Deep Reinforcement Learning-Based Joint Scheduling of 5G and TSN in Industrial Networks
Abstract
:1. Introduction
2. Related Work
2.1. Overview of TSN Scheduling Schemes
2.2. 5G-TSN Integration Architecture
2.3. Related Research on 5G-TSN
3. System Model and Problem Formulation
3.1. System Model
3.2. Problem Formulation
4. Markov Decision Process Modelling
4.1. State Space
4.2. Action Space
4.3. Reward Function Design
5. DDPG-Based Resource Scheduling Algorithm
Algorithm 1: Resource scheduling based on DDPG |
|
6. Results
6.1. Simulation Parameters
6.2. Results Analysis and Discussion
7. Conclusions and Future Works
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Bennis, M.; Debbah, M.; Poor, H.V. Ultrareliable and Low-Latency Wireless Communication: Tail, Risk, and Scale. Proc. IEEE 2018, 106, 1834–1853. [Google Scholar] [CrossRef] [Green Version]
- Bello, L.L.; Steiner, W. A perspective on IEEE time-sensitive networking for industrial communication and automation systems. Proc. IEEE 2019, 107, 1094–1120. [Google Scholar] [CrossRef]
- Lv, J.; Zhao, Y.; Wu, X.; Li, Y.; Wang, Q. Formal Analysis of TSN Scheduler for Real-Time Communications. IEEE Trans. Reliab. 2021, 70, 1286–1294. [Google Scholar] [CrossRef]
- 3GPP Technical Specification TS 23.501 on System Architecture for 5G System. Available online: https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=3144 (accessed on 23 February 2023).
- Atiq, M.K.; Muzaffar, R.; Seijo, O.; Val, I.N.; Bernhard, H.-P. When ieee 802.11 and 5g meet time-sensitive networking. IEEE Open J. Ind. Electron. Soc. 2022, 3, 14–36. [Google Scholar] [CrossRef]
- Messenger, J.L. Time-sensitive networking: An introduction. IEEE Commun. Stand. Mag. 2018, 2, 29–33. [Google Scholar] [CrossRef]
- Nasrallah, A.; Thyagaturu, A.S.; Alharbi, Z.; Wang, C.; Shao, X.; Reisslein, M.; ElBakoury, H. Ultra-low latency (ull) networks: The ieee tsn and ietf detnet standards and related 5g ull research. IEEE Commun. Surv. Tutor. 2019, 21, 88–145. [Google Scholar] [CrossRef] [Green Version]
- Marijanović, L.; Schwarz, S.; Rupp, M. Multiplexing Services in 5G and Beyond: Optimal Resource Allocation Based on Mixed Numerology and Mini-Slots. IEEE Access 2020, 8, 209537–209555. [Google Scholar] [CrossRef]
- Ji, H.; Park, S.; Yeo, J.; Kim, Y.; Lee, J.; Shim, B. Introduction to Ultra Reliable and Low Latency Communications in 5G. arXiv 2017, arXiv:1704.05565. [Google Scholar]
- Anand, A.; de Veciana, G. Resource Allocation and HARQ Optimization for URLLC Traffic in 5G Wireless Networks. IEEE J. Sel. Areas Commun. 2018, 36, 2411–2421. [Google Scholar] [CrossRef] [Green Version]
- Anand, A.; de Veciana, G.; Shakkottai, S. Joint Scheduling of URLLC and eMBB Traffic in 5G Wireless Networks. IEEE/ACM Trans. Netw. 2020, 28, 477–490. [Google Scholar] [CrossRef] [Green Version]
- Ginthör, D.; Guillaume, R.; Schüngel, M.; Schotten, H.D. 5G RAN Slicing for Deterministic Traffic. In Proceedings of the 2021 IEEE Wireless Communications and Networking Conference (WCNC), Nanjing, China, 29 March–1 April 2021. [Google Scholar]
- Alwarafy, A.; Abdallah, M.; Ciftler, B.S.; Al-Fuqaha, A.; Hamdi, M. Deep Reinforcement Learning for Radio Resource Allocation and Management in next Generation Heterogeneous Wireless Networks: A Survey. arXiv 2021, arXiv:2106.00574. [Google Scholar]
- Hu, X.; Liu, S.; Chen, R.; Wang, W.; Wang, C. A Deep Reinforcement Learning-Based Framework for Dynamic Resource Allocation in Multibeam Satellite Systems. IEEE Commun. Lett. 2018, 22, 1612–1615. [Google Scholar] [CrossRef]
- Gu, Z.; She, C.; Hardjawana, W.; Lumb, S.; McKechnie, D.; Essery, T.; Vucetic, B. Knowledge-Assisted Deep Reinforcement Learning in 5G Scheduler Design: From Theoretical Framework to Implementation. IEEE J. Sel. Areas Commun. 2021, 39, 2014–2028. [Google Scholar] [CrossRef]
- Li, J.; Zhang, X. Deep Reinforcement Learning-Based Joint Scheduling of eMBB and URLLC in 5G Networks. IEEE Wirel. Commun. Lett. 2020, 9, 1543–1546. [Google Scholar] [CrossRef]
- Striffler, T.; Michailow, N.; Bahr, M. Time-Sensitive Networking in 5th Generation Cellular Networks—Current State and Open Topics. In Proceedings of the 2019 IEEE 2nd 5G World Forum (5GWF), Dresden, Germany, 30 September–2 October 2019. [Google Scholar]
- Martenvormfelde, L.; Neumann, A.; Wisniewski, L.; Jasperneite, J. A Simulation Model for Integrating 5G into Time Sensitive Networking as a Transparent Bridge. In Proceedings of the 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Vienna, Austria, 8–11 September 2020. [Google Scholar]
- Ginthör, D.; Guillaume, R.; von Hoyningen-Huene, J.; Schüngel, M.; Schotten, H.D. End-to-end Optimized Joint Scheduling of Converged Wireless and Wired Time-Sensitive Networks. In Proceedings of the 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Vienna, Austria, 8–11 September 2020. [Google Scholar]
- Ginthör, D.; von Hoyningen-Huene, J.; Guillaume, R.; Schotten, H. Analysis of Multi-user Scheduling in a TSN-enabled 5G System for Industrial Applications. In Proceedings of the 2019 IEEE International Conference on Industrial Internet (ICII), Orlando, FL, USA, 11–12 November 2019. [Google Scholar]
- Sun, L.; Wang, J.; Lin, S.; Ma, Z.; Li, W.; Qilian, L.; Huang, R. Research on 5G-TSN joint scheduling mechanism based on radio channel information. J. Commun. 2021, 42, 65–75. [Google Scholar]
- Yang, J.; Yu, G. Traffic Scheduling for 5G-TSN Integrated Systems. In Proceedings of the 2022 International Symposium on Wireless Communication Systems (ISWCS), Hangzhou, China, 19–22 October 2022. [Google Scholar]
- Zhang, Y.; Xu, Q.; Li, M.; Chen, C.; Guan, X. QoS-Aware Mapping and Scheduling for Virtual Network Functions in Industrial 5G-TSN Network. In Proceedings of the 2021 IEEE Global Communications Conference (GLOBECOM), Madrid, Spain, 7–11 December 2021. [Google Scholar]
- Luong, N.C.; Hoang, D.T.; Gong, S.; Niyato, D.; Wang, P.; Liang, Y.C.; Kim, D.I. Applications of Deep Reinforcement Learning in Communications and Networking: A Survey. IEEE Commun. Surv. Tutor. 2019, 21, 3133–3174. [Google Scholar] [CrossRef] [Green Version]
- Alwarafy, A.; Abdallah, M.; Ciftler, B.S.; Al-Fuqaha, A.; Hamdi, M. The Frontiers of Deep Reinforcement Learning for Resource Management in Future Wireless HetNets: Techniques, Challenges, and Research Directions. IEEE Open J. Commun. Soc. 2022, 3, 322–365. [Google Scholar] [CrossRef]
- Sklar, B. Rayleigh fading channels in mobile digital communication systems. I. Characterization. IEEE Commun. Mag. 1997, 35, 90–100. [Google Scholar] [CrossRef]
- Ba, J.L.; Kiros, J.R.; Hinton, G.E. Layer Normalization. arXiv 2016, arXiv:1607.06450. [Google Scholar]
The probability of packets arriving within each TTI | 0.5 |
The number of packets arriving within each TTI | The number is valued from 1–3, followed by a uniform distribution |
Time-triggered application packet size | 200 Bytes |
Video flow packet size | 800 Bytes |
gNB transmission power | 20 dBm |
Channel noise power | −90 dBm |
100 | |
Subcarrier interval | 15 kHz |
0.1 | |
EMLR of time-triggered application ) | 6 ms |
Deadline of video flow | 20 ms |
0.2 | |
0.01 | |
0.01 | |
80,000 Bytes per second | |
Discount factor | 0.9 |
min trainset num | 800 |
Layers | Actor Network | Critic Network |
---|---|---|
Input layer | Fully connected layer (40 × 400) | |
Rectified Linear Unit (Relu) nonlinear activation function | ||
Normalization layer | ||
Hidden layer | Fully connected layer (400 × 400) | |
Relu nonlinear activation function | ||
Normalization layer | ||
Output layer | Fully connected layer (400,10) | Fully connected layer (400,1) |
Tanh nonlinear activation function | —— |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhu, Y.; Sun, L.; Wang, J.; Huang, R.; Jia, X. Deep Reinforcement Learning-Based Joint Scheduling of 5G and TSN in Industrial Networks. Electronics 2023, 12, 2686. https://doi.org/10.3390/electronics12122686
Zhu Y, Sun L, Wang J, Huang R, Jia X. Deep Reinforcement Learning-Based Joint Scheduling of 5G and TSN in Industrial Networks. Electronics. 2023; 12(12):2686. https://doi.org/10.3390/electronics12122686
Chicago/Turabian StyleZhu, Yuan, Lei Sun, Jianquan Wang, Rong Huang, and Xueqin Jia. 2023. "Deep Reinforcement Learning-Based Joint Scheduling of 5G and TSN in Industrial Networks" Electronics 12, no. 12: 2686. https://doi.org/10.3390/electronics12122686