Abstract:
European countries began liberalizing their electricity markets to increase competition and reduce prices for consumers [1]. In a liberalized electricity market, electricity is treated as a tradable commodity like any other product. Since then, electricity markets have been subject to the same economic principles of supply and demand as other markets, with prices rising when demand outstrips supply and falling when supply exceeds demand. A variety of methods and ideas have been tried for electricity forecasting in generation, demand, and price domains over the last few decades, with varying degrees of success. Over time. Researchers have applied methodologies from time series analysis, ARIMA models to machine learning and deep learning techniques. The evolution of these techniques have improved cost reductions in the industry. The purpose of this review is to illustrate the evolution of employed methodology, the complexity of applied solutions, and the opportunities and challenges that forecasting tools offer or may encounter.
