Illegal Miner Detection based on Pattern Mining: A Practical Approach

Document Type : Research Article


1 Department of Computer Engineering, Faculty of Engineering, Arak University, Arak, Iran.

2 Power Distribution Company of Markazi Province, Arak, Iran


Since the most critical constituent of the cost of cryptocurrency production is energy bills, the use of illegal electricity in cryptocurrency mining farms is very common. Illegal mining farms have popped up throughout Iran in recent years. They use large collections of computer servers to verify bitcoin transactions, a highly energy-intensive process that can sap hundreds of megawatts from the power grid, which might lead to several large cities facing daily power outages. Therefore, it is essential to detect illegal miners. Although illegal miner detection might seem like a common anomaly detection problem at first glance, the results reported by different power distribution companies in Iran show that the behavior of many normal customers might be very similar to the customers’ that have some illegal miners. In addition, power distribution companies prefer models that can recognize useful insights into the behavioral patterns of the customers. To the best of our knowledge, for the first time, this paper proposes a novel classIfier for miNer detection Based On patteRn miNing (INBORN) that considers the correlation between different attributes and extracts the behavioral patterns of costumers explicitly. INBORN consists of two steps: in the first step, the frequent patterns are extracted and the attributes separating miners and non-miners are determined. In the next step, a decision tree is learned based on the frequency of the patterns. Since the Power Distribution Company of Markazi province is a pioneer in the field of illegal miner detection in Iran, the performance of INBORN is evaluated based on real datasets provided by this company. The experimental results show that INBORN improves the classification accuracy compared to the common algorithms and systems used in the Power Distribution Company of Markazi province.


[1] J. Yli-Huumo, D. Ko, S. Choi, S. Park, and K. Smolander. Where is current research on blockchain technology?—a systematic review. PLoS ONE, 11(10), 2016. [ bib | DOI ]
[2] K. Christidis and M. Devetsikiotis. Blockchains and Smart Contracts for the Internet of Things. IEEE Access, 4:2292--2303, 2016. [ bib | DOI ]
[3] B. Dindar and Ö. Gül. The detection of illicit cryptocurrency mining farms with innovative approaches for the prevention of electricity theft. Energy & Environment, 2021. [ bib | DOI ]
[4] S. Nakamoto. Bitcoin mining pools: A cooperative game theoretic analysis. Decentralized Business Review, 2008. [ bib | DOI ]
[5] Y. Lewenberg, Y. Bachrach, Y. Sompolinsky, A. ohar, and J. S. Rosenschein. Bitcoin mining pools: A cooperative game theoretic analysis. In Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems, pages 919--927. Citeseer, 2015. [ bib | DOI ]
[6] C. Malmo. One Bitcoin Transaction Consumes As Much Energy As Your House Uses in a Week. Vice (blog). November, 1, 2017. [ bib | DOI ]
[7] C. Malmo. Bitcoin Mining and its Energy Footprint. In 25th IET Irish Signals & Systems Conference 2014 and 2014 China-Ireland International Conference on Information and Communications Technologies, page 280 – 285. IET, 2014. [ bib | DOI ]
[8] Cambridge Centre for Alternative Finance. Cambridge bitcoin electricity consumption index., Date Accessed: September 10, 2022. [ bib ]
[9] GlobalPetrolPrices. Iran electricity prices., Date Accessed: September 10, 2022. [ bib ]
[10] M. Amiri, M. Hasanipanah, and H. Bakhshandeh Amnieh. Predicting ground vibration induced by rock blasting using a novel hybrid of neural network and itemset mining. Neural Computing and Applications, 32:14681–14699, 2020. [ bib | DOI ]
[11] M. Amiri, L. Mohammad-Khanli, and R. Mirandola. A sequential pattern mining model for application workload prediction in cloud environment. Journal of Network and Computer Applications, 105:21--62, 2018. [ bib | DOI ]
[12] M. Amiri, L. Mohammad-Khanli, and R. Mirandola. A new efficient approach for extracting the closed episodes for workload prediction in cloud. Computing, 102:141–200, 2020. [ bib | DOI ]
[13] R. Jiang, R. Lu, Y. Wang, J. Luo, C. Shen, and X. Shen. Energy-theft detection issues for advanced metering infrastructure in smart grid. Tsinghua Science and Technology, 19(2):105 -- 120, 2014. [ bib | DOI ]
[14] A. Rahimi, A. Shahrestani, S. Ramezani, P. Zamani, S. O. Tehrani, and M. H. Y. Moghaddam. Filter Based Time-Series Anomaly Detection in AMI using AI Approaches. In 2021 5th International Conference on Internet of Things and Applications (IoT), pages 1--6. IEEE, 2021. [ bib | DOI ]
[15] C. Chahla, H. Snoussi, L. Merghem, and M. Esseghir. A deep learning approach for anomaly detection and prediction in power consumption data. Energy Efficiency, 13(8):1633–1651, 2020. [ bib | DOI ]
[16] S. O. Tehrani, M. H. Y. Moghaddam, and M. Asadi. Decision Tree based Electricity Theft Detection in Smart Grid. In 2020 4th International conference on smart city, internet of things and applications (SCIOT), pages 46--51. IEEE, 2020. [ bib | DOI ]
[17] Z. Ouyang, X. Sun, J. Chen, D. Yue, and T. Zhang. Multi-View Stacking Ensemble for Power Consumption Anomaly Detection in the Context of Industrial Internet of Things. IEEE Access, 6:9623 -- 9631, 2018. [ bib | DOI ]
[18] M. Li, K. Zhang, J. Liu, H. Gong, and Z.Zhang. Blockchain-based anomaly detection of electricity consumption in smart grids. Pattern Recognition Letters, 138:476--482, 2020. [ bib | DOI ]
[19] R. Agrawal and R. Srikant. Fast Algorithms for Mining Association Rules in Large Databases. In Proceedings of the 20th International Conference on Very Large Data Bases, page 487–499. ACM, 1994. [ bib | DOI ]
[20] A. Kulkarni, D. Chong, and F. A. Batarseh. Foundations of data imbalance and solutions for a data democracy. Data Democracy, pages 83--106, 2020. [ bib | DOI ]
[21] S. Visa, B. Ramsay, A. L. Ralescu, and E. Van Der Knaap. Confusion Matrix-Based Feature Selection. In Proceedings of The 22nd Midwest Artificial Intelligence and Cognitive Science Conference, pages 120--127, 2011. [ bib | DOI ]
[22] M. O'Reilly, J. Duffin, T. Ward, and B. Caulfield. Mobile App to Streamline the Development of Wearable Sensor-Based Exercise Biofeedback Systems: System Development and Evaluation. JMIR rehabilitation and assistive technologies, 4(2):83--106, 2017. [ bib | DOI ]
[23] Peter Bruce, Andrew Bruce, and Peter Gedeck. Practical statistics for data scientists: 50+ essential concepts using R and Python. O'Reilly Media, 2020. [ bib ]
[24] T. Wong. Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, 48(9):2839--2846, 2015. [ bib | DOI ]