Multi-Timescale Energy Consumption Management in Smart Buildings Using Hybrid Deep Artificial Neural Networks

Demand side management is a critical issue in the energy sector. Recent events such as the global energy crisis, costs, the necessity to reduce greenhouse emissions, and extreme weather conditions have increased the need for energy efficiency. Thus, accurately predicting energy consumption is one of...

Full description

Saved in:
Bibliographic Details
Main Authors: Favour Ibude, Abayomi Otebolaku, Jude E. Ameh, Augustine Ikpehai
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Journal of Low Power Electronics and Applications
Subjects:
Online Access:https://www.mdpi.com/2079-9268/14/4/54
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850241042096324608
author Favour Ibude
Abayomi Otebolaku
Jude E. Ameh
Augustine Ikpehai
author_facet Favour Ibude
Abayomi Otebolaku
Jude E. Ameh
Augustine Ikpehai
author_sort Favour Ibude
collection DOAJ
description Demand side management is a critical issue in the energy sector. Recent events such as the global energy crisis, costs, the necessity to reduce greenhouse emissions, and extreme weather conditions have increased the need for energy efficiency. Thus, accurately predicting energy consumption is one of the key steps in addressing inefficiency in energy consumption and its optimization. In this regard, accurate predictions on a daily, hourly, and minute-by-minute basis would not only minimize wastage but would also help to save costs. In this article, we propose intelligent models using ensembles of convolutional neural network (CNN), long-short-term memory (LSTM), bi-directional LSTM and gated recurrent units (GRUs) neural network models for daily, hourly, and minute-by-minute predictions of energy consumptions in smart buildings. The proposed models outperform state-of-the-art deep neural network models for predicting minute-by-minute energy consumption, with a mean square error of 0.109. The evaluated hybrid models also capture more latent trends in the data than traditional single models. The results highlight the potential of using hybrid deep learning models for improved energy efficiency management in smart buildings.
format Article
id doaj-art-b83f032a2dc74f2daf26b5f7425a084a
institution OA Journals
issn 2079-9268
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Journal of Low Power Electronics and Applications
spelling doaj-art-b83f032a2dc74f2daf26b5f7425a084a2025-08-20T02:00:42ZengMDPI AGJournal of Low Power Electronics and Applications2079-92682024-11-011445410.3390/jlpea14040054Multi-Timescale Energy Consumption Management in Smart Buildings Using Hybrid Deep Artificial Neural NetworksFavour Ibude0Abayomi Otebolaku1Jude E. Ameh2Augustine Ikpehai3School of Computing and Digital Technologies, Sheffield Hallam University, Sheffield S1 2NU, UKSchool of Computing and Digital Technologies, Sheffield Hallam University, Sheffield S1 2NU, UKSchool of Computing and Digital Technologies, Sheffield Hallam University, Sheffield S1 2NU, UKSchool of Engineering and Built Environment, Sheffield Hallam University, Sheffield S1 2LX, UKDemand side management is a critical issue in the energy sector. Recent events such as the global energy crisis, costs, the necessity to reduce greenhouse emissions, and extreme weather conditions have increased the need for energy efficiency. Thus, accurately predicting energy consumption is one of the key steps in addressing inefficiency in energy consumption and its optimization. In this regard, accurate predictions on a daily, hourly, and minute-by-minute basis would not only minimize wastage but would also help to save costs. In this article, we propose intelligent models using ensembles of convolutional neural network (CNN), long-short-term memory (LSTM), bi-directional LSTM and gated recurrent units (GRUs) neural network models for daily, hourly, and minute-by-minute predictions of energy consumptions in smart buildings. The proposed models outperform state-of-the-art deep neural network models for predicting minute-by-minute energy consumption, with a mean square error of 0.109. The evaluated hybrid models also capture more latent trends in the data than traditional single models. The results highlight the potential of using hybrid deep learning models for improved energy efficiency management in smart buildings.https://www.mdpi.com/2079-9268/14/4/54smart buildingsenergy consumptionhybrid deep learningenergy forecastingbuilding energy management systems
spellingShingle Favour Ibude
Abayomi Otebolaku
Jude E. Ameh
Augustine Ikpehai
Multi-Timescale Energy Consumption Management in Smart Buildings Using Hybrid Deep Artificial Neural Networks
Journal of Low Power Electronics and Applications
smart buildings
energy consumption
hybrid deep learning
energy forecasting
building energy management systems
title Multi-Timescale Energy Consumption Management in Smart Buildings Using Hybrid Deep Artificial Neural Networks
title_full Multi-Timescale Energy Consumption Management in Smart Buildings Using Hybrid Deep Artificial Neural Networks
title_fullStr Multi-Timescale Energy Consumption Management in Smart Buildings Using Hybrid Deep Artificial Neural Networks
title_full_unstemmed Multi-Timescale Energy Consumption Management in Smart Buildings Using Hybrid Deep Artificial Neural Networks
title_short Multi-Timescale Energy Consumption Management in Smart Buildings Using Hybrid Deep Artificial Neural Networks
title_sort multi timescale energy consumption management in smart buildings using hybrid deep artificial neural networks
topic smart buildings
energy consumption
hybrid deep learning
energy forecasting
building energy management systems
url https://www.mdpi.com/2079-9268/14/4/54
work_keys_str_mv AT favouribude multitimescaleenergyconsumptionmanagementinsmartbuildingsusinghybriddeepartificialneuralnetworks
AT abayomiotebolaku multitimescaleenergyconsumptionmanagementinsmartbuildingsusinghybriddeepartificialneuralnetworks
AT judeeameh multitimescaleenergyconsumptionmanagementinsmartbuildingsusinghybriddeepartificialneuralnetworks
AT augustineikpehai multitimescaleenergyconsumptionmanagementinsmartbuildingsusinghybriddeepartificialneuralnetworks