An improved non-intrusive load disaggregation algorithm and its application. (February 2020)

• Record Type: Journal Article
• Authors: Liu, Hui; Yu, Chengming; Wu, Haiping; Chen, Chao; Wang, Ziqi
• Is Part Of: Sustainable cities and society. Volume 53(2020)
• Publication Date: 2020-02
• Subjects: Weighted current harmonic vectors -- Multi-objective particle swarm optimization -- Current superimposition -- Non-intrusive load monitoring; Sustainable urban development -- Periodicals; Sustainable buildings -- Periodicals; Urban ecology (Sociology) -- Periodicals; 307.76
• DOI: 10.1016/j.scs.2019.101918
• Languages: English
• ISSNs: 2210-6707

Abstract

Highlights: The weighted Harmonic vectors are proposed avoiding the higher harmonics being covered up by the first harmonic. The current vectors are calculated in a geometric way without losing any information. The MOPSO method is utilized in this work and the standard deviation of the errors are added to the objective functions. A current superimposing method is built to generate the aggregated current from the one-appliance-running currents. Abstract: The non-intrusive load monitoring (NILM) method is proposed to acquire the energy consumption of appliances in a building. Steady-state current decomposition is one of the most effective and applicable methods in NILM. Although many load features and decomposing models have been developed in the previous work, the harmonic vectors have been rarely discussed. In this study, weighted current harmonic vectors are proposed to increase the weight of the useful harmonic. The harmonic vectors are calculated geometrically so that all the information in features can be retained. A multi-objective particle swarm optimization based model is built to carry out the disaggregation task, where both summation and standard deviation of the errors are considered as objective functions. Moreover, to make the public datasets available in current decomposition, a current superimposing method is proposed. It generates aggregated currents from the currents of appliances running independently. Finally, the proposed model and two contrast models are performed on the WHITED dataset. The experimental results indicate that the proposed method is more robust and has higher current disaggregation precision than the involved comparing methods.