Application of Optimization Algorithm on Cloud Adaptive Gradient Particle Swarm Optimization in Optimal Reactive Power

Reactive power optimization is a typical high-dimensional, nonlinear, discontinuous problem. Particle swarm optimization (PSO) algorithm has high convergence speed and is easy to implement, but it also exists precocious phenomenon. In the later stage of optimization, the improvement is not good and is easy to be trapped in local minima. To overcome this shortcoming, this article will firstly introduce cloud model into particle swarm optimization(CAPSO), so, It is to divide the particle into two parts, close to or away from the best particle, the former particles ’ weight of inertia will be adaptively adjusted by X-condition generator of cloud model then improve it with gradient theory. The article proposes the cloud adaptive gradient particle swarm optimization (CAGPSO) according to this theory. Considering minimum network loss as the objective function, make the simulation in standard IEEE14 and IEEE30 node system. The results show that the improved CAGPSO algorithm can achieve a better global optimal solution