Smart random neural network controller for HVAC using cloud computing technology

A. Javed, H. Larijani, A. Ahmadinia, D. Gibson

Research output: Contribution to journalArticle

7 Downloads (Pure)

Abstract

Smart homes reduce human intervention in controlling the heating ventilation and air conditioning (HVAC) systems for maintaining a comfortable indoor environment. The embedded intelligence in the sensor nodes is limited due to the limited processing power and memory in the sensor node. Cloud computing has become increasingly popular due to its capability of providing computer utilities as internet services. In this study, a model for the intelligent controller by integrating internet of things (IoT) with cloud computing and web services is proposed. The wireless sensor nodes for monitoring the indoor environment and HVAC inlet air, and wireless base station for controlling the actuators of HVAC have been developed. The sensor nodes and base station communicate through RF transceivers at 915 MHz. Random neural network (RNN) models are used for estimating the number of occupants, and for estimating the predicted-mean-vote-based setpoints for controlling the heating, ventilation, and cooling of the building. Three test cases are studied (Case 1-Data storage and implementation of RNN models on the cloud, Case 2-RNN models implementation on base station, Case 3-Distributed implementation of RNN models on sensor nodes and base stations) for determining the best architecture in terms of power consumption. The results have shown that by embedding the intelligence in the base station and sensor nodes (i.e., Case 3), the power consumption of the intelligent controller was 4.4% less than Case 1 and 19.23% less than Case 2.
Original languageEnglish
Pages (from-to)351-360
Number of pages10
JournalIEEE Transactions on Industrial Informatics
Volume13
Issue number1
DOIs
Publication statusPublished - 2 Aug 2016

Fingerprint

Cloud computing
Sensor nodes
Air conditioning
Ventilation
Base stations
Neural networks
Heating
Controllers
Electric power utilization
Data storage equipment
Air intakes
Transceivers
Web services
Actuators
Internet
Cooling
Monitoring
Processing

Keywords

  • HVAC
  • Internet of Things
  • Web services
  • artificial intelligence
  • cloud computing
  • control engineering computing
  • estimation theory
  • home automation
  • home computing
  • indoor environment
  • neurocontrollers
  • wireless sensor networks
  • HVAC inlet air
  • Internet of things
  • Internet services
  • IoT
  • RF transceivers
  • RNN
  • cloud computing technology
  • computer utilities
  • embedded intelligence
  • heating ventilation and air conditioning systems
  • indoor environment monitoring
  • intelligent controller
  • predicted-mean-vote-based setpoint estimation
  • smart homes
  • smart random neural network controller
  • wireless sensor nodes
  • Base stations
  • Cloud computing
  • Energy consumption
  • Memory
  • Neurons
  • Wireless sensor networks
  • Artificial intelligence
  • centralized control
  • decentralized control
  • evolutionary computation
  • intelligent systems
  • internet of things
  • networked control system
  • neural networks
  • temperature control

Cite this

@article{b07ea0f1d55c4207b6a4af6b89d5d45e,
title = "Smart random neural network controller for HVAC using cloud computing technology",
abstract = "Smart homes reduce human intervention in controlling the heating ventilation and air conditioning (HVAC) systems for maintaining a comfortable indoor environment. The embedded intelligence in the sensor nodes is limited due to the limited processing power and memory in the sensor node. Cloud computing has become increasingly popular due to its capability of providing computer utilities as internet services. In this study, a model for the intelligent controller by integrating internet of things (IoT) with cloud computing and web services is proposed. The wireless sensor nodes for monitoring the indoor environment and HVAC inlet air, and wireless base station for controlling the actuators of HVAC have been developed. The sensor nodes and base station communicate through RF transceivers at 915 MHz. Random neural network (RNN) models are used for estimating the number of occupants, and for estimating the predicted-mean-vote-based setpoints for controlling the heating, ventilation, and cooling of the building. Three test cases are studied (Case 1-Data storage and implementation of RNN models on the cloud, Case 2-RNN models implementation on base station, Case 3-Distributed implementation of RNN models on sensor nodes and base stations) for determining the best architecture in terms of power consumption. The results have shown that by embedding the intelligence in the base station and sensor nodes (i.e., Case 3), the power consumption of the intelligent controller was 4.4{\%} less than Case 1 and 19.23{\%} less than Case 2.",
keywords = "HVAC, Internet of Things, Web services, artificial intelligence, cloud computing, control engineering computing, estimation theory, home automation, home computing, indoor environment, neurocontrollers, wireless sensor networks, HVAC inlet air, Internet of things, Internet services, IoT, RF transceivers, RNN, cloud computing technology, computer utilities, embedded intelligence, heating ventilation and air conditioning systems, indoor environment monitoring, intelligent controller, predicted-mean-vote-based setpoint estimation, smart homes, smart random neural network controller, wireless sensor nodes, Base stations, Cloud computing, Energy consumption, Memory, Neurons, Wireless sensor networks, Artificial intelligence, centralized control, decentralized control, evolutionary computation, intelligent systems, internet of things, networked control system, neural networks, temperature control",
author = "A. Javed and H. Larijani and A. Ahmadinia and D. Gibson",
year = "2016",
month = "8",
day = "2",
doi = "10.1109/TII.2016.2597746",
language = "English",
volume = "13",
pages = "351--360",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "IEEE",
number = "1",

}

Smart random neural network controller for HVAC using cloud computing technology. / Javed, A.; Larijani, H.; Ahmadinia, A.; Gibson, D.

In: IEEE Transactions on Industrial Informatics, Vol. 13, No. 1, 02.08.2016, p. 351-360.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Smart random neural network controller for HVAC using cloud computing technology

AU - Javed, A.

AU - Larijani, H.

AU - Ahmadinia, A.

AU - Gibson, D.

PY - 2016/8/2

Y1 - 2016/8/2

N2 - Smart homes reduce human intervention in controlling the heating ventilation and air conditioning (HVAC) systems for maintaining a comfortable indoor environment. The embedded intelligence in the sensor nodes is limited due to the limited processing power and memory in the sensor node. Cloud computing has become increasingly popular due to its capability of providing computer utilities as internet services. In this study, a model for the intelligent controller by integrating internet of things (IoT) with cloud computing and web services is proposed. The wireless sensor nodes for monitoring the indoor environment and HVAC inlet air, and wireless base station for controlling the actuators of HVAC have been developed. The sensor nodes and base station communicate through RF transceivers at 915 MHz. Random neural network (RNN) models are used for estimating the number of occupants, and for estimating the predicted-mean-vote-based setpoints for controlling the heating, ventilation, and cooling of the building. Three test cases are studied (Case 1-Data storage and implementation of RNN models on the cloud, Case 2-RNN models implementation on base station, Case 3-Distributed implementation of RNN models on sensor nodes and base stations) for determining the best architecture in terms of power consumption. The results have shown that by embedding the intelligence in the base station and sensor nodes (i.e., Case 3), the power consumption of the intelligent controller was 4.4% less than Case 1 and 19.23% less than Case 2.

AB - Smart homes reduce human intervention in controlling the heating ventilation and air conditioning (HVAC) systems for maintaining a comfortable indoor environment. The embedded intelligence in the sensor nodes is limited due to the limited processing power and memory in the sensor node. Cloud computing has become increasingly popular due to its capability of providing computer utilities as internet services. In this study, a model for the intelligent controller by integrating internet of things (IoT) with cloud computing and web services is proposed. The wireless sensor nodes for monitoring the indoor environment and HVAC inlet air, and wireless base station for controlling the actuators of HVAC have been developed. The sensor nodes and base station communicate through RF transceivers at 915 MHz. Random neural network (RNN) models are used for estimating the number of occupants, and for estimating the predicted-mean-vote-based setpoints for controlling the heating, ventilation, and cooling of the building. Three test cases are studied (Case 1-Data storage and implementation of RNN models on the cloud, Case 2-RNN models implementation on base station, Case 3-Distributed implementation of RNN models on sensor nodes and base stations) for determining the best architecture in terms of power consumption. The results have shown that by embedding the intelligence in the base station and sensor nodes (i.e., Case 3), the power consumption of the intelligent controller was 4.4% less than Case 1 and 19.23% less than Case 2.

KW - HVAC

KW - Internet of Things

KW - Web services

KW - artificial intelligence

KW - cloud computing

KW - control engineering computing

KW - estimation theory

KW - home automation

KW - home computing

KW - indoor environment

KW - neurocontrollers

KW - wireless sensor networks

KW - HVAC inlet air

KW - Internet of things

KW - Internet services

KW - IoT

KW - RF transceivers

KW - RNN

KW - cloud computing technology

KW - computer utilities

KW - embedded intelligence

KW - heating ventilation and air conditioning systems

KW - indoor environment monitoring

KW - intelligent controller

KW - predicted-mean-vote-based setpoint estimation

KW - smart homes

KW - smart random neural network controller

KW - wireless sensor nodes

KW - Base stations

KW - Cloud computing

KW - Energy consumption

KW - Memory

KW - Neurons

KW - Wireless sensor networks

KW - Artificial intelligence

KW - centralized control

KW - decentralized control

KW - evolutionary computation

KW - intelligent systems

KW - internet of things

KW - networked control system

KW - neural networks

KW - temperature control

U2 - 10.1109/TII.2016.2597746

DO - 10.1109/TII.2016.2597746

M3 - Article

VL - 13

SP - 351

EP - 360

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

IS - 1

ER -