Q-learning based vegetation evolution for numerical optimization and wireless sensor network coverage optimization
Vegetation evolution (VEGE) is a newly proposed meta-heuristic algorithm (MA) with excellent exploitation but relatively weak exploration capacity. We thus focus on further balancing the exploitation and the exploration of VEGE well to improve the overall optimization performance. This paper propose...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016823011201 |
| _version_ | 1827370632945336320 |
|---|---|
| author | Rui Zhong Fei Peng Jun Yu Masaharu Munetomo |
| author_facet | Rui Zhong Fei Peng Jun Yu Masaharu Munetomo |
| author_sort | Rui Zhong |
| collection | DOAJ |
| description | Vegetation evolution (VEGE) is a newly proposed meta-heuristic algorithm (MA) with excellent exploitation but relatively weak exploration capacity. We thus focus on further balancing the exploitation and the exploration of VEGE well to improve the overall optimization performance. This paper proposes an improved Q-learning based VEGE, and we design an exploitation archive and an exploration archive to provide a variety of search strategies, each archive contains four efficient and easy-implemented search strategies. In addition, online Q-Learning, as well as ε-greedy scheme, are employed as the decision-maker role to learn the knowledge from the past optimization process and determine the search strategy for each individual automatically and intelligently. In numerical experiments, we compare our proposed QVEGE with eight state-of-the-art MAs including the original VEGE on CEC2020 benchmark functions, twelve engineering optimization problems, and wireless sensor networks (WSN) coverage optimization problems. Experimental and statistical results confirm that the proposed QVEGE demonstrates significant enhancements and stands as a strong competitor among existing algorithms. The source code of QVEGE is publicly available at https://github.com/RuiZhong961230/QVEGE. |
| first_indexed | 2024-03-08T10:19:24Z |
| format | Article |
| id | doaj.art-0d6a8f8081a0443598d060b8dfbb0f73 |
| institution | Directory Open Access Journal |
| issn | 1110-0168 |
| language | English |
| last_indexed | 2024-03-08T10:19:24Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj.art-0d6a8f8081a0443598d060b8dfbb0f732024-01-28T04:20:10ZengElsevierAlexandria Engineering Journal1110-01682024-01-0187148163Q-learning based vegetation evolution for numerical optimization and wireless sensor network coverage optimizationRui Zhong0Fei Peng1Jun Yu2Masaharu Munetomo3Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan; Corresponding author.Graduate School of Science and Technology, Niigata University, Niigata, JapanInstitute of Science and Technology, Niigata University, Niigata, JapanInformation Initiative Center, Hokkaido University, Sapporo, JapanVegetation evolution (VEGE) is a newly proposed meta-heuristic algorithm (MA) with excellent exploitation but relatively weak exploration capacity. We thus focus on further balancing the exploitation and the exploration of VEGE well to improve the overall optimization performance. This paper proposes an improved Q-learning based VEGE, and we design an exploitation archive and an exploration archive to provide a variety of search strategies, each archive contains four efficient and easy-implemented search strategies. In addition, online Q-Learning, as well as ε-greedy scheme, are employed as the decision-maker role to learn the knowledge from the past optimization process and determine the search strategy for each individual automatically and intelligently. In numerical experiments, we compare our proposed QVEGE with eight state-of-the-art MAs including the original VEGE on CEC2020 benchmark functions, twelve engineering optimization problems, and wireless sensor networks (WSN) coverage optimization problems. Experimental and statistical results confirm that the proposed QVEGE demonstrates significant enhancements and stands as a strong competitor among existing algorithms. The source code of QVEGE is publicly available at https://github.com/RuiZhong961230/QVEGE.http://www.sciencedirect.com/science/article/pii/S1110016823011201Meta-heuristic algorithmVegetation evolutionQ-learningWireless sensor network coverage problems |
| spellingShingle | Rui Zhong Fei Peng Jun Yu Masaharu Munetomo Q-learning based vegetation evolution for numerical optimization and wireless sensor network coverage optimization Alexandria Engineering Journal Meta-heuristic algorithm Vegetation evolution Q-learning Wireless sensor network coverage problems |
| title | Q-learning based vegetation evolution for numerical optimization and wireless sensor network coverage optimization |
| title_full | Q-learning based vegetation evolution for numerical optimization and wireless sensor network coverage optimization |
| title_fullStr | Q-learning based vegetation evolution for numerical optimization and wireless sensor network coverage optimization |
| title_full_unstemmed | Q-learning based vegetation evolution for numerical optimization and wireless sensor network coverage optimization |
| title_short | Q-learning based vegetation evolution for numerical optimization and wireless sensor network coverage optimization |
| title_sort | q learning based vegetation evolution for numerical optimization and wireless sensor network coverage optimization |
| topic | Meta-heuristic algorithm Vegetation evolution Q-learning Wireless sensor network coverage problems |
| url | http://www.sciencedirect.com/science/article/pii/S1110016823011201 |
| work_keys_str_mv | AT ruizhong qlearningbasedvegetationevolutionfornumericaloptimizationandwirelesssensornetworkcoverageoptimization AT feipeng qlearningbasedvegetationevolutionfornumericaloptimizationandwirelesssensornetworkcoverageoptimization AT junyu qlearningbasedvegetationevolutionfornumericaloptimizationandwirelesssensornetworkcoverageoptimization AT masaharumunetomo qlearningbasedvegetationevolutionfornumericaloptimizationandwirelesssensornetworkcoverageoptimization |