Capacity Allocation for Clouds with Parallel Processing, Batch Arrivals, and Heterogeneous Service Requirements

Abstract: Problem Definition: Allocating sufficient capacity to cloud services is a challenging task, especially when demand is time-varying, heterogeneous, contains batches, and requires multiple types of resources for processing. In this setting, providers decide whether to reserve portions of their capacity to individual job classes or to offer it in a flexible manner. Methodology/results: In collaboration with Huawei Cloud, a worldwide provider of cloud services, we propose a heuristic policy that allocates multiple types of resources to jobs and also satisfies their pre-specified service level agreements (SLAs). We model the system as a multi-class queueing network with parallel processing and multiple types of resources, where arrivals (i.e., virtual machines and containers) follow time-varying patterns and require at least one unit of each resource for processing. While virtual machines leave if they are not served immediately, containers can join a queue. We introduce a diffusion approximation of the offered load of such system and investigate its fidelity as compared to the observed data. Then, we develop a heuristic approach that leverages this approximation to determine capacity levels that satisfy probabilistic SLAs in the system with fully flexible servers. Managerial Implications: Using a data set of cloud computing requests over a representative 8-day period from Huawei Cloud, we show that our heuristic policy results in a 20% capacity reduction and better service quality as compared to a benchmark that reserves resources. In addition, we show that the system utilization induced by our policy is superior to the benchmark, i.e., it implies less idling of resources in most instances. Thus, our approach enables cloud operators to both reduce costs and achieve better performance.