Intelligent multi-objective scheduling optimization of microgrids based on IHAOAVO algorithm

Abstract To improve the operational efficiency and energy utilization of microgrids, this paper develops a model of multi-objective optimization scheduling by incorporating wind, solar, gas, diesel power generation and energy storage units, whose objective is to minimize both operating costs and carbon dioxide emissions. To achieve this, an Improved Hybrid Aquila Optimizer and African Vultures Optimization (IHAOAVO) algorithm is introduced to optimize microgrid scheduling. This approach integrates the exploration phase of the Aquila Optimizer (AO) with the exploitation phase of the African Vulture Optimization (AVO) algorithm in the early stages to improve convergence performance. Furthermore, a Composite Opposition-Based Learning (COBL) mechanism is applied to assist search agents in avoiding local optima, while a fitness distance balance (FDB) selection method is used to select more suitable reference individuals for population search, maintaining a balance between exploration and exploitation. Experimental results show that compared to traditional AO and AVO algorithms, the proposed IHAOAVO algorithm reduces total operating costs by approximately 15.21% and average costs by about 15.17%, while also decreasing computation time by 20%. This effectively lowers electricity costs and reduces environmental pollution for users.