Optimal Configuration of Integrated Energy Systems Based on Improved Genetic Algorithm

This paper presents an optimization method for integrated energy systems based on a genetic algorithm, aimed at achieving efficient energy management through multi-energy complementation, improving energy utilization efficiency, reducing carbon emissions, and optimizing economic performance. The study first constructs a capacity optimization model for the integrated energy system based on the resource conditions and energy demand of an industrial park, with the objective of minimizing total system costs and considering carbon trading costs. The system configuration was solved using a genetic algorithm, and simulations were conducted using actual load data from typical summer and winter days. The results show that the optimized system achieved renewable energy utilization rates of 93.59% and 90.0% in summer and winter, respectively, with carbon emissions reduced by approximately 20.46 tons and 17.25 tons. This research provides theoretical support for the design and control of integrated energy systems in industrial parks, demonstrating significant potential in energy conservation and emission reduction.