Data Driven Disaggregation Method for Electricity Based Energy Consumption for Smart Homes

Sustainable energy systems must be capable of ensuring sustainable development by providing affordable and reliable energy to consumers. Hence, knowledge and understanding of energy consumption in the residential sector are indispensable for energy preservation and energy efficiency which can only b...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2022-12, Vol.2385 (1), p.12006
Main Authors: Hussain, Asad, Cimaglia, Jacopo, Romano, Sabrina, Mancini, Francesco, Re, Valerio
Format: Article
Language:English
Subjects:
Algorithms
Datasets
Electricity meters
Energy consumption
Energy efficiency
Experimentation
Monitoring
Physics
Residential energy
Smart buildings
Sustainable development
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Sustainable energy systems must be capable of ensuring sustainable development by providing affordable and reliable energy to consumers. Hence, knowledge and understanding of energy consumption in the residential sector are indispensable for energy preservation and energy efficiency which can only be possible with the help of consumer participation. New energy efficiency methods are developed due to the global adoption of smart meters that monitor and communicate residential energy consumption. Moreover, energy monitoring of each appliance is not feasible, as it is a costly solution. Therefore, energy consumption disaggregation is an answer for cost-cutting and energy saving. Contrary to the non-intrusive load monitoring (NILM) approaches, which are based on high-frequency power signals, we propose a data-driven algorithm that requires only a time-series energy meter dataset, a few appliances’ data, and energy consumption data from a consumer-based online questionnaire. Afterward, the proposed algorithm disaggregates whole house energy consumption into nine different energy consumption sectors such as lighting, kitchen, cooling, heating, etc. The energy consumption disaggregation algorithm is applied to datasets of 10 homes under experimentation. One of the homes provides us with the knowledge of 96.8% energy consumption, where only 28% knowledge is reported by monitoring plugs and 68% knowledge obtained by unmonitored means. Finally, the energy consumption obtained by the algorithm is compared with actual energy consumption, which shows the excellent functioning of the developed method.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2385/1/012006