Skip to main content

Research Repository

Advanced Search

Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings

Luo, X. J.; Oyedele, Lukumon O.; Ajayi, Anuoluwapo O.; Akinade, Olugbenga O.; Owolabi, Hakeem A.; Ahmed, Ashraf

Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings Thumbnail


Authors

Xiaojun Luo Xiaojun.Luo@uwe.ac.uk
Senior Lecturer in Financial Technology

Lukumon Oyedele L.Oyedele@uwe.ac.uk
Professor in Enterprise & Project Management

Anuoluwapo Ajayi Anuoluwapo.Ajayi@uwe.ac.uk
Associate Professor - Big Data Application

Olugbenga Akinade Olugbenga.Akinade@uwe.ac.uk
Associate Professor - AR/VR Development with Artificial Intelligence

Hakeem Owolabi Hakeem.Owolabi@uwe.ac.uk
Associate Professor - Project Analytics and Digital Enterprise

Ashraf Ahmed



Abstract

Accurate forecast of energy consumption is essential in building energy management. Owing to the variation of outdoor weather condition among different seasons, year-round historical weather profile is needed to investigate its feature thoroughly. Daily weather profiles in the historical database contain various features, while different architecture of deep neural network (DNN) models may be identified suitable for specific featuring training datasets. In this study, an integrated artificial intelligence-based approach, consisting of feature extraction, evolutionary optimization and adaptive DNN model, is proposed to forecast week-ahead hourly building energy consumption. The DNN is the fundamental forecasting engine of the proposed model. Feature extraction of daily weather profile is accomplished through clustering techniques. Genetic algorithm is adopted to determine the optimal architecture of each DNN sub-model. Namely, each featuring cluster of weather profile, along with corresponding time signature and building energy consumption, is adopted to train one DNN sub-model. Therefore, the structure, activation function and training approach of DNN sub-models are adaptive to diverse featuring datasets in each cluster. To evaluate the effectiveness of the proposed predictive model, it is implemented on a real office building in the United Kingdom. Mean absolute percentage error of the training and testing cases of the proposed predictive model is 2.87% and 6.12%, which has a 24.6% and 11.9% decrease compared to DNN model with a fixed architecture. With the latest weather forecast, the devised adaptive DNN model can provide accurate week-ahead hourly energy consumption prediction for building energy management system.

Journal Article Type Article
Acceptance Date Jun 8, 2020
Online Publication Date Jun 29, 2020
Publication Date Oct 1, 2020
Deposit Date Jun 30, 2020
Publicly Available Date Jun 30, 2021
Journal Renewable and Sustainable Energy Reviews
Print ISSN 1364-0321
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 131
Article Number 109980
DOI https://doi.org/10.1016/j.rser.2020.109980
Keywords Renewable energy, Sustainability and the environment, Data-driven model, Energy consumption prediction, Feature extraction, Clustering, Adaptive, Deep neural network, Genetic algorithm, Data-driven model
Public URL https://uwe-repository.worktribe.com/output/6134099
Additional Information This article is maintained by: Elsevier; Article Title: Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings; Journal Title: Renewable and Sustainable Energy Reviews; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.rser.2020.109980; Content Type: article; Copyright: © 2020 Elsevier Ltd. All rights reserved.

Files





You might also like



Downloadable Citations