TY - JOUR
T1 - Composite Particle Swarm Optimizer with Historical Memory for Function Optimization
AU - Li, Jie
AU - Zhang, Junqi
AU - Jiang, Changjun
AU - Zhou, Mengchu
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 61272271, Grant 61332008, and Grant 91218301, in part by the NSF of USA under Grant CMMI-1162482, in part by the National Basic Research Program of China (973 Program) under Grant 2014CB340404, in part by the Natural Science Foundation Program of Shanghai under Grant 12ZR1434000, and in part by the International Cooperation Project of Chinese Ministry of Science and Technology under Grant 2012DFG11580. This paper was recommended by Associate Editor Jun Zhang. (Corresponding authors: JunQi Zhang and ChangJun Jiang.).
Publisher Copyright:
© 2015 IEEE.
PY - 2015/10
Y1 - 2015/10
N2 - Particle swarm optimization (PSO) algorithm is a population-based stochastic optimization technique. It is characterized by the collaborative search in which each particle is attracted toward the global best position (gbest) in the swarm and its own best position (pbest). However, all of particles' historical promising pbests in PSO are lost except their current pbests. In order to solve this problem, this paper proposes a novel composite PSO algorithm, called historical memory-based PSO (HMPSO), which uses an estimation of distribution algorithm to estimate and preserve the distribution information of particles' historical promising pbests. Each particle has three candidate positions, which are generated from the historical memory, particles' current pbests, and the swarm's gbest. Then the best candidate position is adopted. Experiments on 28 CEC2013 benchmark functions demonstrate the superiority of HMPSO over other algorithms.
AB - Particle swarm optimization (PSO) algorithm is a population-based stochastic optimization technique. It is characterized by the collaborative search in which each particle is attracted toward the global best position (gbest) in the swarm and its own best position (pbest). However, all of particles' historical promising pbests in PSO are lost except their current pbests. In order to solve this problem, this paper proposes a novel composite PSO algorithm, called historical memory-based PSO (HMPSO), which uses an estimation of distribution algorithm to estimate and preserve the distribution information of particles' historical promising pbests. Each particle has three candidate positions, which are generated from the historical memory, particles' current pbests, and the swarm's gbest. Then the best candidate position is adopted. Experiments on 28 CEC2013 benchmark functions demonstrate the superiority of HMPSO over other algorithms.
KW - Estimation of distribution algorithm (EDA)
KW - historical memory
KW - particle swarm optimization (PSO)
UR - http://www.scopus.com/inward/record.url?scp=84960434942&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84960434942&partnerID=8YFLogxK
U2 - 10.1109/TCYB.2015.2424836
DO - 10.1109/TCYB.2015.2424836
M3 - Article
AN - SCOPUS:84960434942
SN - 2168-2267
VL - 45
SP - 2350
EP - 2363
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
IS - 10
M1 - 7114277
ER -