DeviceScope: An Interactive App to Detect and Localize Appliance Patterns in Electricity Consumption Time Series

TL;DR

DeviceScope is an interactive tool that helps non-expert users understand electricity consumption data by detecting and localizing appliance patterns using a novel weakly supervised learning approach, CamAL.

Contribution

The paper introduces DeviceScope and CamAL, a new weakly supervised method for appliance localization in smart meter data, requiring minimal labeled data.

Findings

Effective detection and localization of appliances in aggregated data

Reduces need for expensive ground-truth labels

Facilitates user understanding of electricity consumption patterns

Abstract

In recent years, electricity suppliers have installed millions of smart meters worldwide to improve the management of the smart grid system. These meters collect a large amount of electrical consumption data to produce valuable information to help consumers reduce their electricity footprint. However, having non-expert users (e.g., consumers or sales advisors) understand these data and derive usage patterns for different appliances has become a significant challenge for electricity suppliers because these data record the aggregated behavior of all appliances. At the same time, ground-truth labels (which could train appliance detection and localization models) are expensive to collect and extremely scarce in practice. This paper introduces DeviceScope, an interactive tool designed to facilitate understanding smart meter data by detecting and localizing individual appliance patterns within a given time period. Our system is based on CamAL (Class Activation Map-based Appliance Localization), a novel weakly supervised approach for appliance localization that only requires the knowledge of the existence of an appliance in a household to be trained. This paper appeared in ICDE 2025.