Evolutionary Computation for Dynamic Complex Systems
Overview
Developing evolutionary algorithms that can track moving optima and adapt to changing environments in real-time decision-making scenarios.
Key Questions
- How can populations maintain sufficient diversity to adapt to unpredictable environmental changes?
- What strategies can effectively detect and respond to different types of environmental changes?
- How can we balance exploration and exploitation in time-varying landscapes?
Our Contributions
- Systematic study of transfer learning in dynamic multiobjective optimization
- Spatial-temporal knowledge transfer for dynamic constrained problems
- Knee point-based approaches for handling imbalanced transfer
Recommended Papers
Proposes a transfer learning framework that leverages historical optimization knowledge to accelerate convergence in dynamic multiobjective environments.
Introduces a spatial-temporal knowledge transfer framework that simultaneously exploits spatial correlations among decision variables and temporal patterns across environmental changes for dynamic constrained multiobjective optimization.
Addresses the imbalanced distribution problem in transfer learning for dynamic multiobjective optimization by leveraging knee point information to guide knowledge transfer.
Recent Work
Explores how large language models can serve as intelligent optimizers for dynamic multiobjective problems, leveraging their reasoning and pattern recognition capabilities to guide the evolutionary search.
Open Problems
- Real-time adaptation for high-frequency environmental changes
- Handling mixed continuous-discrete dynamic problems
- Benchmark design that captures real-world dynamic characteristics
Prospective Student Projects
- Change detection mechanisms for dynamic multiobjective optimization
- Multi-population strategies for tracking multiple moving Pareto fronts
- Surrogate-assisted dynamic optimization for expensive time-varying problems