基于多注意力机制集成的非侵入式负荷分解算法
作者单位:

1.上海海事大学;2.南京信息工程大学;3.同济大学;4.广东海洋大学

基金项目:

国家自然科学青年基金


Non-intrusive Load Decomposition Model Based on Multi-attention Mechanism Integration
Author:
Affiliation:

1.Shanghai Maritime University;2.Nanjing University of Information Engineering;3.Tongji University;4.Guangdong Ocean University

Fund Project:

National Natural Science Youth Foundation of China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对输入负荷特征对分解结果的重要程度不同,以及长短时记忆网络(LSTM)在捕捉长时间用电信息的时间依赖性方面受限导致分解误差高的问题,提出一种基于多注意力机制集成的非侵入式负荷分解算法。首先,利用概率自注意力机制对一维空洞卷积提取到的负荷特征进行优化处理,实现重要负荷特征的遴选;其次,采用时间模式注意力机制对LSTM的隐状态赋予权重,从而增强网络对长时间用电信息之间的时间依赖性的学习能力;最后,利用公开数据集UKDALE和REDD对所提分解模型的有效性和创新性进行验证。实验结果表明,与其他多种现有分解算法相比,基于多注意力机制集成的分解算法不仅具备更好的负荷特征遴选能力,而且能正确建立特征之间的时间依赖关系,有效降低了分解误差。

    Abstract:

    In view of the different importance of input load characteristics to the decomposition results and the high decomposition error caused by the limited time dependence of LSTM in capturing long-term power consumption information, a non-intrusive load decomposition model based on multi-attention mechanism integration is proposed. Firstly, the probsparse self-attention mechanism is used to optimize the load characteristics extracted by one-dimensional dilated convolution. Then, the temporal pattern attention mechanism is used to give weight to the hidden state of LSTM, so as to enhance the learning ability of the network on the time dependence of long-term power consumption information. Finally, the validity of the proposed decomposition model is verified using the publicly available dataset UKDALE and REDD. Experimental results show that, compared with other decomposition algorithms, the decomposition algorithm based on multi-attention mechanism integration not only has the ability to select important load features, but also can correctly establish the time-dependent relationship between features and effectively reduce the decomposition error.

    参考文献
    [1] 余贻鑫, 刘博, 栾文鹏. 非侵入式居民电力负荷监测与分解技术[J]. 南方电网技术, 2013, 7(04): 1-5.
    [2] Nalmpantis C, D Vrakas. Machine learning approaches for non-intrusive load monitoring: from qualitative to quantitative comparation. The Artificial intelligence review[J]. Artificial Intelligence Review, 2018, 52(2): 1-7.
    [3] 邓晓平, 张桂青, 魏庆来, 等. 非侵入式负荷监测综述[J]. 自动化学报, 2020, 1-21.
    [4] Gopinath R, Kumar M, Joshua C, et al. Energy management using non-intrusive load monitoring techniques State-of-the-art and future research directions[J]. Sustainable cities and society, 2018, 52(2): 1-7.
    [5] 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(02):148-155.
    [6] Hart G W. Nonintrusive appliance load monitoring[J]. Proceedings of the IEEE, 1992, 80(12), 1870–1891.
    [7] Hart G W, Kern E C, Schweppe F C. Non-intrusive appliance monitor apparatus[P]. 1989.
    [8] 孙毅, 崔灿, 陆俊, 等. 基于遗传优化的非侵入式家居负荷分解方法[J]. 电网技术, 2016, 40(12): 3912-3917.
    [9] G Ding, C Wu, Y Wang, et al. A Novel Non-intrusive Load Monitoring Method Based on Quantum Particle Swarm Optimization Algorithm [C]. 2019 11th International Conference on Measuring Technology and Mechatronics Automation, 2019.
    [10] 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(05):571-575.
    [11] 许历隆,翟江涛,林鹏,等.一种基于改进深度残差收缩网络的恶意应用检测方法[J/OL].南京信息工程大学学报(自然科学版):1-14.
    [12] Kelly J, Knottenbelt W J. Neural NILM: Deep Neural Networks Applied to Energy Disaggregation[M]. Springer International Publishing, 2015.
    [13] Krystalakos O C, Nalmpantis, Vrakas. Sliding Window Approach for Online Energy Disaggregation Using Artificial Neural Networks[J]. 2018.
    [14] Garcia-Perez D, Perez-Lopez D, Diaz-Blanco I, et al. Fully-convolutional denoising auto-encoders for NILM in large non-residential buildings[J]. IEEE Transactions on Smart Grid, 2021, 12(3): 2722-2731.
    [15] Zhu R, W Liao, Y Wang. Short-term prediction for wind power based on temporal convolutional network[J]. Energy reports, 2020, 6:424-429.
    [16] 李梅,宁德军,郭佳程. 基于注意力机制的CNN-LSTM模型及其应用[J].计算机工程与应用, 2019, 55(13): 20-27.
    [17] LI M, NING D J, GUO J C. Attention mechanism-based CNN-LSTM model and its application[J]. Computer Engineering and Applications, 2019, 55(13): 20-27.
    [18] [17] 李晓, 卢先领. 基于双重注意力机制和GRU的短期负荷预测模型[J].计算机工程, 2021: 1-9.
    [19] [18] 刘建伟, 刘俊文,罗雄麟.深度学习中注意力机制研究进展[J]. 工程科学学报, 2021.43(11): 1499-1511.
    [20] [19] 赵敬娇,赵志宏,杨绍普.基于残差连接和1D-CNN的滚动轴承故障诊断研究[J].振动与冲击, 2021, 40(10):1-6.
    [21] [20] 刘建伟,赵会丹,罗雄麟,等.深度学习批归一化及其相关算法研究进展[J].自动化学报, 2020,46(06):1090-1120.
    [22] [21] 代业明, 高红伟, 高岩, 等. 具有电力需求预测更新的智能电网实时定价机制[J].电力系统自动化, 2018, 42(12): 58-63.
    [23] [22] Donato P G, Carugati I, L Hernández, et al. Review of NILM applications in smart grids: power quality assessment and assisted independent living[C]. Congreso Argentino de Control Automático. 2020.
    [24] [23] Armel K C, Gupta A, Shrimali G, et al. Is disaggregation the holy grail of energy efficiency? The case of electricity[J]. Energy Policy, 2013, 52(JAN.):213-234.
    [25] [24] 程祥, 李林芝, 吴浩, 等. 非侵入式负荷监测与分解研究综述[J]. 电网技术, 2016, 40(10):3108-3117.邓晓平, 张桂青, 魏庆来, 等. 非侵入式负荷监测综述[J]. 自动化学报, 2020, 1-21.
    [26] [25] Liang J, Ng S K, Kendall G, et al. Load Signature Study—Part I: Basic Concept, Structure, and Methodology[J]. IEEE Transactions on Power Delivery, 2010, 25(2): 551-560.
    [27] [26] Zhang C, Zhong M, Wang Z, et al. Sequence-to-point learning with neural networks for nonintrusive load monitoring[A]. The Thirty-Second AAAI Conference [C]. 2018.
    [28] [27] Tongta A, Chooruang K. Long Short-Term Memory (LSTM) Neural Networks Applied to Energy Disaggregation[A]. 2020 8th International Electrical Engineering Congress [C]. 2020.
    [29] [28] Wang K, Zhong H, Nanpeng Y U, et al. Nonintrusive Load Monitoring based on Sequence-to-sequence Model With Attention Mechanism[J]. Proceedings of the CSEE, 2019.
    [30] [29] Niu ZY, Zhong GQ, Yu H. A review on the attention mechanism of deep learning. Neurocomputing (Amsterdam), 2021, 452:48-62.
    [31] [30] 蒙亮, 于超, 张希翔, 等. 基于一维卷积神经网络和自注意力机制的非侵入式负荷分解[J].电力大数据, 2020, 23(10):1-8.-8.
    [32] [31] 余登武, 刘敏, 汪元芹. 基于GRNN与注意力机制模型的非侵入式家用负荷分解[J]. 电力大数据, 2021. 49(03): 74-79.
    [33] [32] Yang M, X Li, Y Liu. Sequence to Point Learning Based on an Attention Neural Network for Nonintrusive Load Decomposition. Electronics (Basel), 2021, 10(1657), 1657.
    [34] [33] Vaswani A, Shazeer N, Parmar N, et al. Attention Is All You Need[J]. Advances in Neural Information Processing Systems, 2017.
    [35] [34] Zhou H, Zhang S, Peng J, et al. Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting[J]. 2020.
    [36] [35] Shih S Y, Sun F K, Lee H Y. Temporal Pattern Attention for Multivariate Time Series Forecasting[J]. 2018.
    [37] [36] Yu F, Koltun V, Funkhouser T. Dilated Residual Networks[C]. IEEE Computer Society, 2017.
    [38] [37] He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[J]. IEEE, 2016.
    [39] [38] Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift[J]. JMLR.org, 2015.
    [40] [39] Babaei T, Abdi H, Lim C P, et al. A study and a directory of energy consumption data sets of buildings[J]. Energy & Buildings, 2015, 94:91-99.
    [41] [40] 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.
    [42] [41] 刘仲民, 侯坤福, 高敬更, 等. 基于时间卷积神经网络的非侵入式居民用电负荷分解方法[J].电力建设(Electric Power Construction), 2021, 42(03):97-106.
    [43] [42] 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.
    [44] [43] J. Z. Kolter, M J Johnson. Redd: A public data set for energydisaggregation research,SIGKDD,2011,25:59-62
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

王赟,葛泉波,姚刚,王梦梦,姜淏予.基于多注意力机制集成的非侵入式负荷分解算法[J].南京信息工程大学学报,,():

复制
分享
文章指标
  • 点击次数:78
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2022-05-16
  • 最后修改日期:2022-06-14
  • 录用日期:2022-06-15

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