基于非侵入式负荷分解的家庭负荷两阶段超短期负荷预测模型

doi:10.19595/j.cnki.1000-6753.tces.230554

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (930 KB)
输出: BibTeX | EndNote (RIS)

摘要

精细化负荷预测为制定家庭新型需求响应策略或能效管理模式提供了可靠的指导信息与理论基础,而负荷监测系统的广泛研究与发展为家庭设备层的负荷预测提供了有力的数据支撑。基于家庭负荷智能电表集中数据,本文提出一种集分解-预测一体化的家庭负荷两阶段超短期负荷预测方法。该方法第一阶段提出了基于卷积神经网络(CNN)和双向门控单元(BiGRU)神经网络的非侵入式负荷分解(NILM)模型,解决了目前深度分解模型中特征提取不充分、分解精度低等问题。第二阶段构建了基于时间模式注意力机制(TPA)的时间卷积神经网络(TCN)负荷预测模型,深度挖掘NILM分解数据、集中负荷数据及日期特征等输入变量的深层交互信息,实现家庭设备层负荷预测。算例部分通过UK-DALE数据集对所提方法进行验证,结果表明,该方法能够获得较高的分解精度和预测效果,为家庭负荷预测提供了良好的条件。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李延珍
	王海鑫
	杨子豪
	陈哲
	杨俊友

关键词 ：非侵入式负荷分解, 负荷预测, 卷积神经网络, 双向门控单元神经网络, 时间卷积网络, 注意力机制

Abstract：

Due to the impact of large-scale renewable energy on the safe and stable operation of power systems, the demand for flexible sources is increasing. The home energy management system is a promising approach to enhance the flexible regulation capability of power systems and improve grid energy efficiency. However, the randomness of residents' electricity behavior, the uncertainty of market information, and the diversity of decision-making subjects make it extremely challenging for residents to participate in fast demand responses. To address these issues, this paper proposes a two-stage household load forecasting method based on the integration of load disaggregation and forecasting. By learning the correlation information from historical electricity consumption data of each appliance obtained by non-intrusive load monitoring (NILM) technology, it accurately realizes the load forecasting of household appliances and flexible cluster load prediction.
First, a NILM model based on convolutional neural network (CNN) and bi-directional gated unit (BiGRU) neural network is established to solve the problem of obtaining the operation data of appliances. Subsequently, considering the randomness and uncertainty of user behavior, a time convolutional network (TCN) load forecasting model based on the time pattern attention (TPA) mechanism is constructed to mine the deep interaction information of input variables. Finally, the proposed method is verified by the UK-DALE data set. The results show that the proposed method can obtain high disaggregation accuracy and prediction effect.
This paper implements two simulations using Keras with a TensorFlow backend. The first one is designed to monitor the appliance-level energy consumption with the proposed CNN-BiGRU-enabled NILM. The results show that the proposed NILM-Based model can accurately capture the start and end time of the appliance, and has a good trend-tracking effect. With the NILM results, the second one is conducted to verify the effectiveness of the proposed load forecasting model. Compared with other deep learning models such as long short-term memory, the e_MAE and e_RMSE of washing machines, microwave ovens, dishwashers and refrigerators based on the proposed forecasting method are reduced by 18.65% and 4.99%, 13.28% and 0.72%, 32.04% and 5.55%, 4.53% and 5.70%, respectively. The comparison of load forecasting results between the ground truth data and the NILM-based data shows that the e_MAE is controlled within 15% and the e_RMSE is controlled within 6%. Finally, to verify the robustness of the proposed model in cluster load forecasting, a bottom-up strategy is applied to obtain the flexible load prediction of group users or communities based on appliance prediction.
The following conclusions can be drawn from the simulation analysis: (1) The load forecasting framework based on NILM reduces the dependence on intrusive monitoring systems, and has strong adaptability and scalability, which can provide a new method for the development of household energy management system-related businesses. (2) Compared with shallow neural networks, CNN-BiGRU has powerful mapping ability and can achieve high accuracy in load disaggregation and event detection. (3) The proposed forecasting model extracts temporal informative features using TCN and subsequently implements dynamic weighting of inputs using TPA to highlight the impact of key features. The case study shows that the proposed method can improve forecasting accuracy compared with traditional deep learning models.

Key words： Non-intrusive load disaggregation load forecasting convolutional neural network bidirectional gated unit neural network time convolutional network attention mechanism

收稿日期: 2023-04-27

PACS:

TM714

基金资助:

高等学校学科创新引智计划资助项目（D23005）

通讯作者: 杨俊友男,1963年生,教授,博士生导师,研究方向为新能源发电与智能微电网、特种电机先进控制等。E-mail：junyouyang@sut.edu.cn

作者简介: 李延珍女,1987年生,博士研究生,研究方向非侵入式负荷监测,家庭能源管理与优化。E-mail：yanzhenlisut@163.com

引用本文:

李延珍, 王海鑫, 杨子豪, 陈哲, 杨俊友. 基于非侵入式负荷分解的家庭负荷两阶段超短期负荷预测模型[J]. 电工技术学报, 0, (): 230554-230554. Li Yanzhen, Wang Haixin, Yang Zihao, Chen Zhe, Yang Junyou. Two-Stage Ultra-Short-Term Load Forecasting Model of Household Appliances Based on Non-Intrusive Load Disaggregation. Transactions of China Electrotechnical Society, 0, (): 230554-230554.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.230554 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/230554

[1] 徐明杰, 赵健, 王小宇, 等. 基于多任务联合模型的居民用电模式分类方法[J]. 电工技术学报, 2022, 37(21): 5490-5502.
Xu Mingjie, Zhao Jian, Wang Xiaoyu, et al.Residential electricity consumption pattern classification method based on multi-task joint model[J]. Transactions of China Electrotechnical Society, 2022, 37(21): 5490-5502.
[2] 贾雁冰, 杨阳方, 刘继春, 等. 售用双方协同优化的家庭柔性负荷管理策略[J]. 电网技术, 2019, 43(4): 1430-1438.
Jia Yanbing, Yang Yangfang, Liu Jichun, et al.Management strategy for domestic flexible load to achieve retailer-user coordinated optimization[J]. Power System Technology, 2019, 43(4): 1430-1438.
[3] 郑若楠, 李志浩, 唐雅洁, 等. 考虑居民用户参与度不确定性的激励型需求响应模型与评估[J]. 电力系统自动化, 2022, 46(8): 154-162.
Zheng Ruonan, Li Zhihao, Tang Yajie, et al.Incentive demand response model and evaluation considering uncertainty of residential customer participation degree[J]. Automation of Electric Power Systems, 2022, 46(8): 154-162.
[4] Razghandi M, Zhou Hao, Erol-Kantarci M, et al.Short-term load forecasting for smart home appliances with sequence to sequence learning[C]//ICC 2021 - IEEE International Conference on Communications, Montreal, QC, Canada, 2021: 1-6.
[5] Razghandi M, Zhou Hao, Erol-Kantarci M, et al.Smart home energy management: sequence-to-sequence load forecasting and Q-learning[C]//2021 IEEE Global Communications Conference (GLOBECOM), Madrid, Spain, 2022: 1-6.
[6] Mohi Ud Din G, Mauthe A U, Marnerides A K. Appliance-level short-term load forecasting using deep neural networks[C]//2018 International Conference on Computing, Networking and Communications (ICNC), Maui, HI, USA, 2018: 53-57.
[7] Wang Shouxiang, Deng Xinyu, Chen Haiwen, et al.A bottom-up short-term residential load forecasting approach based on appliance characteristic analysis and multi-task learning[J]. Electric Power Systems Research, 2021, 196: 107233.
[8] Zheng Zhuang, Chen Hainan, Luo Xiaowei.A Kalman filter-based bottom-up approach for household short-term load forecast[J]. Applied Energy, 2019, 250: 882-894.
[9] 唐贤伦, 陈洪旭, 熊德意, 等. 基于极端梯度提升和时间卷积网络的短期电力负荷预测[J]. 高电压技术, 2022, 48(8): 3059-3067.
Tang Xianlun, Chen Hongxu, Xiong Deyi, et al.Short-term power load forecasting based on extreme gradient boosting and temporal convolutional network[J]. High Voltage Engineering, 2022, 48(8): 3059-3067.
[10] Bai Shaojie, Kolter J Z, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL].2018: arXiv: 1803.01271. https://arxiv.org/abs/1803.01271
[11] 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.
[12] 雷怡琴, 孙兆龙, 叶志浩, 等. 电力系统负荷非侵入式监测方法研究[J]. 电工技术学报, 2021, 36(11): 2288-2297.
Lei Yiqin, Sun Zhaolong, Ye Zhihao, et al.Research on non-invasive load monitoring method in power system[J]. Transactions of China Electrotechnical Society, 2021, 36(11): 2288-2297.
[13] Li Yanzhen, Wang Haixin, Yang Zihao, et al.Stacking ensemble learning-based load identification considering feature fusion by cyber-physical approach[J]. IEEE Sensors Journal, 2023, 23(6): 5997-6007.
[14] Liu Bo, Luan Wenpeng, Yang Jinnan, et al.The balanced window-based load event optimal matching for NILM[J]. IEEE Transactions on Smart Grid, 2022, 13(6): 4690-4703.
[15] Ding Dong, Li Junhuai, Zhang Kuo, et al.Non-intrusive load monitoring method with inception structured CNN[J]. Applied Intelligence, 2022, 52(6): 6227-6244.
[16] 廖荣文, 刘刚, 肖刚. 基于时间模糊化长短时记忆的非侵入式负荷分解方法[J]. 电力系统自动化, 2021, 45(24): 73-80.
Liao Rongwen, Liu Gang, Xiao Gang.Non-intrusive load decomposition method based on time-fuzzified long short-term memory[J]. Automation of Electric Power Systems, 2021, 45(24): 73-80.
[17] Kaselimi M, Doulamis N, Voulodimos A, et al.Context aware energy disaggregation using adaptive bidirectional LSTM models[J]. IEEE Transactions on Smart Grid, 2020, 11(4): 3054-3067.
[18] 徐晓会, 赵书涛, 崔克彬. 基于卷积块注意力模型的非侵入式负荷分解算法[J]. 电网技术, 2021, 45(9): 3700-3706.
Xu Xiaohui, Zhao Shutao, Cui Kebin.Non-intrusive load disaggregate algorithm based on convolutional block attention module[J]. Power System Technology, 2021, 45(9): 3700-3706.
[19] 邓旭晖, 陈中, 杨凯, 等. 基于多任务学习卷积网络的非侵入式负荷监测方法[J]. 电力系统自动化, 2023, 47(8): 189-197.
Deng Xuhui, Chen Zhong, Yang Kai, et al.Non-intrusive load monitoring method based on multi-task learning convolutional network[J]. Automation of Electric Power Systems, 2023, 47(8): 189-197.
[20] 周润, 向月, 王杨, 等. 基于智能电表集总数据的家庭电动汽车充电行为非侵入式辨识与负荷预测[J]. 电网技术, 2022, 46(5): 1897-1908.
Zhou Run, Xiang Yue, Wang Yang, et al.Non-intrusive identification and load forecasting of household electric vehicle charging behavior based on smart meter data[J]. Power System Technology, 2022, 46(5): 1897-1908.
[21] Brucke K, Arens S, Telle J S, et al.A non-intrusive load monitoring approach for very short-term power predictions in commercial buildings[J]. Applied Energy, 2021, 292: 116860.
[22] Kelly J, Knottenbelt W.Neural NILM: deep neural networks applied to energy disaggregation[C]//Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, Seoul, South Korea, 2015: 55-64.
[23] Zhang Chaoyun, Zhong Mingjun, Wang Zongzuo, et al.Sequence-to-point learning with neural networks for non-intrusive load monitoring[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 2604-2611.
[24] 沙建峰, 席乐, 冯亚杰, 等. 基于注意力时序网络的非侵入式负荷分解[J/OL]. 南京信息工程大学学报(自然科版): 1-13[2022-11-01]. http://kns.cnki.net/kcms/detail/32.1801.N.20220819.1255.002.html.
Sha Jianfeng, Xi Le, Feng Yajie, et al. Non-intrusive load decomposition based on attention recurrent network model[J/OL]. Journal of Nanjing University of Information Science & Technology (Natural Science Edition): 1-13,[2022-11-01]. http://kns.cnki.net/kcms/detail/32.1801.N.20220819.1255.002.html.
[25] 杨童亮, 胡东, 唐超, 等. 基于SMA-VMD-GRU模型的变压器油中溶解气体含量预测[J]. 电工技术学报, 2023, 38(1): 117-130.
Yang Tongliang, Hu Dong, Tang Chao, et al.Prediction of dissolved gas content in transformer oil based on SMA-VMD-GRU model[J]. Transactions of China Electrotechnical Society, 2023, 38(1): 117-130.
[26] Çimen H, Çetinkaya N, Vasquez J C, et al.A microgrid energy management system based on non-intrusive load monitoring via multitask learning[J]. IEEE Transactions on Smart Grid, 2021, 12(2): 977-987.
[27] 唐斯, 陈新楚, 郑松. 基于注意力与多尺度卷积神经网络的电机轴承故障诊断[J]. 电气技术, 2020, 21(11): 32-38.
Tang Si, Chen Xinchu, Zheng Song.Fault diagnosis method of motor bearing based on attention and multi-scale convolution neural network[J]. Electrical Engineering, 2020, 21(11): 32-38.
[28] 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.
[29] 孙辉, 杨帆, 高正男, 等. 考虑特征重要性值波动的MI-BILSTM短期负荷预测[J]. 电力系统自动化, 2022, 46(8): 95-103.
Sun Hui, Yang Fan, Gao Zhengnan, et al.Short-term load forecasting based on mutual information and Bi-directional long short-term memory network considering fluctuation in importance values of features[J]. Automation of Electric Power Systems, 2022, 46(8): 95-103.
[30] 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/OL]. 电力系统自动化: 1-13[2023-3-12]. http://kns.cnki.net/kcms/detail/32.1180.
Zhang Pengfei, Hu Bo, He Jinsong, et al. Short-term spatial load forecasting method based on spatio-temporal graph convolutional network[J/OL]. Automation of Electric Power systems, http://kns.cnki.net/kcms/detail/32.1180.TP.20230310.1703.010.html.
[31] 王渝红, 史云翔, 周旭, 等. 基于时间模式注意力机制的BiLSTM多风电机组超短期功率预测[J]. 高电压技术, 2022, 48(5): 1884-1892.
Wang Yuhong, Shi Yunxiang, Zhou Xu, et al.Ultra-short-term power prediction for BiLSTM multi wind turbines based on temporal pattern attention[J]. High Voltage Engineering, 2022, 48(5): 1884-1892.
[32] Kelly J, Knottenbelt W.The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes[J]. Scientific Data, 2015, 2: 150007.