Intelligent 5G/6G: When Wireless Networks Meet Artificial Intelligence (5G+AI=6G)

Figure 1: Future wireless networks (5G/6G cellular networks) enabled by Artificial Intelligence(AI).

Table 1: Typical Artificial Intelligence (AI) algorithms to enhance cellular networks (5G/6G).

Figure 2: The Artificial Intelligence (AI) application framework for reinforcement learning-based greener cellular networks.

Table 2: The evolution toward intelligent 5G/6G.


Future wireless networks (5G/6G cellualr networks) are assumed to be the key enabler and infrastructure provider in the global ICT industry, by offering a variety of services with diverse requirements. The standardization of 5G mobile cellular networks is being expedited around the world, which also implies more of the breakthroufh candidate technologies will be adopted. Therefore, it is worthwhile to provide insight into the emerging candidate techniques as a whole and examine the design philosophy behind them.

In regard to 5G/6G, it is meaningful to highlight one of the most fundamental features among the revolutionary techniques in the 5G and 6G eras, i.e., there emerges ubiquitous intelligence in nearly every important aspect of mobile cellular networks and IoT (Internet of Things), including radio network accessing (e.g. ORAN - Open RAN), radio resource management, mobility management, service provisioning management (e.g. service function chains), networking (e.g., SDN/NFV, slicing, CogMesh, mobile edge and fog computing, cloud, etc.), human behavior recognition, and so on. However, faced with the ever-increasingly complicated configuration issues and the blossoming new service requirements, it is totally insufficient for 5G/6G cellular networks if it lacks strong complete AI(Artificial Intelligence) functionalities.

Hence, we feel necessary to introduce the fundamental concepts, approaches and strengths in Artificial Intelligence and discuss the relationship between AI and the potential techniques in 5G cellular networks (or future 6G). Specifically, we highlight the great opportunities and challenges to exploit AI (e.g., deep learning, reinforcement learning, transfer learning, imitation learning, representation learning, dictionary learning, collaborative learning, swarm intelligecne, and other statistical learning)  to achieve intelligent 5G/6G networks, and demonstrate the tremendous effectiveness of AI to orchestrate and optimize cellular networks. We believe that AI-empowered 5G/6G cellular networks will make the acclaimed dreaming ICT enabler a reality.

[Reference]

  1. David Grace and Honggang Zhang, Cognitive Communications - Distributed Artificial Intelligence (DAI), Regulatory Policy & Economics, Implementation, Wiley Press, ISBN: 9781119951506, August 2012. (http://as.wiley.com/WileyCDA/WileyTitle/productCd-111995150X.html, Amazon Best Sellers in Artificial Intelligence applications in Canada)

  2. Rongpeng Li, Zhifeng Zhao, Xuan Zhou, G. Ding, Yan Chen, Z. Wang, and Honggang Zhang, “Intelligent 5G: When Cellular Networks Meet Artificial Intelligence,” IEEE Wireless Communications, March 2017. (download PDF)

  3. Rongpeng Li, Zhifeng Zhao, Jianchao Zheng, Chengli Mei, Yueming Cai, and Honggang Zhang, “The Learning and Prediction of Application-level Traffic Data in Cellular Networks,” IEEE Trans. Wireless Communications, March 2017. (download PDF)

  4. Xianfu Chen, Z. Han, Honggang Zhang, G. Xue, Y. Xiao, and M. Bennis, “Wireless Resource Scheduling in Virtualized Radio Access Networks Using Stochastic Learning," IEEE Trans. Mobile Computing, August 2017. (download PDF)

  5. Honggang Zhang and Xianfu Chen, "Smart Offloading in Mobile-Edge Computing of 5G Cellular Networks via Deep Reinforcement Learning,"  9th China-Scotland SIPRA Workshop, Suzhou, China, April 2018. (Keynote Speech)

  6. Zhifeng Zhao, Rongpeng Li,  Qi Sun, Chin-Lin I, , Chenyang Yang, Xianfu Chen, Minjian Zhao, and Honggang Zhang, “Deep Reinforcement Learning for Network Slicing,"  https://arxiv.org/abs/1805.06591, May 2018. (download PDF)

  7. Xianfu Chen, Honggang Zhang,  Celimuge Wu, Shiwen Mao, Yusheng Ji, and M. Bennis, “Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning," https://arxiv.org/abs/1805.06146v1, May 2018. (download PDF)

  8. Xianfu Chen, Honggang Zhang,  Celimuge Wu, Shiwen Mao, Yusheng Ji, and M. Bennis, “Performance Optimization in Mobile-Edge Computing via Deep Reinforcement Learning,"  https://arxiv.org/pdf/1804.00514.pdf, March 2018. (download PDF)

  9. Jiaqi Li, Zhifeng Zhao, Rongpeng Li, and Honggang Zhang, “AI-based Two-Stage Intrusion Detection for Software Defined IoT Networks," https://arxiv.org/abs/1806.02566, June 2018. (download PDF)

  10. Yuxiu Hua, Zhifeng Zhao, Rongpeng Li, Xianfu Chen, Zhiming Liu, and Honggang Zhang, “Traffic Prediction Based on Random Connectivity in Deep Learning with Long Short-Term Memory," https://arxiv.org/abs/1711.02833, November 2017. (download PDF)

  11. Celimuge Wu, T. Yoshinaga, Xianfu Chen, L. Zhang, and Y. Ji, “Cluster-based Content Distribution Integrating LTE and IEEE 802.11p with Fuzzy Logic and Q-learning,” IEEE Computational Intelligence Magazine, Feb. 2018. (download PDF)

  12. Sumit Darak, Honggang Zhang, Jacques Palicot, and Christophe Moy, “Decision Making Policy for RF Energy Harvesting Enabled Cognitive Radios in Decentralized Wireless Networks,” Digital Signal Processing (Elsevier), January 2017.  (download PDF)

  13. Jiaqi Li, Zhifeng Zhao, and Rongpeng Li, "Machine Learning-based IDS for Software-Defined 5G Network," IET Networks, PP. 53-60, March 2018. (download PDF) 

  14. Xuan Zhou, Rongpeng Li, Tao Chen, and Honggang Zhang, “Network Slicing as a Service: Enabling Enterprises' Own Software-Defined Cellular Networks," IEEE Communications Magazine, vol. 54, no. 7, pp. 146 - 153, July 2016.  (download PDF)

  15. Xianfu Chen, Jinsong Wu, Yueming Cai, Honggang Zhang, and Tao Chen, "Energy-Efficiency Oriented Traffic Offloading: A Brief Survey for Wireless Networks and a Learning Approach for Heterogeneous Cellular Networks," IEEE Journal Sel. Areas Commun. (JSAC), Vol. 33, No. 4, pp. 627-640, Apr. 2015. (download PDF, Google Scholar Citation)

  16. Sumit Darak, Sumedh Dhabu, Christophe Moy, Honggang Zhang, Jacques Palicot, and Vinod Prasad, "Low Complexity and Efficient Dynamic Spectrum Learning and Tunable Bandwidth Access for Heterogeneous Decentralized Cognitive Radio Networks," Digital Signal Processing (Elsevier), February 2015. (download PDF)

  17. Rongpeng Li, Zhifeng Zhao, Xianfu Chen, Jacques Palicot, and Honggang Zhang, "TACT: A Transfer Actor-Critic Learning Framework for Energy Saving in Cellular Radio Access Networks," IEEE Trans. Wireless Communications,Vol. 13, No. 4, pp. 2000-2011, April 2014.  (download PDF)

  18. Xianfu Chen, Zhifeng Zhao, and Honggang Zhang, "Stochastic Power Adaptation with Multi-agent Reinforcement Learning for Cognitive Wireless Mesh Networks,” IEEE Transactions on Mobile Computing, November 2013.  (download PDF)

  19. Sumit Darak, Jacques Palicot, Honggang Zhang, A. P. Vinod, and Christophe Moy, "Reconfigurable Filter Bank with Complete Control over Subband Bandwidths for Multistandard Wireless Communication Receivers," IEEE Transactions on Very Large Scale Integration (VLSI) Systems, September 2014.  (download PDF)

  20. Xianfu Chen, Honggang Zhang, Allen B. MacKenzie, and Marja Matinmikko,"Predicting Spectrum Occupancies Using a Non-stationary Hidden Markov Model," IEEE Wireless Communications Letters, April 2014.  (download PDF)

  21. Rongpeng Li, Zhifeng Zhao, Xuan Zhou, Jacques Palicot, and Honggang Zhang,"The Predictability Analysis of Cellular Networks Traffic: From Entropy Theory to Networking Practice," IEEE Communications Magazine, June 2014.  (download PDF)

  22. Sumit Darak, A. P. Vinod, E. M-K. Lai, Jacques Palicot, and Honggang Zhang, "Linear Phase VDF Design with Unabridged Bandwidth Control over the Nyquist Band," IEEE Trans. on Circuits and Systems II, June 2014.  (download PDF)

  23. Xianfu Chen, Zhifeng Zhao, and Honggang Zhang, “Reinforcement learning for distributed power control and channel access in cognitive wireless mesh networks,” Cognitive Communications: Distributed  Artificial Intelligence(DAI), Regulatory Policy and Economics, Implementation: Chapter 7, David Grace and Honggang Zhang (Editors), Wiley Press, Sep. 2012.

  24. Xianfu Chen, Zhifeng Zhao, Honggang Zhang, and T. Chen, “Reciprocal learning for energy-efficient opportunistic spectrum access,” Green Communications: Theoretical Fundamentals, Algorithms and Applications: Chapter 5, Jinsong Wu, Sundeep Rangan, and Honggang Zhang (Editors), CRC Press, Sep. 2012.

  25. Xianfu Chen, Zhifeng Zhao, Honggang Zhang, and Tao Chen,“Reinforcement Learning Enhanced Iterative Power Allocation in Stochastic Cognitive Wireless Mesh Networks, ” Springer Wireless Personal Communications Journal,  Special Issue on "Cognitive Radio Networks and Communications", April 2010.

  26. Xianfu Chen, Zhifeng Zhao, Tao Jiang, David Grace, and Honggang Zhang, "Intercluster Connection in Cognitive Wireless Mesh Networks Based on Intelligent Network Coding,” EURASIP Journal on Advances in Signal Processing, Special Issue on "Dynamic Spectrum Access for Wireless Networking", November 2009.

  27. Xianfu Chen, Honggang Zhang, Celimuge Wu, Shiwen Mao,  Yusheng Ji, and Mehdi Bennis,"Performance Optimization in Mobile-Edge Computing via Deep Reinforcement Learning," IEEE VTC 2018-Fall, Chicago, USA, August 2018.

  28. Chujie Wang, Zhifeng Zhao, Honggang Zhang, and Qi Sun, "Deep Learning-based Intelligent Dual Connectivity for Mobility Management in Dense Nertwork," IEEE VTC 2018-Fall, Chicago, USA, August 2018.

  29. Yuxiu Hua, Zhifeng Zhao, Rongpeng Li, Xianfu Chen, Zhiming Liu, and Honggang Zhang, "Traffic Prediction Based on Random Connectivity in Deep Learning with Long Short-Term Memory," IEEE VTC 2018-Fall, Chicago, USA, August 2018.

  30. Chen Yu, Zhifeng Zhao, Yifan Zhou, and Honggang Zhang, "Intelligent Optimizing Scheme for Load Balancing in Software Defined Networks," IEEE VTC 2017-Spring, Sydney, Australia, June 2017.

  31. Xianfu Chen, C. Wu, Y. Zhou, and Honggang Zhang, “A learning approach for traffic offloading in stochastic heterogeneous cellular networks,” in Proc. IEEE ICC, London, UK, Jun. 2015.

  32. Xianfu Chen, Honggang Zhang, Tao Chen, and J. Palicot, “Combined learning for resource allocation in autonomous heterogeneous cellular networks,” in Proc. IEEE PIMRC, London, UK, Sep. 2013.

  33. Xianfu Chen, Tao Chen, W. Cheng, and Honggang Zhang, “Reciprocity inspired learning for opportunistic spectrum access in cognitive radio networks,” in Proc. CROWNCOM, Washington DC, USA, July 2013.

  34. Xianfu Chen, Honggang Zhang, T. Chen, and M. Lasanen, “Improving energy efficiency in green femtocell networks: A hierarchical reinforcement learning framework,” in Proc. IEEE ICC, Budapest, Hungary, Jun. 2013.

  35. Xianfu Chen, Zhifeng Zhao, D. Grace, and Honggang Zhang, “Reciprocal learning for cognitive medium access,” in Proc. IEEE WCNC, Shanghai, China, Apr. 2013.

  36. Xianfu Chen, Zhifeng Zhao, Honggang Zhang, and Tao Chen, “Conjectural variations in multi-agent reinforcement learning for energy-efficient cognitive wireless mesh networks,” in Proc. IEEE WCNC, Paris, France, Apr. 2012.

  37. Rongpeng Li, Zhifeng Zhao, Xianfu Chen, and Honggang Zhang, “Energy Saving through a Learning Framework in Greener Cellular Radio Access Networks,” Proc. of IEEE Globecom 2012, Anaheim, USA, Dec. 2012.

  38. Xianfu Chen, Zhifeng Zhao, and Honggang Zhang, “Power entangling and matching in cognitive wireless mesh networks by applying conjecture based multi-agent QQ-learning approach,” in IEEE GLOBECOM (MCECN Workshop), Miami, USA, Dec. 2010.

  39. Xianfu Chen, Zhifeng Zhao, Honggang Zhang, and Tao Chen, “Applying multi-agent Q-learning scheme in cognitive wireless mesh networks for green communications,” in IEEE PIMRC (W-Green Workshop), Istanbul, Turkey, Sep. 2010.

  40. Xianfu Chen, Zhifeng Zhao, and Honggang Zhang, “Green Transmit Power Assignment for Cognitive Radio Networks by Applying Multi-agent Q-learning Approach,” Proc. European Wireless Technology Conference 2010 (European Microwave Week 2010), Paris, France, September 2010.

  41. Xianfu Chen, Zhifeng Zhao, Tao Jiang, David Grace, and Honggang Zhang, “Inter-Cluster Connection in Cognitive Wireless Mesh Networks Based on Intelligent Network Coding,” Proc. IEEE PIMRC 2009, Tokyo, Japan, September 2009.

  42. Tao Chen, Honggang Zhang, Marcos Kartz, and Zhen Zhou, “Swarm Intelligence Based Dynamic Control Channel Assignment in CogMesh,” Proc. IEEE ICC 2008 (CoCoNets Workshop), Beijing, China, May 19-23, 2008. (download in PDF, Google Scholar Citation)

  43. Tao Chen, Honggang Zhang, G. M.Maggio, and Imrich Chlamtac, "Topology Management in CogMesh: A Cluster-based Cognitive Radio Mesh Network," Proc. IEEE ICC 2007, Glasgow, UK, June, 2007. (download in PDF, Googel Scholar Citation)

  44. Tao Chen, Honggang Zhang, G. M. Maggio, and Imrich Chlamtac, "CogMesh: A Cluster-based Cognitive Radio Network," Proc. the 2007 IEEE Symp. on New Frontiers in Dynamic Spectrum Access Networks (IEEE DySPAN 2007), Dublin, Ireland, April 17-20, 2007. (download in PDF, Google Scholar Citation)