KMS Chongqing Institute of Green and Intelligent Technology, CAS
Quantitative combination load forecasting model based on forecasting error optimization | |
Deng, Song1; Chen, Fulin2; Wu, Di3; He, Yi4; Ge, Hui5; Ge, Yuan6 | |
2022-07-01 | |
摘要 | 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 Quantitative Combination Load Forecasting 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 Least Square-based Load Forecasting Error Model(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. |
关键词 | Gene expression programming Data noise reduction Load forecasting error Combination load forecasting |
DOI | 10.1016/j.compeleceng.2022.108125 |
发表期刊 | COMPUTERS & ELECTRICAL ENGINEERING |
ISSN | 0045-7906 |
卷号 | 101页码:11 |
通讯作者 | Wu, Di(wudi@cigit.ac.cn) |
收录类别 | SCI |
WOS记录号 | WOS:000812902600008 |
语种 | 英语 |