The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
돌연변이 전략의 선택은 미분 진화 알고리즘(DE)의 성능에 큰 영향을 미칩니다. 다양한 유형의 최적화 문제에 대해 서로 다른 돌연변이 전략을 선택해야 합니다. 다양한 문제에 적합한 돌연변이 전략을 선택하는 방법은 어려운 작업입니다. 이 문제를 해결하기 위해 본 논문에서는 FLIDE라고 하는 로컬 피트니스 환경을 기반으로 하는 새로운 DE 알고리즘을 제안합니다. 제안된 방법에서는 돌연변이 연산자의 선택을 안내하기 위해 적합도 환경 정보를 얻습니다. 이러한 방식으로 적절한 진화 메커니즘을 통해 다양한 문제를 해결할 수 있습니다. 또한 인구 조정 방법을 사용하여 검색 능력과 인구 다양성의 균형을 맞춥니다. 한편으로 초기 단계의 인구 다양성은 상대적으로 많은 인구로 인해 향상됩니다. 한편, 계산 비용은 상대적으로 적은 인구로 나중 단계에서 감소합니다. 탐색 방향을 안내하기 위해 진화 정보를 최대한 활용한다. 제안된 방법은 서로 다른 특성을 가진 30개의 테스트 함수에 대해 XNUMX개의 인기 있는 알고리즘과 비교됩니다. 실험 결과는 제안된 FLIDE가 고차원 문제에 더 효과적임을 보여줍니다.
Jing LIANG
Zhengzhou University
Ke LI
Zhengzhou University
Kunjie YU
Zhengzhou University
Caitong YUE
Zhengzhou University
Yaxin LI
Zhengzhou University
Hui SONG
RMIT University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Jing LIANG, Ke LI, Kunjie YU, Caitong YUE, Yaxin LI, Hui SONG, "A Novel Differential Evolution Algorithm Based on Local Fitness Landscape Information for Optimization Problems" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 5, pp. 601-616, May 2023, doi: 10.1587/transinf.2022DLP0010.
Abstract: The selection of mutation strategy greatly affects the performance of differential evolution algorithm (DE). For different types of optimization problems, different mutation strategies should be selected. How to choose a suitable mutation strategy for different problems is a challenging task. To deal with this challenge, this paper proposes a novel DE algorithm based on local fitness landscape, called FLIDE. In the proposed method, fitness landscape information is obtained to guide the selection of mutation operators. In this way, different problems can be solved with proper evolutionary mechanisms. Moreover, a population adjustment method is used to balance the search ability and population diversity. On one hand, the diversity of the population in the early stage is enhanced with a relative large population. One the other hand, the computational cost is reduced in the later stage with a relative small population. The evolutionary information is utilized as much as possible to guide the search direction. The proposed method is compared with five popular algorithms on 30 test functions with different characteristics. Experimental results show that the proposed FLIDE is more effective on problems with high dimensions.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022DLP0010/_p
부
@ARTICLE{e106-d_5_601,
author={Jing LIANG, Ke LI, Kunjie YU, Caitong YUE, Yaxin LI, Hui SONG, },
journal={IEICE TRANSACTIONS on Information},
title={A Novel Differential Evolution Algorithm Based on Local Fitness Landscape Information for Optimization Problems},
year={2023},
volume={E106-D},
number={5},
pages={601-616},
abstract={The selection of mutation strategy greatly affects the performance of differential evolution algorithm (DE). For different types of optimization problems, different mutation strategies should be selected. How to choose a suitable mutation strategy for different problems is a challenging task. To deal with this challenge, this paper proposes a novel DE algorithm based on local fitness landscape, called FLIDE. In the proposed method, fitness landscape information is obtained to guide the selection of mutation operators. In this way, different problems can be solved with proper evolutionary mechanisms. Moreover, a population adjustment method is used to balance the search ability and population diversity. On one hand, the diversity of the population in the early stage is enhanced with a relative large population. One the other hand, the computational cost is reduced in the later stage with a relative small population. The evolutionary information is utilized as much as possible to guide the search direction. The proposed method is compared with five popular algorithms on 30 test functions with different characteristics. Experimental results show that the proposed FLIDE is more effective on problems with high dimensions.},
keywords={},
doi={10.1587/transinf.2022DLP0010},
ISSN={1745-1361},
month={May},}
부
TY - JOUR
TI - A Novel Differential Evolution Algorithm Based on Local Fitness Landscape Information for Optimization Problems
T2 - IEICE TRANSACTIONS on Information
SP - 601
EP - 616
AU - Jing LIANG
AU - Ke LI
AU - Kunjie YU
AU - Caitong YUE
AU - Yaxin LI
AU - Hui SONG
PY - 2023
DO - 10.1587/transinf.2022DLP0010
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2023
AB - The selection of mutation strategy greatly affects the performance of differential evolution algorithm (DE). For different types of optimization problems, different mutation strategies should be selected. How to choose a suitable mutation strategy for different problems is a challenging task. To deal with this challenge, this paper proposes a novel DE algorithm based on local fitness landscape, called FLIDE. In the proposed method, fitness landscape information is obtained to guide the selection of mutation operators. In this way, different problems can be solved with proper evolutionary mechanisms. Moreover, a population adjustment method is used to balance the search ability and population diversity. On one hand, the diversity of the population in the early stage is enhanced with a relative large population. One the other hand, the computational cost is reduced in the later stage with a relative small population. The evolutionary information is utilized as much as possible to guide the search direction. The proposed method is compared with five popular algorithms on 30 test functions with different characteristics. Experimental results show that the proposed FLIDE is more effective on problems with high dimensions.
ER -