Deep reinforcement learning for mobile 5g and beyond : fundamentals, applications, and challenges
Future-generation wireless networks (5G and beyond) must accommodate surging growth in mobile data traffic and support an increasingly high density of mobile users involving a variety of services and applications. Meanwhile, the networks become increasingly dense, heterogeneous, decentralized, and a...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/143868 |
| _version_ | 1826110540585369600 |
|---|---|
| author | Xiong, Zehui Zhang, Yang Niyato, Dusit Deng, Ruilong Wang, Ping Wang, Li-Chun |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Xiong, Zehui Zhang, Yang Niyato, Dusit Deng, Ruilong Wang, Ping Wang, Li-Chun |
| author_sort | Xiong, Zehui |
| collection | NTU |
| description | Future-generation wireless networks (5G and beyond) must accommodate surging growth in mobile data traffic and support an increasingly high density of mobile users involving a variety of services and applications. Meanwhile, the networks become increasingly dense, heterogeneous, decentralized, and ad hoc in nature, and they encompass numerous and diverse network entities. Consequently, different objectives, such as high throughput and low latency, need to be achieved in terms of service, and resource allocation must be designed and optimized accordingly. However, considering the dynamics and uncertainty that inherently exist in wireless network environments, conventional approaches for service and resource management that require complete and perfect knowledge of the systems are inefficient or even inapplicable. Inspired by the success of machine learning in solving complicated control and decision-making problems, in this article we focus on deep reinforcement- learning (DRL)-based approaches that allow network entities to learn and build knowledge about the networks and thus make optimal decisions locally and independently. We first overview fundamental concepts of DRL and then review related works that use DRL to address various issues in 5G networks. Finally, we present an application of DRL for 5G network slicing optimization. The numerical results demonstrate that the proposed approach achieves superior performance compared with baseline solutions. |
| first_indexed | 2024-10-01T02:36:08Z |
| format | Journal Article |
| id | ntu-10356/143868 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:36:08Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1438682021-01-08T02:43:55Z Deep reinforcement learning for mobile 5g and beyond : fundamentals, applications, and challenges Xiong, Zehui Zhang, Yang Niyato, Dusit Deng, Ruilong Wang, Ping Wang, Li-Chun School of Computer Science and Engineering Energy Research Institute @ NTU (ERI@N) Engineering::Computer science and engineering 5G Mobile Communication Deep Reinforcement Learning Future-generation wireless networks (5G and beyond) must accommodate surging growth in mobile data traffic and support an increasingly high density of mobile users involving a variety of services and applications. Meanwhile, the networks become increasingly dense, heterogeneous, decentralized, and ad hoc in nature, and they encompass numerous and diverse network entities. Consequently, different objectives, such as high throughput and low latency, need to be achieved in terms of service, and resource allocation must be designed and optimized accordingly. However, considering the dynamics and uncertainty that inherently exist in wireless network environments, conventional approaches for service and resource management that require complete and perfect knowledge of the systems are inefficient or even inapplicable. Inspired by the success of machine learning in solving complicated control and decision-making problems, in this article we focus on deep reinforcement- learning (DRL)-based approaches that allow network entities to learn and build knowledge about the networks and thus make optimal decisions locally and independently. We first overview fundamental concepts of DRL and then review related works that use DRL to address various issues in 5G networks. Finally, we present an application of DRL for 5G network slicing optimization. The numerical results demonstrate that the proposed approach achieves superior performance compared with baseline solutions. Accepted version 2020-09-28T06:07:21Z 2020-09-28T06:07:21Z 2019 Journal Article Xiong, Z., Zhang, Y., Niyato, D., Deng, R., Wang, P., & Wang, L.-C. (2019). Deep Reinforcement Learning for Mobile 5G and Beyond: Fundamentals, Applications, and Challenges. IEEE Vehicular Technology Magazine, 14(2), 44–52. doi:10.1109/mvt.2019.2903655 1556-6072 https://hdl.handle.net/10356/143868 10.1109/MVT.2019.2903655 2 14 44 52 en IEEE Vehicular Technology Magazine © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/MVT.2019.2903655. application/pdf |
| spellingShingle | Engineering::Computer science and engineering 5G Mobile Communication Deep Reinforcement Learning Xiong, Zehui Zhang, Yang Niyato, Dusit Deng, Ruilong Wang, Ping Wang, Li-Chun Deep reinforcement learning for mobile 5g and beyond : fundamentals, applications, and challenges |
| title | Deep reinforcement learning for mobile 5g and beyond : fundamentals, applications, and challenges |
| title_full | Deep reinforcement learning for mobile 5g and beyond : fundamentals, applications, and challenges |
| title_fullStr | Deep reinforcement learning for mobile 5g and beyond : fundamentals, applications, and challenges |
| title_full_unstemmed | Deep reinforcement learning for mobile 5g and beyond : fundamentals, applications, and challenges |
| title_short | Deep reinforcement learning for mobile 5g and beyond : fundamentals, applications, and challenges |
| title_sort | deep reinforcement learning for mobile 5g and beyond fundamentals applications and challenges |
| topic | Engineering::Computer science and engineering 5G Mobile Communication Deep Reinforcement Learning |
| url | https://hdl.handle.net/10356/143868 |
| work_keys_str_mv | AT xiongzehui deepreinforcementlearningformobile5gandbeyondfundamentalsapplicationsandchallenges AT zhangyang deepreinforcementlearningformobile5gandbeyondfundamentalsapplicationsandchallenges AT niyatodusit deepreinforcementlearningformobile5gandbeyondfundamentalsapplicationsandchallenges AT dengruilong deepreinforcementlearningformobile5gandbeyondfundamentalsapplicationsandchallenges AT wangping deepreinforcementlearningformobile5gandbeyondfundamentalsapplicationsandchallenges AT wanglichun deepreinforcementlearningformobile5gandbeyondfundamentalsapplicationsandchallenges |