Improved Particle Swarm Optimization Algorithm Based on Multiple Strategies

doi:10.12068/j.issn.1005-3026.2023.08.004

Abstract

Abstract: Aiming the problem of slow convergence speed and difficulty in jumping out of the local optimal solution of particle swarm optimization (PSO) algorithm， the standard PSO algorithm is improved with various strategies， and the hybrid dynamic PSO (HDPSO) algorithm is proposed. The algorithm divides particles into dominant particles and inferior particles according to a proportion， and uses different formulas to calculate the inertia weights of each particle respectively. Each particle is assigned a variation coefficient， and the duration of small fitness changes between adjacent particles is recorded. If this duration exceeds a threshold value， the variation coefficient is accumulated and reset to the initial value after reaching the upper limit. The acceleration coefficient is introduced into the position update formula to improve the convergence speed of the algorithm. The standard test functions are used to test the HDPSO algorithm and other PSO algorithms. The results show that HDPSO algorithm has obvious advantages in terms of convergence speed， optimization accuracy and stability， which further proves the effectiveness of the proposed method.

Key words: particle swarm optimization (PSO) algorithm; adaptive inertia weight; mutation; acceleration coefficient; local optimal solution

CLC Number:

TP311

KANG Yan-song， ZANG Shun-lai. Improved Particle Swarm Optimization Algorithm Based on Multiple Strategies[J]. Journal of Northeastern University(Natural Science), 2023, 44(8): 1089-1097.

References

[1]Kennedy J，Eberhart R.Particle swarm optimization［C］//Proceeding of IEEE International Conference on Neural Networks.Piscataway:IEEE，1995:1492-1498.
[2]Shi Y H，Eberhart R.Fuzzy adaptive particle swarm optimization［C］//Proceedings of the 2000 Congress on Evolutionary Computation.Seoul，2000:101-106.
[3]Shi Y H，Eberhart R.Parameter selection in particle swarm optimization［C］//Evolutionary Programming VII.7th International Conference，EP98.San Diego，1998:591-600.
[4]Shi Y H，Eberhart R.A modified particle swarm optimizer［C］//1998 IEEE International Conference on Evolutionary Computation.Anchorage，1998:69-73.
[5]Chatterjee A，Siarry P.Nonlinear inertia weight variation for dynamic adaptation in particle swarm optimization［J］.Computers & Operations Research，2006，33(3):859-871.
[6]Tang Y，Wang Z D，Fang J A.Feedback learning particle swarm optimization［J］.Applied Soft Computing，2011，11(8):4713-4725.
[7]Jiang C W，Etorre B.A self-adaptive chaotic particle swarm algorithm for short term hydroelectric system scheduling in deregulated environment［J］.Energy Conversion and Management，2005，46(17):2689-2696.
[8]Amoshahy M J，Shamsi M，Sedaaghi M H.A novel flexible inertia weight particle swarm optimization algorithm［J］.PLoS One，2016，11(8):e161558.
[9]Houssein E，Gad A，H K，et al.Major advances in particle swarm optimization:theory，analysis，and application［J］.Swarm and Evolutionary Computation，2021，63:100868.
[10]Farooq M，Ahmad A，Hameed A.Opposition-based initialization and a modified pattern for Inertia Weight(IW)in PSO［C］//2017 IEEE International Conference on Inovations in Intelligent Systems and Applications.Gdynia，2017:96-101.
[11]Ozcan E，Mohan C K.Particle swarm optimization:surfing the waves［C］//Proceedings of the 1999 Congress on Evolutionary Computation.Washington D C，1999:1939-1944.
[12]张选平，杜玉平，秦国强，等.一种动态改变惯性权的自适应粒子群算法［J］.西安交通大学学报，2005，39(10):1039-1042.(Zhang Xuan-ping，Du Yu-ping，Qin guo-qiang，et al.Adaptive particle swarm algorithm with dynamically changing inertia weight［J］.Journal of Xian Jiaotong University，2005，39(10):1039-1042.)
[13]Liu B，Wang L，Jin Y H，et al.Improved particle swarm optimization combined with chaos［J］.Chaos，Solitons & Fractals，2005，25(5):1261-1271.
[14]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 Tian-ze，Li Yuan-xiang，Xiang Zheng-long，et al.Paritcle swarm optimization algorithm based on RMSprop method［J］.Computer Engineering and Design，2021，42(3):642-648.)
[15]陈璐璐，邱建林，陈燕云，等.改进的遗传粒子群混合优化算法［J］.计算机工程与设计，2017，38(2):395-399.(Chen Lu-lu，Qiu Jian-lin，Chen Yan-yun，et al.Improved hybrid optimization algorithms based on genetic algorithm and particle swarm optimization［J］.Computer Engineering and Design，2017，38(2):395-399.)
[16]Chen Y G，Li L X，Peng H P，et al.Particle swarm optimizer with two differential mutation［J］.Applied Soft Computing，2017，61:314-330.
[17]Zhou X J，Yang C H G.A particle swarm optimization algorithm with variable random functions and mutation［J］.Acta Automatica Sinica，2014，40(7):1339-1347.
[18]Ren W Z，Cao J.A chaos particle swarm optimization ranging correction location in complex environment［J］.Journal of China Universities of Posts and Telecommunications，2012，19:1-5.
[19]Gandomi A，Yun G J，Yang X S，et al.Chaos-enhanced accelerated particle swarm optimization［J］.Communications in Nonlinear Science and Numerical Simulation，2013，18(2):327-340.
[20]Pluhacek M，Senkerik R，Davendra D.Chaos particle swarm optimization with ensemble of chaotic systems［J］.Swarm and Evolutionary Computation，2015，25:29-35.
[21]Clerc M.The swarm and the queen:towards a deterministic and adaptive particle swarm optimization［C］//Proceedings of the 1999 Congress on Evolutionary Computation.Washington D C，1999:1951-1957.
[22]任子晖，王坚.加速收敛的粒子群优化算法［J］.控制与决策，2011，26(2):201-206.(Ren Zi-hui，Wang Jian.Accelerate convergence particle swarm optimization algorithm［J］.Control and Decision，2011，26(2):201-206.)
[23]Freedman D，Pisani R，Purves R.Statistics［M］.New York:William Warder Norton & Company，2007.
[24]李宁，刘飞，孙德宝.基于带变异算子粒子群优化算法的约束布局优化研究［J］.计算机学报，2004，27(7):897-903.(Li Ning，Liu Fei，Sun De-bao.A study on the particle swarm optimization with mutation operator constrained layout optimization［J］.Chinese Journal of Computers，2004，27(7):897-903.)