Last week I found out that a conference paper I helped co-author with colleagues Alon Harell and Ivan V. Bajic was accepted for publication. Titled WaveNILM: A Causal Neural Network for Power Disaggregation from the Complex Power Signal, it will be presented at the 44th International Conference on Acoustics, Speech, and Signal Processing (ICASSP) on May 17, 2019 in Brighton, UK. ICASSP is the largest and longest-running signal processing conference. Here is the paper abstract:
Non-intrusive load monitoring (NILM) helps meet energy conservation goals by estimating individual appliance power usage from a single aggregate measurement. Deep neural networks have become increasingly popular in attempting to solve NILM problems; however, many of them are not causal which is important for real-time application. We present a causal 1-D convolutional neural network inspired by WaveNet for NILM on low-frequency data. We also study using various components of the complex power signal for NILM, and demonstrate that using all four components available in a popular NILM dataset (current, active power, reactive power, and apparent power) we achieve faster convergence and higher performance than state-of-the-art results for the same dataset.
Keywords: NILM, power disaggregation, convolutional neural network, causality
Source code for this project will soon be available on GitHub.