Abstract
With the large-scale application of the Internet of Things, various sensors continue to produce new and various environmental data. Among them, there may be some failure data caused by environmental interference, device aging, etc., and these failure data are given to relevant scientific researchers and The Internet of Things system brings huge problems. We propose a new kind of Internet of Things nodes combined with programmable switches failure detection method. Different from the method proposed by the predecessors, we perform failure detection during the sensor data packet transmission. This method realizes the interaction between the programmable switch and the local controller. It can perform failure detection on a large amount of sensor data in real-time. Use the processing power of programmable switches to reduce the feature extraction time in machine learning algorithms. In this article, we reviewed the technical background of programmable switch The Internet of Things failure detection and explained its architecture. To prove the feasibility of the system, we implemented it on the bmv2 software switch. The prototype was verified through experiments, simulation evaluation was performed on the real data set, and the average time for the machine learning algorithm to classify each sensor data was 1.26 ms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Roman, R., Zhou, J., Lopez, J.: On the features and challenges of security and privacy in distributed internet of things. Comput. Netw. 57(10), 2266–2279 (2013)
Manyika, J., Chui, M., Bisson, P., et al.: The Internet of Things: mapping the value beyond the hype (2015)
Suthaharan, S., Alzahrani, M., Rajasegarar, S., et al.: Labelled data collection for anomaly detection in wireless sensor networks. In: 2010 Sixth International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Brisbane, QLD, Australia, pp. 269–274. IEEE(2010)
Mqtt Homepage. https://mqtt.org/. Accessed 17 Jan 2021
Bosshart, P., Daly, D., Gibb, G., et al.: P4: Programming protocol-independent packet processors. ACM SIGCOMM Comput. Commun. Rev. 44(3), 87–95 (2014)
P4 Runtime Spec. https://p4.org/p4-spec/docs/P4-16-v1.2.1.html. Accessed 17 Jan 2021
Zhang, Z., Mehmood, A., Shu, L., et al.: A survey on fault diagnosis in wireless sensor networks. IEEE Access 6, 11349–11364 (2018)
Lau, B.C.P., Ma, E.W.M., Chow, T.W.S.: Probabilistic fault detector for wireless sensor network. Expert Syst. Appl. 41(8), 3703–3711 (2014)
Yu, C.B., Hu, J.J., Li, R., et al.: Node fault diagnosis in WSN based on RS and SVM. In: 2014 International Conference on Wireless Communication and Sensor Network, Wuhan, China, pp. 153–156. IEEE (2014)
Babaie, S., Khosrohosseini, A., Khadem-Zadeh, A.: A new self-diagnosing approach based on petri nets and correlation graphs for fault management in wireless sensor networks. J. Syst. Architect. 59(8), 582–600 (2013)
Panda, M., Khilar, P.M.: Distributed self fault diagnosis algorithm for large scale wireless sensor networks using modified three sigma edit test. Ad Hoc Netw. 25, 170–184 (2015)
Chanak, P., Banerjee, I., Sherratt, R.S.: Mobile sink based fault diagnosis scheme for wireless sensor networks. J. Syst. Softw. 119, 45–57 (2016)
Chalapathy R, Chawla S.: Deep learning for anomaly detection: A survey. arXiv preprint arXiv, 1901.03407, (2019)
P4 Homepage. https://p4.org/. Accessed 17 Jan 2021
Grpc. https://grpc.io/. Accessed 17 Jan 2021
Scikit-learn Stochastic Gradient Descentn. https://scikit-learn.org/dev/modules/sgd.html. Accessed 17 Jan 2021
Scikit-learn Multi-layer Perceptron. https://scikit-learn.org/dev/modules/neural_networks_supervised.html. Accessed 17 Jan 2021
Scikit-learn Support Vector Machines. https://scikit-learn.org/stable/modules/svm.html. Accessed 17 Jan 2021
Mininet Homepage. http://mininet.org/. Accessed 17 Jan 2021
BVM 2 Homepage. https://github.com/p4lang/behavioral-model. Accessed 17 Jan 2021
Virtualbox Homepage. https://www.virtualbox.org/. Accessed 17 Jan 2021
Pedregosa, F., Varoquaux, G., Gramfort, A., et al.: Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Paho-Mqtt Homepage. https://pypi.org/project/paho-mqtt/. Accessed 17 Jan 2021
Mosquitto Homepage. https://mosquitto.org/. Accessed 17 Jan 2021
Acknowledgement
When the thesis is finished, I would like to thank my instructor, Junxing Zhang, for his warm care and careful guidance. In the process of writing the thesis, I also received valuable suggestions from Guangfeng Guo and Renbo Yang, and I would like to express my sincere thanks.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, X., Yang, R., Guo, G., Zhang, J. (2021). Sensor Failure Detection Based on Programmable Switch and Machine Learning. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2021. Lecture Notes in Computer Science(), vol 12737. Springer, Cham. https://doi.org/10.1007/978-3-030-78612-0_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-78612-0_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78611-3
Online ISBN: 978-3-030-78612-0
eBook Packages: Computer ScienceComputer Science (R0)