Options-based sequential auctions for dynamic cloud resource allocation

Abstract

With growing demands for cloud computing services, the idea of managing limited cloud resources for making a profit has arisen as an important problem. Auction theory is recently considered as a viable way to solve the problem of cloud resource allocation. In this paper, we consider a model for Cloud of Clouds Networks (CCNs) with different types of servers along with customers with heterogeneous demands, in which customers and cloud servers may join and leave the CCN at will. We propose an options-based sequential auction that not only provides a good match with the dynamic structure of the problem, but also solves the entrance time problem and possesses the truthfulness property. We study both first-price and second-price options-based sequential auctions, and model the price matching processes in those auctions as Markov chains. We provide mathematically tractable methods to find the expected value of the CCN manager's revenue, and further show how the proxy agents' patience time affects the CCN manager's revenue.