基于时空注意力机制的台区多用户短期负荷预测

doi:10.19595/j.cnki.1000-6753.tces.230110

Abstract
Figure/Table
References (0)
Related Citation (5)

Download: PDF (1187 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract

With a large number of customer-side distributed power sources entering the network from low-voltage distribution stations and the widespread use of devices such as smart meters on the customer side, a load forecasting model for multiple users is needed to facilitate point forecasting and probabilistic tasks for a large number of users efficiently and accurately. Traditional methods of customer load forecasting model the temporal characteristics of individual customers and are unable to learn the problems of spatial correlation between customers and the inability to achieve forecasts for multiple customers. Customers in the same region share the same geographic space, weather conditions, holiday information, tariff policies, and other comprehensive factors, and there is often a certain amount of spatial and temporal correlation between customers' electricity consumption behavior. If this spatial-temporal correlation can be fully explored, it will have extremely positive implications for modeling short-term customer loads. A small body of literature has already explored the initial exploration of customer load forecasting, taking spatial-temporal correlation into account. However, the existing spatio-temporal methods can only provide deterministic forecasts, not probabilistic ones. To address these issues, this paper proposes a multi-customer short-term load forecasting model for station areas. Learning spatial-temporal correlation information from historical load data can perform accurate multi-user short-term load point forecasts and probabilistic forecasts for station areas.
Firstly, three modules are embedded for each encoder and decoder by improving the standard Transformer self-attention mechanism: sequence decomposition module, autocorrelation calculation module, and spatial attention module to effectively extract the dynamic spatio-temporal dependencies among highly volatile residential users. Among them, the sequence decomposition module can decompose highly volatile subscriber load curves into relatively smooth multiple sub-series, which helps to extract better the time dependence and period factor of load curves; the autocorrelation calculation is an improved attention mechanism that can mine the time dependence of multiple historical contemporaneous sub-series; and the spatial attention mechanism can extract the dynamic spatial support among multiple users in a station area. The STformer model is then extended to the field of probabilistic forecasting using a Monte Carlo stochastic deactivation method (MC dropout). This method does not require additional modifications to STformer but allows STformer to output both point prediction and probabilistic prediction results. Finally, the STformer model with MC dropout is used to forecast the station customer load, and both point and probabilistic forecasts are output.
In this paper, the model's validity is verified using one-hour-ahead load forecasting and day-ahead load forecasting using accurate station customer load data from a province in the southeast. The proposed STformer model has a MAPE of 4.44% for each user and 2.21% for the total load in station area A. The probabilistic forecast evaluation index pinball is 0.3701; the average relative error MPE for each user and 3.25% for the total load in station area A is 6.21%. is 3.25%, and the probabilistic forecast assessment index pinball is 0.5942. This paper also compares the effects of different modules on the experimental results through ablation experiments. This paper also verifies the change in model inference speed brought about by the addition of FFT, comparing the running memory and time of the autocorrelation-based model with that of the self-attentive-based model during the training phase.
The following conclusions can be drawn from the simulation analysis: (1) Compared with other baselines, the STformer model proposed in this paper extracts the temporal variation pattern of users through the temporal attention mechanism and the spatial dependency between multiple users through the spatial attention mechanism, which ultimately achieves the best prediction results in all scenarios. (2) Each module of STformer contributes to the improvement of prediction accuracy and model robustness. The spatial attention module has the greatest impact on the prediction accuracy of STformer, and the Fourier transform method of the autocorrelated model reduces the computational complexity and thus accelerates the computational speed of the model. (3) The prediction intervals of the proposed STformer model with MC dropout have reliable coverage of the true values and provide narrower prediction intervals, especially at some peaks and troughs, which are critical for the temperature operation of power systems.

Key words： Multi-customers load forecasting spatial-temporal correlation Transformer

Received: 01 February 2023

PACS:

TM743

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Zhao Hongshan
	Wu Yuchen
	Wen Kaiyun
	Sun Chengyan
	Xueyang

Cite this article:

Zhao Hongshan,Wu Yuchen,Wen Kaiyun等. Short-Term Load Forecasting for Multiple Customers in a Station Area based on Spatial-Temporal Attention Mechanism[J]. Transactions of China Electrotechnical Society, 0, (): 239605-239605.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.230110 OR https://dgjsxb.ces-transaction.com/EN/Y0/V/I/239605

[1] 张勇军, 羿应棋, 李立浧, 等. 双碳目标驱动的新型低压配电系统技术展望[J]. 电力系统自动化, 2022, 46(22): 1-12.
Zhang Yongjun, Yi Yingqi, Li Licheng, et al.Prospect of new low-voltage distribution system technology driven by carbon emission peak and carbon neutrality targets[J]. Automation of Electric Power Systems, 2022, 46(22): 1-12.
[2] van der Meer D W, Munkhammar J, Widén J. Probabilistic forecasting of solar power, electricity consumption and net load: investigating the effect of seasons, aggregation and penetration on prediction intervals[J]. Solar Energy, 2018, 171: 397-413.
[3] 康重庆, 夏清, 张伯明. 电力系统负荷预测研究综述与发展方向的探讨[J]. 电力系统自动化, 2004, 28(17): 1-11.
Kang Chongqing, Xia Qing, Zhang Boming.Review of power system load forecasting and its development[J]. Automation of Electric Power Systems, 2004, 28(17): 1-11.
[4] Wang Yi, Chen Qixin, Hong Tao, et al.Review of smart meter data analytics: applications, methodologies, and challenges[J]. IEEE Transactions on Smart Grid, 2019, 10(3): 3125-3148.
[5] Fekri M N, Grolinger K, Mir S.Distributed load forecasting using smart meter data: Federated learning with Recurrent Neural Networks[J]. International Journal of Electrical Power & Energy Systems, 2022, 137: 107669.
[6] 朱天怡, 艾芊, 贺兴, 等. 基于数据驱动的用电行为分析方法及应用综述[J]. 电网技术, 2020, 44(9): 3497-3507.
Zhu Tianyi, Ai Qian, He Xing, et al.An overview of data-driven electricity consumption behavior analysis method and application[J]. Power System Technology, 2020, 44(9): 3497-3507.
[7] 陈锦鹏, 胡志坚, 陈纬楠, 等. 二次模态分解组合DBiLSTM-MLR的综合能源系统负荷预测[J]. 电力系统自动化, 2021, 45(13): 85-94.
Chen Jinpeng, Hu Zhijian, Chen Weinan, et al.Load prediction of integrated energy system based on combination of quadratic modal decomposition and deep bidirectional long short-term memory and multiple linear regression[J]. Automation of Electric Power Systems, 2021, 45(13): 85-94.
[8] 赵登福, 庞文晨, 张讲社, 等. 基于贝叶斯理论和在线学习支持向量机的短期负荷预测[J]. 中国电机工程学报, 2005, 25(13): 8-13.
Zhao Dengfu, Pang Wenchen, Zhang Jiangshe, et al.Based on Bayesian theory and online learning SVM for short term load forecasting[J]. Proceedings of the CSEE, 2005, 25(13): 8-13.
[9] Lee J, Cho Y.National-scale electricity peak load forecasting: traditional, machine learning, or hybrid model?[J]. Energy, 2022, 239: 122366.
[10] 高亚静, 孙永健, 杨文海, 等. 基于新型人体舒适度的气象敏感负荷短期预测研究[J]. 中国电机工程学报, 2017, 37(7): 1946-1955.
Gao Yajing, Sun Yongjian, Yang Wenhai, et al.Weather-sensitive load’s short-term forecasting research based on new human body amenity indicator[J]. Proceedings of the CSEE, 2017, 37(7): 1946-1955.
[11] 吴潇雨, 和敬涵, 张沛, 等. 基于灰色投影改进随机森林算法的电力系统短期负荷预测[J]. 电力系统自动化, 2015, 39(12): 50-55.
Wu Xiaoyu, He Jinghan, Zhang Pei, et al.Power system short-term load forecasting based on improved random forest with grey relation projection[J]. Automation of Electric Power Systems, 2015, 39(12): 50-55.
[12] 王琛, 王颖, 郑涛, 等. 基于ResNet-LSTM网络和注意力机制的综合能源系统多元负荷预测[J]. 电工技术学报, 2022, 37(7): 1789-1799.
Wang Chen, Wang Ying, Zheng Tao, et al.Multi-energy load forecasting in integrated energy system based on ResNet-LSTM network and attention mechanism[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1789-1799.
[13] Tang Xianlun, Dai Yuyan, Wang Ting, et al.Short-term power load forecasting based on multi-layer bidirectional recurrent neural network[J]. IET Generation, Transmission & Distribution, 2019, 13(17): 3847-3854.
[14] 王增平, 赵兵, 纪维佳, 等. 基于GRU-NN模型的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(5): 53-58.
Wang Zengping, Zhao Bing, Ji Weijia, et al.Short-term load forecasting method based on GRU-NN model[J]. Automation of Electric Power Systems, 2019, 43(5): 53-58.
[15] Ahmad Khan Z, Ullah A, Ul Haq I, et al.Efficient short-term electricity load forecasting for effective energy management[J]. Sustainable Energy Technologies and Assessments, 2022, 53: 102337.
[16] 赵洋, 王瀚墨, 康丽, 等. 基于时间卷积网络的短期电力负荷预测[J]. 电工技术学报, 2022, 37(5): 1242-1251.
Zhao Yang, Wang Hanmo, Kang Li, et al.Temporal convolution network-based short-term electrical load forecasting[J]. Transactions of China Electrotechnical Society, 2022, 37(5): 1242-1251.
[17] Jalali S M J, Ahmadian S, Khosravi A, et al. A novel evolutionary-based deep convolutional neural network model for intelligent load forecasting[J]. IEEE Transactions on Industrial Informatics, 2021, 17(12): 8243-8253.
[18] Yu Yang, Fan Jinfu, Wang Zhongjie, et al.A dynamic ensemble method for residential short-term load forecasting[J]. Alexandria Engineering Journal, 2023, 63: 75-88.
[19] Sajjad M, Ahmad Khan Z, Ullah A, et al.A novel CNN-GRU-based hybrid approach for short-term residential load forecasting[J]. IEEE Access, 2020, 8: 143759-143768.
[20] Forootani A, Rastegar M, Sami A.Short-term individual residential load forecasting using an enhanced machine learning-based approach based on a feature engineering framework: a comparative study with deep learning methods[J]. Electric Power Systems Research, 2022, 210: 108119.
[21] Jiang Lianjie, Wang Xinli, Li Wei, et al.Hybrid multitask multi-information fusion deep learning for household short-term load forecasting[J]. IEEE Transactions on Smart Grid, 2021, 12(6): 5362-5372.
[22] 董雷, 陈振平, 韩富佳, 等. 基于图卷积神经网络与K-means聚类的居民用户集群短期负荷预测[J/OL]. 电网技术, 2022: 1-11[2023-04-01]. https://kns.cnki.net/kcms/detail/11.2410.TM.20221013.1648.003.html.
Dong Lei, Chen Zhenping, Han Fujia, et al. Short-term load forecasting of residential user groups based on graph convolutional neural network and K-means clustering[J/OL]. Power System Technology, 2022: 1-11[2023-04-01]. https://kns.cnki.net/kcms/detail/11.2410.TM.20221013.1648.003.html.
[23] 张鹏飞, 胡博, 何金松, 等. 基于时空图卷积网络的短期空间负荷预测方法[J]. 电力系统自动化, 2023, 47(13): 78-85.
Zhang Pengfei, Hu Bo, He Jinsong, et al.Short-term spatial load forecasting method based on spatio-temporal graph convolutional network[J]. Automation of Electric Power Systems, 2023, 47(13): 78-85.
[24] Vaswani A, Shazeer N, Parmar N, et al.Attention is all you need[C]//NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA, 2017: 6000-6010.
[25] Woo S, Park J, Lee J Y, et al.CBAM: convolutional block attention module[C]//Proceedings Part Ⅶ of Computer Vision-ECCV 2018, Munich, Germany, 2018: 3-19.
[26] Zhu Lingxue, Laptev N.Deep and confident prediction for time series at Uber[C]//2017 IEEE International Conference on Data Mining Workshops (ICDMW), New Orleans, LA, USA, 2017: 103-110.
[27] Gal Y, Ghahramani Z.Dropout as a Bayesian approximation: representing model uncertainty in deep learning[C]//ICML'16: Proceedings of the 33rd International Conference on International Conference on Machine Learning, New York, NY, USA, 2016:1050-1059
[28] Zhu Lingxue, Laptev N.Deep and confident prediction for time series at uber[C]//2017 IEEE International Conference on Data Mining Workshops (ICDMW), New Orleans, LA, USA, 2017: 103-110.
[29] Zhang Wenjie, Quan Hao, Srinivasan D.An improved quantile regression neural network for probabilistic load forecasting[J]. IEEE Transactions on Smart Grid, 2019, 10(4): 4425-4434.
[30] Wen Honglin, Ma Jinghuan, Gu Jie, et al.Sparse variational Gaussian process based day-ahead probabilistic wind power forecasting[J]. IEEE Transactions on Sustainable Energy, 2022, 13(2): 957-970.
[31] 储晨阳, 秦川, 鞠平, 等. 基于优化稀疏编码的超短期负荷滚动多步预测[J]. 电工技术学报, 2021, 36(19): 4050-4059.
Chu Chenyang, Qin Chuan, Ju Ping, et al.Multi-step rolling ultra-short-term load forecasting based on the optimized sparse coding[J]. Transactions of China Electrotechnical Society, 2021, 36(19): 4050-4059.