Resource Allocation in Wireless Networks with Federated Learning: Network Adaptability and Learning Acceleration

다국어 초록 (Multilingual Abstract)

Deep reinforcement learning can effectively address resource allocation in wireless networks. However, its learning speed may be slower in more complex networks and a new policy should be learned for a newly-arrived system due to a lack of network adaptability. To address these issues, we propose a federated learning framework for resource allocation in wireless networks with multiple systems. It accelerates the learning speed by aggregating the policy at each system into a central policy and ensures network adaptability by using the central policy. Through experiments, we demonstrate that our proposed framework achieves both learning acceleration and network adaptability.

참고문헌 (Reference)

1 K.B. Letaief, "The roadmap to 6G: AI empowered wireless networks" 57 (57): 84-90, 2019

2 H.-S. Lee, "Resource allocation in wireless networks with deep reinforcement learning: A circumstance-independent approach" 14 (14): 2589-2592, 2020

3 H.H. Zhuo, "Lin, Federated deep reinforcement learning"

4 F. Al-Tam, "Learn to schedule (LEASCH):A deep reinforcement learning approach for radio resource scheduling in the 5G MAC layer" 8 : 108088-108101, 2020

5 W. Shi, "Joint device scheduling and resource allocation for latency constrained wireless federated learning" 20 (20): 453-467, 2021

6 V. Mnih, "Human-level control through deep reinforcement learning" 518 (518): 529-533, 2015

7 C.T. Dinh, "Federated learning over wireless networks:Convergence analysis and resource allocation" 29 (29): 398-409, 2021

8 N. Zhao, "Deep reinforcement learning for user association and resource allocation in heterogeneous cellular networks" 18 (18): 5141-5152, 2019

9 O. Naparstek, "Deep multi-user reinforcement learning for distributed dynamic spectrum access" 18 (18): 310-323, 2019

10 S. Wang, "Content-based vehicle selection and resource allocation for federated learning in iov" 2021

11 J. Xu, "Client selection and bandwidth allocation in wireless federated learning networks: A long-term perspective" 20 (20): 1188-1200, 2021

12 H.-S. Lee, "Adaptive transmission scheduling in wireless networks for asynchronous federated learning" 39 (39): 3673-3687, 2021

13 J. Fan, "A theoretical analysis of deep Qlearning" 486-489, 2020

14 C. Fiandrino, "A machinelearning-based framework for optimizing the operation of future networks" 58 (58): 20-25, 2020

15 M. Chen, "A joint learning and communications framework for federated learning over wireless networks" 20 (20): 269-283, 2021