A Soft Fault Detection Mechanism with High Accuracy on Machine-to-Machine Communication Networks

• Published in: 2014 IEEE International Conference on Internet of Things (iThings), and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) pp. 340 - 343
• Main Authors: Yuan-Kang Shih, Hung-Yu Wei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2014
• Subjects: Accuracy; Communication networks; Conferences; Fault detection; M2M; Machine-to-Machine; QoS; Sensors; Wireless communication; Wireless sensor networks
• ISBN: 1479959677; 9781479959679
• DOI: 10.1109/iThings.2014.63

The machine-to-machine (M2M) communication network is a promising concept to improve the user experience. The M2M communication enables two M2M devices in proximity of each other to establish a direct local link and bypass the base station. Machine-to-machine communication can be applied to various important fields, such as military applications, public safety, environmental monitoring, commercial and social networking, and health and medical monitoring, ect. Hence the networks must exclude the faulty devices or faulty sensors to ensure the network Quality of Service (QoS). Fault detection is highly preferred on machine-to-machine communication networks. Device fault can be divided into two types: hard fault and soft fault. We will give a mechanism with capability to detect and distinguish soft fault devices. The simulation results indicate when a large number of machine-to-machine devices under a machine-to-machine communication network, the false alarm rate of the soft fault detection mechanism is close to 0% and the detection accuracy of it is close to 100%.