A Novel Parallel Processing for Continuous k-Nearest Neighbor Queries

Abstract

Continuous nearest neighbor queries in road networks have recently received many attentions. To evaluate multiple concurrent continuous k nearest neighbors queries towards moving objects, we propose a multi-threading processing of multiple continuous queries (MPMCQ) framework, which exploits pipeline strategy and departs the continuous query processing into three simultaneous stages: query processing, query executing and query results dispatching to improve the parallelism with multi-threading technology. Considering the computational capability of mobile client to locate the edge containing it, we use memory-resident hash table and linear list structures to describe the moving objects and store the directional model. We propose the unidirectional network expansion algorithm to reduce the CPU cost of continuous k-NN queries processing. Experimental results show that the algorithm outperforms existing algorithms including IMA and MKNN algorithms.