MRL-CC: a novel cooperative communication protocol for QoS provisioning in wireless sensor networks

  • Authors:
  • Xuedong Liang;Min Chen;Yang Xiao;Ilangko Balasingham;Victor C. M. Leung

  • Affiliations:
  • Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada.;Department of Computer Science and Engineering, Seoul National University, Korea.;Department of Computer Science, University of Alabama, Tuscaloosa, AL 35487-/0286, USA.;Department of Electronics and Telecommunications, Norwegian University of Science and Technology, NO-/7491 Trondheim, Norway/ Interventional Centre, Oslo University Hospital, N-/0027 Oslo, N ...;Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada

  • Venue:
  • International Journal of Sensor Networks
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Cooperative communications have been demonstrated to be effective in combating the multiple fading effects in wireless networks, and improving the network performance in terms of adaptivity, reliability, data throughput, and network lifetime. In this paper, we investigate the use of cooperative communications for Quality of Service (QoS) provisioning in resource-constrained wireless sensor networks, and propose MRL-CC, a Multi-agent Reinforcement Learning based multi-hop mesh Cooperative Communication mechanism. In MRL-CC, a multi-hop mesh cooperative structure is constructed for reliable data disseminations. The cooperative mechanism that defines cooperative partner assignments, and coding and transmission schemes, is implemented using a multi-agent reinforcement learning algorithm. We compare the network performance of MRL-CC with MMCC, a Multi-hop Mesh structure based Cooperative Communication scheme, and investigate the impacts of network traffic load, interference, and sensor node's mobility on the network performance. Simulation results show that MRL-CC performs well in terms of a number of QoS metrics, and fits well in large-scale networks and highly dynamic environments.