基于注意力时序网络模型的非侵入式负荷分解
作者:
作者单位:

1.国网河南电动汽车服务有限公司;2.南京信息工程大学

中图分类号:

TP

基金项目:

国家自然科学基金


Non-Intrusive Load Decomposition Based on Attention Recurrent Network Model
Author:
Affiliation:

1.State grid henan electric vehicle service company;2.Nanjing University of Information Science and Technology

Fund Project:

National Natural Science Foundation of PR China

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

    非侵入式负荷分解的本质是根据已知的总功率信号分解出单一的负荷设备的功率信号。目前基于深度学习模型大都存在网络模型负荷特征提取不充分、分解精度低、对使用频率较低的负荷设备分解误差大等问题。针对这些问题,本文提出了一种注意力时序网络模型(Attention Recurrent Neural Networks, ARNN)来实现非侵入式负荷分解,它将回归网络与分类网络相结合来解决非侵入式负荷分解问题。该模型通过RNN网络实现对序列信号特征的提取,同时利用注意力机制定位输入序列中重要信息的位置,提高神经网络的表征能力。在公开数据集Wiki-Energy以及UK-DALE上进行的实验表明,我们提出的深度神经网络在所有考虑的实验条件下都优于最先进的神经网络。我们还表明,通过注意力机制和辅助分类网络能够正确检测设备的开启或关闭,并定位高功耗的信号部分,提高了负荷分解的准确性。

    Abstract:

    The non-intrusive load decomposition is to decompose the power signal of a single load device according to the known total power signal. At present, there are many problems based on deep learning models, such as insufficient load feature extraction, low decomposition accuracy, large decomposition error of load equipment with low frequency, and so on. To solve these problems, this paper proposes an attention recurrent neural networks (ARNN) model to realize non-invasive load decomposition, which combines regression network and classification network to solve the non-invasive load decomposition problem. The model extracts the features of sequence signals through RNN network, and uses the attention mechanism to locate the position of important information in the input sequence, so as to improve the representation ability of network. Experiments on public datasets Wiki-Energy and UK-DALE show that our proposed deep neural network is superior to the most advanced neural network under all experimental conditions. We also show that the attention mechanism and auxiliary classification network can correctly detect the opening or closing of devices, and locate the high-power signal part, which improves the accuracy of load decomposition.

    参考文献
    [1] Cominola A, Giuliani M, Piga D, et al. A hybrid signature-based iterative disaggregation algorithm for non-intrusive load monitoring[J]. Applied energy, 2017, 185: 331-344.
    [2] Xia M, Wang Z, Lu M, Pan L. MFAGCN: A new framework for identifying power grid branch parameters[J]. Electric Power Systems Research,2022, 207: 107855.
    [3] Bassamzadeh N, Ghanem R. Multiscale stochastic prediction of electricity demand in smart grids using Bayesian networks[J]. Applied energy, 2017, 193: 369-380.
    [4] Garshasbi S, Kurnitski J, Mohammadi Y. A hybrid Genetic Algorithm and Monte Carlo simulation approach to predict hourly energy consumption and generation by a cluster of Net Zero Energy Buildings[J]. Applied energy, 2016, 179: 626-637.
    [5] 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/OL].南京信息工程大学学报(自然科学版):1-13
    [6] Chang H H, Chen K L, Tsai Y P, et al. A new measurement method for power signatures of nonintrusive demand monitoring and load identification[J]. IEEE Transactions on Industry Applications, 2011, 48(2): 764-771.
    [7] 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(09):3700-3706.
    [8] Lin Y H, Tsai M S. Development of an improved time–frequency analysis-based nonintrusive load monitor for load demand identification[J]. IEEE Transactions on Instrumentation and Measurement, 2013, 63(6): 1470-1483.
    [9] Kim H, Marwah M, Arlitt M, et al. Unsupervised disaggregation of low frequency power measurements[C]//Proceedings of the 2011 SIAM international conference on data mining. Society for Industrial and Applied Mathematics, 2011: 747-758.
    [10] 于超,覃智君,阳育德.基于启停状态识别改进因子隐马尔可夫模型的非侵入式负荷分解[J].电网技术,2021, 45(11):4540-4550.
    [11] Makonin S, Popowich F, Baji? I V, et al. Exploiting HMM sparsity to perform online real-time nonintrusive load monitoring[J]. IEEE Transactions on smart grid, 2015, 7(6): 2575-2585.
    [12] Agyeman K A, Han S, Han S. Real-time recognition non-intrusive electrical appliance monitoring algorithm for a residential building energy management system[J]. Energies, 2015, 8(9): 9029-9048.
    [13] Suzuki K, Inagaki S, Suzuki T, et al. Nonintrusive appliance load monitoring based on integer programming[C]//2008 SICE Annual Conference. IEEE, 2008: 2742-2747.
    [14] Bhotto M Z A, Makonin S, Baji? I V. Load disaggregation based on aided linear integer programming[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2016, 64(7): 792-796.
    [15] 成贵学,陈博野,赵晋斌,费敏锐.基于条件生成对抗网络的非侵入式负荷分解[J].电力系统及其自动化学报,2021,33(08):109-115.
    [16] 陈春玲,夏旻,王珂,曹辉.基于分组空洞残差网络的非侵入式负荷分解[J].计算机应用与软件,2021,38(09):53-59.
    [17] Lin J, Ma J, Zhu J, et al. Deep Domain Adaptation for Non-Intrusive Load Monitoring Based on a Knowledge Transfer Learning Network[J]. IEEE Transactions on Smart Grid, 2021, 13(1): 280-292.
    [18] Cho K, Van Merri?nboer B, Bahdanau D, et al. On the properties of neural machine translation: Encoder-decoder approaches[J]. arXiv preprint arXiv:1409.1259, 2014.
    [19] Young T, Hazarika D, Poria S, et al. Recent trends in deep learning based natural language processing[J]. IEEE Computational intelligenCe magazine, 2018, 13(3): 55-75.
    [20] Raffel C, Ellis D P W. Feed-forward networks with attention can solve some long-term memory problems[J]. arXiv preprint arXiv:1512.08756, 2015.
    相似文献
    引证文献
    引证文献 [0]
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

沙建峰,席乐,冯亚杰,庄伟.基于注意力时序网络模型的非侵入式负荷分解[J].南京信息工程大学学报,,():

复制
分享
文章指标
  • 点击次数:49
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2022-07-03
  • 最后修改日期:2022-08-14
  • 录用日期:2022-08-18

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