Optimization of power output in plateau photovoltaic power stations using a hybrid Kepler and Gaussian quantum particle swarm algorithm

This study presents an innovative hybrid approach for optimizing the power output of photovoltaic (PV) power stations in plateau regions, where environmental factors such as high altitude, extreme sunlight, and frequent snow coverage lead to significant operational challenges. The proposed solution integrates the Kepler Optimization Algorithm (KOA) with the Gaussian Quantum Improved Particle Swarm Optimization (GQPSO) to address multi-objective optimization, with the goal of maximizing power generation, minimizing operational costs, and enhancing system stability. The optimization process is modeled with key decision variables, including panel configurations, snow removal strategies, and system efficiency adjustments. The objective function is designed to balance power output maximization and cost minimization, while accounting for environmental impacts, such as snow accumulation and temperature fluctuations, over a yearly operational horizon. The results of simulations demonstrate the effectiveness of the KOA-GQPSO algorithm, achieving a 12% increase in power generation compared to traditional methods. Additionally, the integration of snow removal strategies guided by the algorithm leads to an annual energy recovery of 3,650 MWh, enhancing overall system efficiency by 5–15%. This work introduces a novel, adaptive multi-objective optimization framework tailored to high-altitude PV systems, offering practical solutions for maintaining energy stability and operational efficiency in challenging environments.