Towards Federated Learning in Edge Computing for Real-Time Traffic Estimation in Smart Cities

Resumo


The wide proliferation of sensors and devices of Internet of Things(IoT), together with Artificial Intelligence (AI), has created the so-called Smart Environments. From a network perspective, these solutions suffer from high latency and increased data transmission. This paper proposes a Federated Learning (FL) architecture for Real-Time Traffic Estimation, supported by Roadside Units (RSU’s) for model aggregation. The solution envisages that learning will be done on clients with their local data, and fully distributed on the Edge, with high learning rates, low latency, and less bandwidth usage. To achieve that,this paper discusses tools and requirements for FL implementation towards a model for real-time traffic estimation, as well as how such solution could be evaluated using VANET and network simulators. As a first practical step, we show a preliminary evaluation of a learning model using a data set of cars that demonstrate a distributed learning strategy. In the future, we will use a similar distributed strategy within our proposed architecture.

Palavras-chave: Federated Learning, Edge Computing, Smart City, Real-Time Traffic Estimation, VANET

Referências

Adetiloye, T. and Awasthi, A. (2017). Predicting short-term congested traffic flow onurban motorway networks. In Handbook of Neural Computation, pages 145-165. El-sevier.

Adetiloye, T. and Awasthi, A. (2019). Multimodal big data fusion for traffic congestionprediction. In Multimodal Analytics for Next-Generation Big Data Technologies andApplications, pages 319-335. Springer.

Barik, R. K., Priyadarshini, R., Lenka, R. K., Dubey, H., and Mankodiya, K. (2020). Fogcomputing architecture for scalable processing of geospatial big data. InternationalJournal of Applied Geospatial Research (IJAGR), 11(1):1-20.

Barrachina, J., Garrido, P., Fogue, M., Martinez, F., Cano, J.-C., Calafate, C., and Man-zoni, P. (2013). Road side unit deployment: A density-based approach. IEEE IntelligentTransportation Systems Magazine, 5:30-39.

Bithas, P. S., Michailidis, E. T., Nomikos, N., Vouyioukas, D., and Kanatas, A. G. (2019).A survey on machine-learning techniques for uav-based communications. Sensors,19(23):5170.

Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon,C., Konecny, J., Mazzocchi, S., McMahan, H. B., et al. (2019). Towards federatedlearning at scale: System design. arXiv preprint arXiv:1902.01046.

Heinrich, S. (2017). Flash memory in the emerging age of autonomy. Proceedings of theFlash Memory Summit, Santa Clara, CA, USA, pages 7-10.

Index, C. G. C. (2018). Forecast and methodology, 2016-2021 white paper. Updated:February, 1.

Kar, G., Jain, S., Gruteser, M., Bai, F., and Govindan, R. (2017). Real-time traffic estima-tion at vehicular edge nodes. In Proceedings of the Second ACM/IEEE Symposium onEdge Computing, pages 1-13.

Kehoe, B., Patil, S., Abbeel, P., and Goldberg, K. (2015). A survey of research on cloudrobotics and automation. IEEE Transactions on automation science and engineering,12(2):398-409.

Konecény, J., McMahan, B., and Ramage, D. (2015). Federated optimization: Distributedoptimization beyond the datacenter. arXiv preprint arXiv:1511.03575.

Konecény, J., McMahan, H. B., Ramage, D., and Richtárik, P. (2016a). Federated op-timization: Distributed machine learning for on-device intelligence. arXiv preprintarXiv:1610.02527.

Konecény, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., and Bacon, D.(2016b). Federated learning: Strategies for improving communication efficiency. arXivpreprint arXiv: 1610.05492.

Krause, J., Stark, M., Deng, J., and Fei-Fei, L. (2013). 3d object representations for fine-grained categorization. In 4th International IEEE Workshop on 3D Representation andRecognition (3dRR-13), Sydney, Australia.

Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D.,and Miao, C. (2019). Federated learning in mobile edge networks: A comprehensive survey. arXiv preprint arXiv: 1909.11875.

Lu, Y., Huang, X., Dai, Y., Maharjan, S., and Zhang, Y. (2019). Differentially privateasynchronous federated learning for mobile edge computing in urban informatics. IEEETransactions on Industrial Informatics.

McMahan, B. and Ramage, D. (2017). Federated learning: Collaborative machine learn-ing without centralized training data. Google Research Blog, 3.

McMahan, H. B., Moore, E., Ramage, D., Hampson, S., et al. (2016). Communication-efficient learning of deep networks from decentralized data. arXiv preprintarXiv:1602.05629.

Nilsson, A., Smith, S., Ulm, G., Gustavsson, E., and Jirstrand, M. (2018). A performanceevaluation of federated learning algorithms. In Proceedings of the Second Workshopon Distributed Infrastructures for Deep Learning, pages 1-8.

Rizwan, P., Suresh, K., and Babu, M. R. (2016). Real-time smart traffic managementsystem for smart cities by using internet of things and big data. In 2016 internationalconference on emerging technological trends (ICETT), pages 1-7. IEEE.

Samarakoon, S., Bennis, M., Saad, W., and Debbah, M. (2018). Federated learning forultra-reliable low-latency v2v communications. In 2018 IEEE Global CommunicationsConference (GLOBECOM), pages 1-7. IEEE.

Sensors, A. (2017). Electronics expo 2017. Detroit, USA (14-15 June 2017).

Siegel, J. E., Erb, D. C., and Sarma, S. E. (2017). A survey of the connected vehiclelandscape—architectures, enabling technologies, applications, and development areas.IEEE Transactions on Intelligent Transportation Systems, 19(8):2391-2406.

Valerio, L., Conti, M., and Passarella, A. (2018). Energy efficient distributed analyticsat the edge of the network for iot environments. Pervasive and Mobile Computing,51:27-42.

Valerio, L., Passarella, A., and Conti, M. (2017). A communication efficient distributedlearning framework for smart environments. Pervasive and Mobile Computing, 41:46-68.

Ye, D., Yu, R., Pan, M., and Han, Z. (2020). Federated learning in vehicular edge com-puting: A selective model aggregation approach. IEEE Access.

Zhang, J. and Letaief, K. B. (2019). Mobile edge intelligence and computing for theinternet of vehicles. Proceedings of the IEEE.

Zhang, Q., Cheng, L., and Boutaba, R. (2010). Cloud computing: state-of-the-art andresearch challenges. Journal of internet services and applications, 1(1):7-18.

Zhou, W., Li, Y., Chen, S., and Ding, B. (2018). Real-time data processing architecturefor multi-robots based on differential federated learning. In 2018 IEEE SmartWorld,Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Com-puting & Communications, Cloud & Big Data Computing, Internet of People andSmart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), pages462-471. IEEE.

Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., and Zhang, J. (2019). Edge intelligence:Paving the last mile of artificial intelligence with edge computing. Proceedings of theIEEE, 107(8):1738-1762.
Publicado
10/12/2020
SILVA, Matteus Vargas Simão da; BITTENCOURT, Luiz Fernando; RIVERA, Adín Ramirez. Towards Federated Learning in Edge Computing for Real-Time Traffic Estimation in Smart Cities. In: WORKSHOP DE COMPUTAÇÃO URBANA (COURB), 4. , 2020, Rio de Janeiro. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 166-177. ISSN 2595-2706. DOI: https://doi.org/10.5753/courb.2020.12361.