Online Learning of Weakly Coupled MDP Policies for Load Balancing and Auto Scaling
Systems and Control
2024-06-21 v1 Artificial Intelligence
Networking and Internet Architecture
Systems and Control
Abstract
Load balancing and auto scaling are at the core of scalable, contemporary systems, addressing dynamic resource allocation and service rate adjustments in response to workload changes. This paper introduces a novel model and algorithms for tuning load balancers coupled with auto scalers, considering bursty traffic arriving at finite queues. We begin by presenting the problem as a weakly coupled Markov Decision Processes (MDP), solvable via a linear program (LP). However, as the number of control variables of such LP grows combinatorially, we introduce a more tractable relaxed LP formulation, and extend it to tackle the problem of online parameter learning and policy optimization using a two-timescale algorithm based on the LP Lagrangian.
Keywords
Cite
@article{arxiv.2406.14141,
title = {Online Learning of Weakly Coupled MDP Policies for Load Balancing and Auto Scaling},
author = {S. R. Eshwar and Lucas Lopes Felipe and Alexandre Reiffers-Masson and Daniel Sadoc Menasché and Gugan Thoppe},
journal= {arXiv preprint arXiv:2406.14141},
year = {2024}
}