Improving Performance of the Convolutional Neural Networks for Electricity Theft Detection by Using Cheetah Optimization Algorithm

  • hassan ghaedi Department of Computer, Neyshabur Branch, Islamic Azad University, Neyshabur, Iran
  • Seyed Reza Kamel Tabbakh Department of Computer, Mashhad Branch, Islamic Azad University, Mashhad, Iran
  • reza ghaemi Department of Computer, Quchan Branch, Islamic Azad University, Quchan, Iran
Keywords: Data mining, Classification, Electricity Theft Detection, Convolutional Neural Network(CNN)

Abstract

This paper presents an efficient approach to improve convolutional neural network(CNN) performance using cheetah optimization algorithm (CHOA). The main challenges of these networks are optimizing the parameters and finding an efficient architecture. Network performance and achieving efficient learning models based on a particular problem, depend on adjusting values of the hyper-parameters and requiring exploring in a complex and large search space. In order to solve these types of problems, heuristic-based searches are used. Therefore, the main idea of this paper is using CHOA algorithm to adjust the optimal hyper-parameters of CNN networks including number of convolutional and pooling layers, number of filters per convolutional layer and their size, stride of each filter, pool size and stride of each pooling layer and Batch size. This paper presents an optimal approach to increase the detection rate of CNN network that abnormal samples are generated and clustered by artificial attacks and CHOA algorithm, respectively.  The resulting architecture is evaluated on the ISSDA dataset. Based on the obtained results, the proposed method with high detection rate identifies unauthorized electricity customers.

References

[1] P. Jokar, N. Arianpoo, and V. C. M. Leung, “Electricity theft detection in AMI using customers’ consumption patterns,” IEEE Trans. Smart Grid, vol. 7, no. 1, pp. 216–226, 2016, doi: 10.1109/TSG.2015.2425222.
[2] H. Ghaedi, S. R. K. Tabbakh, and R. Ghaemi, “Improving Electricity Theft Detection using Combination of Improved Crow Search Algorithm and Support Vector Machine,” Majlesi J. Electr. Eng., vol. 15, no. 4 SE-Articles, Dec. 2021, doi: https://doi.org/10.52547/mjee.15.4.63.
[3] A. Askarzadeh, “A novel metaheuristic method for solving constrained engineering optimization problems: Crow search algorithm,” Comput. Struct., vol. 169, pp. 1–12, 2016, doi: 10.1016/j.compstruc.2016.03.001.
[4] R. Razavi, A. Gharipour, M. Fleury, and I. J. Akpan, “A practical feature-engineering framework for electricity theft detection in smart grids,” Appl. Energy, vol. 238, no. December 2018, pp. 481–494, 2019, doi: 10.1016/j.apenergy.2019.01.076.
[5] Z. Feng, J. Huang, W. H. Tang, and M. Shahidehpour, “Data mining for abnormal power consumption pattern detection based on local matrix reconstruction,” Int. J. Electr. Power Energy Syst., vol. 123, no. February, p. 106315, 2020, doi: 10.1016/j.ijepes.2020.106315.
[6] H. Ghaedi, S. R. Kamel Tabbakh Farizani, and R. Gaemi, “A Novel Meta-heuristic Framework for Solving Power Theft Detection Problem: Cheetah Optimization Algorithm,” Int. J. Ind. Electron. Control Optim., vol. 5, no. 1, pp. 63–76, 2022, doi: 10.22111/ieco.2022.39528.1370.
[7] A. Ullah, N. Javaid, A. S. Yahaya, T. Sultana, F. A. Al-Zahrani, and F. Zaman, “A Hybrid Deep Neural Network for Electricity Theft Detection Using Intelligent Antenna-Based Smart Meters,” Wirel. Commun. Mob. Comput., vol. 2021, p. 9933111, 2021, doi: 10.1155/2021/9933111.
[8] R. Yao, N. Wang, Z. Liu, P. Chen, and X. Sheng, “Intrusion detection system in the advanced metering infrastructure: A cross-layer feature-fusion CNN-LSTM-based approach,” Sensors (Switzerland), vol. 21, no. 2, pp. 1–17, 2021, doi: 10.3390/s21020626.
[9] N. M. Ibrahim, S. T. F. Al-Janabi, and B. Al-Khateeb, “Electricity-theft detection in smart grids based on deep learning,” Bull. Electr. Eng. Informatics, vol. 10, no. 4, pp. 2285–2292, 2021, doi: 10.11591/EEI.V10I4.2875.
[10] M. Nazmul Hasan, R. N. Toma, A. Al Nahid, M. M. Manjurul Islam, and J. M. Kim, “Electricity theft detection in smart grid systems: A CNN-LSTM based approach,” Energies, vol. 12, no. 17, pp. 1–18, 2019, doi: 10.3390/en12173310.
[11] S. Li, Y. Han, X. Yao, S. Yingchen, J. Wang, and Q. Zhao, “Electricity Theft Detection in Power Grids with Deep Learning and Random Forests,” J. Electr. Comput. Eng., vol. 2019, 2019, doi: 10.1155/2019/4136874.
[12] B. Kocaman and V. Tümen, “Detection of electricity theft using data processing and LSTM method in distribution systems,” Sadhana - Acad. Proc. Eng. Sci., vol. 45, no. 1, 2020, doi: 10.1007/s12046-020-01512-0.
[13] H. M. Rouzbahani, H. Karimipour, and L. Lei, “An Ensemble Deep Convolutional Neural Network Model for Electricity Theft Detection in Smart Grids,” Conf. Proc. - IEEE Int. Conf. Syst. Man Cybern., vol. 2020-Octob, pp. 3637–3642, 2020, doi: 10.1109/SMC42975.2020.9282837.
[14] J. Liu, X. Cao, D. Wang, K. Pan, C. Zhang, and X. Wang, “Abnormal electricity detection with hybrid deep neural network model,” MATEC Web Conf., vol. 189, p. 3001, Jan. 2018, doi: 10.1051/matecconf/201818903001.
[15] Z. Zheng, Y. Yang, X. Niu, H. N. Dai, and Y. Zhou, “Wide and Deep Convolutional Neural Networks for Electricity-Theft Detection to Secure Smart Grids,” IEEE Trans. Ind. Informatics, vol. 14, no. 4, pp. 1606–1615, 2018, doi: 10.1109/TII.2017.2785963.
[16] P. Chandel and T. Thakur, “Smart Meter Data Analysis for Electricity Theft Detection using Neural Networks,” Adv. Sci. Technol. Eng. Syst. J., vol. 4, no. 4, pp. 161–168, 2019, doi: 10.25046/aj040420.
[17] X. Feng et al., “A novel electricity theft detection scheme based on text convolutional neural networks,” Energies, vol. 13, no. 21, pp. 1–17, 2020, doi: 10.3390/en13215758.
[18] A. Maamar and K. Benahmed, “A Hybrid Model for Anomalies Detection in AMI System Combining K-means Clustering and Deep Neural Network,” Comput. Mater. Contin., vol. 60, no. 1, pp. 15–39, 2019, doi: 10.32604/cmc.2019.06497.
[19] R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, “Convolutional neural networks: an overview and application in radiology,” Insights Imaging, vol. 9, no. 4, pp. 611–629, 2018, doi: 10.1007/s13244-018-0639-9.
[20] S. Khan, H. Rahmani, S. A. A. Shah, M. Bennamoun, G. Medioni, and S. Dickinson, A Guide to Convolutional Neural Networks for Computer Vision. Morgan & Claypool, 2018.
[21] Y. Tian, “Artificial Intelligence Image Recognition Method Based on Convolutional Neural Network Algorithm,” IEEE Access, vol. 8, pp. 125731–125744, 2020, doi: 10.1109/ACCESS.2020.3006097.
[22] V. Kotu and B. Deshpande, “Chapter 10 - Deep Learning,” V. Kotu and B. B. T.-D. S. (Second E. Deshpande, Eds. Morgan Kaufmann, 2019, pp. 307–342.
[23] “Irish Social Science Data Archive,” 2012. https://www.ucd.ie/issda/data/commissionforenergyregulationcer/.
[24] S. Das, A. Abraham, and A. Konar, “Automatic clustering using an improved differential evolution algorithm,” IEEE Trans. Syst. Man, Cybern. Part ASystems Humans, vol. 38, no. 1, pp. 218–237, 2008, doi: 10.1109/TSMCA.2007.909595.
[25] D. L. Davies and D. W. Bouldin, “A Cluster Separation Measure,” IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-1, no. 2, pp. 224–227, 1979, doi: 10.1109/TPAMI.1979.4766909.
Published
2022-09-30
How to Cite
ghaedi, hassan, Kamel Tabbakh, S. R., & ghaemi, reza. (2022). Improving Performance of the Convolutional Neural Networks for Electricity Theft Detection by Using Cheetah Optimization Algorithm. Majlesi Journal of Electrical Engineering. Retrieved from http://mjee.iaumajlesi.ac.ir/index/index.php/ee/article/view/4700
Section
Articles