An effective DNN-based Approach for Detecting Energy Theft in Smart Grids through User Consumption Patterns

Abstract

The advancement of the Internet has been progressively easing human life. The development of mobile communication technologies has led to the widespread adoption of Internet of Things (IoT) applications. Thus, most systems and devices have connected to the Internet more efficiently. The integration of communication systems into critical infrastructures, such as electricity grids, has given rise to the concept of IoT-based smart grids. In smart grid systems, data communication is facilitated through the Advanced Metering Infrastructure (AMI). Due to the inherent characteristics of communication systems, AMI may be vulnerable to cyber-attacks. Some vulnerabilities have resulted in the emergence of cyber-attack vectors against energy consumption data obtained from smart meters. In this study, an effective energy theft intrusion detection system (IDS) based on users' consumption patterns is proposed. A Deep Neural Network (DNN) based classification model was employed to assess the predictability of both honest and malicious consumption patterns. The proposed model exhibits high and adjustable performance. Extensive experiments have been carried out on a real consumption dataset of approximately 2000 customers. Manipulated data from real readings with two different attack vectors were injected into the dataset. K-fold cross-validation technique was used. The proposed model performed a high performance reaching up to 97.4% accuracy.

Keywords

• AMI
• DNN
• Cyber security
• Energy theft
• Smart grid security

Kullanıcı Tüketim Kalıpları Aracılığıyla Akıllı Şebekelerdeki Enerji Hırsızlığını Tespit Etmek İçin Etkili Bir DNN Tabanlı Yaklaşım

Abstract

İnternetin ilerlemesi insan hayatını giderek kolaylaştırmaktadır. Mobil iletişim teknolojilerinin gelişmesi, Nesnelerin İnterneti (Internet of Things-IoT) uygulamalarının yaygın olarak benimsenmesine yol açmıştır. Böylece, çoğu sistem ve cihaz internete daha verimli bir şekilde bağlanmıştır. İletişim sistemlerinin elektrik şebekeleri gibi kritik altyapılara entegre edilmesi, IoT tabanlı akıllı şebekeler kavramını ortaya çıkarmıştır. Akıllı şebeke sistemlerinde veri iletişimi, Gelişmiş Ölçüm Altyapısı (Advanced Metering Infrastructure - AMI) aracılığıyla sağlanmaktadır. İletişim sistemlerinin doğal özellikleri nedeniyle, AMI siber saldırılara karşı savunmasız olabilir. Bazı güvenlik açıkları, akıllı sayaçlardan elde edilen enerji tüketim verilerine karşı siber saldırı vektörlerinin ortaya çıkmasına neden olmuştur. Bu çalışmada, kullanıcıların tüketim modellerine dayalı etkili bir enerji hırsızlığı saldırı tespit sistemi önerilmektedir. Hem dürüst hem de kötü niyetli tüketim kalıplarının tahmin edilebilirliğini değerlendirmek için Derin Sinir Ağı (Deep Neural Network - DNN) tabanlı bir sınıflandırma modeli kullanılmıştır. Önerilen model yüksek ve ayarlanabilir performans sergilemektedir. Yaklaşık 2000 müşteriden oluşan gerçek bir tüketim veri kümesi üzerinde kapsamlı deneyler gerçekleştirilmiştir. Veri kümesine iki farklı saldırı vektörü ile gerçek okumalardan elde edilen manipüle edilmiş veriler enjekte edilmiştir. K-katlı çapraz-doğrulama tekniği kullanılmıştır. Önerilen model %97,4 doğruluğa ulaşarak yüksek bir performans göstermiştir.

Keywords

• AMI
• DNN
• Siber güvenlik
• Enerji hırsızlığı
• Akıllı şebeke güvenliği

References

1. Gunduz MZ and Das R. Internet of things (IoT): Evolution, components and applications fields. Pamukkale University Journal of Engineering Sciences. 2018; 24(2). doi: 10.5505/pajes.2017.89106.
2. Gunduz MZ and Das R. Analysis of cyber-attacks on smart grid applications. International Conference on Artificial Intelligence and Data Processing (IDAP). 2018; doi: 10.1109/IDAP.2018.8620728.
3. Gündüz MZ and Daş R. Akıllı Şebekelerde İletişim Altyapısı ve Siber Güvenlik. Iğdır Üniv. Fen Bil Enst. Der. 2020;10(2). doi: 10.21597/jist.655990.
4. Sahoo S, Nikovski D, Muso T, and Tsuru K. Electricity theft detection using smart meter data. IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT). 2015. doi: 10.1109/ISGT.2015.7131776.
5. Emmanuel M and Rayudu R. Communication technologies for smart grid applications: A survey. Journal of Network and Computer Applications. 2016;74 doi: 10.1016/j.jnca.2016.08.012.
6. Otuoze AO et al. Electricity theft detection framework based on universal prediction algorithm. Indonesian Journal of Electrical Engineering and Computer Science. 2019;15(2)doi: 10.11591/ijeecs.v15.i2.pp758-768.
7. Gunduz MZ and Das R. Cyber-security on smart grid: Threats and potential solutions. Computer Networks. 2020;169. doi: 10.1016/j.comnet.2019.107094.
8. Baskaran H., Al-Ghaili AM, Ibrahim ZA, Rahim FA, Muthaiyah S and Kasim H. Data falsification attacks in advanced metering infrastructure. Bulletin of Electrical Engineering and Informatics. 2021;10(1). doi: 10.11591/eei.v10i1.2024.

9. Das R and Gunduz MZ. Analysis of cyber-attacks in IoT-based critical infrastructures. International Journal of Information Security Science. 2019;8(4).
10. Na L, Xiaohui X, Xiaoqin M, Xiangfu M, and Peisen Y. Fake Data Injection Attack Detection in AMI System Using a Hybrid Method. IEEE Sustainable Power and Energy Conference (iSPEC). 2021. doi:10.1109/iSPEC53008.2021.9735875.
11. Bhattacharjee S and Das SK. Detection and Forensics against Stealthy Data Falsification in Smart Metering Infrastructure. IEEE Transactions on Dependable and Secure Computing. 2021;18(1) doi:10.1109/TDSC.2018.2889729.
12. Nagi J, Yap KS, Tiong SK, Ahmed SK, and Mohamad M. Nontechnical Loss Detection for Metered Customers in Power Utility Using Support Vector Machines. IEEE Transactions on Power Delivery. 2010;25(2). doi:10.1109/TPWRD.2009.2030890.
13. Ismail M, Shahin M, Shaaban MF, Serpedin E and Qaraqe K. Efficient detection of electricity theft cyber attacks in AMI networks. IEEE Wireless Communications and Networking Conference (WCNC). 2018. doi:10.1109/WCNC.2018.8377010.
14. Viegas JL, Vieira SM, Sousa JMC, Melício R, and Mendes VMF. Electricity demand profile prediction based on household characteristics. 12th International Conference on the European Energy Market (EEM). 2015. doi: 10.1109/EEM.2015.7216746.
15. Viegas JL, Esteves PR, Melício R, Mendes VMF, Vieira SM. Solutions for detection of non-technical losses in the electricity grid: A review. Renewable and Sustainable Energy Reviews. 2017;80. doi: 10.1016/j.rser.2017.05.193.
16. Ayaz I, Kutlu F, Cömert Z, DeepMaizeNet: A novel hybrid approach based on CBAM for implementing the doubled haploid technique. Agronomy Journal. doi: 10.1002/agj2.21396.
17. Kocaman B and Tümen V. Detection of electricity theft using data processing and LSTM method in distribution systems. Sādhanā. 2020; 45(1) doi: 10.1007/s12046-020-01512-0.
18. Jokar P, Arianpoo N, Leung VCM. Intrusion detection in advanced metering infrastructure based on consumption pattern.IEEE International Conference on Communications (ICC). 2013. doi: 10.1109/ICC.2013.6655271.
19. Otuoze AO, Mustafa MW, Mohammed OO, Saeed MS, Surajudeen-Bakinde NT, Salisu S. Electricity theft detection by sources of threats for smart city planning. IET Smart Cities. 2019; 1(2) doi: 10.1049/iet-smc.2019.0045.
20. ISSDA, Irish Social Science Data Archive. https://www.ucd.ie/issda/data/commissionforenergyregulationcer/
21. Şahin K, Hizal S, Zengin A. Design and Implementation of ADevs-Based Cyber-Attack Simulator for Cyber Security. (IJSIMM). 2022; 21(1). doi: https://doi.org/10.2507/IJSIMM21-1-587.
22. Di̇nçer Y, İni̇k Ö. Çevresel Seslerin Evrişimsel Sinir Ağları ile Sınıflandırılması. KONJES. 2023;11(2). doi:10.36306/konjes.1201558.
23. Haq EU, Pei C, Zhang R, Jianjun H, Ahmad F. Electricity-theft detection for smart grid security using smart meter data: A deep-CNN based approach. Energy Reports. 2023;9 doi: 10.1016/j.egyr.2022.11.072.
24. Zheng K, Wang Y, Chen Q, Li Y, Electricity theft detecting based on density-clustering method. IEEE Innovative Smart Grid Technologies (ISGT-Asia). 2017. doi: 10.1109/ISGT-Asia.2017.8378347.
25. Jokar P, Arianpoo N, Leung VCM. Electricity Theft Detection in AMI Using Customers’ Consumption Patterns. IEEE Transactions on Smart Grid. 2016;7(1) doi: 10.1109/TSG.2015.2425222.
26. Souza MA, Pereira JLR, Alves GO, Oliveira BC, Melo ID, Garcia PAN. Detection and identification of energy theft in advanced metering infrastructures. Electric Power Systems Research. 2020; 182. doi: 10.1016/j.epsr.2020.106258.