Multi-task multi-constraint differential evolution with elite-guided knowledge transfer for coal mine integrated energy system dispatching

TL;DR

This paper tackles the high-dimensional, tightly constrained multiobjective dispatch problem of coal mine integrated energy systems by proposing a domain-adaptive, multi-task evolutionary framework. It integrates constraint knowledge through three task-construction modes (constraint-coupled variable space decomposition, constraint strength classification, and constraint handling technique fusion) and enhances differential evolution with elite-guided knowledge transfer and an adaptive neighborhood mutation. Empirical results against a CPLEX solver and seven constrained multiobjective EAs demonstrate improved convergence, diversity, and robustness, along with feasible, energy-aware dispatch strategies that leverage co-produced heat, cooling, and electricity. The approach offers a scalable, knowledge-driven pathway for CMIES optimization with practical implications for reducing operating and abandoned energy costs in industrial energy systems.

Abstract

The dispatch optimization of coal mine integrated energy system is challenging due to high dimensionality, strong coupling constraints, and multiobjective. Existing constrained multiobjective evolutionary algorithms struggle with locating multiple small and irregular feasible regions, making them inaplicable to this problem. To address this issue, we here develop a multitask evolutionary algorithm framework that incorporates the dispatch correlated domain knowledge to effectively deal with strong constraints and multiobjective optimization. Possible evolutionary multitask construction strategy based on complex constraint relationship analysis and handling, i.e., constraint coupled spatial decomposition, constraint strength classification and constraint handling technique, is first explored. Within the multitask evolutionary optimization framework, two strategies, i.e., an elite guided knowledge transfer by designing a special crowding distance mechanism to select dominant individuals from each task, and an adaptive neighborhood technology based mutation to effectively balance the diversity and convergence of each optimized task for the differential evolution algorithm, are further developed. The performance of the proposed algorithm in feasibility, convergence, and diversity is demonstrated in a case study of a coal mine integrated energy system by comparing with CPLEX solver and seven constrained multiobjective evolutionary algorithms.

Figures (14)

• Figure 1: Comparison of typical IES and CMIES frameworks
• Figure 2: Multi-task multi-constraint evolutionary dispatch algorithm framework
• Figure 3: An example of multi-task construction with constraint-coupled variable space decomposition
• Figure 4: An example of multi-task construction with constraint strength classification
• Figure 5: An example of multi-task construction based on CHTs