NEURAL NETWORKS AND ITS APPLICATIONS TO ELECTRIC LOAD FORECASTING

Abstract

Neural Networks are computational models with the capacity to learn, to generalize, or to organize data based on parallel processing. Among all kinds of networks, the most widely used are Multi-Layer Feed Forward Neural Networks that are capable of representing non-linear functional mappings between inputs and outputs. These are called "Universal Approximators". These networks can be trained with a powerful and computationally efficient method called Error Back-Propagation. Forecasting is one of the important applications of neural networks. In this Dissertation work, Multi-Layer Feed-Forward Neural Networks are designed and modeled using MatLab language to do Short Term Electrical Load Forecasting for a sub-power station of I.I.T Roorkee. It is known that electrical load depends on many factors such as weather, calendar and other informations. The model captures these variables, reflect them within the system and provide valuable future forecasting data. Similar models could be designed to solve problems in other fields also as long as the correct relationship between the inputs and outputs can be captured.