Existing in-network query processing techniques are categorized as approximation and aggregation based approaches, where the former achieves lower network traffic at the expense of query response accuracy, whereas the later reduces query response inaccuracy by executing queries at the actual sensor nodes which necessitates the overhead of query specific sensor selection mechanism. In this paper, we propose a hybrid query processing framework that combines the advantages of both the approximation and aggregation based techniques and avoids their limitations. In our approach, we construct a hierarchical probabilistic data model representing the overall sensor data characteristics across the network, which is query independent and is later used for selecting sensor nodes to process user queries. Experimental results illustrate the efficacy of the proposed framework compared to contemporary approximation and aggregation based query processing techniques.
Existing in-network query processing techniques are categorized as approximation and aggregation based approaches. The former achieves lower query response delay at the expense of accuracy, while the latter reduces query response inaccuracy by executing queries at the actual sensor nodes resulting in longer delay. In this paper, we propose a query processing framework which is delay as well as accuracy aware and capable of dynamic adjustment to meet user/application requirements. When query response is required within specific delay, it provides approximated sensor data meeting the delay requirement. On the other hand, when query response accuracy is vital, it tolerates longer delay in acquiring response with the desired accuracy. To achieve this, we propose a novel method of constructing a delay aware spanning tree (DAST) based on query load and organizing sensor data with varied accuracy. Experimental results illustrate superiority of the proposed framework against competing approaches.