Toward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method.

Yu Liu,Shan Gao,Yan Wang,Yu Hong,Xueliang Huang,Qianyun Shi

doi:10.3390/s21217272

Abstract

As a pivotal technological foundation for smart home implementation, non-intrusive load monitoring is emerging as a widely recognized and popular technology to replace the sensors or sockets networks for the detailed household appliance monitoring. In this paper, a probability model framed ensemble method is proposed for the target of robust appliance monitoring. Firstly, the non-intrusive load disaggregation-oriented ensemble architecture is presented. Then, dictionary learning model is utilized to formulate the individual classifier, while the sparse coding-based approach is capable of providing multiple solutions under greedy mechanism. Furthermore, a fully probabilistic model is established for combined classifier, where the candidate solutions are all labelled with probability scores and evaluated via two-stage decision-making. The proposed method is tested on both low-voltage network simulator platform and field measurement datasets, and the results show that the proposed ensemble method always guarantees an enhancement on the performance of non-intrusive load disaggregation. Besides, the proposed approach shows high flexibility and scalability in classification model selection. Therefore, by initializing the architecture and approach of ensemble method-based NILM, this work plays a pioneer role in using ensemble method to improve the robustness and reliability of non-intrusive appliance monitoring.

Highlights

From the view of physical point, non-intrusive load monitoring (NILM) is a problem that identifying the individual appliances from the integral power signals
Notice that the modules in black blocks represent the traditional structures of ensemble approach, while the colored parts are our proposed improvements to take the characteristics of NILM into consideration
Since the data used in COA, TDA and PEA are the same, such results demonstrate the effectiveness of our ensemble strategy to improve the NILM performance with given dataset

Summary

Introduction

With the fast development of whole society, energy awareness of people is gradually growing. Such trend is conducive to dealing with both energy and climate crises, and strongly supported by academic groups and industrial institutions [1]. It is valuable to take full advantage of power data to mine energy use patterns, provide energy consumption insights and contribute to the energy saving implementations [2]. Under such a background, smart socket is proposed at the early stage to capture the energy patterns of specific appliance as needed [3]. The smart socket is deployed to the plug of target appliance, and utilized for the monitoring of only certain appliance

Methods

Results

Conclusion