Chaos quantum-behaved particle swarm optimization based neural networks for short-term load forecasting

To tackle with the premature matter of particles when seeking optimization in local small space in terms of quantum-behaved particle swarm optimization(QPSO), chaos optimization strategy was combined to QPSO algorithm, and defined as chaos quantum-behaved particle swarm optimization(CQPSO) algorithm. The algorithm firstly applied QPSO algorithm to implement evolution operation till QPSO algorithm was in premature state, then chaos seeking mechanism was started to induct the particles to quickly jump out the local optimization, and thus, the convergence speed of QPSO was quicken. In this paper, CQPSO was applied to optimal the weight values of BP neural network, and the optimized well neural network was applied to implement short-term load forecasting(STLF). Eventually, simulation results show that the algorithm possesses high forecasting accuracy, and is an ideal optimal algorithm.