Attention Short-Term Forecasting Method of Distribution Load Based on Multi-Dimensional Clustering

被引：0
|
作者：
Zhong G. [1 ]
Tai N. [1 ]
Huang W. [1 ]
Li R. [1 ]
Fu X. [2 ]
Ji K. [2 ]
机构：
[1] School of Electrical Engineering, Shanghai Jiao Tong University, Shanghai
[2] State Grid Shanghai Municipal Electric Power Company, Shanghai
来源：
Tai, Nengling (nltai@sjtu.edu.cn) | 1600年 / Shanghai Jiaotong University卷 / 55期
关键词：
Daily load sequence; Load clustering; Long short-term memory network; Short-term load forecasting; Similar time-series;
D O I：
10.16183/j.cnki.jsjtu.2021.263
中图分类号：
O212 [数理统计];
学科分类号：
摘要：
Due to the difference in load characteristics and influencing factors in large-scale distribution transformer load forecasting, if all the distribution transformers share a unified model, the prediction accuracy is low, and if the model is built for each distribution transformer, the computational resources will be excessively consumed. An Attention-LSTM short-term forecasting method of distribution load based on multi-dimensional clustering is proposed. The non-parametric kernel method is used to perform probability fitting on the daily load characteristics to form a typical daily load sequence. Improved two-level clustering is applied for load clustering, taking the Euclidean warping distance and influence factors as the similarity evaluation criteria. AP clustering is utilized for obtaining similar time-series, and training sets are formed to train the Attention-LSTM model. Different Attention-LSTM models are obtained by training for different distribution load types and time-series. The effectiveness and practicability of the method proposed are verified by the load data and meteorological data of a municipal distribution network. The accuracy rate is increased by 2.75% and the efficiency is increased by 616.8%. © 2021, Shanghai Jiao Tong University Press. All right reserved.
引用
收藏
页码：1532 / 1543
页数：11
相关论文
共 27 条
  • [1] TAN Xiandong, LIU Jun, XU Zhicheng, Et al., Power supply and demand balance during the 14th five-year plan period under the goal of carbon emission peak and carbon neutrality, Electric Power, 54, 5, pp. 1-6, (2021)
  • [2] XIA C H, ZHANG M, CAO J., A hybrid application of soft computing methods with wavelet SVM and neural network to electric power load forecasting, Journal of Electrical Systems and Information Technology, 5, 3, pp. 681-696, (2018)
  • [3] LI Y Y, HAN D, YAN Z., Long-term system load forecasting based on data-driven linear clustering method, Journal of Modern Power Systems and Clean Energy, 6, 2, pp. 306-316, (2018)
  • [4] KANG Chongqing, Power system load forecast, (2017)
  • [5] CUI Herui, PENG Xu, Summer short-term load forecasting based on ARIMAX model, Power System Protection and Control, 43, 4, pp. 108-114, (2015)
  • [6] XIE Kai, WANG Feng, YU Erken, Et al., Very short-term load forecasting by Kalman filter algorithm, Chinese Society for Electrical Engineering, 16, 4, pp. 245-249, (1996)
  • [7] LU Yi, WANG Minkun, An ultra-short term load forecasting method based on short-term load forecasting, Automation of Electric Power Systems, 30, 16, pp. 102-104, (2006)
  • [8] MA Wenxiao, BAI Xiaomin, MU Lianshun, Short term load forecasting using artificial neuron network and fuzzy inference, Power System Technology, 27, 5, pp. 29-32, (2003)
  • [9] GENG Yan, HAN Xueshan, HAN Li, Short-term load forecasting based on least squares support vector machines, Power System Technology, 32, 18, pp. 72-76, (2008)
  • [10] XU Junhua, LIU Tianqi, An approach to short-term load forecasting based on wavelet transform and aritficial neural network, Power System Technology, 28, 8, pp. 30-33, (2004)
123