Article
Computer Science, Artificial Intelligence
Qingtao Pan, Jun Tang, Haoran Wang, Hao Li, Xi Chen, Songyang Lao
Summary: This paper proposes an improved self-adaptive differential evolution algorithm SFSADE, which effectively improves the performance of DE by introducing a shuffled frog-leaping strategy, a new mutation strategy, and an adaptive adjustment mechanism for control parameters. A large number of simulation experiments on 25 benchmark functions of CEC 2005 and two nonparametric statistical tests have shown that SFSADE significantly enhances the overall diversity of the population during dynamic evolution.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Computer Science, Artificial Intelligence
Yiqiao Cai, Duanwei Wu, Shunkai Fu, Shengming Zeng
Summary: This paper introduces a novel differential evolution framework called self-regulated differential evolution (SrDE) for real parameter optimization. SrDE utilizes a self-regulated neighborhood (SrN) to guide the search process, including dynamic construction of neighborhood relationships, adaptive regulation of neighborhood size, and a neighborhood path-assisted strategy for guiding the mutation process. Experimental results show that SrDE outperforms state-of-the-art DE variants in terms of performance and competitiveness.
APPLIED INTELLIGENCE
(2021)
Article
Energy & Fuels
Zhichen Zeng, Dong Ni, Gang Xiao
Summary: An effective and scalable optimization method is proposed for real-time optimization of heliostat field aiming strategy in solar power tower (SPT) plants, showing better or comparable performance compared to heuristic optimization methods with significantly less computation time.
Article
Computer Science, Information Systems
Zhiqiang Zeng, Huanhuan Zhang
Summary: This study proposes an evolutionary-state-based selection (ESS) strategy for improving single-objective differential evolution (DE) algorithms. By constructing a probability model based on evolutionary states, ESS assigns a certain survival probability to losers in the survivor selection process, effectively solving real-parameter optimization problems. Experimental results show that evolutionary-state-based differential evolution (ESDE) outperforms eight state-of-the-art DE variants, and ESS significantly improves DE performance.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Hu Peng, Yupeng Han, Changshou Deng, Jing Wang, Zhijian Wu
Summary: Engineering design problems with mixed-variable optimization problems (MVOPs) pose challenges due to non-linear functions, complex constraints, and a mix of continuous and discrete variables. This study introduces a new variation of differential evolution called MCDEmv, which combines multi-strategy co-evolution and statistics-based local search to effectively solve MVOPs. Experimental results demonstrate the superior performance and efficiency of MCDEmv compared to similar algorithms in handling mixed-variable engineering design problems.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Mathematical & Computational Biology
Shihao Yuan, Hong Zhao, Jing Liu, Binjie Song
Summary: This paper proposes a differential evolution algorithm based on self-organizing maps and dynamic selection strategy for solving multimodal optimization problems. The algorithm improves the performance of differential evolution in solving multimodal optimization problems by reasonably dividing the population, expanding the search space, and balancing exploration and exploitation.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Yupeng Han, Hu Peng, Changrong Mei, Lianglin Cao, Changshou Deng, Hui Wang, Zhijian Wu
Summary: This paper proposes a new multistrategy multiobjective differential evolutionary algorithm, RLMMDE, to solve the exploration and exploitation dilemma in multiobjective optimization problems (MOPs). The algorithm utilizes a multistrategy and multicrossover DE optimizer, an adaptive reference point activation mechanism based on RL, and a reference point adaptation method. Experimental results show that RLMMDE outperforms some advanced MOEAs on benchmark test suites and practical mixed-variable optimization problems.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Automation & Control Systems
Xiao-Fang Liu, Jun Zhang, Jun Wang
Summary: This article presents a cooperative differential evolution algorithm with an attention-based prediction strategy for dynamic multiobjective optimization. Multiple populations are used to optimize multiple objectives and find subparts of the Pareto front. The algorithm achieves a balanced approximation of the Pareto front and adapts to changes in the environment by using a new attention-based prediction strategy. Experimental results demonstrate the superiority of the proposed method to state-of-the-art algorithms.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Automation & Control Systems
Yue-Jiao Gong, Yi-Wen Liu, Ying Lin, Wei-Neng Chen, Jun Zhang
Summary: This paper presents a two-stage taxi-passenger matching system that optimizes the quality and profit of taxi-passenger matching by utilizing a fuzzy controller and a polynomial Kuhn-Munkres algorithm.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Computer Science, Information Systems
Zhenyu Meng, Cheng Yang
Summary: DE algorithm is a powerful evolutionary algorithm for global optimization with great success in engineering applications. However, existing DE variants have two main weaknesses in mutation strategy and parameter control. To address these weaknesses, a novel Hip-DE algorithm is proposed with historical population-based mutation strategy and parameter adaptive mechanisms for performance enhancement.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Heba Abdel-Nabi, Mostafa Z. Ali, Arafat Awajan, Rami Alazrai, Mohammad I. Daoud, Ponnuthurai N. Suganthan
Summary: This paper proposes a novel evolutionary algorithm, Ic3-aDSF-EA, which combines the exploitative and explorative merits of two main evolutionary algorithms, Stochastic Fractal Search (SFS) and a Differential Evolution (DE) variant. The algorithm gradually emphasizes the work of the best-performing algorithm during the search process without ignoring the effects of other inferior algorithms.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Zhiping Tan, Yu Tang, Huasheng Huang, Shaoming Luo
Summary: Differential evolution (DE) is an efficient evolutionary algorithm for solving continuous or discrete numerical optimization problems. This paper proposes a dynamic fitness landscape-based adaptive mutation strategy selection differential evolution (DFLDE) algorithm, which selects the optimal mutation strategy based on the dynamic fitness landscape characteristics of each optimization problem. Experimental results show that DFLDE outperforms five well-known DE variants in terms of searching for the optimal value, convergence speed, and robustness.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Naili Luo, Wu Lin, Genmiao Jin, Changkun Jiang, Jianyong Chen
Summary: In this paper, a novel genetically hybrid differential evolution strategy (GHDE) for recombination in MOEA/Ds is proposed to enhance search capability by introducing two composite operator pools. Through adaptive parameter tuning and fitness-rate-rank-based multiarmed bandit (FRRMAB), the best operator pool is selected, demonstrating the superiority of MOEA/D-GHDE in multiobjective optimization problems.
Article
Computer Science, Artificial Intelligence
Libao Deng, Yifan Qin, Chunlei Li, Lili Zhang
Summary: Differential evolution (DE) is an efficient global optimization algorithm, but its random nature can cause individuals to deviate from the global optima, leading to a waste of computing resources. To address this, we propose an adaptive mutation strategy correction framework (AMSC) for DEs. AMSC splits the population into two subpopulations and designs auxiliary mutant vectors to enhance their exploration and exploitation abilities. Additionally, an adaptive cooperative rule is introduced to balance exploration and exploitation based on the crossover rates. Experimental results show that AMSC significantly improves DEs' performance.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Wu Deng, Shifan Shang, Xing Cai, Huimin Zhao, Yongquan Zhou, Huayue Chen, Wuquan Deng
Summary: The proposed HMCFQDE combines quantum evolutionary algorithm (QEA) and cooperative coevolution evolutionary algorithm (CCEA) to improve the solution efficiency and search speed. A new hybrid mutation strategy is designed to enhance convergence accuracy and stability in solving high-dimensional complex functions.
KNOWLEDGE-BASED SYSTEMS
(2021)