Top-K with diversity-M data retrieval in wireless sensor networks

Publication Year:
2014
Usage 78
Downloads 63
Abstract Views 15
Repository URL:
http://scholarsmine.mst.edu/masters_theses/7338
Author(s):
Puram, Kiran Kumar
Publisher(s):
Missouri University of Science and Technology
Tags:
Computer Sciences
thesis / dissertation description
"Wireless Sensor Network is a network of a few to several thousand sensors deployed over an area to sense data and report that data back to the base station. There are many applications of wireless sensor networks including environment monitoring, wildlife tracking, troop tracking etc. The deployed sensors have many constraints like limited battery, limited memory and very little processing capacity. These constraints show direct effect on the network life time.In many applications of Wireless Sensor Networks, such as monitoring chemical leak, the user is not interested in all the data points from the entire region, but may want only top-k values. Moreover, a user may also be interested in getting top-k with diversity-m, Top (k,m), that is, top-k data should come from m different sub-regions (i.e., clusters). In this thesis, thus, we have considered the problem of continuous top-k query with diversity-m, i.e. we want to find the k highest values from at least m different clusters over a period of time in a wireless sensor network. In this context, we introduce an energy efficient scheme called Top (k,m). Our scheme is to utilize the Gaussian's probability function in estimating the probability of a sensor node value being in the final top-k set. Based on the probability, the node decides whether to forward data values to the base station or not. Moreover, we also make sure that top-k data items are coming from at least m-clusters, which is very helpful in monitoring applications. We have examined the performance of our scheme with respect to EXTOK and Grid approaches in terms of communication, energy usage and network life time"--Abstract, page iii.