Parallel processing of nearest neighbor queries in declustered spatial data

Abstract

In this paper, we propose an &cient solution to the problem of nearest neighbor query processing in decluste red spatial data. Recently a branch-and-bound nearest neighbor finding (BB-NNF) algorithm has been designed to process nearest neighbor queries in R-trees. However, this algorithm is strictly serial (branch-and-bound oriented) and its performance degrades if applied to a parallel environment, since it does not exploit any kind of parallelization.We develop an eEicient query processing strategy tir parallel nearest neighbor finding (P-NNF), assuming a shared nothing multi-processor architecture, where the processors i communicate via a network. In our method, the relevant : sites are activated simultaneously.In order to achieve this goal, statistical information is used. The dTiciency mcasurc is the response time of a given query. E2cperimental results, based on real-life and synthetic datasets, show that the proposed method outperforms the branch-andbound method by factors.We focus on Zd space but generalizations to higher dimensions are straightforward.

On efficiently processing nearest neighbor queries in a loosely coupled set of data sources

“…RWQ_ObjDens and RWQ_ObjCnt represent our adaptations to the algorithms introduced in [16]. RNNQ_ObjCnt simulates the algorithms presented in [23], while RNNQ_Max and RWQ_Max simulate the behavior of the other approaches from literature discussed in Section 2.4.…”

“…In [23,25] several algorithms are proposed that aim at minimizing the number of source databases to be queried and the number of objects to be fetched from each system. They use a distributed R-Tree approach where the upper part is stored at the primary server and the leaves of the tree are stored at source databases.…”

“…Besides being expensive to keep the object counts up-to-date, this guaranteed single iteration behavior leads to a lot of extra work. [16] refers to this method as the "Bucket-Based Method", [24] calls this range the threshold distance, [23] uses this range in the "Parallel Nearest Neighbor Finding Method".…”

Towards real-time parallel processing of spatial queries

“…But the query processing and optimization algorithms incorporate both kinds of components to achieve better performance. In [9], Papadopoulos and Manolopoulos studied the performance of nearest neighbor queries in multi-disk multi-processor parallel architectures. They utilized statistical information to estimate the number of leaf-node accesses and to determine an efficient parallel execution strategy over all processors.…”

“…The detailed processing procedure for a window query is described in Section 2.2 9 We assume the entire universe is a square unit. We adopt two spatial datasets in our experiment, one synthetic dataset and one real dataset.…”