| The focus of this work is on maximizing the benefits of parallelization when processing some queries over Spatial and Spatio-Temporal data by fusing the semantics of: (1) data itself; i.e. modeling, representation, and storage. (2) the underlying processing environment such as multi-core architecture and distributed cloud storage and computing. We have applied this paradigm to several specific examples - Spatio-Temporal range and nearest neighbor queries and Spatial aggregates queries. Specifically we analyzed different data and query partitioning strategies and their impact on the load assignment, balancing, and cooperation on multi core settings. From alternative perspective, we considers the impact of different contexts when attempting to exploit parallelization approaches for processing queries over various computing environments. Algorithmic solutions for parallel processing of queries cater to splitting the load (i.e. data or query) among units relying on a certain set of features of a given environment. We postulate that incorporating the service-features should be coupled with the algorithms/heuristics for processing particular queries, in addition to the volume of the data. |
