Skip to Main Content
To deal with reactive power optimization problem, an adaptive Niche Particle Swarm Optimization algorithm (ANPSO) is presented. Differential Evolution algorithm (DE) is easy to use and has the advantages of strong robustness, but its efficiency is limited and probably to fall into local optimum because the population loss of diversity after several generations. ANDE introduces niche-sharing mechanisms to change the individual values and accelerates to eliminate individuals which have low value. Niching radius can also be adjusted adaptively on the basis of the relative distance between individuals which reflect the aggregation of population. Using the above method, algorithm's global searching ability is improved. The proposed algorithm is tested on a realistic planning project and the results show its better performance on celerity, accuracy and efficiency.