基于非支配遗传算法及协同进化算法的多目标多区域电网规划

Multi-objective and Multi-district Transmission Planning Based on NSGA-II and Cooperative Co-evolutionary Algorithm

基于快速分类的非支配遗传算法(NSGA-II)是一种新型的多目标遗传算法,文中首次将其应用于电网优化规划。多个算例分析表明NSGA-II算法在电网规划中具有良好的优化效果,为各目标之间的权衡分析提供了有效的工具;协同进化算法采用分解-协调的思想处理复杂系统的演化,可以克服当优化问题规模扩大时,常规进化算法易于出现过早收敛的现象。据此提出将协同进化算法和NSAG-II算法相结合,以用于处理大规模多区域的电力系统规划问题,在各子网采用NSAG-II算法优化的过程中进行多区域协调。与常规遗传算法相比,算例分析取得了更好的规划结果。

Fast non-dominated sorting genetic algorithm （NSGA-II）, a new multi-objective genetic algorithm, is applied to transmission planning for the first time. Simulation results illustrate that NSGA-II has better convergence and flexibility and provides an effective tool for measure the performance of different objective functions. For large scale and multi-area transmission systems planning, the cooperative co-evolutionary algorithm combined with NSGA-II is adopted to overcome some disadvantages of GA such as premature convergence. Sub-system which is optimized by NSGA-II coevolves with other sub-systems. A practical system planning shows it can give satisfy results for such problems.