Deep Learning at the Mobile Edge: Opportunities for 5G Networks
Source abstract
Abstract
Mobile edge computing (MEC) within 5G networks brings the power of cloud computing, storage, and analysis closer to the end user. The increased speeds and reduced delay enable novel applications such as connected vehicles, large-scale IoT, video streaming, and industry robotics. Machine Learning (ML) is leveraged within mobile edge computing to predict changes in demand based on cultural events, natural disasters, or daily commute patterns, and it prepares the network by automatically scaling up network resources as needed. Together, mobile edge computing and ML enable seamless automation of network management to reduce operational costs and enhance user experience. In this paper, we discuss the state of the art for ML within mobile edge computing and the advances needed in automating adaptive resource allocation, mobility modeling, security, and energy efficiency for 5G networks.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: IoT and Edge/Fog Computing · Opportunistic and Delay-Tolerant Networks · Advanced Data and IoT Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Network Engineering, Universitat Politècnica de Catalunya (UPC), Esteve Terradas, 7, 08860 Castelldefels, Spain
Funding
Ministerio de Economía, Industria y Competitividad, Gobierno de España
References (100+)
Show source-provided references
1. Wood, L. (2019). 5G Optimization: Mobile Edge Computing, APIs, and Network Slicing 2019–2024, Technical Report for Research and Markets.
2. Hu, Y.C., Patel, M., Sabella, D., Sprecher, N., and Young, V. (2020, July 08). ETSI White Paper No. 11. Mobile Edge Computing: A Key Technology towards 5G. Technical Report, ETSI. Available online: https://www.etsi.org/images/files/ETSIWhitePapers/etsi_wp11_mec_a_key_technology_towards_5g.pdf.
3. Survey on Multi-Access Edge Computing for Internet of Things Realization10.1109/COMST.2018.2849509 ↗
4. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv, Available online: https://arxiv.org/abs/1409.1556.
5. Collobert, R., and Weston, J. (2008, January 5–9). A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. Proceedings of the 25th International Conference on Machine Learning (ICML 2008), Helsinki, Finland.10.1145/1390156.1390177 ↗
6. Wireless Network Intelligence at the Edge10.1109/JPROC.2019.2941458 ↗
7. All one needs to know about fog computing and related edge computing paradigms: A complete survey10.1016/j.sysarc.2019.02.009 ↗
8. Pham, Q., Fang, F., Ha, V.N., Piran, M.J., Le, M., Le, L.B., Hwang, W., and Ding, Z. (2020). A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art. IEEE Access.10.1109/ACCESS.2020.3001277 ↗
9. Adversarial Learning Targeting Deep Neural Network Classification: A Comprehensive Review of Defenses Against Attacks10.1109/JPROC.2020.2970615 ↗
10. Future Intelligent and Secure Vehicular Network Toward 6G: Machine-Learning Approaches10.1109/JPROC.2019.2954595 ↗
11. Building Autonomic Elastic Optical Networks with Deep Reinforcement Learning10.1109/MCOM.001.1900151 ↗
12. Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks10.1109/JSAC.2019.2904329 ↗
13. (2018). ETSI GS MEC 002 (V2.1.1): Multi-Access Edge Computing (MEC); Phase 2: Use Cases and Requirements. Available online: https://www.etsi.org/deliver/etsi_gs/MEC/001_099/002/02.01.01_60/gs_MEC002v020101p.pdf.
14. (2020, July 08). Increasing Mobile Operators’ Value Proposition with Edge Computing. Technical Report, Intel and Nokia Siemens Networks. Available online: https://www.intel.co.id/content/dam/www/public/us/en/documents/technology-briefs/edge-computing-tech-brief.pdf.
15. Varghese, B., Wang, N., Barbhuiya, S., Kilpatrick, P., and Nikolopoulos, D. (2016, January 18–20). Challenges and Opportunities in Edge Computing. Proceedings of the 1st IEEE International Conference on Smart Cloud (SmartCloud 2016), New York, NY, USA.10.1109/SmartCloud.2016.18 ↗
16. (2020, July 08). ETSI GS MEC 003 (V2.1.1): Multi-Access Edge Computing (MEC); Framework and Reference Architecture. Available online: https://www.etsi.org/deliver/etsi_gs/MEC/001_099/003/02.01.01_60/gs_MEC003v020101p.pdf.
17. (2020, July 08). Enable Edge Computing with Azure IoT Edge. Available online: https://azure.microsoft.com/en-us/resources/videos/microsoft-ignite-2017-enable-edge-computing-with-azure-iot-edge/.
18. (2020, May 30). Edge TPU. Available online: https://cloud.google.com/edge-tpu/.
19. (2020, May 30). AWS IoT Greengrass. Available online: https://aws.amazon.com/greengrass/.
20. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2008, January 5–9). ImageNet Classification with Deep Convolutional Neural Networks. Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS 2012), Lake Tahoe, Nevada.
21. Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., and Darrell, T. (2014, January 21–26). DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. Proceedings of the 31st International Conference on International Conference on Machine Learning (ICML 2014), Beijing, China.
22. Mastering the game of Go without human knowledge10.1038/nature24270 ↗
23. Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M.A. (2013). Playing Atari with Deep Reinforcement Learning. arXiv, Available online: https://arxiv.org/abs/1312.5602.
24. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: http://www.deeplearningbook.org.
25. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20–25). ImageNet: A Large-Scale Hierarchical Image Database. Proceedings of the IEEE Computer Society Conference on Computer Vision (CVPR 2009), Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
26. Wang, J., Tang, J., Xu, Z., Wang, Y., Xue, G., Zhang, X., and Yang, D. (2017, January 1–4). Spatiotemporal modeling and prediction in cellular networks: A big data enabled deep learning approach. Proceedings of the IEEE International Conference on Computer Communications (INFOCOM 2017), Atlanta, GA, USA.10.1109/INFOCOM.2017.8057090 ↗
27. Spatio-Temporal Analysis and Prediction of Cellular Traffic in Metropolis10.1109/TMC.2018.2870135 ↗
28. Toward In-Network Deep Machine Learning for Identifying Mobile Applications and Enabling Application Specific Network Slicing10.1587/transcom.2017CQI0002 ↗
29. Many-Layered Learning10.1162/08997660260293319 ↗
30. A Comprehensive Survey on Machine Learning for Networking: Evolution, Applications and Research Opportunities10.1186/s13174-018-0087-2 ↗
31. Zeiler, M.D., and Fergus, R. (2014, January 6–12). Visualizing and Understanding Convolutional Networks. Proceedings of the 13th European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland.10.1007/978-3-319-10590-1_53 ↗
32. Bega, D., Gramaglia, M., Fiore, M., Banchs, A., and Costa-Pérez, X. (2019, January 25–27). DeepCog: Cognitive Network Management in Sliced 5G Networks with Deep Learning. Proceedings of the IEEE International Conference on Computer Communications (INFOCOM 2019), Paris, France.10.1109/INFOCOM.2019.8737488 ↗
33. Shakev, N.G., Ahmed, S.A., Popov, V.L., and Topalov, A.V. (2018, January 25–27). Recognition and Following of Dynamic Targets by an Omnidirectional Mobile Robot using a Deep Convolutional Neural Network. Proceedings of the 9th International Conference on Intelligent Systems (IS 2018), Madeira, Portugal.10.1109/IS.2018.8710581 ↗
34. Azari, A., Papapetrou, P., Denic, S.Z., and Peters, G. (2019). User Traffic Prediction for Proactive Resource Management: Learning-Powered Approaches. arXiv, Available online: https://arxiv.org/abs/1906.00951.10.1109/GLOBECOM38437.2019.9014115 ↗
35. A novel deep learning driven low-cost mobility prediction approach for 5G cellular networks: The case of the Control/Data Separation Architecture (CDSA)10.1016/j.neucom.2019.01.031 ↗
36. Geron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, O’Reilly Media, Inc.. [2nd ed.].
37. A Markovian Decision Process
38. Agarwal, P., and Alam, M. (2019). A Lightweight Deep Learning Model for Human Activity Recognition on Edge Devices. arXiv, Available online: https://arxiv.org/abs/1909.12917.
39. Yang, S., Gong, Z., Ye, K., Wei, Y., Huang, Z., and Huang, Z. (2019). EdgeCNN: Convolutional Neural Network Classification Model with small inputs for Edge Computing. arXiv, Available online: https://arxiv.org/abs/1909.13522.
40. Li, E., Zeng, L., Zhou, Z., and Chen, X. (2019). Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing. arXiv, Available online: https://arxiv.org/abs/1910.05316.
41. Teerapittayanon, S., McDanel, B., and Kung, H.T. (2016, January 4–8). BranchyNet: Fast inference via early exiting from deep neural networks. Proceedings of the 23rd International Conference on Pattern Recognition (ICPR 2016), Cancún, Mexico.10.1109/ICPR.2016.7900006 ↗
42. Wong, A., Lin, Z.Q., and Chwyl, B. (2019, January 16–29). AttoNets: Compact and Efficient Deep Neural Networks for the Edge via Human-Machine Collaborative Design. Proceedings of the 1st Computer Vision and Pattern Recognition Workshops (CVPR 2019), Long Beach, CA, USA.10.1109/CVPRW.2019.00095 ↗
43. Lin, Y., Han, S.W., Mao, H., Wang, Y., and Dally, W.J. (2017). Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. arXiv, Available online: https://arxiv.org/abs/1712.01887.
44. Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Konecný, J., Mazzocchi, S., and McMahan, H.B. (2019). Towards Federated Learning at Scale: System Design. arXiv, Available online: https://arxiv.org/abs/1902.01046.
45. Lim, W.Y., 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, Available online: https://arxiv.org/abs/1909.11875.
46. Teerapittayanon, S., McDanel, B., and Kung, H.T. (2017, January 5–8). Distributed Deep Neural Networks Over the Cloud, the Edge and End Devices. Proceedings of the 37th IEEE International Conference on Distributed Computing Systems (ICDCS 2017), Atlanta, GA, USA.10.1109/ICDCS.2017.226 ↗
47. Adaptive Federated Learning in Resource Constrained Edge Computing Systems10.1109/JSAC.2019.2904348 ↗
48. Liu, L., Zhang, J., Song, S.H., and Letaief, K.B. (2019). Client-Edge-Cloud Hierarchical Federated Learning. arXiv, Available online: https://arxiv.org/abs/1905.06641.
49. Tao, Z., and Li, Q. (2018, January 10). eSGD: Communication Efficient Distributed Deep Learning on the Edge. Proceedings of the 1st Hot Topics in Edge Computing (HotEdge 2018), Boston, MA, USA.
50. Wickramasuriya, D.S., Perumalla, C.A., Davaslioglu, K., and Gitlin, R.D. (2017, January 24–25). Base station prediction and proactive mobility management in virtual cells using recurrent neural networks. Proceedings of the 18th IEEE Wireless and Microwave Technology Conference (WAMICON 2017), Cocoa Beach, FL, USA.10.1109/WAMICON.2017.7930254 ↗
51. Multiple contents offloading mechanism in AI-enabled opportunistic networks
52. (2020, July 08). An Introduction to Network Slicing. Technical Report, GSM Association. Available online: https://www.gsma.com/futurenetworks/wp-content/uploads/2017/11/GSMA-An-Introduction-to-Network-Slicing.pdf.
53. Dynamic Reservation and Deep Reinforcement Learning Based Autonomous Resource Slicing for Virtualized Radio Access Networks10.1109/ACCESS.2019.2909670 ↗
54. Koo, J., Mendiratta, V.B., Rahman, M.R., and Elwalid, A. (2019). Deep Reinforcement Learning for Network Slicing with Heterogeneous Resource Requirements and Time Varying Traffic Dynamics. arXiv, Available online: https://arxiv.org/abs/1908.03242.10.23919/CNSM46954.2019.9012702 ↗
55. Sciancalepore, V., Samdanis, K., Costa, X.P., Bega, D., Gramaglia, M., and Banchs, A. (2017, January 1–4). Mobile traffic forecasting for maximizing 5G network slicing resource utilization. Proceedings of the IEEE International Conference on Computer Communications (INFOCOM 2017), Atlanta, GA, USA.10.1109/INFOCOM.2017.8057230 ↗
56. Bega, D., Gramaglia, M., Banchs, A., Sciancalepore, V., Samdanis, K., and Costa, X.P. (2017, January 1–4). Optimising 5G infrastructure markets: The business of network slicing. Proceedings of the IEEE International Conference on Computer Communications (INFOCOM 2017), Atlanta, GA, USA.10.1109/INFOCOM.2017.8057045 ↗
57. Deep Reinforcement Learning for Resource Management in Network Slicing10.1109/ACCESS.2018.2881964 ↗
58. Khatibi, S., and Jano, A. (2019, January 18–21). Elastic Slice-Aware Radio Resource Management with AI-Traffic Prediction. Proceedings of the 28th European Conference on Networks and Communications (EuCNC 2019), Valencia, Spain.10.1109/EuCNC.2019.8801995 ↗
59. Kim, Y., Kim, S., and Lim, H. (2019). Reinforcement Learning Based Resource Management for Network Slicing. Appl. Sci., 9.10.3390/app9112361 ↗
60. Li, J., Gao, H., Lv, T., and Lu, Y. (2018, January 15–18). Deep reinforcement learning based computation offloading and resource allocation for MEC. Proceedings of the IEEE Wireless Communications and Networking Conference (IEEE WCNC 2018), Barcelona, Spain.10.1109/WCNC.2018.8377343 ↗
61. Joint Optimization of Caching, Computing, and Radio Resources for Fog-Enabled IoT Using Natural Actor–Critic Deep Reinforcement Learning10.1109/JIOT.2018.2878435 ↗
62. Learn to Cache: Machine Learning for Network Edge Caching in the Big Data Era10.1109/MWC.2018.1700317 ↗
63. Integrated Networking, Caching, and Computing for Connected Vehicles: A Deep Reinforcement Learning Approach10.1109/TVT.2017.2760281 ↗
64. Cognitive multi-agent empowering mobile edge computing for resource caching and collaboration10.1016/j.future.2019.08.001 ↗
65. Q-learning based collaborative cache allocation in mobile edge computing10.1016/j.future.2019.08.032 ↗
66. Twin-Timescale Artificial Intelligence Aided Mobility-Aware Edge Caching and Computing in Vehicular Networks10.1109/TVT.2019.2893898 ↗
67. Yang, J., Zhang, J., Ma, C., Wang, H., Zhang, J., and Zheng, G.H. (2019). Deep learning-based edge caching for multi-cluster heterogeneous networks. Neural Comput. Appl.10.1007/s00521-019-04040-z ↗
68. Socially Aware Caching in D2D Enabled Fog Radio Access Networks10.1109/ACCESS.2019.2924939 ↗
69. Data-Driven Computing and Caching in 5G Networks: Architecture and Delay Analysis10.1109/MWC.2018.1700216 ↗
70. Deep Reinforcement Learning for Vehicular Edge Computing: An Intelligent Offloading System10.1145/3317572 ↗
71. Deep reinforcement learning-based joint task offloading and bandwidth allocation for multi-user mobile edge computing10.1016/j.dcan.2018.10.003 ↗
72. Cooperative task offloading in three-tier mobile computing networks: An ADMM framework10.1109/TVT.2019.2892176 ↗
73. Network Resource Allocation System for QoE-Aware Delivery of Media Services in 5G Networks10.1109/TBC.2018.2828608 ↗
74. Fog Computing for 5G Tactile Industrial Internet of Things: QoE-Aware Resource Allocation Model10.1109/TII.2019.2902574 ↗
75. Cache Less for More: Exploiting Cooperative Video Caching and Delivery in D2D Communications10.1109/TMM.2018.2885931 ↗
76. Alsenwi, M., Tran, N.H., Bennis, M., Shashi RajPandey, A.K.B., and Hong, C.S. (2020). Intelligent Resource Slicing for eMBB and URLLC Coexistence in 5G and Beyond: A Deep Reinforcement Learning Based Approach. arXiv, Available online: https://arxiv.org/abs/2003.07651.10.1109/TWC.2021.3060514 ↗
77. Maaz, D., Galindo-Serrano, A., and Elayoubi, S.E. (2018, January 26–28). URLLC User Plane Latency Performance in New Radio. Proceedings of the 25th International Conference on Telecommunications (ICT 2018), Saint Malo, France.10.1109/ICT.2018.8464912 ↗
78. Ultrareliable and Low-Latency Wireless Communication: Tail, Risk, and Scale10.1109/JPROC.2018.2867029 ↗
79. Handover Mechanism in NR for Ultra-Reliable Low-Latency Communications10.1109/MNET.2018.1700235 ↗
80. Energy Efficiency and Delay in 5G Ultra-Reliable Low-Latency Communications System Architectures10.1109/MNET.2018.1700260 ↗
81. Siddiqi, M.A., Yu, H., and Joung, J. (2019). 5G Ultra-Reliable Low-Latency Communication Implementation Challenges and Operational Issues with IoT Devices. Electronics, 8.10.3390/electronics8090981 ↗
82. Strubell, E., Ganesh, A., and McCallum, A. (2019). Energy and Policy Considerations for Deep Learning in NLP. arXiv, Available online: https://arxiv.org/abs/1906.02243.10.18653/v1/P19-1355 ↗
83. Ahvar, E., Orgerie, A., and Lébre, A. (2019). Estimating Energy Consumption of Cloud, Fog and Edge Computing Infrastructures. IEEE Trans. Sustain. Comput., 1–12.
84. Multi-User Multi-Task Computation Offloading in Green Mobile Edge Cloud Computing10.1109/TSC.2018.2826544 ↗
85. A Fast Algorithm for Energy-Saving Offloading With Reliability and Latency Requirements in Multi-Access Edge Computing10.1109/ACCESS.2019.2961453 ↗
86. Security in Mobile Edge Caching with Reinforcement Learning10.1109/MWC.2018.1700291 ↗
87. Thantharate, A., Paropkari, R., Walunj, V., Beard, C., and Kankariya, P. (2020, January 6–8). Secure5G: A Deep Learning Framework Towards a Secure Network Slicing in 5G and Beyond. Proceedings of the 10th Annual Computing and Communication Workshop and Conference (CCWC 2020), Las Vegas, NV, USA.10.1109/CCWC47524.2020.9031158 ↗
88. Truex, S., Liu, L., Chow, K.H., Gursoy, M.E., and Wei, W. (2020, January 27). LDP-Fed: Federated Learning with Local Differential Privacy. Proceedings of the 3rd ACM International Workshop on Edge Systems, Analytics and Networking (EdgeSys 2020), Heraklion, Greece.10.1145/3378679.3394533 ↗
89. Akundi, S., Prabhu, S., BK, N.U., and Mondal, S.C. (2020, January 4–7). Suppressing Noisy Neighbours in 5G Networks: An End-to-End NFV-Based Framework to Detect and Suppress Noisy Neighbours. Proceedings of the 21st International Conference on Distributed Computing and Networking (ICDCN 2020), Kolkata, India.10.1145/3369740.3372768 ↗
90. Kafle, V.P., Fukushima, Y., Martinez-Julia, P., and Miyazawa, T. (2018, January 26–28). Consideration on Automation of 5G Network Slicing with Machine Learning. Proceedings of the 10th ITU Kaleidoscope: Machine Learning for a 5G Future (ITU K 2018), Santa Fe, Argentina.10.23919/ITU-WT.2018.8597639 ↗
91. Automation of 5G Network Slice Control Functions with Machine Learning10.1109/MCOMSTD.001.1900010 ↗
92. (2020, July 08). ETSI GS ENI 005 (V1.1.1): Experiential Networked Intelligence (ENI). System Architecture. Available online: https://www.etsi.org/deliver/etsi_gs/ENI/001_099/005/01.01.01_60/gs_ENI005v010101p.pdf.
93. (2020, July 08). ETSI GS ENI 002 (V2.1.1): Experiential Networked Intelligence (ENI). ENI Requirements. Available online: https://www.etsi.org/deliver/etsi_gs/ENI/001_099/002/01.01.01_60/gs_ENI002v010101p.pdf.
94. (2020, July 08). ETSI GR ENI 001 (V1.1.1): Experiential Networked Intelligence (ENI). ENI Use Cases. Available online: https://www.etsi.org/deliver/etsi_gr/ENI/001_099/001/01.01.01_60/gr_ENI001v010101p.pdf.
95. (2020, July 08). 3GPP TR 23.791 (V16.1.0): Study of Enablers for Network Automation for 5G, Phase 2 (Release 17). Available online: https://www.3gpp.org/ftp/Specs/archive/23_series/23.700-91/23700-91-030.zip.
96. (2020, July 08). ETSI GR ZSM 004 V1.1.1 (2020-03) Zero-Touch Network and Service Management (ZSM). Available online: https://www.etsi.org/deliver/etsi_gr/ZSM/001_099/004/01.01.01_60/gr_ZSM004v010101p.pdf.
97. (2020, June 17). FG-ML5G-ARC5G “Unified Architecture for Machine Learning in 5G and Future Networks”. Available online: https://www.itu.int/en/ITU-T/focusgroups/ml5g/Documents/ML5G-delievrables.pdf.
98. (2020, July 08). Supplement 55 to ITU-T, Y.3170 “Machine Learning in Future Networks Including IMT-2020: Use Cases”. Available online: https://www.itu.int/rec/T-REC-Y.Sup55-201910-I.
99. (2020, July 08). ITU-T, Y.3172 “Architectural Framework for Machine Learning in Future Networks including IMT-2020”. Available online: https://www.itu.int/rec/T-REC-Y.3172-201906-I/en.
100. (2020, July 08). ITU-T, Y.3173 “Framework for Evaluating Intelligence Level of Future Networks including IMT-2020: Use Cases”. Available online: https://www.itu.int/rec/T-REC-Y.3173-202002-I.