Smart City Gnosys
Smart city article details
| Title | Multi-Stage Federated Learning Mechanism With Non-Iid Data In Internet Of Vehicles; [面向非独立同分布数据的车联网多阶段联邦学习机制] |
|---|---|
| ID_Doc | 38417 |
| Authors | Tang X.; Liang Y.; Chen W. |
| Year | 2024 |
| Published | Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 61, 9 |
| DOI | http://dx.doi.org/10.7544/issn1000-1239.202330885 |
| Abstract | The Internet of vehicles (IoV) plays an indispensable role in the construction of smart cities, where cars are not just a means of transportation but also a crucial medium for information collection and transmission in the era of big data. With the rapid growth in the volume of data collected from vehicles and the increased awareness of privacy protection, ensuring users’ data security and preventing data breaches in IoV have become an urgent issue to address. Federated learning, as a “data-does-not-move, model-moves” approach, offers a feasible method for protecting user privacy while achieving excellent performance. However, because of the differences of devices, regions and individual habits, data collected from multiple vehicle typically exhibit non-independent and identically distributed (non-IID) characteristics. Traditional federated learning algorithms have slow model convergence when processing non-IID data. In response to this challenge, we propose a multi-stage federated learning algorithm with non-IID data in IoV, named FedWO. In Stage 1, FedWO utilizes the federated averaging algorithm to expedite the global model in reaching a basic level of accuracy. In Stage 2, FedWO employs weighted federated learning, where the weight of a vehicle in the global model is calculated based on its data characteristics. This aggregation results in an improved global model. Moreover, we design a transmission control strategy to reduce communication overhead caused by model transmission. The Stage 3 involves personalized computation, where each vehicle employs its own data for personalized learning, fine-tuning the local model to obtain a model more aligned with local data. We conducted experimental evaluations using a driving behavior dataset. The results demonstrate that, compared with traditional methods, FedWO preserves data privacy while improving the accuracy of algorithms in non-IID data scenarios. © 2024 Science Press. All rights reserved. |
| Author Keywords | federated learning (FL); Internet of vehicles (IoV); non-IID data; privacy preserving; transmission control |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
42595  | 0.874 | Soares K.; Shinde A.A.; Patil M. | Ppfedsl: Privacy Preserving Split And Federated Learning Enabled Secure Data Sharing Model For Internet Of Vehicles In Smart City | International Journal of Computer Networks and Applications, 12, 2 (2025) |
| 26371 | 0.874 | Rani P.; Sharma C.; Ramesh J.V.N.; Verma S.; Sharma R.; Alkhayyat A.; Kumar S. | Federated Learning-Based Misbehavior Detection For The 5G-Enabled Internet Of Vehicles | IEEE Transactions on Consumer Electronics, 70, 2 (2024) |
| 1664 | 0.867 | Khatua S.; De D.; Maji S.; Maity S.; Nielsen I.E. | A Federated Learning Model For Integrating Sustainable Routing With The Internet Of Vehicular Things Using Genetic Algorithm | Decision Analytics Journal, 11 (2024) |
| 43124 | 0.866 | Naresh V.S.; Ayaaappa D. | Privacy Preserving Hierarchical Federated Learning Approach For Secure Urban Mobility Prediction | Peer-to-Peer Networking and Applications, 18, 4 (2025) |
| 22682 | 0.865 | Valente R.; Senna C.; Rito P.; Sargento S. | Embedded Federated Learning For Vanet Environments | Applied Sciences (Switzerland), 13, 4 (2023) |
| 32142 | 0.862 | Gupta D.; Moni S.S.; Tosun A.S. | Integration Of Digital Twin And Federated Learning For Securing Vehicular Internet Of Things | 2023 Research in Adaptive and Convergent Systems RACS 2023 (2023) |
| 26308 | 0.862 | Sepasgozar S.S.; Pierre S. | Fed-Ntp: A Federated Learning Algorithm For Network Traffic Prediction In Vanet | IEEE Access, 10 (2022) |
| 18978 | 0.861 | Biswas M.; Banerjee S.; Das D.; Das S.; Dhibar S.; Kisku D.; Das P.; Biswas U. | Design Of A Smart Road Accident Management Framework Using Federated Learning | Smart Innovation, Systems and Technologies, 433 (2025) |
| 14729 | 0.859 | Ullah F.; Srivastava G.; Mostarda L.; Cacciagrano D. | Collaborative Intrusion Detection System For Intermittent 10 Vs Using Federated Learning And Deep Swarm Particle Optimization | 2024 IEEE 11th International Conference on Data Science and Advanced Analytics, DSAA 2024 (2024) |
| 26356 | 0.855 | Valente R.; Senna C.; Rito P.; Sargento S. | Federated Learning Framework To Decentralize Mobility Forecasting In Smart Cities | Proceedings of IEEE/IFIP Network Operations and Management Symposium 2023, NOMS 2023 (2023) |