ANN and ANFIS Based Approach for Very Short Term Load Forecasting: A Step Towards Smart Energy Management System

For planning of new electrical plant, it is crucial that load forecasting needs to be done more precisely. It also helps in balancing the load flow in the power distribution network. In a liberated market it is required for the electric utility to think about the market load interest for creating close to accurate power. Momentary electric burden gauge is critical for the security administration and cost control of the electrical industry, and subsequently it is vital to improve the veracity. Basically, for the forecaster, the main motto is to collect historical data and determine the pattern hidden in it. In this paper, focus is on short term load forecasting which is substantial for controlling and operation in real time of the power system. The proposition is the use of artificial intelligence techniques like artificial neural network and adaptive neuro-fuzzy inference system. Both models are studied for the set of data considered and the results are analysed. Also, the results obtained from both the methods is compared to the desired output and the mean absolute percentage error is calculated.