LAUSR

In this paper, we examine new plan pricing schemes for multimedia applications that offload computing-intensive tasks to computing servers incurring both communication and computing costs. Pricing schemes offered to users include: 1) a pay-as-you-go payment for usage of communication or computing resources, 2) an upfront data (resp. computing) plan for unlimited usage of communication (resp. computing) resources during a period, and 3) an upfront combo plan for unlimited usage of both communication and computing resources during a period. We aim to solve an online plan reservation problem: the amount of resources needed by a task is only known when it arrives, i.e., the future is unknown. However, even if the resource usage of future tasks is known in advance, the plan reservation problem is NP-hard and thus challenging. To tackle this problem, we propose a randomized online reservation (ROR) scheme to reserve plans probabilistically, where the probability is determined by the recent usage of resources. The performance gap (competitive ratio) between our proposed scheme and the optimal solution is analyzed and derived in closed-form, and this gap is proved to be the minimum among all online algorithms which do not know the usage of future tasks. Trace-driven simulations verify the cost advantage of ROR and characterize how different prices of plans influence users’ plan reservation strategies.