Intrusion detection and mitigation of attacks in microgrid using enhanced deep belief network

ABSTRACT

The convergence from the electric grid to the smart microgrid motivates the incorporation of the intrusion detection system to identify intruders and mitigate the resultant damages to ensure system stability. It is planned to employ the Deep Belief Network (DBN), which is one of the deep learning techniques with some improvement to detect the attacks in a microgrid. To improve the accuracy of the detection, a rule-based detection technique is added to enhance the detection of intruders using DBN. The proposed technique is supported with the layered micro-grid architecture that makes the system flexible and simple toward the implementation. The proposed Enhanced DBN (EDBN) performance is measured in different bus representations for identifying the higher hit rate and rejection rate, lesser miss rate and false-positive rate. Two attacks, such as False Data Injection and Denial of Service attacks, are generated by Greedy Algorithm and are detected by the proposed technique. Compared to the existing detection and control system, the proposed EDBN technique provides accuracy higher than 92%, false alarm rate less than 1%. Thus, the experimental results show that the proposed technique accuracy is higher than the existing intrusion detection techniques in a microgrid.

KEYWORDS:

• Intrusion detection
• MicroGrid
• deep belief network
• Rule-Based Intrusion Detection
• restricted Boltzmann machine
• greedy algorithm

Disclosure statement

No potential conflict of interest was reported by the author(s).

Author contributions

Concepts, methodology, and validation of the work related to DBN in this paper were done by Danalakshmi Durairaj and Abolfazl Mehbodniya. Thiruppathy Kesavan Venkatasamy contributed the work related to Intrusion Detection methodology and visualization. Draft preparation, editing, and visualization were contributed by Tanweer Alam. Literature review and formal analysis were done by Syed Umar.

Supplementary material

Supplemental data for this article can be accessed on the publisher’s website.

Additional information

Notes on contributors

Danalakshmi Durairaj

Danalakshmi Durairaj has received her B.E. degree in Electrical and Electronics Engineering from Thiagarajar College of Engineering, Madurai, affiliated to Madurai Kamaraj University, India in 2003 and M.E. degree in Power Systems Engineering from Thiagarajar College of Engineering, Madurai, affiliated to Anna University, Chennai, Tamil Nadu, India, in 2006. She has completed her Ph.D. degree in Kalasalingam University in September 2017. Presently, she is working as Associate Professor in the Department of Electrical & Electronics Engineering, GMR Institute of Technology, Andhra Pradesh. She is actively involved in research for the past seven years. She is presently working in the area of Power System Optimization, Renewable energy, Power system security and Smart Grid.

Thiruppathy Kesavan Venkatasamy

Thiruppathy Kesavan Venkatasamy completed his M.E. and Ph.D. in the field of Computer Science and Engineering from Anna University, Chennai, India, and Kalasalingam University, Krishnankoil, India respectively. He has more than 17 years of Teaching Experience from 2003 onwards. He worked as Assistant Professor in Kalasalingam University, Associate Professor in Renganayagi Varatharaj College of Engineering, Sivakasi, Tamil Nadu, Senior Assistant Professor in Madanapalle Institute of Technology and Science, Madanapalle, Andhra Pradesh, India, Professor in GMR Institute of Technology, Rajam, Andhra Pradesh and presently working as Professor in Visvodaya Engineering College, Kavali, Andhra Pradesh. His areas of interest include Internet of Things, Wireless Sensor Networks, Computer Networks, Network Security, System Software and Microprocessors.

Abolfazl Mehbodniya

Abolfazl Mehbodniya is an associate professor and head of ECE department at Kuwait College of Science and Technology (KCST). Before coming to KCST, he worked as a Marie-Curie senior research Fellow at university college Dublin, Ireland and prior to that he worked as an assistant professor at Tohoku University, Japan and as a research scientist in advanced telecommunication research (ATR) international, Kyoto, Japan. Dr Mehbodniya received his Ph.D. from INRS-EMT University of Quebec, Montreal, Canada in 2010. His research interests are in the field of communications engineering, IoT and artificial intelligence in wireless networks and real world applications. He is the recipient of numerous awards including JSPS young faculty startup grant, KDDI foundation grant, Japan Radio Communications Society (RCS) active researcher award, European commission Marie Skodowska-Curie Fellowship and NSERC Visiting Fellowships in Canadian Government Laboratories. He is a senior member of IEEE and IEICE.

Syed Umar

Syed Umar presently is working as Professor in Dept. of Computer Science, College of Engineering, Wollega University, Nekemte, Ethiopia. He has total 15 years of Teaching and Research Experience. He has published 100+ research papers in National and International journals of repute with very good citations and h-index and presented more than 40 papers in various National and International conferences. Many students received Best poster award under his able guidance. He has filed four patents to Indian Patent Office. He has filed 2 International patents to Australia Patent Office. His area of research is Computer Networks, wireless communication, Sensor Networks, Mobile Communication etc. He is a life member of Computer Society of Indian CSI, IAENG, SDIWC.

Tanweer Alam

Tanweer Alam is an associate professor of computer science, faculty of Computer and Information Systems at Islamic University of Madinah, Saudi Arabia since 2013. He has obtained his Ph.D. degree in Computer Science, M.Phil. Degree in Computer Science, MCA and M.Sc. His research interests include Networking, Internet of Things, and Mobile Computing etc. He has published numerous peer-reviewed papers in journals and conferences, including IEEE, Scopus, and SCI journals.