Abstract
Appliance recognition is one of the vital sub-tasks of NILM in which a machine learning classier is used to detect and recognize active appliances from power measurements. The performance of the appliance classifier highly depends on the signal features used to characterize the loads. Recently, different appliance features derived from the voltage–current (V–I) waveforms have been extensively used to describe appliances. However, the performance of V–I-based approaches is still unsatisfactory as it is still not distinctive enough to recognize devices that fall into the same category. Instead, we propose an appliance recognition method utilizing the recurrence graph (RG) technique and convolutional neural networks (CNNs). We introduce the weighted recurrent graph (WRG) generation that, given one-cycle current and voltage, produces an image-like representation with more values than the binary output created by RG. Experimental results on three different sub-metered datasets show that the proposed WRG-based image representation provides superior feature representation and, therefore, improves classification performance compared to V–I-based features.
Highlights
The introduction of smart meters as part of smart grids will produce quantities of data energy consumption data at very fast rates
Considerable research attention has been lately devoted to deep neural networks (DNN) to solve energy disaggregation problems [6,7,8,9,10,11,12]
Motivated by the quest to create strong feature representation and improve classification performance, in this study, we propose new feature representation for appliance classification which relies on the recurrence graph (RG), known as the recurrence plot
Summary
The introduction of smart meters as part of smart grids will produce quantities of data energy consumption data at very fast rates. The use of V–I-based features for appliance classification was first introduced in [18], where wave-shape features were hand-engineered the from a V-I trajectory (e.g., number of self-interceptions), and used as input to supervised machine learning classifiers. The wave-based features were found to have a direct correspondence to operating characteristics of appliances, and several other features such as peak of middle segment and asymmetry were later developed and evaluated in [20] This approach compresses the information in the V–I-trajectory into a limited amount of hand-engineering feature space. Experimental evaluation in the three sub-metered datasets shows that the proposed WRG feature representation offers superior performance when compared to the V–I-based image feature. We conduct an empirical investigation on how different parameters of the proposed WRG influence classification performance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
