Level Biased Random Walk for Information Discovery in Wireless Sensor Networks

Abstract

In this paper, we consider the problem of information discovery in Wireless Sensor Networks (WSNs), where the search initiator is unaware of any of the γ locations of target information. One of the fundamental techniques which is used for this purpose is Random walk since it has several advantages like low cost (number of bytes transmitted) compared to flooding, load balancing among nodes, and minimal state maintenance. Even though Random walk reduces cost, it is still high enough for energy constrained networks like WSNs. Furthermore, Random walk incurs high latencies making it infeasible for delay sensitive applications. To alleviate the above mentioned problems in Random walk, we propose a variant of Random walk called Level Biased Random Walk (LBRW). In LBRW, the search packet traverses from the sink node (search initiator) to the circumference nodes (nodes without children) of the network and vice versa via random paths. The idea is to improve the node coverage of LBRW compared to that of Random walk by forcing it to move in some particular directions. We show by extensive simulations that the cost and latency of LBRW are only 56-69% of that by Random walk, when γ = 3 and at reasonable densities.