Quantitative combination load forecasting model based on forecasting error optimization. (July 2022)

• Record Type: Journal Article
• Authors: Deng, Song; Chen, Fulin; Wu, Di; He, Yi; Ge, Hui; Ge, Yuan
• Is Part Of: Computers & electrical engineering. Volume 101(2022)
• Publication Date: 2022-07
• Subjects: Gene expression programming -- Data noise reduction -- Load forecasting error -- Combination load forecasting; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108125
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Accurate load forecasting is indispensable in various applications of the electric power industry. Although existing load forecasting methods perform well, they cannot handle complicated scenarios where load-related data are highly random and uncertain. To deal with this issue, A Q uantitative C ombination L oad F orecasting model(QCLF) is proposed. Its main idea is to incorporate the load forecasting errors into the forecasting process as an optimization problem, which can significantly reduce the adverse impacts of random and uncertain load-related data. First, we propose an improved K -Means and L east S quare-based L oad F orecasting E rror M odel(LFEM-KLS) to improve the availability and effectiveness of load-related data. Second, we employ gene expression programming (GEP) to optimize the proposed LFEM-KLS to achieve highly accurate load forecasting. Experimental results on three load datasets demonstrate that a QCLF model significantly outperforms other related load forecasting models. Highlights: It proposes an improve K-Means and least square-based load forecasting error model. It proposes a QCLF model based on GEP and LFEM-KLS. It provides the algorithm design and analysis for our proposed model.