Published March 23, 2023 | Version v1
Conference paper Open

The Cost of Learning: Efficiency vs. Efficacy of Learning-Based RRM for 6G

  • 1. University of Padova

Description

In the past few years, Deep Reinforcement Learning (DRL) has become a valuable solution to automatically learn efficient resource management strategies in complex networks. In many scenarios, the learning task is performed in the Cloud, while experience samples are generated directly by edge nodes or users. Therefore, the learning task involves some data exchange which, in turn, subtracts a certain amount of transmission resources from the system. This creates a friction between the need to speed up convergence towards an effective strategy, which requires the allocation of resources to transmit learning samples, and the need to maximize the amount of resources used for data plane communication, maximizing users' Quality of Service (QoS), which requires the learning process to be efficient, i.e., minimize its overhead. In this paper, we investigate this trade-off and propose a dynamic balancing strategy between the learning and data planes, which allows the centralized learning agent to quickly converge to an efficient resource allocation strategy while minimizing the impact on QoS. Simulation results show that the proposed method outperforms static allocation methods, converging to the optimal policy (i.e., maximum efficacy and minimum overhead of the learning plane) in the long run.

Files

m67408-lahmer paper.pdf

Files (749.2 kB)

Name Size Download all
md5:45fb8664f0b1610bb31c9d3ea90bed94
749.2 kB Preview Download

Additional details

Related works

Is identical to
Conference paper: 10.48550/arXiv.2211.16915 (DOI)