Smart City Gnosys

Smart city article details

Title	Federate Learning For Solar Power Forecasting In Smart Cities
ID_Doc	26314
Authors	Hassna A.-A.; Fatima M.; Abdellatif K.; Mohammed E.K.
Year	2024
Published	Proceedings - IEEE Global Communications Conference, GLOBECOM
DOI	http://dx.doi.org/10.1109/GLOBECOM52923.2024.10901217
Abstract	The integration of solar energy into smart grids introduces challenges for accurate power prediction due to the variability of solar resources and the distributed nature of generation systems. Federated learning offers a promising solution for collaborative model training without centralized data collection. However, its application in solar power prediction faces unique challenges, including data heterogeneity across different geographical regions and communication constraints in edge devices. In this work, we propose a federated learning framework that incorporates data normalization techniques and adaptive model aggregation strategies to address these challenges. We evaluate our approach using real-world solar power datasets and demonstrate its effectiveness in improving prediction accuracy while ensuring data privacy and reducing communication overhead. © 2024 IEEE.
Author Keywords	communication constraints; data heterogeneity; Federated learning; smart grids; solar power prediction

Similar Articles

Id	Similarity	Authors	Title	Published
26399	0.912	Al-Quraan M.; Khan A.; Centeno A.; Zoha A.; Imran M.A.; Mohjazi L.	Fedratrees: A Novel Computation-Communication Efficient Federated Learning Framework Investigated In Smart Grids	Engineering Applications of Artificial Intelligence, 124 (2023)
51169	0.897	Abdulla N.; Demirci M.; Ozdemir S.	Smart Meter-Based Energy Consumption Forecasting For Smart Cities Using Adaptive Federated Learning	Sustainable Energy, Grids and Networks, 38 (2024)
26366	0.883	Mendes N.; Moura P.; Mendes J.; Antunes C.H.; Mohammadi J.	Federated Learning Optimization For Energy Communities In Smart Cities	Proceedings of 2023 IEEE International Smart Cities Conference, ISC2 2023 (2023)
26320	0.867	Alzamil I.	Federated Deep Learning For Scalable And Explainable Load Forecasting In Privacy-Conscious Smart Cities	IEEE Access (2025)
43181	0.862	Zhang X.-Y.; Cordoba-Pachon J.-R.; Guo P.; Watkins C.; Kuenzel S.	Privacy-Preserving Federated Learning For Value-Added Service Model In Advanced Metering Infrastructure	IEEE Transactions on Computational Social Systems, 11, 1 (2024)
26322	0.856	Moayyed H.; Moradzadeh A.; Mohammadi-Ivatloo B.; Ghorbani R.	Federated Deep Learning Technique For Power And Energy Systems Data Analysis	Intelligent Data Mining and Analysis in Power and Energy Systems: Models and Applications for Smarter Efficient Power Systems (2022)
35079	0.852	Gargees R.S.	Leveraging Federated Learning For Weather Classification In The Era Of Smart Cities	2024 IEEE 3rd International Conference on Computing and Machine Intelligence, ICMI 2024 - Proceedings (2024)
22945	0.85	Dhanwanth B.; Dhanasakkaravarthi B.; Belshi J.V.G.; Mohanaprakash T.A.; Saranya S.; Naveen P.	Empowering Solar Energy With Advanced Iot-Based Forecasting: A Hybrid Deep Learning Model For Enhanced Efficiency With Big Data	International Conference on Sustainable Communication Networks and Application, ICSCNA 2023 - Proceedings (2023)