A Dataset and Baseline Approach for Identifying Usage States from Non-Intrusive Power Sensing With MiDAS IoT-based Sensors

TL;DR

This paper introduces a new dataset and baseline method for identifying system usage states using non-intrusive power sensing, aiming to advance research in power pattern recognition across various institutions.

Contribution

It provides a publicly available power usage dataset from multiple sectors and an initial unsupervised machine learning baseline for state identification.

Findings

Dataset includes data from 8 diverse institutions.

Baseline approach offers a starting point for future research.

Facilitates development of non-intrusive power sensing techniques.

Abstract

The state identification problem seeks to identify power usage patterns of any system, like buildings or factories, of interest. In this challenge paper, we make power usage dataset available from 8 institutions in manufacturing, education and medical institutions from the US and India, and an initial un-supervised machine learning based solution as a baseline for the community to accelerate research in this area.