Procurement Auctions to Trade Computing Capacity in the Cloud

Cloud computing is often seen as a part of larger development towards long-dreamed vision of society where computing is delivered as a utility. However, we argue that more research on the business side of cloud computing need to be done to help service providers to create innovative cloud business models and to get cloud computing to grow and develop in sustainable manner. In particular, the analysis and development of adequate revenue models and pricing mechanisms for cloud services is a critical challenge in this scenario, because pricing is expected to be one of the key changes compared to current paradigm. From the provider perspective, using an effective dynamic pricing strategy can make a difference between making a profit or a loss: in an open cloud marketplace, the strategy is even more important given its very dynamic and volatile nature. In this paper we analyze auction-based mechanisms to trade spare computing resources, which are alternative to the direct-sell and may turn to be profitable for both providers and consumers. Performed simulations show that accurate modeling and tuning of auction parameters can lead to maximize the utilization of resources.