Research on Neural Networks Based on Culture Particle Swarm Optimization and Its Application in Power Load Forecasting

The neural network has been applied to the area of power load forecast successfully, but it has such disadvantages of local optimization and slow convergence speed. A new kind of neural networks forecast model based on culture particle swarm optimization was proposed for overcoming those disadvantages. Utilizing the colony aptitude of particle swarm and the ability of conserving the evolving knowledge of the culture algorithm, the new algorithm (called culture particle swarm optimization) constructed the population space based on particle swarm and the knowledge space. The two spaces evolved independently, at the same time, the population space continuously transferred the evolving knowledge to the knowledge space, and then the knowledge space used that knowledge to direct the population space to achieve global optimization. This algorithm can solve the above disadvantages of normal neural networks and the premature problem of particle swarm optimization. The application in power load forecasting showed that this neural network based on culture particle swarm optimization achieved better forecast result.