Cost-efficient partitioning of spatial data on cloud

With the rise of mobile technologies (e.g., smart phones, wearable technologies) and location-aware Internet browsers, a massive amount of spatial data is being collected since such tools allow users to geo-tag user content (e.g., photos, tweets). Meanwhile, cloud computing providers such as Amazon and Microsoft allow users to lease computing resources where users are charged based on the amount of time they reserve each server, with no consideration of utilization. One key factor that affects server utilization is partitioning method especially in data-driven location-based services. Because if the data partitions are not accessed, the servers storing them remain idle but the user is still charged. Whereas, existing spatial data partitioning techniques aim to 1) cluster spatially close data objects to minimize disk I/O and 2) create equi-sized partitions. On the contrary, the objective is different for cloud given the current pricing models. In this paper, we propose a novel cost-efficient partitioning method for spatial data where an increase in the servers' utilizations yields less number of servers to support the same workload, thus saving cost. Extensive experiments on Amazon EC2 infrastructure demonstrate that our approach is efficient and reduces the cost by up to 40%.