Browsing by Author "Liu, Rui"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Monitoring Routing Topology in Dynamic Wireless Sensor Network Systems
    (IEEE, 2015) Liu, Rui; Liang, Yao; Zhong, Xiaoyang; Department of Computer & Information Science, School of Science
    In large-scale multi-hop wireless sensor networks (WSNs) for data collection, the ability of monitoring per-packet routing paths at the sink is essential in better understanding network dynamics, and improving routing protocols, topology control, energy conservation, anomaly detection, and load balance in WSN deployments. In this study, we consider this important problem under tremendous WSN routing dynamics, which cannot be addressed by previous methods based on a routing tree model. We formulate the WSN topology inference as a novel optimization problem, and devise efficient decoding algorithms to effectively recover WSN routing topology at the sink in real-time using a small fixed-size path measurement attached to each packet. Rigorous complexity analysis of the devised algorithms is given. Performance evaluation is conducted via extensive simulations. The results reveal that our approach significantly outperforms other state-of-the-art methods including MNT, Pathfinder, and CSPR. Furthermore, we validate our approach intensively with a real-world outdoor WSN deployment running collection tree protocol for environmental data collection.
  • Thumbnail Image
    Item
    Understanding Compressed Sensing Inspired Approaches for Path Reconstruction in Wireless Sensor Networks
    (IEEE, 2015-12) Liu, Rui; Liang, Yao; Zhong, Xiaoyang; Department of Computer & Information Science, School of Science
    Abstract: Understanding per-packet routing dynamics in deployed and complex wireless sensor networks (WSNs) has become increasingly important for many essential tasks such as network performance analysis, operation optimization, system maintenance, and network diagnosis. In this paper, we study routing path recovery for data collection in multi-hop WSNs at the sink using a very small and fixed path measurement carried in each packet. We analyze the two recent compressed sensing (CS) inspired approaches called RTR and CSPR. We evaluate RTR versus CSPR as well as other state-of-the-art approaches including MNT and Pathfinder via simulations. Our work provides insights into the better understanding of the profound impacts of different CS-inspired approaches on their respective path reconstruction performance and the resource requirement on sensor nodes. The evaluation results show that the RTR significantly outperforms CSPR, MNT and Pathfinder.