In both resource-scarce and resource-abundant scenarios (i.e., in the scenarios where service demands exceed/do not exceed available resources), it is a critical challenge to design efficient task allocation model and algorithm in network slicing in 5G/Beyond 5G (B5G)/6G networks, especially in resource-scarce scenario. This challenge faces the following three difficult tasks: 1) fully utilize network resources, 2) satisfy all user requests, and 3) make the best trade-offs among service latency, service failure rate, and Mobile Network Operator (MNO) cost. To address this challenge, we propose a three objective optimization model, the Versatile Storage Routing (VSR) model. It facilitates collaborative multi-device sharing for a single Virtual Network Function (VNF) and parallel multi-path data transmission, thus enabling full utilization of the resources. Also, it can provide efficient resource allocation schemes in both resource-abundant and resource-scarce scenarios to satisfy all user requests. Furthermore, we design a novel evolutionary algorithm for VSR model called VSR-EA based on Non-dominated Sorting Genetic Algorithm II (NSGA II) framework. It features customized encoding/decoding and evolutionary operators to handle multi-device storage allocation, multi-path routing selection and distributed transmission resource allocation. As a result, the best trade-offs among service latency, service failure rate, and MNO cost can be obtained. Simulation results demonstrate that VSR-EA exhibits broader applicability and yields significantly superior solutions compared to benchmark algorithms.

The multicast routing problem in software-defined networking (SDN) is an NP-hard problem. The existing solution methods based on deep strength learning suffer from the problems of branch redundancy, an excessively large action space and slow convergence of the intelligent models. In this paper, an intelligent multicast routing algorithm based on deep hierarchical reinforcement learning is proposed to circumvent the aforementioned problems. First, the optimal multicast tree problem is decomposed into two subproblems: fork node selection and the construction of an optimal path from a fork node to a destination node. Second, a multichannel matrix is designed as the state space for the internal and external controllers of hierarchical reinforcement learning based on the global network-aware information characteristics of SDN. Then, different action spaces are designed for the upper and lower subproblems, four action selection policies are designed for constructing multicast paths, and different reward policies are designed at different levels. Finally, a series of experiments and their results show that the designed algorithm not only searches the multicast tree efficiently but also converges faster and without redundant branches, with better performance in terms of bandwidth, delay and packet loss rate than the current mainstream solution algorithms. The codes for DHRL-FNMR are open and available at https://github.com/GuetYe/DHRL-FNMR.

Fog Computing usefully extends Cloud to the edge of the network for the sake of meeting users’ expanding demand for low latency. However, due to its scattered distribution and open architecture, fog nodes are highly vulnerable to security threats, resulting in an inevitable sharp conflict between quick response time and high data security. This conflict motivates the need for effective data placement among fog nodes towards a trade-off between security and time. Existing studies merely offer independent solutions by considering either security or response time. By contrast, we establish a dynamic multi-objective optimization model in this article by optimizing security and response time simultaneously. With this model, we propose an efficient evolutionary algorithm, referred to asDynamic Interactive Security-and-Time cognizant algorithm(DIST), to obtain optimal data placement strategies under Fog environments. To improve efficiency,DISTallows users to gradually incorporate their preference information into the search process so as to find their most preferred solutions without exploring the whole search space. We demonstrate the superiority ofDISTby rigorous comparison with the most state-of-art data placement strategy and other well-applied strategies. Experimental results manifest thatDISToutperforms other strategies in obtaining solutions with higher data security and shorter response time. Furthermore,DISTis capable of efficiently and continuously tracking the Pareto optimal solution under dynamically changing Fog environments while other existing strategies cannot.

Multi-installment scheduling (MIS) has been deemed as a promising paradigm that can sharply reduce the processing time of large-scale divisible workloads on various network-based compute platforms. Unfortunately, the practicality of MIS was crippled due to its overwhelming complexity for deriving optimal values for (n × m) + 2 related variables, i.e., we have to obtain an optimal number n of required computing resources, optimal number m of installments, and optimal load partition matrix A = (αij)n×m which determines the sizes of load fractions assigned to each computing unit in every installment. To circumvent this complexity, in this paper, we first derive explicit analytical expressions for optimal load partition matrix A of size n × m based on a given number of n and m. Then we propose a heuristic algorithm referred to as Time, Resource, and Energy Efficient MIS (TREE-MIS) to determine optimal values of n and m. The efficiency of our approach is shown to significantly improve since it can produce globally optimal solutions directly for (n × m) variables among (n × m) + 2 in total for MIS problems based on the derived analytical expressions within a short runtime. We conduct extensive simulations to demonstrate the effectiveness of the proposed algorithm. Simulation results show that our TREE-MIS can not only minimize the processing time of workloads as well as improve resource utilization of the compute platform but also drastically reduce the runtime compared to other state-of-art MIS strategies. Furthermore, while handling large-scale workloads in any large network infrastructures would inexorably result in significant amounts of energy wastage if the strategy is not prudently designed. As an offshoot of our analysis and design, we clearly demonstrate that the energy wastage in adopting our TREE-MIS is kept minimum when compared to other currently available strategies in practice.

Multi-Installment Divisible-Load Scheduling model is a hot topic in the field of Big Data Processing in heterogeneous parallel and distributed systems. The effective division of data and the determination of scheduling strategy are the key and difficult problems. Minimizing the make-span of the entire divisible load is the primary objective of multi-installment scheduling in heterogeneous parallel and distributed systems. It has been demonstrated that the make-span is minimized when the processor sequence follows the order in which the link speed decrease in single-installment scheduling, however, the optimization of multi-installment divisible-load scheduling is a very hard problem. The descending order of link speeds is usually not an optimal order. To solve this problem, we propose a multi-installment scheduling model considering the processor order, and design an efficient global optimization genetic algorithm to solve the model. Experimental results show that the proposed algorithm has better performance than that of the compared multi-Installment methods.

Ever-increasing big data forces enterprises to migrate data to cloud storage systems. Data retrieval time from the cloud will directly affect the overall application performance. Meanwhile, sensitive data stored on cloud necessitates a robust security arrangement against cyberattacks. Therefore, it is imperative that both data retrieval time and data security should be taken into account simultaneously when designing a data placement strategy. In this paper, we formulate, design and evaluate the performance of a multi-objective evolutionary algorithm based data placement strategy. We show that our strategy offers users a choice to strike a balance between retrieval time and security through a set of uniformly distributed Pareto-optimal solutions. We evaluate and quantify the performance of our strategy on different cloud storage systems.

Multi-installment scheduling (MIS) has shown great effectiveness in minimizing the processing time for large-scale partitionable workloads. To derive an optimal MIS strategy, one has to explicitly determine optimal numbers of installments and processors. Existing studies tend to solve this problem by treating the influence of number of installments (and processors) w.r.t processing time as time-continuous functions and taking the derivative of these functions to determine the optimal values, which may lead to invalid solutions. In this paper, we employ periodic multi-installment scheduling (P-MIS) models for homogeneous and heterogeneous single-level tree networks. Using these models we make the following significant contributions. First, we derive a closed-form solution for an optimal number of installments based on a given network size and a fixed load distribution sequence. Second, we propose a heuristic algorithm for determining an optimal number of processors by first proving several important intermediate lemmas and theorems. Third, for heterogeneous systems, we propose a genetic algorithm to determine an optimal load distribution sequence. Finally, we conduct various experiments to illustrate the effectiveness of the proposed algorithms and perform rigorous analysis on the influence of load distribution sequence on processing time, on the basis of which a practical advice for determining a near-optimal load distribution sequence is given.

The scheduling for divisible load in heterogeneous distributed system is a well known NP-hard problem. The problem is even more complex and challenging when its model has more than one objective, The difficulty is to satisfy multiple objectives that may be of conflicting nature. This paper investigates a multi-objective scheduling problem for divisible load in heterogeneous distributed systems. First, the cost of the system is taken into account and its quantitative formula is given. Second, a bi-objective optimization model, which minimizes the cost of system and the makespan of the load, is established. For the sake of solving the bi-objective optimization model efficiently, a novel effective bi-objective genetic algorithm combing the idea of MOEA/D is proposed. Finally, numerical simulation experiments are conducted, and the experimental results indicate that the effectiveness of the proposed model and algorithm.

The weighted sum of objective functions is one of the simplest fitness functions widely applied in evolutionary algorithms (EAs) for multiobjective programming. However, EAs with this fitness function cannot find uniformly distributed solutions on the entire Pareto front for nonconvex and complex multiobjective programming. In this paper, a novel EA based on adaptive multiple fitness functions and adaptive objective space division is proposed to overcome this shortcoming. The objective space is divided into multiple regions of about the same size by uniform design, and one fitness function is defined on each region by the weighted sum of objective functions to search for the nondominated solutions in this region. Once a region contains fewer nondominated solutions, it is divided into several sub-regions and one additional fitness function is defined on each sub-region. The search will be carried out simultaneously in these sub-regions, and it is hopeful to find more nondominated solutions in such a region. As a result, the nondominated solutions in each region are changed adaptively, and eventually are uniformly distributed on the entire Pareto front. Moreover, the complexity of the proposed algorithm is analyzed. The proposed algorithm is applied to solve 13 test problems and its performance is compared with that of 10 widely used algorithms. The results show that the proposed algorithm can effectively handle nonconvex and complex problems, generate widely spread and uniformly distributed solutions on the entire Pareto front, and outperform those compared algorithms.

Among the many-objective optimization problems, there exists a kind of problem with redundant objectives, it is possible to design effective algorithms by removing the redundant objectives and keeping the non-redundant objectives so that the original problem becomes the one with much fewer objectives. In this paper, a new non-redundant objective set generation algorithm is proposed. To do so, first, a multi-objective evolutionary algorithm based decomposition is adopted to generate a small number of representative non-dominated solutions widely distributed on the Pareto front. Then, the conflicting objective pairs are identified through these non-dominated solutions, and the non-redundant objective set is determined by these pairs. Finally, the experiments are conducted on a set of benchmark test problems and the results indicate the effectiveness and efficiency of the proposed algorithm.

The era of big data computing is coming. As scientific applications become more data intensive, finding an efficient scheduling strategy for massive computing in parallel and distributed systems has drawn increasingly attention. Most existing studies considered single-installment scheduling models, but very few literature involved multi-installment scheduling, especially in heterogeneous parallel and distributed systems. In this paper, we proposed a new model for periodic multi-installment divisible-load scheduling in which the make-span of the workload is minimized, and a genetic algorithm was designed to solve this model. Finally, experimental results show the effectiveness and efficiency of the proposed algorithm.

Minimizing the make-span of the entire divisible load is the primary objective of multi-installment scheduling in heterogeneous parallel and distributed systems. This is a significantly difficult problem to address because we have to find the optimal number m of installments, optimal number n of processors taking part in computation, and optimal load partition A = [αij]n×mwith each element represents the load fraction assigned to each processor in different installment. Therefore, this problem involves 2+n m variables. In this paper, we first find the function expression of the optimal load partition A with respect to the number m of installments and the number n of processors participating in computation, i.e., A = f (n, m), thereby reducing the dimension of the problem down to 2. Then we propose a new heuristic method for finding the optimal numbers of installments and processors. Finally, experimental results show that the make span of the entire divisible load obtained by the proposed method is smaller than those by the existing multi-installment scheduling methods, which implies the effectiveness of the proposed method.

The problem of divisible load scheduling in network based heterogeneous distributed systems is addressed in this paper, where a general platform is considered, and the communication is in non-blocking message receiving mode, moreover, the communication speeds, computation speeds, start-up overheads and workload size are arbitrary. To solve the problem efficiently, we set up an optimization model which can effectively tackle the following three issues: (1) how many and which processors are required in computation; (2) in which order the load fractions are distributed to processors; (3) how much the load fraction should be distributed to each processor. For this model, a novel genetic algorithm is proposed, and the convergence of the proposed algorithm to a globally optimal solution with probability one is proved. Finally, the experiments on several examples indicate the efficiency and effectiveness of the proposed algorithm.

Soaring power consumption of data centers has drawn increasing attentions. Reducing energy consumption will not only cut down the operational cost of data centers, but also reduce the amount of greenhouse gases emissions. From the perspective of optimizing energy efficiency of servers in a data center, and by taking data layout policies and the requirement of data locality for task execution, as well as the relationship between servers' performance and energy consumption into consideration, a new bi-level multiobjective task scheduling model based on MapReduce is proposed first. To sole the problem efficiently, a tailor-made encoding and decoding methods are designed, then, two explicit objective functions, energy efficiency function and localized ratio function are defined. Based on all these, an improved bi-level multiobjective evolutionary algorithm based on MOEA/D is proposed to solve this model, in which a local search operator is introduced to accelerate its convergent speed and enhance its searching ability. Finally, simulation results show that the proposed algorithm is effective and efficient.