An Analysis of Machine Learning Methods for Electricity Price Forecasting

Short-term electricity price forecasting plays an essential role in shaping the decision-making process of market participants in the electricity industry, as it enables them to make informed decisions about their energy trading activities. In recent years, there has been a growing interest in developing accurate and reliable price forecasting techniques, which can help to reduce the uncertainty associated with electricity price movements. In this study, we present a comparative analysis of various short-term electricity price forecasting techniques based on machine learning methods. The study is based on a comprehensive data set of hourly electricity prices from a major energy market, spanning a period of five years.Various statistical measures such as root mean squared error (RMSE), mean absolute error (MAE), R-squared value are used to evaluate the performance of the different machine learning models for forecasting. The results highlights the accuracy of different machine learning models during training and testing. The Various regression analysis methods were employed to forecast the price of the ISO New England electricity market using MATLAB software.