Evolutionary Deep Nets for Non-Intrusive Load Monitoring
This work addresses energy efficiency for households by improving appliance-level electricity tracking, but it is incremental as it applies existing methods to a known dataset.
The paper tackles the problem of Non-Intrusive Load Monitoring (NILM) by using deep learning models, including deep neural networks, convolutional neural networks, and recurrent neural networks, with sparse evolutionary training to accelerate training efficiency, applied to the UK-Dale dataset.
Non-Intrusive Load Monitoring (NILM) is an energy efficiency technique to track electricity consumption of an individual appliance in a household by one aggregated single, such as building level meter readings. The goal of NILM is to disaggregate the appliance from the aggregated singles by computational method. In this work, deep learning approaches are implemented to operate the desegregations. Deep neural networks, convolutional neural networks, and recurrent neural networks are employed for this operation. Additionally, sparse evolutionary training is applied to accelerate training efficiency of each deep learning model. UK-Dale dataset is used for this work.