基于进化能力的多策略粒子群优化算法

doi:10.3778/j.issn.1002-8331.2111-0423

摘要/Abstract

摘要： 针对粒子群优化算法易早熟收敛、求解精度低等缺点，提出基于进化能力的多策略粒子群优化算法（multi-strategy particle swarm optimization algorithm based on evolution ability）。将粒子按照适应值变化方向分为进步粒子和停退粒子。对于进步粒子按照原始进化策略更新，保留原算法的优点。对于停退粒子进一步根据粒子活性分为暂时停退粒子和长久停退粒子，针对暂时停退的粒子，减小对个体历史速度的依赖甚至向相反方向学习，针对长久停退粒子，根据粒子的适应值优劣采用不同的进化策略，提高全局寻优能力。同时，设计一种带随机波动的惯性权重，使粒子在算法后期仍然具有跳出当前区域的能力，利于全局搜索。通过与其他算法在10个测试函数不同维度上的优化结果对比表明，该算法无论对低维还是高维问题求解的收敛速度和求解精度均有优势。将EAMSPSO算法应用于半无限规划问题的求解，实验结果表明，该算法可以用于半无限规划问题的求解，且具有优势。

关键词: 粒子群优化, 适应值变化方向, 粒子活性, 惯性权重, 半无限规划

Abstract: Aiming at the shortcomings of particle swarm optimization algorithm, such as easy premature convergence and low solution accuracy, a multi-strategy particle swarm optimization algorithm based on evolution ability is proposed. According to the change direction of fitness value, particles are divided into progressive particles and retrogressive particles. The progressive particles are updated according to the original evolution strategy, retaining the advantages of the original algorithm. For the retrogressive particles, it is further divided into temporarily retrogressive particles and long-term retrogressive particles according to the particle activity. For temporarily retrogressive particles, the dependence on individual historical speed is reduced or even learning in the opposite direction. For the long-term retrogressive particles, different evolution strategies are adopted according to the fitness value of the particles to improve the global optimization ability. At the same time, it designs a kind of inertia weight with random fluctuations, so that the particles still have the ability to jump out of the current area in the later stage of the algorithm, which is conducive to the global search. Comparing the optimization results with other algorithms in 10 test functions in different dimensions shows that this algorithm has advantages in both the convergence speed and accuracy of solving low-dimensional and high-dimensional problems. The EAMSPSO algorithm is applied to solve semi-infinite programming problems. Experimental results show that this algorithm is suitable for solving semi-infinite programming problems and has advantages.

Key words: particle swarm optimization, fitness value change direction, particle activity, inertial weight, semi-infinite programming

王晓艳, 曹德欣. 基于进化能力的多策略粒子群优化算法[J]. 计算机工程与应用, 2023, 59(5): 78-86.

WANG Xiaoyan, CAO Dexin. Multi-Strategy Particle Swarm Optimization Algorithm Based on Evolution Ability[J]. Computer Engineering and Applications, 2023, 59(5): 78-86.

参考文献

[1] KENNEDY J，EBERHART R C.Particle swarm optimization[C]//Proceedings of the IEEE International Conference on Neural Networks，1995：1942-1948.
[2] CHEN K，ZHOU F Y，YUAN X F.Hybrid particle swarm optimization with spiral-shaped mechanism for feature selection[J].Expert Systems with Applications，2019，128：140-156.
[3] ZHANG Q B，WANG P，CHEN Z H.An improved particle filter for mobile robot localization based on particle swarm optimization[J].Expert Systems with Applications，2019，135：181-193.
[4] LIU H，WANG Y，TU L，et al.A modified particle swarm optimization for large-scale numerical optimizations and engineering design problems[J].Journal of Intelligent Manufacturing，2019，30（6）：2407-2433.
[5] SHI Y H，EBERHART R C.A modified particle swarm optimizer[C]//Proceedings of 1998 IEEE International Conference on Evolutionary Computation，1998：69-73.
[6] EBERHART R C，SHI Y H.Tracking and optimizing dynamic systems with particle swarms[C]//Proceedings of the 2001 Congress on Evolutionary Computation，2001：94-100.
[7] 李龙澍，张效见.一种新的自适应惯性权重混沌PSO算法[J].计算机工程与应用，2018，54（9）：139-144.
LI L S，ZHANG X J.New chaos particle swarm optimization based on adaptive inertia weight[J].Computer Engineering and Applications，2018，54（9）：139-144.
[8] LIANG J J，QIN A K，SUGANTHAN P N，et al.Comprehensive learning particle swarm optimizer for global optimization of multimodal functions[J].IEEE Transactions on Evolutionary Computation，2006，10（3）：281-295.
[9] 张天泽，李元香，项正龙，等.基于RMSprop的粒子群优化算法[J].计算机工程与设计，2021，42（3）：642-648.
ZHANG T Z，LI Y X，XIANG Z L，et al.Particle swarm optimization algorithm based on RMSprop method[J].Computer Engineering and Design，2021，42（3）：642-648.
[10] 张津源，张军，季伟东，等.具备自纠正和逐维学习能力的粒子群算法[J].小型微型计算机系统，2021，42（5）：919-926.
   ZHANG J Y，ZHANG J，JI W D，et al.Particle swarm optimization algorithm with self-correcting and dimension by dimension learning capabilities[J].Journal of Chinese Computer Systems，2021，42（5）：919-926.
[11] TAM J H，ONG Z C，ISMAIL Z，et al.A new hybrid GA-ACO-PSO algorithm for solving various engineering design problems[J].International Journal of Computer Mathematics，2019，96（5）：883-919.
[12] 张强，李盼池.一种自适应多策略行为粒子群优化算法[J].控制与决策，2020，35（1）：115-122.
   ZHANG Q，LI P C.An adaptive multi-strategy behavior particle swarm optimization algorithm[J].Control and Decision，2020，35（1）：115-122.
[13] 廖玮霖，程杉，尚冬冬，等.多策略融合的粒子群优化算法[J].计算机工程与应用，2021，57（1）：69-76.
LIAO W L，CHENG S，SHANG D D，et al.Particle swarm optimization algorithm integrated with multiple-strategies[J].Computer Engineering and Applications，2021，57（1）：69-76.
[14] 梁田，曹德欣.基于莱维飞行的改进简化粒子群算法[J].计算机工程与应用，2021，57（20）：188-196.
   LIANG T，CAO D X.Improved and simplified particle swarm optimization algorithm based on Levy flight[J].Computer Engineering and Applications，2021，57（20）： 188-196.
[15] 韦鹏，曹德欣.混合三群粒子群优化算法求解min-max-min问题[J].计算机工程与应用，2010，46（35）：219-221.
   WEI P，CAO D X.Hybrid three sub-swarms particle swarm optimizer for min-max-min problem[J].Computer Engineering and Applications，2010，46（35）：219-221.
[16] 倪庆剑，邓建明，邢汉承.基于异构多种群策略的动态概率粒子群优化算法[J].模式识别与人工智能，2014，27（2）：146-152.
NI Q J，DENG J M，XING H C.Dynamic probabilistic particle swarm optimization based on heterogeneous multiple population strategy[J].Pattern Recognition and Artificial Intelligence，2014，27（2）：146-152.
[17] 仝秋娟，李萌，赵岂.基于分类思想的改进粒子群优化算法[J].现代电子技术，2019，42（19）：11-14.
TONG Q J，LI M，ZHAO Q.An improved particle swarm optimization algorithm based on classification[J].Modern Electronics Technique，2019，42（19）：11-14.
[18] 袁小平，蒋硕.基于分层自主学习的改进粒子群优化算法[J].计算机应用，2019，39（1）：148-153.
YUAN X P，JIANG S.Improved particle swarm optimization algorithm based on hierarchical autonomous learning[J].Journal of Computer Applications，2019，39（1）：148-153.
[19] LIN Q，LOXTON R，TEO K L，et al.A new exact penalty method for semi-infinite programming problems[J].Journal of Computational and Applied Mathematics，2014，261：271-286.
[20] SU K，XU C，REN L L.Filter trust region method for nonlinear semi-infinite programming problem[J].Mathematical Problems in Engineering，2018（1）：1-9.
[21] 张昕.约束半无限规划问题的区间算法[D].徐州：中国矿业大学，2017.
ZHANG X.Constrained interval algorithms for semi-infinite programming problems[D].Xuzhou：China University of Mining and Technology，2017.
[22] SINGH N，SINGH S B.Hybrid algorithm of particle swarm optimization and grey wolf optimizer for improving convergence performance[J].Journal of Applied Mathematics，2017：2030489.
[23] CONN A R，GOULD N I M.An exact penalty function for semi-infinite programming[J].Mathematical Programming，1987，37（1）：19-40.
[24] PANG L P，LV J，WANG J H.Constrained incremental bundle method with partial inexact oracle for nonsmooth convex semi-infinite programming problems[J].Computational Optimization and Applications，2016，64（2）：433-465.
[25] TANAKA Y，FUKUSHIMA M，IBARAKI T.A comparative study of several semi-infinite nonlinear programming algorithms[J].European Journal of Operational Research，1988，36（1）：92-100.