Title: Energy-aware task scheduling by a true online reinforcement learning in wireless sensor networks

Authors: Muhidul Islam Khan; Kewen Xia; Ahmad Ali; Nelofar Aslam

Addresses: School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China ' School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China ' School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China ' School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China

Abstract: Wireless sensor networks (WSNs) are an attractive platform for various pervasive computing applications. A typical WSN application is composed of different tasks. In this paper, an energy-aware task scheduling method is proposed to achieve better energy consumption/performance trade-off. The proposed method exploits a true online reinforcement learning algorithm. This method is compared with the existing approaches exploiting online learning: distributed independent reinforcement learning (DIRL), reinforcement learning (RL), cooperative reinforcement learning (CRL) and exponential weight for exploration and exploitation (Exp3), in terms of tracking quality/energy consumption trade-off. Simulation results show that our proposed method outperforms existing methods for the target tracking application.

Keywords: WSNs; wireless sensor networks; task scheduling; energy-awareness; true online reinforcement learning; DIRL; distributed independent reinforcement learning; CRL; cooperative reinforcement learning; adversarial bandit solvers.

DOI: 10.1504/IJSNET.2017.087899

International Journal of Sensor Networks, 2017 Vol.25 No.4, pp.244 - 258

Received: 01 Oct 2015
Accepted: 27 Jun 2016

Published online: 07 Nov 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article