Citation |
Favaro, A., Lowery, C. and Zhihan Xu WP1 Appliance Disaggregation: High Frequency Appliance Disaggregation Analysis Handover, ETI, 2018. https://doi.org/10.5286/UKERC.EDC.000636. Cite this using DataCite |
Author(s) |
Favaro, A., Lowery, C. and Zhihan Xu |
Project partner(s) |
Baringa Partners LLP |
Publisher |
ETI |
DOI |
https://doi.org/10.5286/UKERC.EDC.000636 |
Download |
AdHoc_SSH_SS9019_2.pdf |
Abstract |
The ETI commissioned the HEMS & ICT Market project to undertake an in depth study and assessment of HEMS along with what data, processes and controls andpotential additional services enabled via a linked ICT system. The project delivers key insights and findings in terms of potential future offerings and capabilities of these products along with market assessment information. The aim of the project was to characterise the existing market for HEMS and ICT systems and to quantify the market/commercial opportunities for future HEMS and ICT propositions for both consumer and business.
The High Frequency Appliance Disaggregation Analysis (HFADA) project builds upon work undertaken in the Smart Systems and Heat (SSH) programme delivered by the Energy Systems Catapult for the ETI, to refine intelligence and gain detailed smart home energy data. The project analysed in depth datafrom five homes that trialed the SSH programme’s Home Energy Management System (HEMS) to identify which appliances are present within a building and when they are in operation. The main goal of the HFADA project was to detect human behaviour patterns in order to forecast the home energy needs of people in the future. In particular the project delivered a detailed set of data mining algorithms to help identify patterns of building occupancy and energy use within domestic homes from water, gas and electricity data.
The ETI collected utility meter and other data (e.g. room temperatures, humidity, and HEMS control data) from five dwellings over a period of six months. Using the collected data, work was conducted to evaluate different machine learning algorithms, research appropriate data features and calibrations thereof, and test the “art of the possible”. Thework sought not only to understand historical human activity within the building, but also to estimate probabilities of future hot water usage, occupancy and heating needs.
The described work resulted in Baringa and ASI jointly developing several Python scripts and notebooks for ETI. This document sets out to explain the purpose of the various scripts and notebooks required to rerun the analysis, the relationship between the various files and explain how to run the code. The document starts with an overview of the workflow and code, before diving into a detailed description of each section of the workflow and the corresponding code. |
Associated Project(s) |
ETI-SS1403: Smart Systems and Heat (SSH) Programme - Home Energy Management System (HEMS) |
Associated Dataset(s) |
Home Energy Management System (HEMS) ICT Market Study - HEMS ICT Market Forecast Tool |
Associated Publication(s) |
ETI Insights Report - Domestic Energy Services Home Energy Management System (HEMS) ICT Market Study - Main Report Home Energy Management System (HEMS) ICT Market Study - Market Forecast Supplemental Report Home Energy Management System (HEMS) ICT Market Study - Request for proposals Infographic - Domestic Heat Infographic - How can people get the heat they want at home without carbon ? List of projects for the ETI Smart Systems and Heat (SSH) Programme SSH Stagegate 1 - Review of International Smart Systems and Heat Initiatives - Final Report WP1 Appliance Disaggregation: Data Analysis Pre-processing WP1 Appliance Disaggregation: Data Quality Report WP1 Appliance Disaggregation: Dynamic Modelling WP1 Appliance Disaggregation: Final Report WP1 Appliance Disaggregation: High Frequency Appliance Disaggregation Analysis: Insights Overview WP1 Appliance Disaggregation: Incorporation of Appliance and layout information WP1 Appliance Disaggregation: Online learning and distributed learning WP1 Appliance Disaggregation: Pattern Mining |
|