Users’ time preference based stochastic resource allocation in cloud spot market: cloud provider’s perspective

Cloud Computing spot markets have enabled the users to make use of the spare computing capacities of the cloud providers at a relatively cheaper price which in turn has given the providers such as Amazon and Google an opportunity to earn extra money by auctioning-off the underutilized resources. However, resource availability is a problem in the spot market owing to spot-price fluctuations. Ignoring the customer’s preference is one of the potential reasons behind this. In this paper, we propose a time preference (value of service at different points of time) based stochastic integer linear programming model to allocate the cloud resources among the cloud users with a view to maximizing the revenue of cloud providers from the spot-market.