Optimization Algorithm of Industrial Multi-Objective Centralized Maintenance for Power Grid Stability

Le résumé fourni par la source

Traditional power grid maintenance methods mostly use regular power outages for maintenance, which often involve large-scale power outages within a predetermined time period, causing industrial enterprises to inevitably stop production for a long time. Especially when the load is high or important production lines are shut down, the impact of maintenance on production is particularly serious. This paper studies the optimization of power grid stability through industrial multi-objective centralized maintenance methods. This study first determines the research problem and the goal setting of the algorithm. Then, this paper proposes the main optimization objectives of grid load balancing, grid stability improvement and industrial enterprise production efficiency in the multi-objective optimization model. Next, this paper sets the constraints, boundary settings and objective functions of the GA-PSO (Genetic Algorithm-Particle Swarm Optimization) algorithm, and trains historical data through the GA-PSO algorithm to achieve the optimal resource allocation for power grid maintenance. Finally, experiments are conducted using Province A's power grid load data in the summer of 2024, production data from multiple industrial enterprises, maintenance resource data, and historical maintenance data. The experimental results show that during the low-load period in spring and autumn (00:00-06:00), the load fluctuation coefficient of GA-PSO is 0.15, which is significantly lower than that of other algorithms. The load peak-to-valley ratio of GA-PSO during the low-load period in spring and autumn is 1.15. The fault repair time of GA-PSO algorithm is significantly shorter than that of other algorithms.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.