Quantifying the Performance Gap for Simple Versus Optimal Dynamic Server Allocation Policies
This work helps service providers balance costs and delays in cloud systems, but it is incremental as it builds on existing models for policy analysis.
The paper tackles the problem of dynamic server allocation in cloud computing by comparing simple policies to optimal ones, finding that simple policies can achieve performance close to optimal with a quantified gap.
Cloud computing enables the dynamic provisioning of server resources. To exploit this opportunity, a policy is needed for dynamically allocating (and deallocating) servers in response to the current load conditions. In this paper we describe several simple policies for dynamic server allocation and develop analytic models for their analysis. We also design semi-Markov decision models that enable determination of the performance achieved with optimal policies, allowing us to quantify the performance gap between simple, easily implemented policies, and optimal policies. Finally, we apply our models to study the potential performance benefits of state-dependent routing in multi-site systems when using dynamic server allocation at each site. Insights from our results are valuable to service providers wanting to balance cloud service costs and delays.