Study On The Short Term Load Forecasting Based On Artificial Neural Net

Short term load forecasting (STLF) is the precondition of economic and secure operation of power system, and because the power system are getting more and more marketable, STLF with high quality is getting more and more important and exigent. The artificial neural net (ANN) way is universal regard as one of the most effective ways of STLF. In this paper, some research is developed for STLF using ANN ways in several parts:The first part is about the arithmetic of ANN based on BP model, namely the advanced of traditional BP arithmetic, one alterable step and scale BP arithmetic based on comparability of model and probability of accepting BP arithmetic is used to enhances a lot the convergence rate of learning process of BP network, but also avoid the stagnation problem to some extent. It indicates that the ANN'S efficiency and precision by the way can be ameliorated by the simulation of real data.In the second is about the ANN'S structure, one genetic arithmetic (GA) is used to chose the most logical number of connotative layer, so it can void the blindness of chose the number of connotative layer. Because based on more logical net structure , the precision of forecasting is improved.The third part is about the characteristic of load and forecasting model. In this part , the characteristic of load in Zhengzhou is studied as an example, and on the base one forecasting model for normal day based on ANN by analysis the difference of weather situation and one forecasting model for special holiday based on fuzzy logic is bring forward.