Reinforcement Learning-Based Network Slice Resource Allocation for Federated Learning Applications
Publication Date
1-1-2022
Document Type
Conference Proceeding
Publication Title
2022 IEEE Global Communications Conference, GLOBECOM 2022 - Proceedings
DOI
10.1109/GLOBECOM48099.2022.10001715
First Page
3647
Last Page
3652
Abstract
This paper addresses a resource allocation strategy for network slices, where each network slice supports a different federated learning task. A slice is established when a new federated learning model needs to be trained and is released once the training is complete. The goal is to minimize the average network slice holding time while also providing fairness between slice tenants and improving network efficiency. We propose a reinforcement learning-based strategy to periodically reallocate resources according to the current state of each federated learning task. We offer two reinforcement learning models. The first model achieves more stable performance and considers correlations between tasks, while the second model utilizes fewer parameters and is more robust to varying number of tasks. Both approaches have better performance than baseline heuristic methods. We also propose a method to alleviate the effect of various resources scales to make the training stable.
Funding Number
CNS-2008856
Funding Sponsor
National Science Foundation
Keywords
federated learning, network slice, reinforcement learning, resource allocation
Department
Computer Science
Recommended Citation
Zhouxiang Wu, Genya Ishigaki, Riti Gour, Congzhou Li, and Jason P. Jue. "Reinforcement Learning-Based Network Slice Resource Allocation for Federated Learning Applications" 2022 IEEE Global Communications Conference, GLOBECOM 2022 - Proceedings (2022): 3647-3652. https://doi.org/10.1109/GLOBECOM48099.2022.10001715
