TY - GEN
T1 - Operator-Adapted Evolutionary Large-Scale Multiobjective Optimization for Voltage Transformer Ratio Error Estimation
AU - HUANG, Changwu
AU - LI, Lianghao
AU - HE, Cheng
AU - CHENG, Ran
AU - YAO, Xin
N1 - This work was supported by the Guangdong Basic and Applied Basic Research Foundation (Grant No. 2019A1515110575), the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), the Program for Guangdong Introducing Innovative and Entrepreneurial Teams (Grant No. 2017ZT07X386), the Shenzhen Science and Technology Program (Grant No. KQTD2016112514355531), the Program for University Key Laboratory of Guangdong Province (Grant No. 2017KSYS008), and the National Natural Science Foundation of China (No. 61903178 and 61906081).
PY - 2021
Y1 - 2021
N2 - Large-scale multiobjective optimization problems (LSMOPs) exist widely in real-world applications, and they are challenging for existing evolutionary algorithms due to their massive volume of search space. Despite that a number of large-scale multiobjective evolutionary algorithms (LSMOEAs) have been proposed in recent years, their effectiveness in solving LSMOPs remains unsatisfactory. One main reason is that most existing LSMOEAs may fail to balance convergence enhancement and diversity maintenance, especially for solving real-world problems. To address this issue, we propose to use a hybridized LSMOEA with adaptive operator selection (AOS) to handle real-world LSMOPs. Specifically, the proposed hybridized LSMOEA with AOS (AOS-LSMOEA) includes multiple different offspring generation and environmental selection strategies extracted from some existing LSMOEAs. Then it uses the AOS to adaptively determine the application rates of different offspring generation and environmental selection operators in an online manner. The proposed approach is capable of taking advantage of existing LSMOEAs, and the AOS enables the algorithm to choose suitable operators for solving different LSMOPs. In this study, the proposed algorithm is expected to solve the voltage transformer ratio error estimation (TREE) problems effectively. Experimental results show that AOS-LSMOEA achieves significant performance improvement due to the hybridization of different operators and the adoption of AOS method. © 2021, Springer Nature Switzerland AG.
AB - Large-scale multiobjective optimization problems (LSMOPs) exist widely in real-world applications, and they are challenging for existing evolutionary algorithms due to their massive volume of search space. Despite that a number of large-scale multiobjective evolutionary algorithms (LSMOEAs) have been proposed in recent years, their effectiveness in solving LSMOPs remains unsatisfactory. One main reason is that most existing LSMOEAs may fail to balance convergence enhancement and diversity maintenance, especially for solving real-world problems. To address this issue, we propose to use a hybridized LSMOEA with adaptive operator selection (AOS) to handle real-world LSMOPs. Specifically, the proposed hybridized LSMOEA with AOS (AOS-LSMOEA) includes multiple different offspring generation and environmental selection strategies extracted from some existing LSMOEAs. Then it uses the AOS to adaptively determine the application rates of different offspring generation and environmental selection operators in an online manner. The proposed approach is capable of taking advantage of existing LSMOEAs, and the AOS enables the algorithm to choose suitable operators for solving different LSMOPs. In this study, the proposed algorithm is expected to solve the voltage transformer ratio error estimation (TREE) problems effectively. Experimental results show that AOS-LSMOEA achieves significant performance improvement due to the hybridization of different operators and the adoption of AOS method. © 2021, Springer Nature Switzerland AG.
KW - Adaptive operator selection
KW - Large-scale optimization
KW - Multiobjective optimization
KW - Voltage transformer ratio error estimation
UR - http://www.scopus.com/inward/record.url?scp=85107315144&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-72062-9_53
DO - 10.1007/978-3-030-72062-9_53
M3 - Conference paper (refereed)
SN - 9783030720612
T3 - Lecture Notes in Computer Science
SP - 672
EP - 683
BT - Evolutionary Multi-Criterion Optimization : 11th International Conference, EMO 2021, Shenzhen, China, March 28–31, 2021, Proceedings
A2 - ISHIBUCHI, Hisao
A2 - ZHANG, Qingfu
A2 - CHENG, Ran
A2 - LI, Ke
A2 - LI, Hui
A2 - WANG, Handing
A2 - ZHOU, Aimin
PB - Springer Science and Business Media Deutschland GmbH
T2 - 11th International Conferenceon Evolutionary Multi-Criterion Optimization
Y2 - 28 March 2021 through 31 March 2021
ER -