Cyber Security in Wind Energy Generation Via Deep Learning

International Journal of Computer Science and Engineering

© 2022 by SSRG - IJCSE Journal

Volume 9 Issue 12

Year of Publication : 2022

Authors : P. Rajadurai

10.14445/23488387/IJCSE-V9I12P101

How to Cite?

P. Rajadurai, "Cyber Security in Wind Energy Generation Via Deep Learning," SSRG International Journal of Computer Science and Engineering , vol. 9,  no. 12, pp. 1-6, 2022. Crossref, https://doi.org/10.14445/23488387/IJCSE-V9I12P101

Abstract:

This paper introduces a novel cyberattack classification via a convolutional neural network. Initially, the data are gathered using wind turbine sensors. The designed infrastructure is used to keep an eye on the cyberattacks as they happen and to ensure the stability of CNC machines for efficient cutting processes that can assist in raising product quality. In order to detect the vibration conditions, for this reason, a force sensor has been installed in the milling CNC machine center. This paper proposes cyber security in wind energy via deep learning, an optimized algorithm that uses CNN to classify differences between CNC machines to maintain the CNC machine. Consequently, the proposed deep learning can properly classify four different types of attacks, namely combinatorial attacks, denial-of-service (DOS) attacks, phishing attacks, and zero-day attacks. Multiple schemes are shown to illustrate the reliability of the proposed system, namely one in which the scheme may instantly secure itself when the cyberattack triggers the backup broker to switch to the backup. Successful cyberattacks on wind farms can harm power systems in several ways, including the grid's stability, the operation of the energy market, and the stability of the wind farm system. Considering the cybersecurity of wind generators, the specific aspects of cyber-attack modeling, detection, and mitigation are the greatest priority. Ultimately, efforts must be made to create smart wind assets that are also cyber-resilient to keep uninterrupted operations. Sensitivity, accuracy, specificity, and recall are the parameters considered when evaluating the proposed model's effectiveness. The suggested technique exceeds RNN, ANN, and DNN in terms of global accuracy by 99.01%.

Keywords:

Deep learning, Industry 4.0, Internet of Things, Smart machines, Milling process, Sensors, CNN.

References:

[1] Syeda Manjia Tahsien, Hadis Karimipour, and Petros Spachos, “Machine Learning Based Solutions for Security of Internet of Things (IoT): A Survey,” Journal of Network and Computer Applications, vol. 161, p. 102630, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Mahmoud Elsisi et al., “Effective IoT-Based Deep Learning Platform for Online Fault Diagnosis of Power Transformers Against Cyber Attacks and Data Uncertainties,” Measurement, vol. 190, p. 110686, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] S.Veerapandi, R.Surendiran, and K.Alagarsamy, "Enhanced Fault Tolerant Cloud Architecture to Cloud based Computing using Both Proactive and Reactive Mechanisms," DS Journal of Digital Science and Technology, vol. 1, no. 1, pp. 32-40, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mahmoud Elsisi et al., “Reliable Industry 4.0 Based on Machine Learning and IoT for Analyzing, Monitoring, and Securing Smart Meters,” Sensors, vol. 21, no. 2, p. 487, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Diptiban Ghillani, “Deep Learning and Artificial Intelligence Framework to Improve the Cyber Security,” Authorea Preprints, 2022. [Google Scholar] [Publisher Link] [6] Peravali Kavya, "An Efficient Machine Learning based Algorithm for Preventing Phishing Websites," SSRG International Journal of Computer Science and Engineering, vol. 5, no. 12, pp. 10-13, 2018.
[CrossRef] [Publisher Link]
[7] Cheng Feng et al., “A Deep Learning-Based Framework for Conducting Stealthy Attacks in Industrial Control Systems,” arXiv preprint arXiv:1709.06397, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[8] B Sunaina Sharma, "Enlargement of an Intellectual and Energy Proficient Spindle System," SSRG International Journal of Mechanical Engineering, vol. 3, no. 12, pp. 5-9, 2016.
[CrossRef] [Publisher Link]
[9] Jiafu Wan et al., “Software-Defined Industrial Internet of Things in the Context of Industry 4.0,” IEEE Sensors Journal, vol. 16, no. 20, pp. 7373-7380, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Mahmoud Elsisi et al., “An Improved Neural Network Algorithm to Efficiently Track Various Trajectories of Robot Manipulator Arms,” IEEE Access, vol. 9, pp. 11911-11920, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Ganiyu Adedayo Ajenikoko et al., "Development of a Technique for Identification of Critical Locations for Maintaining Voltage Stability with Penetration of Wind Generation in Power Systems," SSRG International Journal of Electrical and Electronics Engineering, vol. 7, no. 5, pp. 9-20, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Mahmoud Elsisi et al., “Effective Nonlinear Model Predictive Control Scheme Tuned by Improved NN for Robotic Manipulators,” IEEE Access, vol. 9, pp. 64278-64290, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Zewen Li et al., “A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 12, pp. 6999-7019, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Mulumudi Rajesh, and A. Lakshmi Devi, "Wind, PV Solar, Hydro and Hybrid Energy Storage System-Based Intelligent Adaptive Control for Standalone Distributed Generation System," SSRG International Journal of Electrical and Electronics Engineering, vol. 9, no. 11, pp. 67-94, 2022.
[CrossRef] [Publisher Link]
[15] Jiuxiang Gu et al., “Recent Advances in Convolutional Neural Networks,” Pattern Recognition, vol. 77, pp. 354-377, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[16] S. Priyanka et al., "IoT Based Hybrid Artificial Tree for Solar/Wind Power Generation with Pollution Control and Monitoring," SSRG International Journal of Computer Science and Engineering, vol. 8, no. 4, pp. 1-3, 2021.
[CrossRef] [Publisher Link]