Integrating Graph Signal Processing and Multitask Temporal Convolutional Networks for Household Nonintrusive Load Monitoring

Highly accurate nonintrusive load monitoring (NILM) models are essential for energy management, optimization decisions, and system monitoring. However, the sparsity of load features and spatio-temporal relationships hidden in loads have not been fully tackled, hindering the accuracy of NILM models. To solve the above problems, a load disaggregation (LD) framework that cascades graph signal processing (GSP) with multitask temporal convolution network (TCN) is proposed. In this framework, the GSP is designed as a direct load feature extractor to tackle the sparsity of load features. The multitask TCN can leverage GSP outputs and total power to extract spatio-temporal relationships among loads, and then generate precise LD results for each load simultaneously. Afterward, the implementation of the GSP-based direct load feature extractor is designed, including the construction of graph representation of load features, pattern matching, and direct load features correction. Then the implementation scheme of multitask TCN is proposed, consisting of load features fusion strategy, the spatio-temporal relationships extractor design, and the loss function setting and training strategy. The experiment shows that our model can concurrently output LD results for eight appliances. Meanwhile, compared to existing advanced methods, our model has an over 13% reduction on mean absolute error (MAE).

I. Introduction

The household nonintrusive load monitoring (NILM) is a technique that extracts the power consumption of single appliances out of total household power [1]. Compared to intrusive load monitoring, it eliminates the need to install sensors for each electrical device and to modify and maintain existing electrical lines [2]. For users, timely access to device details obtained through load monitoring can lead them toward responsible electricity usage, thus achieving energy conservation [3]. From a macro perspective, the power grid can utilize specific load usage information as a basis for planning and scheduling the power system. With these information, the power grid can develop appropriate generation plans to enhance grid efficiency and reduce electricity waste [4].