Enhancing energy consumption prediction in smart homes: a convergence-aware federated transfer learning approach

Achieving accurate energy consumption prediction can be challenging, particularly in residential buildings, which experience highly variable consumption behavior due to changes in occupants and the construction of new buildings. This variability, combined with the potential for privacy breaches thro...

Full description

Saved in:
Bibliographic Details
Main Authors: Rizwan Atif, Khan Anam Nawaz, Ahmad Rashid, Hassan Hassan Zohair, Atteia Ghada, Alkanhel Reem, Samee Nagwan Abdel
Format: Article
Language:English
Published: EDP Sciences 2024-01-01
Series:Science and Technology for Energy Transition
Subjects:
Online Access:https://www.stet-review.org/articles/stet/full_html/2024/01/stet20240177/stet20240177.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846173798072582144
author Rizwan Atif
Khan Anam Nawaz
Ahmad Rashid
Hassan Hassan Zohair
Atteia Ghada
Alkanhel Reem
Samee Nagwan Abdel
author_facet Rizwan Atif
Khan Anam Nawaz
Ahmad Rashid
Hassan Hassan Zohair
Atteia Ghada
Alkanhel Reem
Samee Nagwan Abdel
author_sort Rizwan Atif
collection DOAJ
description Achieving accurate energy consumption prediction can be challenging, particularly in residential buildings, which experience highly variable consumption behavior due to changes in occupants and the construction of new buildings. This variability, combined with the potential for privacy breaches through conventional data collection methods, underscores the need for novel approaches to energy consumption forecasting. The proposed study suggests a new approach to predict energy consumption, utilizing Federated Learning (FL) to train a global model while ensuring local data privacy and transferring knowledge from information-rich to information-poor buildings. The proposed method learns the transferable knowledge from the source building without any privacy leakage and utilizes it for target buildings. Since the performance of the global model could be negatively affected by some participating nodes with poor performance due to noisy or limited data, we propose a client selection strategy on the server based on the normal distribution for choosing the best possible participants for the global model. Our method enables clients to participate selectively in the aggregation procedure to avoid model divergence due to poor performance. The proposed model is evaluated and conducts in-depth analyses of energy consumption patterns. We validate the performance by comparing its Mean Absolute Error (MAE), Mean Square Error (MSE), and R2 values to those of existing traditional and ensemble models. Our findings indicate that the proposed FL-based model with selective client participation outperforms its counterpart methods regarding predictive accuracy and robustness. The source code is available on GitHub (https://github.com/atifrizwan1/TFL-PP).
format Article
id doaj-art-16f1db55ee8143479730a1118aa73328
institution Kabale University
issn 2804-7699
language English
publishDate 2024-01-01
publisher EDP Sciences
record_format Article
series Science and Technology for Energy Transition
spelling doaj-art-16f1db55ee8143479730a1118aa733282024-11-08T09:35:40ZengEDP SciencesScience and Technology for Energy Transition2804-76992024-01-01798510.2516/stet/2024060stet20240177Enhancing energy consumption prediction in smart homes: a convergence-aware federated transfer learning approachRizwan Atif0https://orcid.org/0000-0001-6669-8147Khan Anam Nawaz1Ahmad Rashid2https://orcid.org/0000-0001-6922-7412Hassan Hassan Zohair3Atteia Ghada4https://orcid.org/0000-0002-5462-595XAlkanhel Reem5Samee Nagwan Abdel6Department of Electronic Engineering, Kyung Hee UniversityDepartment of Computer Engineering, Jeju National UniversityFaculty of Computing and IT, Sohar UniversityDepartment of Mechanical Engineering, College of Engineering, Alfaisal UniversityDepartment of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman UniversityDepartment of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman UniversityDepartment of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman UniversityAchieving accurate energy consumption prediction can be challenging, particularly in residential buildings, which experience highly variable consumption behavior due to changes in occupants and the construction of new buildings. This variability, combined with the potential for privacy breaches through conventional data collection methods, underscores the need for novel approaches to energy consumption forecasting. The proposed study suggests a new approach to predict energy consumption, utilizing Federated Learning (FL) to train a global model while ensuring local data privacy and transferring knowledge from information-rich to information-poor buildings. The proposed method learns the transferable knowledge from the source building without any privacy leakage and utilizes it for target buildings. Since the performance of the global model could be negatively affected by some participating nodes with poor performance due to noisy or limited data, we propose a client selection strategy on the server based on the normal distribution for choosing the best possible participants for the global model. Our method enables clients to participate selectively in the aggregation procedure to avoid model divergence due to poor performance. The proposed model is evaluated and conducts in-depth analyses of energy consumption patterns. We validate the performance by comparing its Mean Absolute Error (MAE), Mean Square Error (MSE), and R2 values to those of existing traditional and ensemble models. Our findings indicate that the proposed FL-based model with selective client participation outperforms its counterpart methods regarding predictive accuracy and robustness. The source code is available on GitHub (https://github.com/atifrizwan1/TFL-PP).https://www.stet-review.org/articles/stet/full_html/2024/01/stet20240177/stet20240177.htmlfederated learningenergy consumption forecastingenergy managementsmart buildingspartial client participation
spellingShingle Rizwan Atif
Khan Anam Nawaz
Ahmad Rashid
Hassan Hassan Zohair
Atteia Ghada
Alkanhel Reem
Samee Nagwan Abdel
Enhancing energy consumption prediction in smart homes: a convergence-aware federated transfer learning approach
Science and Technology for Energy Transition
federated learning
energy consumption forecasting
energy management
smart buildings
partial client participation
title Enhancing energy consumption prediction in smart homes: a convergence-aware federated transfer learning approach
title_full Enhancing energy consumption prediction in smart homes: a convergence-aware federated transfer learning approach
title_fullStr Enhancing energy consumption prediction in smart homes: a convergence-aware federated transfer learning approach
title_full_unstemmed Enhancing energy consumption prediction in smart homes: a convergence-aware federated transfer learning approach
title_short Enhancing energy consumption prediction in smart homes: a convergence-aware federated transfer learning approach
title_sort enhancing energy consumption prediction in smart homes a convergence aware federated transfer learning approach
topic federated learning
energy consumption forecasting
energy management
smart buildings
partial client participation
url https://www.stet-review.org/articles/stet/full_html/2024/01/stet20240177/stet20240177.html
work_keys_str_mv AT rizwanatif enhancingenergyconsumptionpredictioninsmarthomesaconvergenceawarefederatedtransferlearningapproach
AT khananamnawaz enhancingenergyconsumptionpredictioninsmarthomesaconvergenceawarefederatedtransferlearningapproach
AT ahmadrashid enhancingenergyconsumptionpredictioninsmarthomesaconvergenceawarefederatedtransferlearningapproach
AT hassanhassanzohair enhancingenergyconsumptionpredictioninsmarthomesaconvergenceawarefederatedtransferlearningapproach
AT atteiaghada enhancingenergyconsumptionpredictioninsmarthomesaconvergenceawarefederatedtransferlearningapproach
AT alkanhelreem enhancingenergyconsumptionpredictioninsmarthomesaconvergenceawarefederatedtransferlearningapproach
AT sameenagwanabdel enhancingenergyconsumptionpredictioninsmarthomesaconvergenceawarefederatedtransferlearningapproach