Load Forecasting Using Artificial Neural Network

Abstract

The key role of load forecasting is the power system energy management system. Load forecasting helps to diminish the production cost, spinning reserve capacity and enhance the reliability of the power system. Load forecasting is tremendously essential for financial institutions, power suppliers and other participants in electric energy market i.e. transmission, generation and distribution. The economic allotment of generation is a vital purpose of short term load forecasting. This thesis presents a solution methodology using an artificial neural network for short term load forecasting. The inputs using for forecasting the load, i.e. Dry bulb temperature, Dew point temperature, humidity and load data. The load data is taken from the 66kv substation, Bhai Roopa, Bathinda and weather data from weather stations “IMD” Pune. The data are taken from the year 2015 and 2016. The back propagation algorithm has been implemented to minimize the error function derived on the basis of computed load and actual load. The effectiveness is also checked through its implemented under the MATLAB environment. Where, the Levenberg Marquardt algorithm is used and the performance is investigated under Multilayer Neural Network.