A Comparision Study of Machine Learning Methods for Unit Price Estimation in Smartgrid

Abstract

Electricity price volatility directly affects the deregulated electricity market where each market player is trying to sell their power with minimum cost. Hence effective price forecasting plays an important role for stability of electricity market and effective management of the interconnected power system network. The uncertainty in load demand and the distributed energy resources also directly affects the electricity price and the operational cost. The serious consequences of price dynamics can be avoided by designing more effective and accurate price forecasting models. This study compares three different intelligent techniques for unit price forecasting using machine learning. The three different artificial intelligent techniques are Support vector machine (SVM), Random forest and decision trees. As per the results obtained from the three models, all three models are effective for electricity price forecasting, but SVM model gives better performance than other two in terms of root mean square error.