Challenges in Gaussian Processes for Non Intrusive Load Monitoring

TL;DR

This paper evaluates the use of Gaussian Processes for non-intrusive load monitoring, highlighting their advantages like uncertainty modeling and domain knowledge integration, while discussing the challenges faced in practical application.

Contribution

The paper demonstrates the potential of Gaussian Processes for NILM and discusses specific challenges in applying GPs to this domain.

Findings

GPs inherently model uncertainty in NILM.

Designing kernels allows incorporation of domain expertise.

Challenges include computational complexity and data requirements.

Abstract

Non-intrusive load monitoring (NILM) or energy disaggregation aims to break down total household energy consumption into constituent appliances. Prior work has shown that providing an energy breakdown can help people save up to 15\% of energy. In recent years, deep neural networks (deep NNs) have made remarkable progress in the domain of NILM. In this paper, we demonstrate the performance of Gaussian Processes (GPs) for NILM. We choose GPs due to three main reasons: i) GPs inherently model uncertainty; ii) equivalence between infinite NNs and GPs; iii) by appropriately designing the kernel we can incorporate domain expertise. We explore and present the challenges of applying our GP approaches to NILM.