More Web Proxy on the site http://driver.im/

research-article

Open access

PFDRL: Personalized Federated Deep Reinforcement Learning for Residential Energy Management

Authors:

Fateme Nikseresht,

Viswajith Govinda Rajan,

Bradford CampbellAuthors Info & Claims

ICPP '23: Proceedings of the 52nd International Conference on Parallel Processing

Pages 402 - 411

https://doi.org/10.1145/3605573.3605641

Published: 13 September 2023 Publication History

All formats PDF

Abstract

The rise of the Internet of Things (IoT) has increased standby energy consumption due to the growing number of smart devices in homes. Existing approaches use real-time energy data and machine learning to identify and minimize standby energy for residential energy management but rely on cloud-based data aggregation and collaborative training due to limited edge device data. However, such an approach incurs extra cloud service costs, risks personal data leakage, and fails to capture residence diversity, resulting in suboptimal energy management performance.

In this paper, we propose a privacy-preserving and cloud-service-free residential energy management system (EMS) that utilizes personalized federated deep reinforcement learning (PFDRL) to reduce household standby energy consumption. PFDRL consists of three components: First, we develop a decentralized federated learning (DFL) framework instead of using a centralized cloud service to aggregate the model to keep both the data and the model in the local area. Second, we apply DFL with deep reinforcement learning (DRL) to share the EMS plan among local residences for collaborative training. Third, we divide the neural network in the DRL into two parts, base layers and personalization layers to enhance model convergence while maximizing EMS performance for each client in the system. We evaluate the proposed PFDRL framework on the real-world Pecan Street dataset [3], demonstrating superior performance compared to centralized settings and conventional solutions.

References

[1]

2020. Energy Information Administration. https://www.eia.gov/ (2020).

[2]

2020. Texas Electricity Rates. https://comparepower.com (2020).

[3]

2021. Dataport Database. https://dataport.pecanstreet.org.

[4]

2021. Help Net Security.https://www.helpnetsecurity.com (2021).

[5]

U. Aivodji. 2019. IOTFLA: A secured and privacy-preserving smart home architecture implementing federated learning. In SPW.

[6]

M. Al Faruque and K. Vata. 2015. Energy management-as-a-service over fog computing platform. IEEE internet of things journal (2015).

[7]

Lijuan Cao. 2003. Support vector machines experts for time series forecasting. Neurocomputing 51 (2003), 321–339.

[8]

G. Din, A. Mauthe, and A. Marnerides. 2018. Appliance-level short-term load forecasting using deep neural networks. In ICCNC.

[9]

Ali Fallah and Aryan Mokhtari. 2020. Personalized federated learning: A meta-learning approach. arXiv preprint arXiv:2002.07948 (2020).

[10]

Jiechao Gao, Mingyue Tang, Tianhao Wang, and Bradford Campbell. 2022. PFed-LDP: A Personalized Federated Local Differential Privacy Framework for IoT Sensing Data. In Sensys.

[11]

Jiechao Gao, Wenpeng Wang, Zetian Liu, Md Fazlay Rabbi Masum Billah, and Bradford Campbell. 2021. Decentralized federated learning framework for the neighborhood: a case study on residential building load forecasting. In Sensys.

[12]

Jonas Geiping and Hartmut Bauermeister. 2020. Inverting gradients-how easy is it to break privacy in federated learning?NeurIPS (2020).

[13]

K Gram-Hanssen. 2010. Standby consumption in households analyzed with a practice theory approach. Journal of Industrial Ecology (2010).

[14]

J. Haj-Yahya. 2020. Techniques for Reducing the Connected-Standby Energy Consumption of Mobile Devices. In 2020 IEEE HPCA.

[15]

Yaochen Hu and Di Niu. 2019. FDML: A collaborative machine learning framework for distributed features. In Proceedings of the 25th SIGKDD.

Digital Library

[16]

W. Kong. 2017. Short-term residential load forecasting based on LSTM recurrent neural network. IEEE TSG (2017).

[17]

[17] Lawrence Berkeley Laboratory. 2008. https://standby.lbl.gov/docs/.

[18]

S. Lee. 2020. Federated reinforcement learning for energy management of multiple smart homes with distributed energy resources. IEEE TII.

[19]

M. Lu and J. Lai. 2020. Review on carbon emissions of commercial buildings. Renewable and Sustainable Energy Reviews (2020).

[20]

R Lu. 2019. Demand response for home energy management using reinforcement learning and artificial neural network. TSG.

[21]

X. Luo. 2019. Development of an IoT-based big data platform for day-ahead prediction of building heating and cooling demands. AEI.

[22]

Gregory P Meyer. 2021. An alternative probabilistic interpretation of the Huber loss. In Proceedings of the IEEE/CVF CVPR.

[23]

Yusuf Ozturk and Prakash Jha. 2013. A personalized home energy management system for residential demand response. In 4th ICPEEED.

[24]

P Raj, M Sudhakaran, P Philomen-D-Anand Raj, 2009. Estimation of standby power consumption for typical appliances. JESTR (2009).

[25]

M. Soliman and T. Abiodun. 2013. Smart home: Integrating internet of things with web services and cloud computing. In IEEE ICCCTS.

[26]

Idil Sülo and Theodore Brown. 2019. Energy efficient smart buildings: LSTM neural networks for time series prediction. In Deep-ML.

[27]

Afaf Taïk and Soumaya Cherkaoui. 2020. Electrical load forecasting using edge computing and federated learning. In ICC. IEEE.

[28]

Lin Wang. 2015. Back propagation neural network with adaptive differential evolution algorithm for time series forecasting. ESWA.

[29]

S. Wang, T. Tuor, and T. Salonidis. 2019. Adaptive Federated Learning in Resource Constrained Edge Computing Systems. IEEE JSAC (2019).

[30]

W Wang, J Su, Za Hicks, and Bradford Campbell. 2020. The Standby Energy of Smart Devices: Problems, Progress, & Potential. In IoTDI.

[31]

Q Wu and X Chen. 2020. FedHome: Cloud-Edge based Personalized Federated Learning for In-Home Health Monitoring. TMC (2020).

[32]

W Xu. 2019. A hybrid modeling method for time series forecasting based on a linear regression model and deep learning. AI (2019).

[33]

Xu Xu and Youwei Jia. 2020. A multi-agent reinforcement learning-based data-driven method for home energy management. TSG (2020).

[34]

L. Yang, X. Chen, J. Zhang, and H. Poor. 2014. Optimal privacy-preserving energy management for smart meters. In IEEE INFOCOM.

Cited By

Yao DZhu ZLiu TXu ZJin H(2024)Rethinking Personalized Federated Learning from Knowledge PerspectiveProceedings of the 53rd International Conference on Parallel Processing10.1145/3673038.3673112(991-1000)Online publication date: 12-Aug-2024
https://dl.acm.org/doi/10.1145/3673038.3673112

Recommendations

A review of reinforcement learning for autonomous building energy management
Abstract
The area of building energy management has received a significant amount of interest in recent years. This area is concerned with combining advancements in sensor technologies, communications and advanced control algorithms to optimize ...
From the Perspective of Prototypes: A Privacy-Preserving Personalized Federated Learning Framework
Information Security Practice and Experience
Abstract
Federated learning, as a collaborative learning approach that protects user privacy, has garnered significant attention from researchers in recent years. However, traditional federated learning paradigm generally suffers from two major limitations:...
Memory-based optimization methods for model-agnostic meta-learning and personalized federated learning

In recent years, model-agnostic meta-learning (MAML) has become a popular research area. However, the stochastic optimization of MAML is still underdeveloped. Existing MAML algorithms rely on the "episode" idea by sampling a few tasks and data points to ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICPP '23: Proceedings of the 52nd International Conference on Parallel Processing

August 2023

858 pages

ISBN:9798400708435

DOI:10.1145/3605573

Copyright © 2023 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 September 2023

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

NobleReach
Commonwealth Cyber Initiative
NSF (National Science Foundation)

Conference

ICPP 2023

ICPP 2023: 52nd International Conference on Parallel Processing

August 7 - 10, 2023

UT, Salt Lake City, USA

Acceptance Rates

Overall Acceptance Rate 91 of 313 submissions, 29%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
734
Total Downloads

Downloads (Last 12 months)597
Downloads (Last 6 weeks)117

Reflects downloads up to 11 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Yao DZhu ZLiu TXu ZJin H(2024)Rethinking Personalized Federated Learning from Knowledge PerspectiveProceedings of the 53rd International Conference on Parallel Processing10.1145/3673038.3673112(991-1000)Online publication date: 12-Aug-2024
https://dl.acm.org/doi/10.1145/3673038.3673112

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents