WANG Hai-wen, TAN Ai-guo, PENG Sai, WANG Long, TIAN Xiang-peng, LIAO Hong-hua, ZHONG Jian-wei
（College of Intelligent Systems Science and Engineering, Hubei Minzu University, Enshi 445000, China）
Abstract: To address the issue of low accuracy in short-term power load forecasting caused by the nonlinearity, volatility, and inadequate feature extraction of historical load data, a short-term power load forecasting model based on VMD-SGWO multi-model optimization was proposed. Firstly, the variational mode decomposition (VMD) method was employed to decompose the historical load data into five modal components and a residual sequence. Then, the Sine chaotic mapping was used to improve the grey wolf optimizer (GWO), resulting in the sine-enhanced grey wolf optimizer (SGWO). This improved algorithm was applied to optimize the parameters of the light gradient boosting machine (LightGBM), support vector regression (SVR), and extreme gradient boosting (XGBoost) models for different modals. Subsequently,the optimized models were used to predict the different modal components separately. Finally, the prediction results were reconstructed and optimized to obtain the final forecast. Experiments demonstrated that VMD, SGWO, and the multi-model collaborative forecasting approach effectively enhanced the accuracy of short-term power load forecasting. The proposed VMD-based multi-model optimization algorithm was compared with LightGBM, SVR, XGBoost, temporal convolutional network (TCN), gated recurrent unit (GRU), and long short-term memory network (LSTM) in terms of short-term power load forecasting results, showing reductions in root mean square error by 86.25%, 82.68%, 87.29%, 86.30%, 89.78%, and 84.79%, respectively, and the prediction accuracy was significantly improved based on VMDSGWO multi-model optimization.
Key words: short-term power load forecasting; variational mode decomposition; grey wolf optimizer; multi-model optimization
參考文獻
[1] 朱莉，高靖凱，朱春強，等. 基于分量感知動態(tài)圖 Transformer 的短期電力負荷預測[J]. 計算機應用研究，2025，42(2) ：381-390.
[2] 查瓊睿. 基于智能算法的電力短期負荷預測方法[J] .光源與照明，2023(8) ：96-98.
[3] 魏步晗，鮑剛，李振華. 基于支持向量回歸預測模型考慮天氣因素和分時電價因素的短期電力負荷預測[J] .電網與清潔能源，2023，39(11) ：9-19.
[4] 張琳，高勝強，宋煜，等. 基于 ALIF-VMD 二次分解的 NGO-CNN-LSTM 電力負荷短期組合預測模型[J]. 科學技術與工程，2025，25(11) ：4583-4597.
[5] 陳緯楠，胡志堅，岳菁鵬，等. 基于長短期記憶網絡和 LightGBM 組合模型的短期負荷預測[J]. 電力系統(tǒng)自動化，2021，45(4) ：91-97.
[6] 張未，余成波，王士彬，等. 基于 VMD-LSTM-LightGBM 的多特征短期電力負荷預測[J] . 南方電網技術，2023，17(2) ：74-81.
[7] 王海文，譚愛國，彭賽，等. 基于 LGWO-XGBoost-LightGBM-GRU 的短期電力負荷預測算法[J]. 湖北民族大學學報(自然科學版)，2025，43(1) ：73-79.
[8] 肖威，方娜，鄧心. 基于 VMD-LSTM-IPSO-GRU 的電力負荷預測[J] . 科學技術與工程，2024，24(16) ：6734-6741.
[9] 王國彬，黃偉，郭汶昇，等. 基于 CEEMDAN-VMD-BiGRU 模型的印刷園區(qū)電力負荷預測[J]. 印刷與數(shù)字媒體技術研究，2024(4) ：276-287.
[10] FAYYAZBAKHSH A, KIENBERGER T, WRIENZ V J.Comparative Analysis of Load Profile Forecasting: LSTM, SVR, and Ensemble Approaches for Singular and Cumulative Load Categories[J].Smart Cities，2025，8(2) ：65.
[11] ZENG Shuang, LIU Chang, ZHANG Heng, et al.Short-Term Load Forecasting in Power Systems Based on the Prophet-BO-XGBoost Model[J].Energies，2025，18(2) ：227.
[12] LIAN Huihui, JI Ying, NIU Menghan, et al.A hybrid load prediction method of office buildings based on physical simulation database and LightGBM algorithm[J].Applied Energy，2025，377(1) ：124620.
[13] CHOPRA N, KUMAR G, MEHTA S.Multi-Objective Economic Emission Load Dispatch using Grey Wolf Optimization[J].International Journal of Advanced Engineering Research and Science，2016，3(11) ：26-33.
