Non-Intrusive Load Identification Method Based on Improved KM Algorithm

Yong Xiao,Yun Zhao,Hengjing He,Dongguo Zhou,Yue Hu,Wenshan Hu

doi:10.1109/access.2019.2948079

Yong Xiao, Yun Zhao + Show 4 more

Open Access

https://doi.org/10.1109/access.2019.2948079

Copy DOI

Abstract

To achieve load disaggregation in non-intrusive load monitoring (NILM) system, a load event matching method based on graph theory is proposed, which is built on the improved Kuhn-Munkras algorithm. In this method, firstly, an adaptive fitting method using time window is applied to detect the load whether it is switched on and/or off. Particularly, to avoid the fluctuation of load signatures, the kernel density estimation is then built by a number of the independent features of the load switching on, including the active and reactive power signatures. The distribution of load signatures is thereby obtained, allowing the load event to be classified by its features. The load matching, which is based on the improved KM algorithm, is then utilized to resolve the matrix formed by the matching probability of the load event. Similarly, load identification can also be realized by matching the features of events with the signatures in the database. Finally, the experimental results using datasets of our lab and REDD demonstrate that the proposed method can obtain the desirable result for load event matching, and promote the performance in load identification.

Highlights

A non-intrusive load monitoring (NILM) system, of which the measurement device is installed at the main electric power input, has become a mainstream technology to know the energy consumption of individual appliances in a household
There are several significant advantages of NILM [1] in contrast to the intrusive load monitoring: (1) it’s the convenient way to install at main electric power input, instead of the voltage sensor and current sensor in each load, reducing the cost [2] and increasing the security of measuring devices; (2) it can help build the ongoing smart grid since the smart meter technology of NILM enables the prediction of the power demand and the decision making for policy makers [3]; (3) it can achieve easy maintenance and extension when the new appliances join, and support the revamping of appliances
AND DISCUSSION we shall present the results of the proposed method by using our lab test data and REDD dataset for verification

Summary

Introduction

A non-intrusive load monitoring (NILM) system, of which the measurement device is installed at the main electric power input, has become a mainstream technology to know the energy consumption of individual appliances in a household. There are several significant advantages of NILM [1] in contrast to the intrusive load monitoring: (1) it’s the convenient way to install at main electric power input, instead of the voltage sensor and current sensor in each load, reducing the cost [2] and increasing the security of measuring devices; (2) it can help build the ongoing smart grid since the smart meter technology of NILM enables the prediction of the power demand and the decision making for policy makers [3]; (3) it can achieve easy maintenance and extension when the new appliances join, and support the revamping of appliances. The supervised disaggregation methods require existing specific information of devices and need initial training phase. It depends on the adequate labelled data for learning the model. Some literatures take several algorithms into consideration to promote the performance of NILM, obtaining the comprehensive result as discussed in [18]

Methods

Results

Conclusion