Abstract
With the development of urbanization, the social demand for energy is increasing. The safety production monitoring of electric power has always been an important issue related to the national economy and people’s livelihood. Thanks to deep learning technology, a large number of monitoring and computer vision analysis algorithms have begun to popularize, but only in some simple scenes, or only after investigation and evidence collection. Due to the lack of training samples, the traditional machine learning method cannot be used to train the generative model in hazard situations. Besides, it is a pressure and challenge to the calculation capacity, bandwidth and storage of the system. This paper proposes a platform level solution based on data flow, which can use a large number of cost-effective general-purpose devices to form a cluster, and adjust the task load of each computing unit through software level resource scheduling. The equipment adopts 2U general specification, which can provide better heat dissipation and improve the cooling efficiency of the cluster. At present, the system has been deployed in several pilot projects of the State Grid. It uses LSTM algorithm to establish the contour with normal data training, and uses the deviation of 12.5% as the threshold to identify the abnormal scene. It can accurately identify the obvious suspected abnormal behavior with 98.6% and push it to the operation and maintenance personnel for secondary confirmation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pliatsios, D., Sarigiannidis, P.G., Lagkas, T., et al.: A survey on SCADA systems: secure protocols, incidents, threats, and tactics. IEEE Commun. Surv. Tutor. 99 (2020)
Han, J., Liu, J., Lei, H.: Agent-based simulation of emergency response of urban oil and gas pipeline leakage. In: The 11th International Conference (2019)
Karbovskii, V., Voloshin, D., Karsakov, A., Bezgodov, A., Zagarskikh, A.: Multiscale agent-based simulation in large city areas: emergency evacuation use case. Proc. Comput. Sci. 51, 2367–2376 (2015)
Francia, G.A., Thornton, D., Brookshire, T.: Wireless vulnerability of SCADA systems. ACM (2012)
Rakha, T., Liberty, A., Gorodetsky, A., Kakillioglu, B., Velipasalar, S.: Heat mapping drones: an autonomous computer-vision based procedure for building envelope inspection using unmanned aerial systems (UAS). Technol.|Archit.+ Des. 2(1), 30–44 (2018)
Danielski, I., Fröling, M.: Diagnosis of buildings’ thermal performance-a quantitative method using thermography under non-steady state heat flow. Energy Proc. 83, 320–329 (2015)
Oord, A., Dieleman, S., Zen, H., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)
Yang, L., Shi, M., Gao, S.: The method of the pipeline magnetic flux leakage detection image formation based on the artificial intelligence. In: Proceedings of the International Conference on Video and Image Processing, ICVIP 2017, pp. 20–24. Association for Computing Machinery, New York (2017)
Rajalakshmi, A., Shahnasser, H.: Internet of Things using Node-Red and Alexa. In: 2017 17th International Symposium on Communications and Information Technologies (ISCIT), Cairns, QLD, pp. 1–4 (2017)
Busogi, M., Shin, D., Ryu, H., Oh, Y.G., Kim, N.: Weighted affordance-based agent modeling and simulation in emergency evacuation. Saf. Sci. 96, 209–227 (2017)
Jumadi, J., Carver, S., Quincey, D.: A conceptual framework of volcanic evacuation simulation of Merapi using agent-based model and GIS. Proc. - Soc. Behav. Sci. 227, 402–409 (2016)
Zhou, C., Wang, H.H., Zhuo, H.: A multi-agent coordinated planning approach for deadline required emergency response tasks. IET Control Theory Appl. 9, 447–455 (2014)
Shafiee, M.E., Berglund, E.Z.: Agent-based modeling and evolutionary computation for disseminating public advisories about hazardous material emergencies. Comput. Environ. Urban Syst. 57, 12–25 (2016)
Cheng, M., Li, Q., Lv, J., et al.: Multi-scale LSTM model for BGP anomaly classification. IEEE Trans. Serv. Comput. 1–17 (2018)
Zhu, Q.Z., et al.: Development status and trend of global oil and gas pipelines. Oil Gas Storage Transp. 04, 375–380 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Fan, X., Gong, M., Pang, X., Feng, H. (2022). Safety Application Platform of Energy Production Surveillance Based on Data Flow. In: Wei, J., Zhang, LJ. (eds) Big Data – BigData 2021. BigData 2021. Lecture Notes in Computer Science(), vol 12988. Springer, Cham. https://doi.org/10.1007/978-3-030-96282-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-96282-1_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96281-4
Online ISBN: 978-3-030-96282-1
eBook Packages: Computer ScienceComputer Science (R0)