation of service instances can be regarded as the selection problem from a set of service instances, it is found the set-based representation scheme in S-PSO is natural for the considered problem. In addition, the S-PSO provides an effective way to take advantage of problem-based heuristics to further accelerate search. We define penalty-based fitness functions to address the multiple QoS constraints and integrate the S-PSO with seven heuristics. A discrete version of the comprehensive learning PSO (CLPSO) algorithm based on the S-PSO method is implemented. Experimental results show that the proposed approach is very competitive especially on the instances with tight QoS constraints.

Developing techniques for optimal allocation of limited resources to a set of activities has received increasing attention in recent years. In this paper, an efficient resource allocation scheme based on particle swarm optimization (PSO) is developed. Different from many existing evolutionary algorithms for solving resource allocation problems (RAPs), this PSO algorithm incorporates a novel representation of each particle in the population and a comprehensive learning strategy for the PSO search process. The novelty of this representation lies in that the position of each particle is represented by a pair of points, one on each side of the constraint hyper-plane in the problem space. The line joining these two points intersects the constraint hyper-plane and their intersection point indicates a feasible solution. With the evaluation value of the feasible solution used as the fitness value of the particle, such a representation provides an effective way to ensure the equality resource constraints in RAPs are met. Without the distraction of infeasible solutions, the particle thus searches the space smoothly. In addition, particles search for optimal solutions by learning from themselves and their neighborhood using the comprehensive learning strategy, helping prevent premature convergence and improve the solution quality for multimodal problems. This new algorithm is shown to be applicable to both single-objective and multiobjective RAPs, with performance validated by a number of benchmarks and by a real-world bed capacity planning problem. Experimental results verify the effectiveness and efficiency of the proposed algorithm.

The rapid development of radio frequency identification (RFID) technology creates the challenge of optimal deployment of an RFID network. The RFID network planning (RNP) problem involves many constraints and objectives and has been proven to be NP-hard. The use of evolutionary computation (EC) and swarm intelligence (SI) for solving RNP has gained significant attention in the literature, but the algorithms proposed have seen difficulties in adjusting the number of readers deployed in the network. However, the number of deployed readers has an enormous impact on the network complexity and cost. In this paper, we develop a novel particle swarm optimization (PSO) algorithm with a tentative reader elimination (TRE) operator to deal with RNP. The TRE operator tentatively deletes readers during the search process of PSO and is able to recover the deleted readers after a few generations if the deletion lowers tag coverage. By using TRE, the proposed algorithm is capable of adaptively adjusting the number of readers used in order to improve the overall performance of RFID network. Moreover, a mutation operator is embedded into the algorithm to improve the success rate of TRE. In the experiment, six RNP benchmarks and a real-world RFID working scenario are tested and four algorithms are implemented and compared. Experimental results show that the proposed algorithm is capable of achieving higher coverage and using fewer readers than the other algorithms.

The selection of parameters in time-delay embedding for phase space reconstruction is crucial to chaotic time series analysis and forecasting. Although various methods have been developed for determining the parameters of embedding dimension and time delay for uniform embedding, the study of parameter selection for non-uniform embedding is progressed at a slow pace. In a non-uniform embedding which enables different dimensions in the phase space to have different time delays, the optimal selection of time delays presents a difficult optimization problem with combinatorial explosion. To solve this problem, this paper proposes an ant colony optimization (ACO) approach. The advantages of ACO for the embedding parameter selection problem are in two aspects. First, as ACO builds solution in an incremental way, it does not need to use a fixed embedding dimension as the encoding length of a solution. Instead, both the embedding dimension and the time delays can be optimized together. Second, ACO enables the use of problem-based heuristics. Therefore heuristics designed based on the original observed time series can be used to accelerate the search speed of ACO. Experimental results show that the proposed algorithm is promising.

Project scheduling under uncertainty is a challenging field of research that has attracted an increasing attention in recent years. While most existing studies only considered the classical single-mode project scheduling problem with makespan criterion under uncertainty, this paper aims to deal with a more realistic and complicated model called the stochastic multi-mode resource constrained project scheduling problem with discounted cash flows (S-MRCPSPDCF). In the model, uncertainty is sourced from activity durations and costs, which are given by random variables. The objective is to find an optimal baseline schedule so that the project's expected net present value (NPV) of cash flows is maximized. In order to solve this intractable problem, an ant colony system (ACS) algorithm is designed. The algorithm dispatches a group of ants to build baseline schedules iteratively based on pheromones and an expected discounted cost (EDC) heuristic. In addition, because it is impossible to evaluate the expected NPVs of baseline schedules directly due to the presence of random variables, the algorithm adopts Monte Carlo (MC) simulations to evaluate the performance of baseline schedules. Experimental results on 33 instances demonstrate the effectiveness of the proposed scheduling model and the ACS approach.

Particle swarm optimization (PSO) is predominately used to find solutions for continuous optimization problems. As the operators of PSO are originally designed in ann-dimensional continuous space, the advancement of using PSO to find solutions in a discrete space is at a slow pace. In this paper, a novel set-based PSO (S-PSO) method for the solutions of some combinatorial optimization problems (COPs) in discrete space is presented. The proposed S-PSO features the following characteristics. First, it is based on using a set-based representation scheme that enables S-PSO to characterize the discrete search space of COPs. Second, the candidate solution and velocity are defined as a crisp set, and a set with possibilities, respectively. All arithmetic operators in the velocity and position updating rules used in the original PSO are replaced by the operators and procedures defined on crisp sets, and sets with possibilities in S-PSO. The S-PSO method can thus follow a similar structure to the original PSO for searching in a discrete space. Based on the proposed S-PSO method, most of the existing PSO variants, such as the global version PSO, the local version PSO with different topologies, and the comprehensive learning PSO (CLPSO), can be extended to their corresponding discrete versions. These discrete PSO versions based on S-PSO are tested on two famous COPs: the traveling salesman problem and the multidimensional knapsack problem. Experimental results show that the discrete version of the CLPSO algorithm based on S-PSO is promising.

The multimode resource-constrained project-scheduling problem with discounted cash flows (MRCPSPDCF) is important and challenging for project management. As the problem is strongly nondeterministic polynomial-time hard, only a few algorithms exist and the performance is still not satisfying. To design an effective algorithm for the MRCPSPDCF, this paper proposes an ant colony optimization (ACO) approach. ACO is promising for the MRCPSPDCF due to the following three reasons. First, MRCPSPDCF can be formulated as a graph-based search problem, which ACO has been found to be good at solving. Second, the mechanism of ACO enables the use of domain-based heuristics to accelerate the search. Furthermore, ACO has found good results for the classical single-mode scheduling problems. But the utility of ACO for the much more difficult MRCPSPDCF is still unexplored. In this paper, we first convert the precedence network of the MRCPSPDCF into a mode-on-node (MoN) graph, which becomes the construction graph for ACO. Eight domain-based heuristics are designed to consider the factors of time, cost, resources, and precedence relations. Among these heuristics, the hybrid heuristic that combines different factors together performs well. The proposed algorithm is compared with two different genetic algorithms (GAs), a simulated annealing (SA) algorithm, and a tabu search (TS) algorithm on 55 random instances with at least 13 and up to 98 activities. Experimental results show that the proposed ACO algorithm outperforms the GA, SA, and TS approaches on most cases.

Grid workflow scheduling problem has been a research focus in grid computing in recent years. Various deterministic or meta-heuristic scheduling approaches have been proposed to solve this NP-complete problem. These existing algorithms, however, are not suitable to tackle a class of workflows, namely the time-varying workflow, in which the topologies change over time. In this paper, we propose an ant colony optimization (ACO) approach to tackle such kind of scheduling problems. The algorithm evaluates the overall performance of a schedule by tracing the sequence of its topologies in a period. Moreover, integrated pheromone information is designed to balance the workflow's cost and makespan. In the case study, a 9-task grid workflow with four topologies is used to test our approach. Experimental results demonstrate the effectiveness and robustness of the proposed algorithm.

Grid computing is increasingly considered as a promising next-generation computational platform that supports wide-area parallel and distributed computing. In grid environments, applications are always regarded as workflows. The problem of scheduling workflows in terms of certain quality of service (QoS) requirements is challenging and it significantly influences the performance of grids. By now, there have been some algorithms for grid workflow scheduling, but most of them can only tackle the problems with a single QoS parameter or with small-scale workflows. In this frame, this paper aims at proposing an ant colony optimization (ACO) algorithm to schedule large-scale workflows with various QoS parameters. This algorithm enables users to specify their QoS preferences as well as define the minimum QoS thresholds for a certain application. The objective of this algorithm is to find a solution that meets all QoS constraints and optimizes the user-preferred QoS parameter. Based on the characteristics of workflow scheduling, we design seven new heuristics for the ACO approach and propose an adaptive scheme that allows artificial ants to select heuristics based on pheromone values. Experiments are done in ten workflow applications with at most 120 tasks, and the results demonstrate the effectiveness of the proposed algorithm.

Grid application in virtue of open service grid architecture (OGSA) are promising next-generation computation techniques. One of the most important and challenging problems about grid application is the workflow scheduling problem to achieve the users’ QoS (quality of service) requirements as well as to minimize the cost. This paper proposes an ant colony optimization (ACO) algorithm to tackle this problem. Several new features are introduced to the algorithm. First, we define two kinds of pheromone and three kinds of heuristic information to guide the search direction of ants for this bi-criteria problem. Each ant uses either one from these heuristic types and pheromone types in each iteration based on the probabilities controlled by two parameters. These two parameters are adaptively adjusted in the process of the algorithm. Second, we use the information of partial solutions to modify the bias of ants so that inferior choices will be ignored. Moreover, the experimental results in 3 workflow applications under different deadline constraints show that the performance of our algorithm is very promising, for it outperforms the Deadline-MDP algorithm in most cases.

Research into setting the values of the acceleration coefficients c1and c2in Particle Swarm Optimization (PSO) is one of the most significant and promising areas in evolutionary computation. Parameters c1and c2in PSO indicate the “self-cognitive” and “social-influence” components which are important for the ability to explore and converge respectively. Instead of using fixed value of c1and c2with 2.0, this paper presents the use of clustering analysis to adaptively adjust the value of these two parameters in PSO. By applying the K-means algorithm, distribution of the population in the search space is clustered in each generation. An adaptive system which is based on considering the relative size of the cluster containing the best particle and the one containing the worst particle is used to adjust the values of c1and c2. The proposed method has been applied to optimize multidimensional mathematical functions, and the simulation results demonstrate that the proposed method performs with a faster convergence rate and better solutions when compared with the methods with fixed values of c1and c2.

Particle Swarm Optimization (PSO), which simulates the unpredictable flight of a bird flock, is one of the intelligent computation algorithms. PSO is well-known to solve the continuous problems, yet by proper modification, it can also be applied to discrete problems, such as the classical test model: Traveling Salesman Problem (TSP). In this paper, a novel discrete PSO call C3DPSO for TSP, with modified update formulas and a new parameter c3 (called mutation factor, to help to keep the balance between exploitation and exploration), is proposed. In the new algorithm, the particle is not a permutation of numbers but a set of edges, which is different from most other algorithms for TSP. However, it still keeps the most important characteristics of PSO that the whole swarm is guided by pbest and gbest. According to some benchmarks in TSP lib, it is proved that the proposed PSO works well even with 200 cities.

Job shop scheduling problem (JSP) is one of the most difficult NP-hard combinatorial optimization problems due to the "combination explosion" effect. This paper presents the implementation of ant colony system on JSP by proposing a novel combination of path-construction and pheromone-representation. Based on the simple traditional path-construction, a kind of more effective pheromone is employed to improve the optimization performance. Numerical experiment is executed on several benchmark JSP cases, and yields favorable results compared with results obtained by traditional implementation of ACS for JSP.