TY - GEN
T1 - A Hybrid Replacement Strategy for MOEA/D
AU - Chen, Xiaoji
AU - Shi, Chuan
AU - Zhou, Aimin
AU - Xu, Siyong
AU - Wu, Bin
N1 - Publisher Copyright:
© 2018, Springer Nature Singapore Pte Ltd.
PY - 2018
Y1 - 2018
N2 - In MOEA/D, the replacement strategy plays a key role in balancing diversity and convergence. However, existing adaptive replacement strategies either focus on neighborhood or global replacement strategy, which may have no obvious effects on balance of diversity and convergence in tackling complicated MOPs. In order to overcome this shortcoming, we propose a hybrid mechanism balancing neighborhood and global replacement strategy. In this mechanism, a probability threshold is applied to determine whether to execute a neighborhood or global replacement strategy, which could balance diversity and convergence. Furthermore, we design an offspring generation method to generate the high-quality solution for each subproblem, which can ease mismatch between subproblems and solutions. Based on the classic MOEA/D, we design a new algorithm framework, called MOEA/D-HRS. Compared with other state-of-the-art MOEAs, experimental results show that the proposed algorithm obtains the best performance.
AB - In MOEA/D, the replacement strategy plays a key role in balancing diversity and convergence. However, existing adaptive replacement strategies either focus on neighborhood or global replacement strategy, which may have no obvious effects on balance of diversity and convergence in tackling complicated MOPs. In order to overcome this shortcoming, we propose a hybrid mechanism balancing neighborhood and global replacement strategy. In this mechanism, a probability threshold is applied to determine whether to execute a neighborhood or global replacement strategy, which could balance diversity and convergence. Furthermore, we design an offspring generation method to generate the high-quality solution for each subproblem, which can ease mismatch between subproblems and solutions. Based on the classic MOEA/D, we design a new algorithm framework, called MOEA/D-HRS. Compared with other state-of-the-art MOEAs, experimental results show that the proposed algorithm obtains the best performance.
KW - Evolutionary algorithm
KW - MOEA/D
KW - Multiobjective optimization
KW - Replacement strategy
UR - https://www.scopus.com/pages/publications/85055839924
U2 - 10.1007/978-981-13-2826-8_22
DO - 10.1007/978-981-13-2826-8_22
M3 - 会议稿件
AN - SCOPUS:85055839924
SN - 9789811328251
T3 - Communications in Computer and Information Science
SP - 246
EP - 262
BT - Bio-inspired Computing
A2 - Zhang, Qingfu
A2 - Qiao, Jianyong
A2 - Zhao, Xinchao
A2 - Zuo, Xingquan
A2 - Huang, Shanguo
A2 - Pan, Linqiang
A2 - Zhang, Xingyi
PB - Springer Verlag
T2 - 13th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2018
Y2 - 2 November 2018 through 4 November 2018
ER -