Construction Vehicle Routing Planning Based on Improved Hippopotamus Optimization Algorithm

With the rapid development of renewable energy, pumped storage power stations—critical energy storage facilities—are experiencing exponential growth. During construction, efficient vehicle path planning significantly impacts cost, schedule, and environmental sustainability. However, traditional path planning methods struggle with convergence accuracy and computational efficiency in the complex terrain of pumped storage sites. To address these challenges, this paper proposes an Improved Hippopotamus Optimization Algorithm (IHOA) for construction vehicle path planning. The key innovations include: SPM chaotic mapping for population initialization to prevent local optima; An adaptive weighting strategy to balance global exploration and local refinement; Elite reverse learning to enhance population diversity. Experimental results demonstrate that IHOA outperforms conventional methods in convergence speed and solution quality, offering an effective tool for optimizing path planning in pumped storage power station construction.