Novel Sensor Scheduling Scheme for Intruder Tracking in Energy Efficient Sensor Networks

Diddigi, Raghuram Bharadwaj and Prabuchandran, KJ and Bhatnagar, Shalahh (2018) Novel Sensor Scheduling Scheme for Intruder Tracking in Energy Efficient Sensor Networks. In: IEEE WIRELESS COMMUNICATIONS LETTERS, 7 (5). pp. 712-715.

PDF Ieee_Wir_Com_Let_7-5_712_2018.pdf - Published Version Restricted to Registered users only Download (319kB) | Request a copy

Abstract

We consider the problem of tracking an intruder using a network of wireless sensors. For tracking the intruder at each instant, the optimal number and the right configuration of sensors has to be powered. As powering the sensors consumes energy, there is a trade off between accurately tracking the position of the intruder at each instant and the energy consumption of sensors. This problem has been formulated in the framework of partially observable Markov decision process (POMDP). Even for the state-of-the-art algorithm in the literature, the curse of dimensionality renders the problem intractable. In this letter, we formulate the intrusion detection (ID) problem with a suitable state-action space in the framework of POMDP and develop a reinforcement learning algorithm utilizing the upper confidence tree search method to solve the ID problem. Through simulations, we show that our algorithm performs and scales well with the increasing state and action spaces.

Item Type:	Journal Article
Publication:	IEEE WIRELESS COMMUNICATIONS LETTERS
Publisher:	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Additional Information:	Copy right for this article belong to IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Keywords:	Wireless sensor networks; intruder tracking; Monte Carlo tree search
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation Division of Interdisciplinary Sciences > Robert Bosch Centre for Cyber Physical Systems
Date Deposited:	31 Oct 2018 13:58
Last Modified:	31 Oct 2018 13:58
URI:	http://eprints.iisc.ac.in/id/eprint/60998

Actions (login required)

View Item