File(s) under permanent embargo
FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers
conference contribution
posted on 2023-04-19, 06:11 authored by Muhammad Akbar HusnooMuhammad Akbar Husnoo, Adnan AnwarAdnan Anwar, Nasser Hosseinzadeh, Shama IslamShama Islam, AN Mahmood, Robin Ram Mohan DossRobin Ram Mohan DossAs Smart Meters are collecting and transmitting household energy consumption data to Retail Energy Providers (REP), the main challenge is to ensure the effective use of fine-grained consumer data while ensuring data privacy. In this manuscript, we tackle this challenge for energy load consumption forecasting in regards to REPs which is essential to energy demand management, load balancing and infrastructure planning. Specifically, we note that existing energy load forecasting is centralized, which are not scalable and most importantly, is vulnerable to data privacy threats. Besides, REPs are individual market participants and liable to ensure the privacy of their own customers. To address this issue, we propose a novel horizontal privacy-preserving federated learning framework for REPs energy load forecasting, namely FedREP. We consider a differential privacy-based federated learning system consisting of a control centre and multiple retailers by enabling multiple REPs to build a common, robust machine learning model without sharing data, thus addressing critical issues such as data privacy, data security and scalability. For forecasting, we use a state-of-The-Art Long Short-Term Memory (LSTM) neural network due to its ability to learn long term sequences of observations and promises of higher accuracy with time-series data while solving the vanishing gradient problem. Finally, we conduct extensive data-driven experiments using a real energy consumption dataset. Experimental results demonstrate that our proposed federated learning framework can achieve sufficient performance in terms of MSE ranging between 0.3 to 0.4 and is relatively similar to that of a centralized approach while preserves privacy and improves scalability.
History
Volume
2022-NovemberPagination
1-6Location
Melbourne, VictoriaPublisher DOI
Start date
2022-11-20End date
2022-11-23ISSN
2157-4839eISSN
2157-4847ISBN-13
9781665467384Language
engPublication classification
E1 Full written paper - refereedTitle of proceedings
APPEEC 2022 : Proceedings of the 14th Asia-Pacific Power and Energy Engineering ConferenceEvent
Asia-Pacific Power and Energy Engineering. Conference (2022 : 14th : Melbourne, Victoria)Publisher
IEEEPlace of publication
Piscataway, N.J.Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC