Research On Heat Burden Prediction And Control Of Substation Based On PSO Algorithm

Prediction of heat burden has emerged as the base of control and adjustment in heat supply system. Prediction of heat burden level is an important research topic in energy economization and environment protection today.For fulfilling such prediction, the use of BP neural network (NN) is applied to predict the heat burden of a heat substation in Qinhuangdao City, based on deep analysis of heat supplying characteristic. But their training ,usually with back-propagation(BP) algorithm or other gradient algorithms, is often with certain drawbacks, such as:1) very slow convergence, and 2) easily stuck in a local minimum. In this paper, a newly developed method, particle swarm optimization (PSO) model, is adopted to train perceptrons, and as a result, a PSO-based neural network approach is presented. For improving the predicting results, two improved PSO algorithm are presented also in this paper: Velocity Mutation PSO and hybrid PSO. Both the two approaches are demonstrated to be feasible and effective by predicting heat burden and the identification of the heat exchanger system in substation. At last, based on a dynamic transfer function of the heat exchanger through step-response experiment, the step-response control simulations of both the PID controller and NN predict controller are presented.