Research on the Improved Particle Swarm Optimization Algorithm Applying in the Reservoir Optimal Scheduling

ABSTRACT

Particle Swarm Optimization Algorithm (PSO) is often used to solve complex optimal scheduling. But in the process of particle swarm optimization, the homogenization of particle swarm is prone to premature homogenization result. In order to solve this problem, this paper proposes the new mechanisms to assign the value to inertia factor adaptively and dynamically with the evolution speed factor and mean fitness variance of population diversity factor to improve the traditional linear method. Then the improved particle swarm optimization algorithm is applied to the actual reservoir optimal scheduling to verify that the algorithm has faster homogenization speed to get the global extreme and overcomes the shortcomings of easily fall into local optimum. This provides a new way for the reservoir optimal scheduling problem.

Keywords:

Adaptability, evolution speed, inertia factor, mean fitness variance of population diversity, particle Swarm optimization algorithm, reservoir optimal scheduling.