What is it about?
This paper proposes a new approach towards Non-Intrusive-Load-Monitoring using Graph Neural Networks.
Featured Image
Photo by DeepMind on Unsplash
Why is it important?
The research objectives of this publication which makes it important are: - Develop a model for NILM that avoids sequential data processing, to efficiently learn time-invariant relationships. - Propose the first Graph Neural Network based approach for NILM inspired by their application on neural machine translation. - Find meaningful way to transform the energy consumption time-series data into a directed graph structure.
Perspectives
This publication proposes the first graph neural network approach towards NILM which was inspired by the neural machine translation domain.
Sotirios Athanasoulias
Plegma Labs
Read the Original
This page is a summary of: A First Approach using Graph Neural Networks on Non-Intrusive-Load-Monitoring, June 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3529190.3534722.
You can read the full text:
Contributors
The following have contributed to this page
