Solving Dynamic Multiobjective Problem via Autoencoding Evolutionary Search
Top Cited Papers
- 1 October 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 52 (5) , 2649-2662
Abstract
Dynamic multiobjective optimization problem (DMOP) denotes the multiobjective optimization problem, which contains objectives that may vary over time. Due to the widespread applications of DMOP existed in reality, DMOP has attracted much research attention in the last decade. In this article, we propose to solve DMOPs via an autoencoding evolutionary search. In particular, for tracking the dynamic changes of a given DMOP, an autoencoder is derived to predict the moving of the Pareto-optimal solutions based on the nondominated solutions obtained before the dynamic occurs. This autoencoder can be easily integrated into the existing multiobjective evolutionary algorithms (EAs), for example, NSGA-II, MOEA/D, etc., for solving DMOP. In contrast to the existing approaches, the proposed prediction method holds a closed-form solution, which thus will not bring much computational burden in the iterative evolutionary search process. Furthermore, the proposed prediction of dynamic change is automatically learned from the nondominated solutions found along the dynamic optimization process, which could provide more accurate Pareto-optimal solution prediction. To investigate the performance of the proposed autoencoding evolutionary search for solving DMOP, comprehensive empirical studies have been conducted by comparing three state-of-the-art prediction-based dynamic multiobjective EAs. The results obtained on the commonly used DMOP benchmarks confirmed the efficacy of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (61876025, 61876162)
- Venture and Innovation Support Program for Chongqing Overseas Returnees (cx2018044, cx2019020)
- City University of Hong Kong Research Fund (9610397)
- Shenzhen Scientific Research and Development Funding Program (JCYJ20180307123637294)
- Research Grants Council of Hong Kong SAR (CityU11202418, CityU11209219)
This publication has 46 references indexed in Scilit:
- Dynamic Multi-objective Optimization: A Survey of the State-of-the-Art2013
- Multi-strategy ensemble evolutionary algorithm for dynamic multi-objective optimizationMemetic Computing, 2009
- Evolutionary multi-objective optimization: a historical view of the fieldIEEE Computational Intelligence Magazine, 2006
- Evolutionary Optimization in Uncertain Environments—A SurveyIEEE Transactions on Evolutionary Computation, 2005
- Dynamic Multiobjective Optimization Problems: Test Cases, Approximations, and ApplicationsIEEE Transactions on Evolutionary Computation, 2004
- Genetic Diversity as an Objective in Multi-Objective Evolutionary AlgorithmsEvolutionary Computation, 2003
- The balance between proximity and diversity in multiobjective evolutionary algorithmsIEEE Transactions on Evolutionary Computation, 2003
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- A comparison of dominance mechanisms and simple mutation on non-stationary problems1998
- Adaptation to a changing environment by means of the feedback thermodynamical genetic algorithm1998