Automated Machine Learning: A Case Study on Non-Intrusive Appliance Load Monitoring
This work addresses energy disaggregation for household appliance monitoring, providing a cost-effective tool for industry practitioners, but it is incremental as it adapts existing AutoML methods to a specific domain.
The study tackled the problem of applying Automated Machine Learning (AutoML) to Non-Intrusive Appliance Load Monitoring (NIALM) by using Bayesian Optimization, resulting in an open-source tool that enables domain experts to use state-of-the-art ML methods and showing that simple models like Decision Trees often outperform existing approaches.
We propose a novel approach to enable Automated Machine Learning (AutoML) for Non-Intrusive Appliance Load Monitoring (NIALM), also known as Energy Disaggregation, through Bayesian Optimization. NIALM offers a cost-effective alternative to smart meters for measuring the energy consumption of electric devices and appliances. NIALM methods analyze the entire power consumption signal of a household and predict the type of appliances as well as their individual power consumption (i.e., their contributions to the aggregated signal). We enable NIALM domain experts and practitioners who typically have no deep data analytics or Machine Learning (ML) skills to benefit from state-of-the-art ML approaches to NIALM. Further, we conduct a survey and benchmarking of the state of the art and show that in many cases, simple and basic ML models and algorithms, such as Decision Trees, outperform the state of the art. Finally, we present our open-source tool, AutoML4NIALM, which will facilitate the exploitation of existing methods for NIALM in the industry.