Skip to main content

Research Repository

Advanced Search

Genetic algorithm-determined deep feedforward neural network architecture for predicting electricity consumption in real buildings

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

Genetic algorithm-determined deep feedforward neural network architecture for predicting electricity consumption in real 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

Manuel Davila Delgado Manuel.Daviladelgado@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

A genetic algorithm-determined deep feedforward neural network architecture (GA-DFNN) is proposed for both day-ahead hourly and week-ahead daily electricity consumption of a real-world campus building in the United Kingdom. Due to the comprehensive relationship between affecting factors and real-world building electricity consumption, the adoption of multiple hidden layers in the deep neural network (DFNN) algorithm would improve its prediction accuracy. The architecture of a DFNN model mainly refers to its quantity of hidden layers, quantity of neurons in the hidden layers, activation function in each layer and learning process to obtain the connecting weights. The optimal architecture of DFNN model was generally determined through a trial-and-error process, which is an exponential combinatorial problem and a tedious task. To address this problem, genetic algorithm (GA) is adopted to automatically design an optimal architecture with improved generalization ability. One year and six months of measurement data from a campus building is used for training and testing the proposed GA-DFNN model, respectively. To demonstrate the effectiveness of the proposed GA-DFNN prediction model, its prediction performance, including mean absolute percentage error, coefficient of determination, root mean square error and mean absolute error, was compared to the reference feedforward neural network models with single hidden layer, DFNN models with other architecture, random search determined DFNN model, long-short-term-memory model and temporal convolutional network model. The comparison results show that the proposed GA-DFNN predictive model has superior performance than all the reference prediction models, demonstrating the optimization effectiveness of GA and the prediction effectiveness of DFNN model with multiple hidden layers and optimal architecture.

Journal Article Type Article
Acceptance Date Jun 27, 2020
Online Publication Date Jul 7, 2020
Publication Date Nov 1, 2020
Deposit Date Aug 3, 2020
Publicly Available Date Aug 4, 2020
Journal Energy and AI
Print ISSN 2666-5468
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 2
Article Number 100015
DOI https://doi.org/10.1016/j.egyai.2020.100015
Public URL https://uwe-repository.worktribe.com/output/6472760
Additional Information This article is maintained by: Elsevier; Article Title: Genetic algorithm-determined deep feedforward neural network architecture for predicting electricity consumption in real buildings; Journal Title: Energy and AI; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.egyai.2020.100015; Content Type: article; Copyright: © 2020 The Author(s). Published by Elsevier Ltd.

Files





You might also like



Downloadable Citations