Design and Application of Energy Internet Optimization Algorithm for Carbon Neutralization

As a key technological framework connecting energy production and consumption, the Energy Internet plays a crucial role in promoting the transformation of energy structures and enhancing energy utilization efficiency. This paper introduces a Neighborhood Search Moth-Flame Optimization (NSMFO) algorithm based on Differential Evolution (DE) to enhance global search capabilities, avoid local optima, and improve solution precision through neighborhood search strategies. The algorithm demonstrates promising applications in Energy Internet optimization problems, effectively supporting the realization of carbon neutrality goals. Through theoretical analysis and empirical studies, an innovative optimization algorithm framework is proposed to address challenges faced by the Energy Internet in energy distribution, scheduling, and storage. In the case study of a "Green Smart Park," the NSMFO algorithm significantly improved energy utilization efficiency, reduced carbon emissions, and brought substantial economic benefits. After optimization, the total carbon emissions in the park decreased by approximately 13.23%, with reductions also seen in energy costs and maintenance expenses. Compared to traditional Genetic Algorithms (GA) and Particle Swarm Optimization (PSO), NSMFO exhibits superior convergence speed and solution quality in multi-objective optimization problems. This research provides strong technical support and practical examples for promoting smart energy management and constructing low-carbon sustainable urban development models.