Deep Reinforcement Learning Algorithms in Intelligent Infrastructure
Intelligent infrastructure, including smart cities and intelligent buildings, must learn and adapt to the variable needs and requirements of users, owners and operators in order to be future proof and to provide a return on investment based on Operational Expenditure (OPEX) and Capital Expenditure (...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-08-01
|
Series: | Infrastructures |
Subjects: | |
Online Access: | https://www.mdpi.com/2412-3811/4/3/52 |
id |
doaj-0f478eb6856b45899b9e3fbd91134935 |
---|---|
record_format |
Article |
spelling |
doaj-0f478eb6856b45899b9e3fbd911349352020-11-25T02:09:31ZengMDPI AGInfrastructures2412-38112019-08-01435210.3390/infrastructures4030052infrastructures4030052Deep Reinforcement Learning Algorithms in Intelligent InfrastructureWill Serrano0Alumni Imperial College London, Intelligent Systems and Networks Group, Electrical and Electronic Engineering, South Kensington, London SW7 2AZ, UKIntelligent infrastructure, including smart cities and intelligent buildings, must learn and adapt to the variable needs and requirements of users, owners and operators in order to be future proof and to provide a return on investment based on Operational Expenditure (OPEX) and Capital Expenditure (CAPEX). To address this challenge, this article presents a biological algorithm based on neural networks and deep reinforcement learning that enables infrastructure to be intelligent by making predictions about its different variables. In addition, the proposed method makes decisions based on real time data. Intelligent infrastructure must be able to proactively monitor, protect and repair itself: this includes independent components and assets working the same way any autonomous biological organisms would. Neurons of artificial neural networks are associated with a prediction or decision layer based on a deep reinforcement learning algorithm that takes into consideration all of its previous learning. The proposed method was validated against an intelligent infrastructure dataset with outstanding results: the intelligent infrastructure was able to learn, predict and adapt to its variables, and components could make relevant decisions autonomously, emulating a living biological organism in which data flow exhaustively.https://www.mdpi.com/2412-3811/4/3/52deep reinforcement learningneural networksintelligent buildingsintelligent infrastructuresmart citiesbuilding information modelInternet of Things |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Will Serrano |
spellingShingle |
Will Serrano Deep Reinforcement Learning Algorithms in Intelligent Infrastructure Infrastructures deep reinforcement learning neural networks intelligent buildings intelligent infrastructure smart cities building information model Internet of Things |
author_facet |
Will Serrano |
author_sort |
Will Serrano |
title |
Deep Reinforcement Learning Algorithms in Intelligent Infrastructure |
title_short |
Deep Reinforcement Learning Algorithms in Intelligent Infrastructure |
title_full |
Deep Reinforcement Learning Algorithms in Intelligent Infrastructure |
title_fullStr |
Deep Reinforcement Learning Algorithms in Intelligent Infrastructure |
title_full_unstemmed |
Deep Reinforcement Learning Algorithms in Intelligent Infrastructure |
title_sort |
deep reinforcement learning algorithms in intelligent infrastructure |
publisher |
MDPI AG |
series |
Infrastructures |
issn |
2412-3811 |
publishDate |
2019-08-01 |
description |
Intelligent infrastructure, including smart cities and intelligent buildings, must learn and adapt to the variable needs and requirements of users, owners and operators in order to be future proof and to provide a return on investment based on Operational Expenditure (OPEX) and Capital Expenditure (CAPEX). To address this challenge, this article presents a biological algorithm based on neural networks and deep reinforcement learning that enables infrastructure to be intelligent by making predictions about its different variables. In addition, the proposed method makes decisions based on real time data. Intelligent infrastructure must be able to proactively monitor, protect and repair itself: this includes independent components and assets working the same way any autonomous biological organisms would. Neurons of artificial neural networks are associated with a prediction or decision layer based on a deep reinforcement learning algorithm that takes into consideration all of its previous learning. The proposed method was validated against an intelligent infrastructure dataset with outstanding results: the intelligent infrastructure was able to learn, predict and adapt to its variables, and components could make relevant decisions autonomously, emulating a living biological organism in which data flow exhaustively. |
topic |
deep reinforcement learning neural networks intelligent buildings intelligent infrastructure smart cities building information model Internet of Things |
url |
https://www.mdpi.com/2412-3811/4/3/52 |
work_keys_str_mv |
AT willserrano deepreinforcementlearningalgorithmsinintelligentinfrastructure |
_version_ |
1724923242402021376 |