Resource Constrained Vehicular Edge Federated Learning With Highly Mobile Connected Vehicles

This paper proposes a vehicular edge federated learning (VEFL) solution, where an edge server leverages highly mobile connected vehicles’ (CVs’) onboard central processing units (CPUs) and local datasets to train a global model. Convergence analysis reveals that the VEFL training loss depends on the successful receptions of the CVs’ trained models over the intermittent vehicle-to-infrastructure (V2I) wireless links. Owing to high mobility, in the full device participation case (FDPC), the edge server aggregates client model parameters based on a weighted combination according to the CVs’ dataset sizes and sojourn periods, while it selects a subset of CVs in the partial device participation case (PDPC). We then devise joint VEFL and radio access technology (RAT) parameters optimization problems under delay, energy and cost constraints to maximize the probability of successful reception of the locally trained models. Considering that the optimization problem is NP-hard, we decompose it into a VEFL parameter optimization sub-problem, given the estimated worst-case sojourn period, delay and energy expense, and an online RAT parameter optimization sub-problem. Finally, extensive simulations are conducted to validate the effectiveness of the proposed solutions with a practical 5G new radio (5G-NR) RAT under a realistic microscopic mobility model.

[1]  Yuehua Wu,et al.  Efficient Asynchronous Federated Learning Research in the Internet of Vehicles , 2023, IEEE Internet of Things Journal.

[2]  S. Zeadally,et al.  Edge Computing-Enabled Internet of Vehicles: Towards Federated Learning Empowered Scheduling , 2022, IEEE Transactions on Vehicular Technology.

[3]  Qingqi Pei,et al.  Vehicle Selection and Resource Optimization for Federated Learning in Vehicular Edge Computing , 2022, IEEE Transactions on Intelligent Transportation Systems.

[4]  Md Ferdous Pervej,et al.  Mobility, Communication and Computation Aware Federated Learning for Internet of Vehicles , 2022, 2022 IEEE Intelligent Vehicles Symposium (IV).

[5]  Junbo Wang,et al.  Semi-Synchronous Federated Learning Protocol With Dynamic Aggregation in Internet of Vehicles , 2022, IEEE Transactions on Vehicular Technology.

[6]  Md Ferdous Pervej,et al.  Efficient Content Delivery in User-Centric and Cache-Enabled Vehicular Edge Networks with Deadline-Constrained Heterogeneous Demands , 2022, IEEE Transactions on Vehicular Technology.

[7]  R. Hu,et al.  Energy Efficiency and Delay Tradeoff in an MEC-Enabled Mobile IoT Network , 2022, IEEE Internet of Things Journal.

[8]  Soumaya Cherkaoui,et al.  Clustered Vehicular Federated Learning: Process and Optimization , 2022, IEEE Transactions on Intelligent Transportation Systems.

[9]  Xingqin Lin,et al.  An Overview of 5G Advanced Evolution in 3GPP Release 18 , 2022, IEEE Communications Standards Magazine.

[10]  Cheng-lin Zhao,et al.  Joint resource management for mobility supported federated learning in Internet of Vehicles , 2021, Future Gener. Comput. Syst..

[11]  Hao Jiang,et al.  Semi-asynchronous Hierarchical Federated Learning for Cooperative Intelligent Transportation Systems , 2021, ArXiv.

[12]  Shengli Xie,et al.  FedParking: A Federated Learning Based Parking Space Estimation With Parked Vehicle Assisted Edge Computing , 2021, IEEE Transactions on Vehicular Technology.

[13]  Jia Liu,et al.  Anarchic Federated Learning , 2021, ICML.

[14]  Gunasekaran Raja,et al.  Federated Learning Empowered Computation Offloading and Resource Management in 6G-V2X , 2021, IEEE Transactions on Network Science and Engineering.

[15]  Shaohua Wan,et al.  FedCPF: An Efficient-Communication Federated Learning Approach for Vehicular Edge Computing in 6G Communication Networks , 2021, IEEE Transactions on Intelligent Transportation Systems.

[16]  M. Shamim Hossain,et al.  Mobility-Aware Proactive Edge Caching for Connected Vehicles Using Federated Learning , 2021, IEEE Transactions on Intelligent Transportation Systems.

[17]  Walid Saad,et al.  Multi-Task Federated Learning for Traffic Prediction and Its Application to Route Planning , 2021, 2021 IEEE Intelligent Vehicles Symposium (IV).

[18]  Youngbin Im,et al.  MoDEMS: Optimizing Edge Computing Migrations for User Mobility , 2021, IEEE Journal on Selected Areas in Communications.

[19]  H. Vincent Poor,et al.  Federated Learning Over Energy Harvesting Wireless Networks , 2021, IEEE Internet of Things Journal.

[20]  Kevin I-Kai Wang,et al.  Two-Layer Federated Learning With Heterogeneous Model Aggregation for 6G Supported Internet of Vehicles , 2021, IEEE Transactions on Vehicular Technology.

[21]  Qinglei Kong,et al.  Privacy-Preserving Aggregation for Federated Learning-Based Navigation in Vehicular Fog , 2021, IEEE Transactions on Industrial Informatics.

[22]  Mugen Peng,et al.  Resource Allocation for Energy-Efficient MEC in NOMA-Enabled Massive IoT Networks , 2021, IEEE Journal on Selected Areas in Communications.

[23]  M. Bennis,et al.  Federated Learning on the Road Autonomous Controller Design for Connected and Autonomous Vehicles , 2021, IEEE Transactions on Wireless Communications.

[24]  Ekram Hossain,et al.  Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networks , 2020, IEEE Transactions on Communications.

[25]  Zhibin Wang,et al.  Federated Learning via Intelligent Reflecting Surface , 2020, IEEE Transactions on Wireless Communications.

[26]  Xiaoheng Deng,et al.  Maximize Potential Reserved Task Scheduling for URLLC Transmission and Edge Computing , 2020, 2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall).

[27]  Mung Chiang,et al.  Fast-Convergent Federated Learning , 2020, IEEE Journal on Selected Areas in Communications.

[28]  Pengcheng Zhu,et al.  Joint Long-Term Energy Efficiency Optimization in C-RAN With Hybrid Energy Supply , 2020, IEEE Transactions on Vehicular Technology.

[29]  Haijian Sun,et al.  Scheduling Policy and Power Allocation for Federated Learning in NOMA Based MEC , 2020, GLOBECOM 2020 - 2020 IEEE Global Communications Conference.

[30]  H. Dai,et al.  Communication Efficient Federated Learning with Energy Awareness over Wireless Networks , 2022 .

[31]  Choong Seon Hong,et al.  Energy Efficient Federated Learning Over Wireless Communication Networks , 2019, IEEE Transactions on Wireless Communications.

[32]  H. Poor,et al.  A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks , 2019, IEEE Transactions on Wireless Communications.

[33]  Deniz Gündüz,et al.  Federated Learning Over Wireless Fading Channels , 2019, IEEE Transactions on Wireless Communications.

[34]  Xiang Li,et al.  On the Convergence of FedAvg on Non-IID Data , 2019, ICLR.

[35]  Junaid Qadir,et al.  Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and the Way Forward , 2019, IEEE Communications Surveys & Tutorials.

[36]  Tao Guo,et al.  Enabling 5G RAN Slicing With EDF Slice Scheduling , 2019, IEEE Transactions on Vehicular Technology.

[37]  Weisong Shi,et al.  A Mobility-Aware Vehicular Caching Scheme in Content Centric Networks: Model and Optimization , 2019, IEEE Transactions on Vehicular Technology.

[38]  Anit Kumar Sahu,et al.  Federated Optimization in Heterogeneous Networks , 2018, MLSys.

[39]  Yun-Pang Flötteröd,et al.  Microscopic Traffic Simulation using SUMO , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[40]  Walid Saad,et al.  Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications , 2018, IEEE Transactions on Communications.

[41]  Geoffrey Ye Li,et al.  Machine Learning for Vehicular Networks: Recent Advances and Application Examples , 2018, IEEE Vehicular Technology Magazine.

[42]  Kin K. Leung,et al.  Adaptive Federated Learning in Resource Constrained Edge Computing Systems , 2018, IEEE Journal on Selected Areas in Communications.

[43]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[44]  Derrick Wing Kwan Ng,et al.  Optimal Joint Power and Subcarrier Allocation for Full-Duplex Multicarrier Non-Orthogonal Multiple Access Systems , 2016, IEEE Transactions on Communications.

[45]  Stephen P. Boyd,et al.  CVXPY: A Python-Embedded Modeling Language for Convex Optimization , 2016, J. Mach. Learn. Res..

[46]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[47]  Ha H. Nguyen,et al.  Joint Optimization of Cooperative Beamforming and Relay Assignment in Multi-User Wireless Relay Networks , 2014, IEEE Transactions on Wireless Communications.

[48]  Johannes Stallkamp,et al.  The German Traffic Sign Recognition Benchmark: A multi-class classification competition , 2011, The 2011 International Joint Conference on Neural Networks.

[49]  Radhika Ranjan Roy,et al.  Handbook of Mobile Ad Hoc Networks for Mobility Models , 2010 .

[50]  Giorgio Buttazzo,et al.  Hard Real-Time Computing Systems: Predictable Scheduling Algorithms and Applications , 1997 .

[51]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[52]  I. Stancu-Minasian.  Nonlinear Fractional Programming , 1997 .