Non-Intrusive Load Disaggregation Using Graph Signal Processing
Non-Intrusive Load Disaggregation Using Graph Signal Processing
复制标题
DOI：
10.1109/tsg.2016.2598872
复制
发表时间：
2018-05-01
影响因子：
9.6
通讯作者：
Stankovic, Vladimir
中科院分区：
文献类型：
--
作者：
He, Kanghang;Stankovic, Lina;Stankovic, Vladimir
随着智能计量在全球范围内的大规模推广，越来越需要考虑到设备对负载需求的单独贡献。在本文中，我们设计了一个图形信号处理（GSP）为基础的非侵入式家电负载监测（NILM）的方法，即，将能源消耗总量分解到所使用的各个电器。利用电力负荷信号的分段平滑性，提出了两种基于高斯分布的NILM方法。第一种方法，基于全图变差最小化，在已知的标签约束下搜索平滑的图信号。第二种方法使用总图变化最小化作为通过模拟退火进一步细化的起点。所提出的基于GSP的NILM方法旨在通过一种新的基于事件的图方法来解决传统的基于图的方法的大的训练开销和相关的复杂性。使用两个数据集的真实的房子测量的仿真结果表明，相对于传统上使用的隐马尔可夫模型为基础的方法和决策树为基础的方法的基于GSP的方法的竞争力的表现。
With the large-scale roll-out of smart metering worldwide, there is a growing need to account for the individual contribution of appliances to the load demand. In this paper, we design a graph signal processing (GSP)-based approach for non-intrusive appliance load monitoring (NILM), i.e., disaggregation of total energy consumption down to individual appliances used. Leveraging piecewise smoothness of the power load signal, two GSP-based NILM approaches are proposed. The first approach, based on total graph variation minimization, searches for a smooth graph signal under known label constraints. The second approach uses the total graph variation minimizer as a starting point for further refinement via simulated annealing. The proposed GSP-based NILM approach aims to address the large training overhead and associated complexity of conventional graph-based methods through a novel event-based graph approach. Simulation results using two datasets of real house measurements demonstrate the competitive performance of the GSP-based approaches with respect to traditionally used hidden Markov model-based and decision tree-based approaches.