Abstract
This paper provides a comprehensive review of the emerging technology of federated reinforcement learning in the edge intelligence scenario. Starting from the problems and challenges faced by edge intelligence, we introduce the federated learning framework and use reinforcement learning algorithms to solve the problem of resource scheduling. This paper introduces the generation background, definition and classification of federated reinforcement learning, and focuses on the horizontal and vertical federal reinforcement learning technology and comparison research. Finally, it analyzes and improves the application of federal reinforcement learning in edge intelligence scenarios.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Qiao, D., Guo, S., He, J., Zhu, Y.: Edge intelligence: research progress and challenges. Radio Commu. Technol. 48(01), 34-45 (2022)
Chen, M., Zhang, J., Li, T.: Summary of federal learning attack and defense studies. Computer Science 49(07), 310–323 (2022)
Mo, Z., Gao, Z., Miao, D.: Edge intelligence: a new tentacles of artificial intelligence to edge distribution. Data and Computing Development Frontier 2(04), 16-27 (2020)
Zhao, Y., Zhang, H., Wang, S.: The federal learning review. Comp. Program. Tips Maint. (01), 117–119 (2022). https://doi.org/10.16184/j.cnki.comprg.2022.01.063
Liang, T., Zeng, B., Chen, G.: Federal learning review: concepts, technologies, applications, and challenges. Computer application 1–13 [2022–10–20]. http://kns.cnki.net/kcms/detail/51.1307.TP.20211231.1727.014.html
Zhu, P.: A federated learning model and algorithm based on mobile edge computing. Nanjing University of Posts and Telecommunications (2021). https://doi.org/10.27251/d.cnki.gnjdc.2021.001160
Gao, S., Yuan, L., Zhu, J., Ma, X., Zhang, R., Ma, J.: A blockchain-based privacy-preserving asynchronous federated learning. Chinese Sci. Info. Sci. 51(10), 1755–1774 (2021)
Chen, L., Liu, W.: Frontier and application of data security technology from the perspective of compliance. Frontiers of Data and Computing Development 3(03), 19–31 (2021)
Liu, Z.: Channel estimation and resource management research. Beijing Jiaotong University (2021). https://doi.org/10.26944/d.cnki.gbfju.2021.001145
Hu, X.: Research and application of target detection algorithm based on border collaboration. Harbin Institute of Technology (2021). https://doi.org/10.27061/d.cnki.ghgdu.2021.003651
Anning, Z.Z.: Anti-jamming resource dispatching method for D2D communication network based on deep reinforcement learning. Electric Power Info. Commu. Technol. 20(09), 108–114 (2022). https://doi.org/10.16543/j.2095-641x.electric.power.ict.2022.09.014
Liu, C.: Reinforcement learning algorithm research based on ESN. Hainan University (2021). https://doi.org/10.27073/d.cnki.ghadu.2021.000172
Dong, S., Yang, C., Liu, T.: Federated learning-based wireless tasks: does data non-IID necessarily affect performance? Signal Process. 37(08), 1365–1377 (2021). https://doi.org/10.16798/j.issn.1003-0530.2021.08.003
Jiang, Z.: Reinforcement learning-based cloud computing resource scheduling algorithm research. Wuhan University (2021). https://doi.org/10.27379/d.cnki.gwhdu.2021.000128
Pu, T., Du, S., Li, Y., Wang, X.: Distributed power supply collaborative optimization strategy based on federated reinforcement learning. Power System Automation: 1–12 [2022–10–31]. http://kns.cnki.net/kcms/detail/32.1180.tp.20221025.1937.013.html
Chen, M., Sun, Y., Hu, Y., Liu, C., Pang, P., Xie, Z.: Collaborative training and optimization management method of residential community integrated energy system based on longitudinal federal intensive learning. Chinese J. Elec. Eng. 42(15), 5535–5550 (2022). https://doi.org/10.13334/j.0258-8013.pcsee.210812
Li, J., Shao, J., Lin, J.: Review of the federal reinforcement learning literature. Fintech Era 29(10), 87–89 (2021)
Wang, X., Fan, F., Sun, Y., Wu, Y.: Internet of vehicles resource allocation based on federated deep reinforcement learning. Electr. Measure. Techniq. 44(10), 114–120 (2021). https://doi.org/10.19651/j.cnki.emt.2106047
Zhou, Jr.: Research and application of multi-agent deep reinforcement learning collaborative technology. Univ. Elec. Sci. Technolo. (2021). https://doi.org/10.27005/d.cnki.gdzku.2021.003772
Jiang, J.: Research on resource allocation and task scheduling oriented to edge intelligence. Jilin University (2020). https://doi.org/10.27162/d.cnki.gjlin.2020.000122
Zhang, X., Liu, Y., Liu, J., Han, Y.: Federated learning review for edge intelligence. Computer Research and Development 1–27 [2022–10–31]. http://kns.cnki.net/kcms/detail/11.1777.TP.20221027.0839.002.html
Wanduo, H.M., Xiao, M., Zhang, Y.: Review of heterogeneous parallel computing platforms for edge-oriented intelligent computing. Computer Engineering and Application: 1–12 [2022–10–31]. http://kns.cnki.net/kcms/detail/11.2127.TP.20221006.1805.004.html
Guo, Y.: Task unloading and resource allocation based on federated learning. Guangzhou University (2022). https://doi.org/10.27040/d.cnki.ggzdu.2022.001385
Cai, X.: Research on resource optimization allocation for distributed edge intelligence. Guangdong University of Technology (2022). https://doi.org/10.27029/d.cnki.ggdgu.2022.000975
Wang, R., Qi, J., Chen, L., Yang, L.: Edge collaborative inference review for edge intelligence. Computer Research and Development: 1–17 [2022–10–31]. http://kns.cnki.net/kcms/detail/11.1777.tp.20220426.1612.006.html
Yuan, X.: Federated learning node selection mechanism in an edge intelligent network. University of Electronics, Science and Technology (2022). https://doi.org/10.27005/d.cnki.gdzku.2022.000290
Shu, Z.: Research on federated learning methods based on edge computation. Nanjing University of Posts and Telecommunications (2021). https://doi.org/10.27251/d.cnki.gnjdc.2021.000897
Sun, B., Liu, Y., Wang, T., Peng, S., Wang, G., Jia, W.: Summary of federated learning efficiency optimization in mobile edge networks. Comp. Res. Develop. 59(07), 1439-1469 (2022)
Qi, J., et al.: Federated reinforcement learning: techniques, applications, and open challenges (2021). arXiv preprint arXiv:2108.11887
Hu, Y., et al.: Reward shaping based federated reinforcement learning. IEEE Access 9, 67259–67267 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sheng, X., Gao, Z., Cui, X., Yu, C. (2023). Federated Reinforcement Learning Technology and Application in Edge Intelligence Scene. In: Barolli, L. (eds) Advances in Internet, Data & Web Technologies. EIDWT 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 161. Springer, Cham. https://doi.org/10.1007/978-3-031-26281-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-26281-4_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26280-7
Online ISBN: 978-3-031-26281-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)