Name
Abstract | ||
|---|---|---|
Energy disaggregation is to discover the energy consumption of individual appliances from their aggregated energy values. Most existing approaches rely on either appliances' signatures or their state transition patterns, both hard to obtain in practice. In addition, load data may be corrupted due to various reasons. To overcome the problems, this paper utilizes easily accessible knowledge of appliances and the sparsity of the switching events to design a Sparse Switching Event Recovering (SSER) method. Furthermore, a robust version of this method (RSSER) is developed to tackle the problems caused by corrupted data and unknown appliances. By minimizing the total variation of the sparse event matrix and introducing a virtual appliance, RSSER can obtain accurate energy disaggregation results in the presence of outliers, without using any explicit data cleansing method. To speed up RSSER, a Parallel Local Optimization Algorithm (PLOA) is proposed to solve the problem in active epochs of appliance activities in parallel. To automatically acquire the power consumption knowledge of appliances whose information is unknown, we develop a K-median clustering based power division approach and establish an appliance power configuration platform. Using real-world trace data from our energy monitoring platform, the performance of RSSER is compared with that of the state-of-the-art solutions, including the least square estimation methods and a machine learning method using iterative Hidden Markov Model. The results show that RSSER not only has an overall better performance in both detection accuracy and overhead, but also can tolerate the interference of corrupted data and unknown appliances. (C) 2016 Elsevier Inc. All rights reserved. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1016/j.suscom.2016.01.004 | Sustainable Computing: Informatics and Systems |
Keywords | Field | DocType |
Non-intrusive appliance load monitoring,Energy disaggregation,Optimization,Measurement | Data mining,Data cleansing,Computer science,Outlier,Virtual appliance,Local search (optimization),Cluster analysis,Hidden Markov model,Energy consumption,Speedup | Journal |
Volume | ISSN | Citations |
9 | 2210-5379 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guoming Tang | 1 | 67 | 17.62 |
| Kui Wu | 2 | 30 | 5.06 |
| Jingsheng Lei | 3 | 12 | 1.26 |
| Jiuyang Tang | 4 | 4 | 4.17 |