Problem
Research questions and friction points this paper is trying to address.
heterogeneous load balancing
unknown service rates
Shortest-Expected-Delay (SED)
empirical policies
online learning
Learning Adaptive SED for heterogeneous load balancing
🤖 AI Summary
研究通过在线学习算法解决异构服务速率未知情况下的负载均衡问题，该算法在学习服务速率的同时收敛到SED策略。
📝 Abstract
We study a two-server load balancing system with heterogeneous service rates that are a priori unknown to the dispatcher. The goal is to route customers according to the Shortest--Expected--Delay (SED) policy, but this requires knowledge of the service rates. Empirical policies that route based on estimates perform poorly: due to estimation error, the empirical policy disagrees with the oracle on an infinite region of the state space. We propose an online learning algorithm that converges to SED while learning the service rates. The algorithm carefully balances empirical SED routing with forced exploration phases that guarantee sufficient sampling of both servers. We prove that our algorithm achieves finite regret; this differs from classical Multi-Armed Bandit settings where regret typically grows logarithmically in time. Finally, numerical experiments demonstrate the performance of our algorithm and highlight the regimes in which forced exploration is especially beneficial.
Innovation
Methods, ideas, or system contributions that make the work stand out.
online learning algorithm
Shortest-Expected-Delay (SED) policy
forced exploration
finite regret
🔎 Similar Papers
No similar papers found.
