A Machine Learning-Based Algorithm for Short-Term SMP Forecasting Using 2-Step Method

• Published in: Journal of electrical engineering & technology Vol. 18; no. 3; pp. 1493 - 1501
• Main Authors: Shim, Sang Woo, Lee, Da Han, Roh, Jae Hyung, Park, Jong-Bae
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.05.2023; Springer Nature B.V; 대한전기학회
• Subjects: Electrical Engineering; Electrical Machines and Networks; Electronics and Microelectronics; Engineering; Instrumentation; Original Article; Power Electronics; 전기공학; System marginal price; Shapley value; 2-Step method; Ensemble
• ISSN: 1975-0102; 2093-7423
• DOI: 10.1007/s42835-023-01473-4

System marginal price (SMP) forecasting is essential for power generation companies or virtual transaction operators participating in the electricity market. In forecasting SMP, the load data is one of the most important pieces of information. Therefore, this paper presents a 2-Step method for SMP forecasting after load forecasting. This paper performed feature selection using Shapley additional explanations and Pearson correlation coefficient and adjusted the hyperparameters of the forecasting model by Grid search. Through this, the total load and SMP in 2021 were forecasted, and the forecasting results were presented through MAPE (mean absolute percentage error), nMAE (normalized mean absolute error), and nRMSE (normalized root mean square error). This paper used XGBoost for load forecasting and XGBoost, random forest, light gradient boosting machine, and linear regression for SMP forecasting. As a result of forecasting SMP, in the average of 2021, LGBM and RF ensemble models showed the best performance with 3.33% in MAPE. In addition, when the forecasting results were shown by dividing it into 4 seasons, the ensemble model of LGBM and random forest showed the best performance in MAPE except for spring.