Resilient Topology Design for Wireless Backhaul: A Deep Reinforcement Learning Approach

被引：5

作者：

Abdelmoaty, Ahmed ^{[1
,2
]}

Naboulsi, Diala ^{[2
,3
]}

Dahman, Ghassan ^{[2
,4
]}

Poitau, Gwenael ^{[5
]}

Gagnon, Francois

机构：

[1] Ecole Technol Super, Elect Engn Dept, Montreal, PQ H3C 1K3, Canada

[2] Ecole Technol Super, Resilient Machine Learning Inst, Montreal, PQ H3C 1K3, Canada

[3] Ecole Technol Super, Software Engn Dept & IT, Montreal, PQ H3C 1K3, Canada

[4] Ultra Intelligence & Commun, Montreal, PQ H4T 1V7, Canada

[5] Dell Technol, Toronto, ON M2H 3N5, Canada

来源：

IEEE WIRELESS COMMUNICATIONS LETTERS | 2022年 / 11卷 / 12期

基金：

加拿大自然科学与工程研究理事会;

关键词：

Deep reinforcement learning; graph theory; Integer Linear Program (ILP); resiliency; wireless backhaul;

D O I：

10.1109/LWC.2022.3207358

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Ultra-dense 5G and beyond deployments are setting significant burden on cellular networks, especially for wireless backhauls. Today, a careful planning for wireless backhaul is more critical than ever. In this letter, we study the hierarchical wireless backhaul topology design problem. We introduce a Deep Reinforcement Learning (DRL) based algorithm that can solve the problem efficiently. We compare the quality of the solutions derived by our DRL approach to the optimal solution, derived according to the Integer Linear Program (ILP) formulation in our previous work. A simulation using practical channel propagation scenarios and different network densities proves that our DRL-based algorithm is providing a sub-optimal solution with different levels of resiliency. Our DRL algorithm is further shown to scale for larger instances of the problem.

引用

页码：2532 / 2536

页数：5

共 50 条

[1] IAB Topology Design: A Graph Embedding and Deep Reinforcement Learning Approach
Simsek, Meryem
Orhan, Oner
Nassar, Marcel
Elibol, Oguz
Nikopour, Hosein
[J]. IEEE COMMUNICATIONS LETTERS, 2021, 25 (02) : 489 - 493
[2] On The Design of Resilient and Reliable Wireless Backhaul Networks
Abdelmoaty, Ahmed
Dahman, Ghassan
Naboulsi, Diala
Poitau, Gwenael
Gagnon, Francois
[J]. 2022 IEEE 95TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2022-SPRING), 2022,
[3] A Reinforcement Learning Approach for Wireless Backhaul Spectrum Sharing in IoE HetNets
Jaber, Mona
Alam, Atm Shafiul
[J]. 2020 IEEE 31ST ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS (IEEE PIMRC), 2020,
[4] Resilient Topology design for Free Space Optical Cellular Backhaul Networking
Li, Yuan
Pappas, Nikolaos
Angelakis, Vangelis
Pioro, Michal
Yuan, Di
[J]. 2014 GLOBECOM WORKSHOPS (GC WKSHPS), 2014, : 487 - 492
[5] Reinforcement Learning for Channel and Radio Allocations to Wireless Backhaul Links
Liman, Juliana
Yen, Li-Hsing
[J]. 2022 23RD ASIA-PACIFIC NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM (APNOMS 2022), 2022, : 363 - 366
[6] Topology Design for Data Center Networks Using Deep Reinforcement Learning
Qi, Haoran
Shu, Zhan
Chen, Xiaomin
[J]. 2023 INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING, ICOIN, 2023, : 251 - 256
[7] Deep Reinforcement Learning Based Cross-Layer Design in Terahertz Mesh Backhaul Networks
Hu, Zhifeng
Han, Chong
Wang, Xudong
[J]. IEEE-ACM TRANSACTIONS ON NETWORKING, 2024, 32 (03) : 2159 - 2173
[8] Dealing with Limited Backhaul Capacity in Millimeter-Wave Systems: A Deep Reinforcement Learning Approach
Feng, Mingjie
Mao, Shiwen
[J]. IEEE COMMUNICATIONS MAGAZINE, 2019, 57 (03) : 50 - 55
[9] Exploring grid topology reconfiguration using a simple deep reinforcement learning approach
Subramanian, Medha
Viebahn, Jan
Tindemans, Simon H.
Donnot, Benjamin
Marot, Antoine
[J]. 2021 IEEE MADRID POWERTECH, 2021,
[10] ?Deep reinforcement learning for engineering design through topology optimization of elementally discretized design domains?
Brown, Nathan K.
Garland, Anthony P.
Fadel, Georges M.
Li, Gang
[J]. MATERIALS & DESIGN, 2022, 218

← 1 2 3 4 5 →