基于多头概率稀疏自注意力模型的综合能源系统多元负荷短期预测

doi:10.12204/j.issn.1000-7229.2024.02.011

摘要/Abstract

摘要：

精准的多元负荷短期预测是综合能源系统调度和运行的基础。综合能源系统中的多种负荷之间存在较强的耦合作用,目前已有的单一负荷预测难以挖掘不同负荷之间复杂的内在联系。对此,提出一种基于多头概率稀疏自注意力模型的多元负荷短期预测方法。首先,采用皮尔逊相关系数分析多元负荷之间的相关性,并提取多元负荷之间的耦合特征;然后,使用改进位置编码的多头概率稀疏自注意力机制学习长序列输入的依赖关系,并且采用多元预测任务的参数软共享机制,通过不同子任务对共享特征的差异化选择,实现多元负荷的联合预测;最后,在亚利桑那州立大学Tempe校区的多元负荷数据集上对所提模型的性能进行验证,结果表明所提预测方法相较于其他预测模型能够有效提高预测精度。

关键词: 综合能源系统, 多元负荷预测, 多头概率稀疏自注意力模型, 位置编码

Abstract:

Accurate short-term forecasting of multienergy loads is the basis for the dispatch and operation of integrated energy systems. There is a strong coupling between multiple loads in an integrated energy system, and the existing single load forecasting is challenging to explore the complex internal relationship between multiple loads. Therefore, a short-term forecasting method for multienergy loads based on a multihead probabilistic sparse self-attention (MPSS) model was proposed. First, the Pearson correlation coefficient was used to analyze the correlation between multiple loads, the coupling features between multiple loads were extracted, a multihead probabilistic sparse self-attention mechanism with improved location coding was used to learn the dependencies of long-sequence inputs, and the parameter soft sharing mechanism of multivariate prediction tasks was adopted. The sharing mechanism realizes the joint prediction of multiple loads through a differentiated selection of shared features using different subtasks. Finally, the performance of the proposed model was verified using the multiple-load dataset of the Tempe Campus of Arizona State University. Compared with other forecasting models, the results show that the proposed multivariate load forecasting method can effectively improve forecasting accuracy.

Key words: integrated energy system, multienergy load forecasting, multihead probabilistic sparse self-attention model, location coding

中图分类号:

TM714

韩宝慧, 陆玲霞, 包哲静, 于淼. 基于多头概率稀疏自注意力模型的综合能源系统多元负荷短期预测[J]. 电力建设, 2024, 45(2): 127-136.

HAN Baohui, LU Lingxia, BAO Zhejing, YU Miao. Short-term Forecasting of Multienergy Loads of Integrated Energy System Based on Multihead Probabilistic Sparse Self-attention Model[J]. ELECTRIC POWER CONSTRUCTION, 2024, 45(2): 127-136.

图/表 10

图1 多元负荷的皮尔逊相关系数

Fig.1 Pearson correlation coefficient of multi-energy load

图2 多元负荷预测网络框图

Fig.2 Diagram of multi-energy loads forecasting model

表1 模型超参数

Table 1 The model hyper-parameter

表2 对比模型的超参数

Table 2 Hyper-parameters of the comparison models

表3 各模型预测精度对比

Table 3 Comparison of prediction accuracy of each model

图3 电负荷预测结果

Fig.3 Electricity load forecasting results

图4 冷负荷预测结果

Fig.4 Cold load forecasting results

图5 热负荷预测结果

Fig.5 Heat load forecasting results

表4 单一负荷输入与多元负荷输入的预测精度对比

Table 4 Comparison of prediction accuracy between single load input and multiple load input

表5 有无辅助信息的预测精度对比

Table 5 Comparison of prediction accuracy with and without auxiliary information

参考文献 30

[1]	曾鸣, 刘英新, 周鹏程, 等. 综合能源系统建模及效益评价体系综述与展望[J]. 电网技术, 2018, 42(6): 1697-1708.
	ZENG Ming, LIU Yingxin, ZHOU Pengcheng, et al. Review and prospects of integrated energy system modeling and benefit evaluation[J]. Power System Technology, 2018, 42(6): 1697-1708.
[2]	艾芊, 郝然. 多能互补、集成优化能源系统关键技术及挑战[J]. 电力系统自动化, 2018, 42(4): 2-10, 46.
	AI Qian, HAO Ran. Key technologies and challenges for multi-energy complementarity and optimization of integrated energy system[J]. Automation of Electric Power Systems, 2018, 42(4): 2-10, 46.
[3]	别朝红, 王旭, 胡源. 能源互联网规划研究综述及展望[J]. 中国电机工程学报, 2017, 37(22): 6445-6462, 6757.
	BIE Zhaohong, WANG Xu, HU Yuan. Review and prospect of planning of energy internet[J]. Proceedings of the CSEE, 2017, 37(22): 6445-6462, 6757.
[4]	HAQ M R, NI Z. A new hybrid model for short-term electricity load forecasting[J]. IEEE Access, 2019, 7: 125413-125423. doi: 10.1109/ACCESS.2019.2937222
[5]	WANG Y, ZHANG N, TAN Y S, et al. Combining probabilistic load forecasts[J]. IEEE Transactions on Smart Grid, 2019, 10(4): 3664-3674. doi: 10.1109/TSG.5165411 URL
[6]	SHARMA S, MAJUMDAR A, ELVIRA V, et al. Blind Kalman filtering for short-term load forecasting[J]. IEEE Transactions on Power Systems, 2020, 35(6): 4916-4919. doi: 10.1109/TPWRS.59 URL
[7]	魏步晗, 鲍刚, 李振华. 基于支持向量回归预测模型考虑天气因素和分时电价因素的短期电力负荷预测[J]. 电网与清洁能源, 2023, 39(11): 9-19.
	WEI Buhan, BAO Gang, LI Zhenhua. Short-term electricity load forecasting based on support vector regression forecasting model considering weather factors and time-of-use tariff factors[J]. Power System and Clean Energy, 2023, 39(11): 9-19.
[8]	KONG W C, DONG Z Y, JIA Y W, et al. Short-term residential load forecasting based on LSTM recurrent neural network[J]. IEEE Transactions on Smart Grid, 2019, 10(1): 841-851. doi: 10.1109/TSG.2017.2753802 URL
[9]	刘文杰, 刘禾, 王英男, 等. 基于完整自适应噪声集成经验模态分解的LSTM-Attention网络短期电力负荷预测方法[J]. 电力建设, 2022, 43(2): 98-108. doi: 10.12204/j.issn.1000-7229.2022.02.012
	LIU Wenjie, LIU He, WANG Yingnan, et al. Short-term power load forecasting method based on CEEMDAN and LSTM-attention network[J]. Electric Power Construction, 2022, 43(2): 98-108. doi: 10.12204/j.issn.1000-7229.2022.02.012
[10]	曾囿钧, 肖先勇, 徐方维, 等. 基于CNN-BiGRU-NN模型的短期负荷预测方法[J]. 中国电力, 2021, 54(9): 17-23.
	ZENG Youjun, XIAO Xianyong, XU Fangwei, et al. A short-term load forecasting method based on CNN-BiGRU-NN model[J]. Electric Power, 2021, 54(9): 17-23.
[11]	任建吉, 位慧慧, 邹卓霖, 等. 基于CNN-BiLSTM-Attention的超短期电力负荷预测[J]. 电力系统保护与控制, 2022, 50(8): 108-116.
	REN Jianji, WEI Huihui, ZOU Zhuolin, et al. Ultra-short-term power load forecasting based on CNN-BiLSTM-Attention[J]. Power System Protection and Control, 2022, 50(8): 108-116.
[12]	庄家懿, 杨国华, 郑豪丰, 等. 基于多模型融合的CNN-LSTM-XGBoost短期电力负荷预测方法[J]. 中国电力, 2021, 54(5): 46-55.
	ZHUANG Jiayi, YANG Guohua, ZHENG Haofeng, et al. Short-term load forecasting method based on multi-model fusion using CNN-LSTM-XGBoost framework[J]. Electric Power, 2021, 54(5): 46-55.
[13]	MOKEEV V V. Prediction of heating load and cooling load of buildings using neural network[C]// 2019 International Ural Conference on Electrical Power Engineering (UralCon). IEEE, 2019: 417-421.
[14]	ZHENG H H, ZHAO X M, WU Y T, et al. Research on cold load forecasting model based on long short-term memory[C]// 2021 2nd International Conference on Computer Science and Management Technology (ICCSMT). IEEE, 2022: 87-91.
[15]	LIN T, PAN Y, XUE G X, et al. A novel hybrid spatial-temporal attention-LSTM model for heat load prediction[J]. IEEE Access, 2020, 8: 159182-159195. doi: 10.1109/Access.6287639 URL
[16]	赵峰, 孙波, 张承慧. 基于多变量相空间重构和卡尔曼滤波的冷热电联供系统负荷预测方法[J]. 中国电机工程学报, 2016, 36(2): 399-406.
	ZHAO Feng, SUN Bo, ZHANG Chenghui. Cooling, heating and electrical load forecasting method for CCHP system based on multivariate phase space reconstruction and Kalman filter[J]. Proceedings of the CSEE, 2016, 36(2): 399-406.
[17]	TANG Y, LIU H M, XIE Y F, et al. Short-term forecasting of electricity and gas demand in multi-energy system based on RBF-NN model[C]// 2019 IEEE International Conference on Energy Internet (ICEI). IEEE, 2019: 542-547.
[18]	朱刘柱, 王绪利, 马静, 等. 基于小波包分解与循环神经网络的综合能源系统短期负荷预测[J]. 电力建设, 2020, 41(12): 131-138.
	ZHU Liuzhu, WANG Xuli, MA Jing, et al. Short-term load forecast of integrated energy system based on wavelet packet decomposition and recurrent neural network[J]. Electric Power Construction, 2020, 41(12): 131-138.
[19]	LI K, SUN Y X, LI S Z, et al. Load forecasting method for CCHP system based on deep learning strategy using LSTM-RNN[C]// 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA). IEEE, 2019: 827-831.
[20]	TAN Z F, DE G, LI M L, et al. Combined electricity-heat-cooling-gas load forecasting model for integrated energy system based on multi-task learning and least square support vector machine[J]. Journal of Cleaner Production, 2020, 248: 119252. doi: 10.1016/j.jclepro.2019.119252 URL
[21]	WANG X, WANG S X, ZHAO Q Y, et al. A multi-energy load prediction model based on deep multi-task learning and ensemble approach for regional integrated energy systems[J]. International Journal of Electrical Power & Energy Systems, 2021, 126: 106583. doi: 10.1016/j.ijepes.2020.106583 URL
[22]	孙庆凯, 王小君, 张义志, 等. 基于LSTM和多任务学习的综合能源系统多元负荷预测[J]. 电力系统自动化, 2021, 45(5): 63-70.
	SUN Qingkai, WANG Xiaojun, ZHANG Yizhi, et al. Multiple load prediction of integrated energy system based on long short-term memory and multi-task learning[J]. Automation of Electric Power Systems, 2021, 45(5): 63-70.
[23]	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.
[24]	侯健敏, 孟莹, 李志, 等. 基于综合相关性指标与SA-BiGRU的综合能源系统多元负荷预测[J/OL]. 电力建设: 1-11 [2023-12-28]. http://kns.cnki.net/kcms/detail/11.2583.TM.20231031.1351.006.html.
	HOU Jianmin, MENG Ying, LI Zhi, et al. Multi-energy load forecasting in integrated energy systems based on comprehensive correlation index and SA-BiGRU network[J/OL]. Electric Power Construction: 1-11 [2023-12-28]. http://kns.cnki.net/kcms/detail/11.2583.TM.20231031.1351.006.html.
[25]	WANG C, SHE Z, CAO L. Coupled attribute analysis on numerical data[C]// Proceedings of the Twenty-third International Joint Conference on Artificial Intelligence. 2013: 1736-1742.
[26]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 6000-6010.
[27]	ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer: beyond efficient transformer for long sequence time-series forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(12): 11106-11115. doi: 10.1609/aaai.v35i12.17325 URL
[28]	YAN H, DENG B C, LI X N, et al. TENER: adapting transformer encoder for named entity recognition[EB/OL]. [2023-08-10] 2019: arXiv: 1911.04474. http://arxiv.org/abs/1911.04474.pdf.
[29]	Arizona State University. Campus metabolism[EB/OL]. [2023-08-10]. https://cm.asu.edu/.
[30]	National centers for environmental information[EB/OL]. [2023-08-10]. https://www.ncei.noaa.gov/.