A deep learning technique Alexnet to detect electricity theft in smart grids

被引:2
作者
Khan, Nitasha [1 ]
Amir Raza, Muhammad [2 ]
Ara, Darakhshan [3 ]
Mirsaeidi, Sohrab [4 ]
Ali, Aamir [5 ]
Abbas, Ghulam [6 ]
Shahid, Muhammad [7 ]
Touti, Ezzeddine [8 ]
Yousef, Amr [9 ,10 ]
Bouzguenda, Mounir [11 ]
机构
[1] Univ Kuala Lumpur, British Malaysian Inst, Sungai Pusu, Malaysia
[2] Mehran Univ Engn & Technol, Dept Elect Engn, Khairpur, Sindh, Pakistan
[3] Dawood Univ Engn & Technol, Dept Informat Sci & Humanities, Karachi, Pakistan
[4] Beijing Jiaotong Univ, Sch Elect Engn, Beijing, Peoples R China
[5] Quaid E Awam Univ Engn Sci & Technol, Dept Elect Engn, Nawabshah, Sindh, Pakistan
[6] Southeast Univ, Sch Elect Engn, Nanjing, Peoples R China
[7] Dawood Univ Engn & Technol, Dept Elect Engn, Karachi, Pakistan
[8] Northern Border Univ, Coll Engn, Dept Elect Engn, Ar Ar, Saudi Arabia
[9] Univ Business & Technol, Dept Elect Engn, Jeddah, Saudi Arabia
[10] Alexandria Univ, Fac Engn, Engn Math Dept, Alexandria, Egypt
[11] King Faisal Univ, Dept Elect Engn, Al Hufuf, Saudi Arabia
关键词
deep learning; electricity theft; smart grid; Chinese smart meter; loss-free intelligent power system;
D O I
10.3389/fenrg.2023.1287413
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Electricity theft (ET), which endangers public safety, creates a problem with the regular operation of grid infrastructure and increases revenue losses. Numerous machine learning, deep learning, and mathematical-based algorithms are available to find ET. Still, these models do not produce the best results due to problems like the dimensionality curse, class imbalance, improper hyper-parameter tuning of machine learning and deep learning models, etc. We present a hybrid deep learning model for effectively detecting electricity thieves in smart grids while considering the abovementioned concerns. Pre-processing techniques are first employed to clean up the data from the smart meters. Then, the feature extraction technique, like AlexNet, addresses the curse of dimensionality. The effectiveness of the proposed method is evaluated through simulations using a real dataset of Chinese intelligent meters. To conduct a comparative analysis, various benchmark models are implemented as well. Our proposed model achieves accuracy, precision, recall, and F1, up to 86%, 89%, 86%, and 84%, respectively.
引用
收藏
页数:13
相关论文
共 42 条
[1]   LSTM and Bat-Based RUSBoost Approach for Electricity Theft Detection [J].
Adil, Muhammad ;
Javaid, Nadeem ;
Qasim, Umar ;
Ullah, Ibrar ;
Shafiq, Muhammad ;
Choi, Jin-Ghoo .
APPLIED SCIENCES-BASEL, 2020, 10 (12)
[2]   Pattern-based and context-aware electricity theft detection in smart grid [J].
Ahir, Rajesh K. ;
Chakraborty, Basab .
SUSTAINABLE ENERGY GRIDS & NETWORKS, 2022, 32
[3]   Techno-economic optimal planning of an industrial microgrid considering integrated energy resources [J].
Ahmed, Mohammad Adel ;
Abbas, Ghulam ;
Jumani, Touqeer Ahmed ;
Rashid, Nasr ;
Bhutto, Aqeel Ahmed ;
Eldin, Sayed M. .
FRONTIERS IN ENERGY RESEARCH, 2023, 11
[4]   Towards Sustainable Energy Efficiency With Intelligent Electricity Theft Detection in Smart Grids Emphasising Enhanced Neural Networks [J].
Aldegheishem, Abdulaziz ;
Anwar, Mubbashra ;
Javaid, Nadeem ;
Alrajeh, Nabil ;
Shafiq, Muhammad ;
Ahmed, Hasan .
IEEE ACCESS, 2021, 9 :25036-25061
[5]   Multi-Objective Optimal Siting and Sizing of Distributed Generators and Shunt Capacitors Considering the Effect of Voltage-Dependent Nonlinear Load Models [J].
Ali, Aamir ;
Abbas, Ghulam ;
Keerio, Muhammad Usman ;
Mirsaeidi, Sohrab ;
Alshahr, Shahr ;
Alshahir, Ahmed .
IEEE ACCESS, 2023, 11 :21465-21487
[6]   Solution of constrained mixed-integer multi-objective optimal power flow problem considering the hybrid multi-objective evolutionary algorithm [J].
Ali, Aamir ;
Abbas, Ghulam ;
Keerio, Muhammad Usman ;
Koondhar, Mohsin Ali ;
Chandni, Kiran ;
Mirsaeidi, Sohrab .
IET GENERATION TRANSMISSION & DISTRIBUTION, 2023, 17 (01) :66-90
[7]   A Combined Deep Learning and Ensemble Learning Methodology to Avoid Electricity Theft in Smart Grids [J].
Aslam, Zeeshan ;
Javaid, Nadeem ;
Ahmad, Ashfaq ;
Ahmed, Abrar ;
Gulfam, Sardar Muhammad .
ENERGIES, 2020, 13 (21)
[8]   Predictive Data Analytics for Electricity Fraud Detection Using Tuned CNN Ensembler in Smart Grid [J].
Ayub, Nasir ;
Ali, Usman ;
Mustafa, Kainat ;
Mohsin, Syed Muhammad ;
Aslam, Sheraz .
FORECASTING, 2022, 4 (04) :936-948
[9]   A Novel Evasion Attack Against Global Electricity Theft Detectors and a Countermeasure [J].
Badr, Mahmoud M. ;
Mahmoud, Mohamed M. E. A. ;
Abdulaal, Mohammed ;
Aljohani, Abdulah Jeza ;
Alsolami, Fawaz ;
Balamsh, Abdullah .
IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (12) :11038-11053
[10]   Overview and performance assessment of the clustering methods for electrical load pattern grouping [J].
Chicco, Gianfranco .
ENERGY, 2012, 42 (01) :68-80