Short Term Load Forecasting Using Probabilistic Neural Network Based Algorithm

This paper discusses the half an hour ahead electric load forecasting, using a Neural network algorithm having a mathematical, statistical background. Due to restructuring, of the electricity markets, forecasting the system demand, has become even more important, in order to make an appropriate market decision. A number of Short Term Load Forecasting tools have been recently developed using nonlinear modeling methods, including those based on the Neural Network modeling framework. And if the underlying mechanism of the electric load data generating process is to be included into the analysis, a statistical approach may be the best. It is seen that certain Artificial Neural Networks, especially a class of Radial Basis Function Networks (RBFN), can provide some statistical approaches. PNN is a statistical algorithm, by organizing the flow of operations into layers, and assigning some primitive operations to individual neurons in each layer, the algorithm can resemble a four layer feed forward network with exponential activation functions.