Analysis of novel random neural network controller for residential building temperature control

Abbas Javed, Hadi Larijani, Ali Ahmadinia, Rohinton Emmanuel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Random neural networks (RNN) have strong generalisation capabilities and are easy to implement on hardware as compared to Artificial Neural Networks (ANN). In this paper, a novel RNN controller is proposed to maintain a comfortable indoor environment in a single zone residential building fitted with radiators for heating. This controller is capable of maintaining a comfortable indoor environment on the basis of a predicted mean vote (PMV)-based set point. The implemented RNN controller is compared with ANN controller for energy consumption, indoor room temperature, and minimum square error. Results show that for same training data and learning algorithm parameters, RNN converges faster and it consumes less energy, results in better comfortable room temperature as compared to ANN controller.
Original languageEnglish
Title of host publicationENERGY 2014 : The Fourth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies
PublisherInternational Academy, Research, and Industry Association
Pages63-68
Number of pages6
ISBN (Electronic) 978-1-61208-332-2
Publication statusPublished - 24 Apr 2014

Fingerprint

Temperature control
Neural networks
Controllers
Radiators
Learning algorithms
Energy utilization
Hardware
Heating
Temperature

Keywords

  • random neural network
  • building temperature
  • indoor environment

Cite this

Javed, A., Larijani, H., Ahmadinia, A., & Emmanuel, R. (2014). Analysis of novel random neural network controller for residential building temperature control. In ENERGY 2014 : The Fourth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies (pp. 63-68). International Academy, Research, and Industry Association.
Javed, Abbas ; Larijani, Hadi ; Ahmadinia, Ali ; Emmanuel, Rohinton. / Analysis of novel random neural network controller for residential building temperature control. ENERGY 2014 : The Fourth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. International Academy, Research, and Industry Association, 2014. pp. 63-68
@inproceedings{edc0ba86f1f142158d1267341209f436,
title = "Analysis of novel random neural network controller for residential building temperature control",
abstract = "Random neural networks (RNN) have strong generalisation capabilities and are easy to implement on hardware as compared to Artificial Neural Networks (ANN). In this paper, a novel RNN controller is proposed to maintain a comfortable indoor environment in a single zone residential building fitted with radiators for heating. This controller is capable of maintaining a comfortable indoor environment on the basis of a predicted mean vote (PMV)-based set point. The implemented RNN controller is compared with ANN controller for energy consumption, indoor room temperature, and minimum square error. Results show that for same training data and learning algorithm parameters, RNN converges faster and it consumes less energy, results in better comfortable room temperature as compared to ANN controller.",
keywords = "random neural network, building temperature, indoor environment",
author = "Abbas Javed and Hadi Larijani and Ali Ahmadinia and Rohinton Emmanuel",
year = "2014",
month = "4",
day = "24",
language = "English",
pages = "63--68",
booktitle = "ENERGY 2014 : The Fourth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies",
publisher = "International Academy, Research, and Industry Association",

}

Javed, A, Larijani, H, Ahmadinia, A & Emmanuel, R 2014, Analysis of novel random neural network controller for residential building temperature control. in ENERGY 2014 : The Fourth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. International Academy, Research, and Industry Association, pp. 63-68.

Analysis of novel random neural network controller for residential building temperature control. / Javed, Abbas; Larijani, Hadi; Ahmadinia, Ali; Emmanuel, Rohinton.

ENERGY 2014 : The Fourth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. International Academy, Research, and Industry Association, 2014. p. 63-68.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Analysis of novel random neural network controller for residential building temperature control

AU - Javed, Abbas

AU - Larijani, Hadi

AU - Ahmadinia, Ali

AU - Emmanuel, Rohinton

PY - 2014/4/24

Y1 - 2014/4/24

N2 - Random neural networks (RNN) have strong generalisation capabilities and are easy to implement on hardware as compared to Artificial Neural Networks (ANN). In this paper, a novel RNN controller is proposed to maintain a comfortable indoor environment in a single zone residential building fitted with radiators for heating. This controller is capable of maintaining a comfortable indoor environment on the basis of a predicted mean vote (PMV)-based set point. The implemented RNN controller is compared with ANN controller for energy consumption, indoor room temperature, and minimum square error. Results show that for same training data and learning algorithm parameters, RNN converges faster and it consumes less energy, results in better comfortable room temperature as compared to ANN controller.

AB - Random neural networks (RNN) have strong generalisation capabilities and are easy to implement on hardware as compared to Artificial Neural Networks (ANN). In this paper, a novel RNN controller is proposed to maintain a comfortable indoor environment in a single zone residential building fitted with radiators for heating. This controller is capable of maintaining a comfortable indoor environment on the basis of a predicted mean vote (PMV)-based set point. The implemented RNN controller is compared with ANN controller for energy consumption, indoor room temperature, and minimum square error. Results show that for same training data and learning algorithm parameters, RNN converges faster and it consumes less energy, results in better comfortable room temperature as compared to ANN controller.

KW - random neural network

KW - building temperature

KW - indoor environment

M3 - Conference contribution

SP - 63

EP - 68

BT - ENERGY 2014 : The Fourth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies

PB - International Academy, Research, and Industry Association

ER -

Javed A, Larijani H, Ahmadinia A, Emmanuel R. Analysis of novel random neural network controller for residential building temperature control. In ENERGY 2014 : The Fourth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. International Academy, Research, and Industry Association. 2014. p. 63-68