Surrogated-Assisted Heterogeneous Multi-Objective Optimization for Integrated Energy Systems

As the global energy landscape shifts towards sustainability, Integrated Energy Systems have emerged as crucial solutions for enhancing energy efficiency and reducing environmental impact. The complexity of IES arises from the integration of diverse energy sources, requiring a balance of economic, environmental, and reliability objectives. This study introduces a novel surrogate-assisted heterogeneous multi-objective optimization algorithm to address these challenges. By employing Kriging models alongside a parallel SPEA2 algorithm, the approach effectively reduces computational burdens associated with slow objective evaluations. Additionally, a polynomial decay-based strategy dynamically updates surrogate model parameters, enhancing adaptability and minimizing unnecessary computational costs. Through comprehensive case studies, the algorithm demonstrates superior capability in optimizing equipment capacity, highlighting its potential to drive sustainable development in energy systems. This work provides a robust framework for tackling complex optimization problems in Integrated Energy Systems, underscoring its significance in advancing sustainable energy solutions.