Bayesian optimization (BO), a data-efficient method for expensive black-box optimization, has traditionally focused on single-task scenarios, ignoring potential correlations among related tasks and leading to resource inefficiency due to repeated explorations. While existing multi-task BO methods mainly enhance surrogate models and sampling strategies, they rely on implicit knowledge transfer mechanisms that risk performance degradation from interference tasks, leveraging existing knowledge to optimize similar tasks instead of jointly optimizing multiple tasks from scratch. To address these issues, we propose a novel algorithm with adaptive knowledge transfer via kernelized autoencoding for multi-task Bayesian optimization (AKT-MTBO), which mainly has two core innovations. One is a kernel-induced task similarity measurement, where a kernelized autoencoding mechanism is employed to capture the nonlinear relationships between datasets. The other is an adaptive explicit knowledge transfer mechanism, where a heuristic rule is introduced to dynamically adjust the priority of selection of auxiliary tasks, ensuring selective collaboration while mitigating interference. Experiments on benchmark problems demonstrate that our proposed AKT-MTBO performs reliably in terms of both optimization efficiency and optimal solution success rates.

Symbolic regression, a multifaceted optimization challenge involving the refinement of both structural components and coefficients, has gained significant research interest in recent years. The Equation Learner (EQL), a neural network designed to optimize both equation structure and coefficients through gradient-based optimization algorithms, has emerged as an important topic of concern within this field. Thus far, several variations of EQL have been introduced. Nevertheless, these existing EQL methodologies suffer from a fundamental constraint that they necessitate a predefined network structure. This limitation imposes constraints on the complexity of equations and makes them ill-suited for high-dimensional or high-order problem domains. To tackle the aforementioned shortcomings, we present a novel approach known as the evolving Equation Learner (eEQL). eEQL introduces a unique network structure characterized by automatically defined functions (ADFs). This new architectural design allows for dynamic adaptations of the network structure. Moreover, by engaging in self-learning and self-evolution during the search process, eEQL facilitates the generation of intricate, high-order, and constructive sub-functions. This enhancement can improve the accuracy and efficiency of the algorithm. To evaluate its performance, the proposed eEQL method has been tested across various datasets, including benchmark datasets, physics datasets, and real-world datasets. The results have demonstrated that our approach outperforms several well-known methods.

Genetic programming (GP) is a widely recognized and powerful approach for symbolic regression (SR) problems. However, existing GP methods rely on a single form to solve the problem, which limits their search diversity and increases the likelihood of getting stuck in local optima, especially in complex scenarios. In this paper, we propose a general multiform GP framework to improve the performance of GP on complicated SR problems. As far as we know, this paper is the first attempt to integrate the multiform optimization paradigm with GP to accelerate the search performance. The key idea of the proposed framework is to construct multiple forms to solve the same problem cooperatively at the same time. During the evolution process, knowledge gained from different forms is shared among the solvers to improve the search diversity and efficiency. A knowledge transfer mechanism is specifically designed to facilitate knowledge transfer among GP solvers with different modeling forms. In addition, an adaptive resource control mechanism is designed to reallocate computing resources according to the problem-solving efficiency of different solvers to further improve search efficiency. To demonstrate the effectiveness of the proposed framework, a multiform GEP algorithm (MF-GEP) is designed and tested on 20 problems, including physical datasets, synthetic datasets, and real-world datasets. The experimental results have demonstrated the effectiveness of the proposed framework.

Guidance signage placement is a fundamental operation for crowd control in public places.The currentmethods mainly rely on manual design ormathematicalmodels, which are not flexible and effective enough for crowd control in large public places. To address this issue, this article proposes a multiobjective evolutionary framework that can search for high-quality guidance signage placement strategies automatically. In the proposed method, an agent-based crowd simulation model is proposed to simulate the wayfinding behaviors of pedestrians in public places. Furthermore, a new safety metric is proposed to quantitatively evaluate the quality of guidance signage placement strategies. On this basis, an indicator-based multiobjective evolutionary algorithm (IBEA) is utilized to search for optimal guidance signage placement strategies that have tradeoffs between crowd safety and pedestrians’ travel time. Simulation experiments on both synthetic and real-world scenes were conducted to evaluate the proposed method, and the simulation results show that the proposed framework can generate very promising guidance signage placement strategies in comparison with several existing methods.

Evolutionary multitasking (EMT), which aims to exploit effective knowledge among similar tasks to improve search efficiency, is a hot research topic that has recently attracted a lot of attention. Ant Colony Optimization (ACO), which is inspired by the foraging behavior of ant species, is a popular and powerful search algorithm for NP-hard combinatorial optimization problems. However, EMT has seldom been integrated with the ACO. Inspired by the remarkable success of multitasking evolutionary algorithms in numerous research fields, this paper proposes a multitasking ant colony optimization framework (MTACO). The proposed framework enables ants to exploit the pheromones of ant colonies with similar tasks through certain conditions to improve the efficiency and the quality of results of ACO when processing multiple similar tasks dynamically. Furthermore, a multitasking ACS (MTACS) is implemented based on the proposed MTACO framework to solve dynamic vehicle path planning problems (DVPP). The experimental results on DVPP have verified that MTACO can improve the performance of ACO in terms of both algorithm efficiency and quality of results, when ACO is handling multiple tasks simultaneously.

Deploying guardrails near elevator entrances is an effective way to alleviate congestion and improve the flow rate in subway stations. How to properly design the guardrail layout is a complex black-box optimization problem. Existing methods are mainly based on manual design, which are highly dependent on the empirical experience of the designers and may not get satisfactory results in complicated scenarios. To address the above issues, this article proposes an evolutionary framework to automatically optimize guardrail layouts in subway stations. In the proposed framework, a novel guardrail layout encoding method is proposed, which can facilitate the algorithm to generate regular guardrail layout design solutions. Furthermore, a new fitness evaluation function is proposed to effectively measure the quality of a given guardrail layout design strategy. To validate its effectiveness, the proposed framework is applied to two scenarios with different characteristics. Simulation results have demonstrated that the proposed framework can provide promising guardrail layout designs, which can alleviate the congestion of subway stations effectively.

In software defined networking (SDN), a controller may manage several SDN switches to be cost-effective while a switch may demand management service from multiple controllers for fault tolerance. The controller placement problem (CPP) is to determine the locations of SDN controllers to minimize the total deployment cost subject to constraints such as controller-switch latency, inter-controller latency, and controller capacity. This problem is challenging especially in interconnected geo-distributed SDN networks. Existing centralized solutions do not well adapt to network dynamics. This paper proposes several distributed mechanisms based on the exact potential game. These mechanisms dynamically adapt to network faults such as link and controller failures. The simulation result shows that these mechanisms need fewer controllers than an existing approach in static networks. When links or controllers may fail, our mechanisms still perform better while only a part of the network nodes is affected. The latter is impossible in non-adaptive approaches.

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.

Grid technologies allow for distributed computing and collaboration. Scientists and others utilizing grid collaboration tools often need to share resources using applications besides seeing and hearing each other with audio and video. The ability to share applications in real time is crucial for distant learning and remote collaboration. Web browser sharing is particularly important to long distance biomedical education and research, since a range of biomedical information resources are accessible via the web, including databases of gene sequences, protein structures, biomedical literature, drug and clinical trials. The National Library of Medicine (NLM) has focused on increasing the interactivity and functionality of the shared web browser on Access Grid. Satisfactory synchronization performance was observed as well as the return of retrieval to all participating browsers when NLM's online databases were searched. NLM plans to apply those methods to other shared applications for highly interactive long distance training and research collaboration.