Data Center Server Provision: Distributed Asynchronous Control for Coupled Renewal Systems

TL;DR

This paper introduces a distributed control algorithm for data center servers that minimizes costs by managing asynchronous server states and request routing without requiring probabilistic traffic information, validated through real traffic simulations.

Contribution

It develops a novel online distributed control algorithm for server state management and request routing that is near optimal and does not rely on traffic probability models.

Findings

Algorithm achieves near optimal cost with probability 1.

Uses a single queue via virtualization with similar performance.

Demonstrates efficiency through real data center traffic simulations.

Abstract

This paper considers a cost minimization problem for data centers with N servers and randomly arriving service requests. A central router decides which server to use for each new request. Each server has three types of states (active, idle, setup) with different costs and time durations. The servers operate asynchronously over their own states and can choose one of multiple sleep modes when idle. We develop an online distributed control algorithm so that each server makes its own decisions, the request queues are bounded and the overall time average cost is near optimal with probability 1. The algorithm does not need probability information for the arrival rate or job sizes. Next, an improved algorithm that uses a single queue is developed via a "virtualization" technique which is shown to provide the same (near optimal) costs. Simulation experiments on a real data center traffic trace demonstrate the efficiency of our algorithm compared to other existing algorithms.