Reinforcement learning with model-based approaches for dynamic resource allocation in a tandem queue - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Reinforcement learning with model-based approaches for dynamic resource allocation in a tandem queue

Abstract

We consider three-tier network architecture modeled with two physical nodes in tandem where an autonomous agent controls the number of active resources on each node. We analyse the learning of auto-scaling strategies in order to optimise both performance and energy consumption of the whole system. We compare several model-based reinforcement learning with model-free Q-learning algorithm. The relevance of these algorithms is to faster update Q-value function with an additional planning phase allowed by approximated model of the dynamics of the environment. Secondly, we consider the same tandem queue scenario with MMPP (Markov modulated Poisson process) for arrivals. In this context, the arrival rate is varying over time and this information is hidden to the agent. Our goal is to assess the robustness of such model-based reinforcement learning algorithms in this particular scenario.
No file

Dates and versions

hal-03781620 , version 1 (20-09-2022)

Identifiers

Cite

Thomas Tournaire, Jeanne Barthélemy, Hind Castel-Taleb, Emmanuel Hyon. Reinforcement learning with model-based approaches for dynamic resource allocation in a tandem queue. ASMTA: International Conference on Analytical and Stochastic Modeling Techniques and Applications, Dec 2021, Tsukuba, Japan. pp.243-263, ⟨10.1007/978-3-030-91825-5_15⟩. ⟨hal-03781620⟩
35 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More