基于RWT-SVM的台区配电网日前负荷预测研究
作者:
中图分类号:

TM743

基金项目:

国家电网公司科技项目(524608210006)


Day-ahead load forecasting of distributed power grids based on RWT-SVM
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    日前负荷预测对于制定合理的调度计划,保证电力系统安全可靠具有重要意义.电力负荷时间序列通常存在随机误差,而基于智能算法的预测模型为了充分提取负荷信息,结构复杂、计算量大.为此,本文利用台区配电网的历史电力负荷时间序列,提出一种基于重复小波变换-支持向量机(RWT-SVM)混合模型的日前电力负荷预测方法.该方法利用小波变换技术将台区配电网电力负荷时间序列分解为多个子序列;利用平均绝对误差(MAE)计算每个子序列的预报误差贡献度;对MAE最大的序列进一步分解,从而提升模型的预测能力,得到精度更高的预测结果.仿真结果表明,RWT-SVM混合模型的预测精度高于三种对比方法.

    Abstract:

    Day-ahead load forecasting is an important task for the power dispatching center to formulate reasonable dispatching plans thus to ensure the safety and reliability of power system operation.However, random errors exist in time series of power loads, and the intelligent algorithm based prediction models are complex in structure and incapable of fully extracting load information enough for load calculation and load forecasting.Here, we propose a day-ahead power load forecasting approach based on Repeated Wavelet Transform-Support Vector Machine (RWT-SVM) by using the historical power load time series of distributed power grids.The approach uses wavelet transform to decompose the power load time series of distributed power grids into multiple subsequences, then applies the Mean Absolute Error (MAE) to calculate the prediction errors contributed by each subsequence, and further decomposes the sequence with the largest MAE to improve the prediction ability of the model.The simulation results show that the proposed RWT-SVM approach outperforms other methods in forecasting accuracy.

    参考文献
    [1] 廖剑波, 陈清鹤, 监浩军, 等.主动配电网的日前-日内两阶段优化调度[J].现代电力, 2020, 37(1):27-34 LIAO Jianbo, CHEN Qinghe, JIAN Haojun, et al.Day-ahead and intraday two-stage optimal dispatch of active distribution network[J].Modern Electric Power, 2020, 37(1):27-34
    [2] 吴迪, 王正风.基于逐日分段气象算法的日前负荷预测[J].电气应用, 2020, 39(6):61-67 WU Di, WANG Zhengfeng.Day-ahead whether sensitive power load forecasting based on daily segmentation meteorological algorithm[J].Electrotechnical Application, 2020, 39(6):61-67
    [3] 李杰.面向售电商的电力负荷日前预测模型研究[D].北京:华北电力大学, 2019 LI Jie.Research on day-ahead load forecasting model for electricity sellers[D].Beijing:North China Electric Power University, 2019
    [4] 陈莹, 黄永彪, 谢瑾.人工智能辅助下人机交互隔空手势识别模型[J].计算机仿真, 2021, 38(3):360-364 CHEN Ying, HUANG Yongbiao, XIE Jin.Human-computer interaction gesture recognition model based on artificial intelligence[J].Computer Simulation, 2021, 38(3):360-364
    [5] 祝毅鸣.面向图像角点特征取证的人工智能检测仿真[J].计算机仿真, 2021, 38(1):486-490 ZHU Yiming.Artificial intelligence detection simulation for image corner feature forensics[J].Computer Simulation, 2021, 38(1):486-490
    [6] 吴香华, 华亚婕, 官元红, 等.基于CNN-Attention-BP的降水发生预测研究[J].南京信息工程大学学报(自然科学版), 2022, 14(2):148-155 WU Xianghua, HUA Yajie, GUAN Yuanhong, et al.Application of CNN-Attention-BP to precipitation forecast[J].Journal of Nanjing University of Information Science & Technology (Natural Science Edition), 2022, 14(2):148-155
    [7] 郭佳丽, 邢双云, 栾昊, 等.基于改进的LSTM算法的时间序列流量预测[J].南京信息工程大学学报(自然科学版), 2021, 13(5):571-575 GUO Jiali, XING Shuangyun, LUAN Hao, et al.Prediction of time series traffic based on improved LSTM algorithm[J].Journal of Nanjing University of Information Science & Technology (Natural Science Edition), 2021, 13(5):571-575
    [8] 张诤杰.基于门循环单元神经网络的微电网日前电力负荷预测[D].徐州:中国矿业大学, 2020 ZHANG Zhengjie.Day-ahead load forecasting of microgrid based on GRU network[D].Xuzhou:China University of Mining and Technology, 2020
    [9] 王玥, 张宇帆, 李昭昱, 等.即插即用能量组织日前负荷概率预测方法[J].电网技术, 2019, 43(9):3055-3060 WANG Yue, ZHANG Yufan, LI Zhaoyu, et al.Day-ahead probability load forecasting of energy tissues with plug-and-play function[J].Power System Technology, 2019, 43(9):3055-3060
    [10] 孙晓燕, 李家钊, 曾博, 等.基于特征迁移学习的综合能源系统小样本日前电力负荷预测[J].控制理论与应用, 2021, 38(1):63-72 SUN Xiaoyan, LI Jiazhao, ZENG Bo, et al.Small-sample day-ahead power load forecasting of integrated energy system based on feature transfer learning[J].Control Theory & Applications, 2021, 38(1):63-72
    [11] 李正浩.基于NACEMD-GRU的组合型日前负荷预测方法[J].电网与清洁能源, 2021, 37(6):43-50 LI Zhenghao.A combined method of day-ahead load forecasting based on NACEMD-GRU[J].Advances of Power System & Hydroelectric Engineering, 2021, 37(6):43-50
    [12] 尚帅, 韩立国, 周晨光, 等.基于时频能量重排的改进小波变换谱分解[J].地球物理学进展, 2015, 30(5):2206-2211 SHANG Shuai, HAN Liguo, ZHOU Chenguang, et al.Improved wavelet spectral decomposition using energy reassignment in time-frequency map[J].Progress in Geophysics, 2015, 30(5):2206-2211
    [13] 张玩乐, 王小虎, 张志健.基于小波变换与奇异值分解的航空器弹性自适应陷波方法[J].航天控制, 2018, 36(4):59-64, 71 ZHANG Wanle, WANG Xiaohu, ZHANG Zhijian.AWT & SVD based adaptive Notch filter for aircraft elastic constraint[J].Aerospace Control, 2018, 36(4):59-64, 71
    [14] 肖勇, 李博, 尹家悦, 等.基于小波变换和小波包变换的间谐波检测[J].智慧电力, 2022, 50(1):101-107, 114 XIAO Yong, LI Bo, YIN Jiayue, et al.Interharmonic detection based on wavelet transform and wavelet packet transform[J].Smart Power, 2022, 50(1):101-107, 114
    [15] 隋新, 何建敏, 李亮.时变视角下基于MODWT的沪深300指数现货与期货市场间波动溢出效应[J].系统工程, 2015, 33(1):31-38 SUI Xin, HE Jianmin, LI Liang.The volatility spillover effects between HS300 stock index future and spot market based on MODWT from a time-varying perspective[J].Systems Engineering, 2015, 33(1):31-38
    [16] Emhamed A A, Shrivastava J.Electrical load distribution forecasting utilizing support vector model (SVM)[J].Materials Today:Proceedings, 2021, 47:41-46
    [17] Brauns K, Scholz C, Schultz A, et al.Vertical power flow forecast with LSTMs using regular training update strategies[J].Energy and AI, 2022, 8:100143
    相似文献
    引证文献
引用本文

丁宏,陶晓峰,陆春艳,张士成.基于RWT-SVM的台区配电网日前负荷预测研究[J].南京信息工程大学学报(自然科学版),2023,15(3):330-336
DING Hong, TAO Xiaofeng, LU Chunyan, ZHANG Shicheng. Day-ahead load forecasting of distributed power grids based on RWT-SVM[J]. Journal of Nanjing University of Information Science & Technology, 2023,15(3):330-336

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-05-31
  • 在线发布日期: 2023-06-28

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司