Short-Term Electricity Price Forecasting and the Impact of Energy Storage on Electricity Price Using GMDH Neural Network and K-Means Algorithm

Articles in Press

Document Type : Original Article

Authors

Department of Power Engineering - Faculty of Electrical and Computer Engineering - University of Birjand - Birjand - Iran

Abstract

With the establishment of a competitive environment in the power industry, along with the smartening of power networks and the advancement of artificial intelligence algorithms, electricity price forecasting over different time horizons has become one of the most critical issues in power system planning and operation. The restructuring of the power industry and the integration of renewable energy sources and energy storage systems have fundamentally transformed electricity pricing mechanisms. In electricity markets, several factors—including energy supply and demand, production, transmission, and distribution costs, as well as governmental policies—play a significant role in determining electricity prices. With the increasing penetration of renewable energy and storage technologies, electricity prices are also increasingly influenced by these elements. In this study, short-term (24-hour) electricity price forecasting is performed using real market data and the Group Method of Data Handling (GMDH) neural network in the presence of renewable energy sources. Furthermore, the k-means clustering technique is employed to evaluate the impact of storage systems on market prices. The results obtained from this research demonstrate the high accuracy of the proposed model in short-term electricity price forecasting.

Keywords

Main Subjects

Tabriz Journal of Electrical Engineering

Articles in Press, Corrected Proof
Available Online from 22 September 2025

Files

Share

How to cite

Statistics