Detection of Faults in Flying Wireless Sensor Networks Using Adaptive Reinforcement Learning
G. Kiruthiga1, K. Kalaiselvi2, R. S Shudapreyaa3, V. Dineshbabu4

1Dr. G. Kiruthiga, IES College of Engineering, (Kerala), India.
2K. Kalaiselvi, Karpagam Institute of Technology, Coimbatore (Tamil Nadu), India.
3R. S Shudapreyaa, Karpagam Institute of Technology, Coimbatore (Tamil Nadu), India.
4V. Dineshbabu, Karpagam Institute of Technology Coimbatore (Tamil Nadu), India.
Manuscript received on 06 June 2019 | Revised Manuscript received on 30 June 2019 | Manuscript Published on 04 July 2019 | PP: 761-763 | Volume-8 Issue-1S4 June 2019 | Retrieval Number: A11410681S419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: In recent decade, diagnosing the fault in Unmanned Autonomous Vehicle (UAV) based Wireless Sensor Networks (WSN) has received a little attention by the researchers. The limitations of UAV-WSN environment possibly affects the fault diagnosis. The limitations associated with UAV-WSN conditions are considered as the scope of present study in diagnosing the fault in network. The study focuses mainly on improving the overall lifespan of network and further it tends to increase the network scalability. Since, the overall network lifetime and scalability reduces as the condition of the network worsens. Hence, the observation on network becomes poor in identifying the faults associated with the network. To resolve the issue, anAdaptive Reinforcement Learning is proposed in the study for the fault detection of flying sensor nodes in UAV-WSN. This approach diagnoses the faults in the network in an effective way and improves the overall efficiency of the network.
Keywords: Fault Diagnosis, UAV, WSN, Adaptive Reinforcement Learning.
Scope of the Article: Adaptive Systems