Swarm and Evolutionary Computation最新文献

Multi-objective optimization problems (MOPs) aim to obtain a set of Pareto-optimal solutions, and as the number of objectives increases, the quantity of these optimal solutions grows exponentially. However, a plethora of optimal solutions can impose significant decision stress on decision-makers. Subset selection, as the extension of a model, can extract a representative set of solutions, thereby alleviating the decision-makers’ choice pressure. In addition, extending a model undoubtedly incurs additional time costs. To cope with the foregoing issues, a fast subset selection method named ranking-based subset selection (RBSS) is proposed in this paper. It can efficiently select a small number of optimal solutions within an unbounded external archive and can be directly applied to any multi-objective evolutionary algorithm. This allows it to maintain good distribution and diversity with very little time investment. We employed a ranking-based approach to map the objective space to a ranking space (an integer space) defined by us and then selected the corresponding subset in the ranking space. The well-behaved mathematical properties of the ranking space and the advantages of using integer calculations accelerated the subset selection process. Experimental results indicate that compared to several state-of-the-art subset selection methods, RBSS is capable of selecting a set of representative and diverse solutions across different types of MOPs, while consuming significantly less time. Specifically, for problems where the Pareto front is a two-dimensional manifold and a one-dimensional manifold, the time consumption of RBSS is approximately only 0.028% to 27.5% and 4.6e−4% to 0.15% of that required by other algorithms, respectively.

Due to the increasing demand for green manufacturing, energy-saving scheduling problems have garnered significant attention. These problems aim to reduce energy consumption at the production system level within workshops. To simulate a realistic production environment, this study addresses an energy-saving flexible job shop scheduling problem that considers two types of speed-adjustable resources, namely machines and transporters. The optimization objective is to minimize the comprehensive energy consumption of the workshop. A novel mathematical model is initially constructed based on the specific characteristics of the problem at hand. Given its NP-hard nature, a new Q-learning-based biology migration algorithm (QBMA) is proposed, which encompasses diverse search strategies and employs a Q-learning algorithm to dynamically select search strategies, thereby preventing blind search during the evolutionary process. The experimental results of our study demonstrate the promising efficacy of QBMA in effectively addressing the aforementioned problem, while also highlighting the positive impact of considering resources with adjustable speed.

In this paper, we study the stochastic resource-constrained project scheduling problem with transfer and idle costs (SRCPSP-TIC) under uncertain environments, where the resource transfer and idle take time and costs. Priority rule (PR) based heuristics are the most commonly used approaches for project scheduling under uncertain environments due to their simplicity and efficiency. For PR-based heuristics of the SRCPSP-TIC, activity priority rules (APRs) and transfer priority rules (TPRs) are necessary to decide the activity sequence and resource transfer. Traditionally, APRs and TPRs need to be manually designed, which is time-consuming and difficult to adapt to different scheduling scenarios. Therefore, based on two individual representation methods, we propose two co-evolution genetic programming (CGP) based hyper-heuristics to evolve APRs and TPRs automatically. Furthermore, a fitness function surrogate-assisted method and a transfer learning mechanism are designed to improve the efficiency and solution quality of the CGP. Based on the instances with different stochastic activity duration distributions, we test the performance of different CGP-based hyper-heuristics and compare the evolved PRs with the classical PRs to demonstrate the effectiveness of evolved PRs. Experimental results show that the proposed algorithms can automatically evolve efficient PRs for the SRCPSP-TIC.

Optimization algorithms and large language models (LLMs) enhance decision-making in dynamic environments by integrating artificial intelligence with traditional techniques. LLMs, with extensive domain knowledge, facilitate intelligent modeling and strategic decision-making in optimization, while optimization algorithms refine LLM architectures and output quality. This synergy offers novel approaches for advancing general AI, addressing both the computational challenges of complex problems and the application of LLMs in practical scenarios. This review outlines the progress and potential of combining LLMs with optimization algorithms, providing insights for future research directions.

In this paper, we address the prize-collecting generalized minimum spanning tree problem (PC-GMSTP) which aims to find a minimum spanning tree to connect a network of clusters using exactly one vertex per cluster, minimizing the total cost of connecting the clusters while considering both the costs of edges and the prizes offered by the vertices. An Adaptive Multi-meme Memetic Algorithm (AMMA) is proposed to tackle PC-GMSTP, which combines an adaptive reproduction procedure and a collaborated local search procedure. The adaptive reproduction procedure uses either crossover or mutation to produce offspring to maintain a good balance between exploration and exploitation of the search space, and the probability to use crossover or mutation is adaptively adjusted based on the diversity of population. The collaborated local search procedure, which includes two efficient local search operators, can effectively enhance the intensification ability of AMMA due to their complementary features. Extensive computational experiments on 126 challenging instances demonstrate the superiority of AMMA, outperforming 23 best-known solutions from existing literature while achieving similar solutions for the remaining 103 instances. Wilcoxon’s signed rank test confirms that the performance of AMMA is significantly better than the state-of-the-art algorithms.

Many real multi-objective optimization problems with 20-50 decision variables often have only a small number of function evaluations available, because of their heavy time/money burden. Therefore, surrogate models are often utilized as alternatives for expensive function evaluations. However, the approximation error of the surrogate model is inevitable compared to the real function evaluation. The approximation error has a similar impact on the algorithm as noise, i.e., different optimization stages suffer from various impacts. Therefore, the current optimization stage can be indirectly detected via measuring the impact of the noise formulated by the approximation error. In addition, the rising dimension of the search space leads to an increase in the approximation errors of the surrogate models, which poses a huge challenge for existing surrogate-assisted multi-objective evolutionary algorithms. In this work, we propose a stage-adaptive surrogate-assisted multi-objective evolutionary algorithm to solve the medium-scale optimization problems. In the proposed algorithm, the ensemble model consisting of the latest and historical models is used as the surrogate model, on the basis of which a set of potential candidates can be discovered. Then, a stage-adaptive infill sampling strategy selects the most suitable sampling strategy by analyzing the demand of the current optimization stage on convergence, diversity, model accuracy to sample from the candidates. As for the current optimization stage, it is detected by a noise impact indicator, where the approximation errors of surrogate models are formulated as noise. The experimental results on a series of medium-scale expensive test problems demonstrate the superiority of the proposed algorithm over six state-of-the-art compared algorithms.

Feature selection (FS), as one of the most significant preprocessing techniques in the fields of machine learning and pattern recognition, has received great attention. In recent years, evolutionary computation has become a popular technique for handling FS problems due to its superior global search performance. In this paper, a comprehensive review of evolutionary computation research on the FS problems is presented. Firstly, a new taxonomy for the basic components of evolutionary feature selection algorithms (EFSs) is proposed, including encoding strategy, population initialization, population updating, local search, multi-FS hybrid and ensemble. Secondly, we summarize the latest research progress of EFSs on some new and complex scenarios, including large-scale high-dimensional data, multi-objective/metric scenario, multi-label data, distributed storage data, multi-task scenario, multi-modal scenario, interpretable FS and stable FS, etc. Moreover, this survey provides also an in-depth analysis of real-world applications of EFSs, such as hyperspectral band selection, bioinformatics gene selection, text classification and fault detection, etc. Finally, several opportunities for future work are pointed out.

Energy consumption and makespan of workflow execution are two core performance indicators in operating cloud platforms. But, simultaneously optimizing these two indicators encounters various challenges, such as elastic resources, large-scale decision variables, and sophisticated workflow structures. To handle these challenges, we design an adaptive evolutionary scheduling algorithm, namely AESA, with three innovative strategies. First, a heuristic population initialization strategy is devised to gather workflow tasks onto limited potential resources, thereby alleviating the negative impact of redundant cloud resources on evolutionary search efficiency. Then, a variable analysis strategy is designed to dynamically measure the contribution of each decision variable in pushing the population towards Pareto-optimal fronts. Moreover, AESA embraces an adaptive strategy to reward more evolutionary opportunities for decision variables with higher contributions to handle large-scale decision variables in a targeted manner, further improving the efficiency of evolutionary search. Finally, extensive experiments are performed based on real-world cloud platforms and workflow traces to verify the effectiveness of the proposed AESA. The comparison results validate its superior performance by significantly outperforming five representative baselines in optimizing makespan and energy consumption. Also, the results of ablation experiments demonstrate that all three components contribute to AESA’s overall performance, with the adaptive reward mechanism being the most significant.

The automation of meta-heuristic algorithm configuration holds the utmost significance in evolutionary computation. A hierarchical reinforcement learning-aware hyper-heuristic algorithm with fitness landscape analysis (HRLHH) is proposed to flexibly configure the suitable algorithms under various optimization scenarios. Two kinds of fitness landscape analysis techniques improved based on specific problem characteristics construct the state spaces for hierarchical reinforcement learning. Among them, an adaptive classification based on dynamic ruggedness of information entropy is designed to discern the complexity of problems, which serves as the basis for decision-making actions in upper-layer space. Additionally, an online dispersion metric based on knowledge is further presented to distinguish the precise landscape features in lower-layer space. In light of the characteristics of the state spaces, the hierarchical action spaces composed of meta-heuristics with disparate exploration and exploitation are designed, and various action selection strategies are introduced. Taking into account the real-time environment and algorithm evolution behavior, dynamic reward mechanisms based on evolutionary success rate and population convergence rate are utilized to enhance search efficiency. The experimental results on the IEEE Congress on Evolutionary Computation (CEC) 2017, CEC 2014, and large-scale CEC 2013 test suites demonstrate that the proposed HRLHH exhibits superiority in terms of accuracy, stability, and convergence speed, and possesses strong generalization.

The role of multi-area economic dispatch (MAED) in power system operation is increasingly significant. It is a non-linear and multi-constraint problem with many local extremes when considering the valve point effects, posing challenges in obtaining a globally optimal solution, especially for large-scale systems. In this study, an improved variant of differential evolution (DE) called CLDE based on comprehensive learning strategy (CLS) is proposed to solve this problem. Three improved strategies are employed to enhance the performance of CLDE. (1) A CLS-based guided mutation strategy is proposed, in which learning exemplars constructed by competent individuals are used to generate mutant vectors to prevent the searching away from global optimum and speed up convergence. (2) A time-varying increasing crossover rate is devised. It can endow CLDE with a larger probability at the later stage to help individuals escape from local extremes. (3) A CLS-based crossover strategy is presented. Trial vectors directly utilize the information from learning exemplars for evolving, which can ensure the search efficiency and population diversity. CLDE is applied to six MAED cases. Compared with DE, it approximately consumes 32 %, 35 %, 10 %, 22 %, 62 %, and 20 % of evaluations to attain comparable results, saves 126.2544$/h, 81.8173$/h, 152.0660$/h, 360.7907$/h, 65.5757$/h, and 1732.8544$/h in fuel costs on average, and exhibits improvements of 34.77 %, 1.80 %, 0.00 %, 76.09 %, 95.15 %, and 16.76 % in robustness, respectively. Moreover, it also outperforms other state-of-the-art algorithms significantly in statistical analysis. Furthermore, the effects of improved strategies on CLDE are thoroughly investigated.