Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


toledo1341522225.pdf (1.63 MB)

ETD Abstract Container

Abstract Header

Modeling, Detection, and Prevention of Electricity Theft for Enhanced Performance and Security of Power Grid

Depuru, Soma Shekara
http://rave.ohiolink.edu/etdc/view?acc_num=toledo1341522225

Abstract Details

2012, Doctor of Philosophy in Engineering, University of Toledo, College of Engineering.
This dissertation contributes to the development and implementation of novel algorithms for analyzing the electricity consumption patterns of customers and identifying illegal consumers based on irregularities in consumption. Distribution of electricity involves significant Technical as well as Non-Technical Losses (NTL). Illegal consumption of electricity or electricity theft constitutes a major share of NTL. This dissertation discusses several methods implemented by illegal consumers for stealing electricity and provides relevant literature review. A comprehensive review of the advantages, challenges and technologies involved in the design, development, and deployment of smart meters is presented. With the advent of advanced metering technologies, real-time energy consumption data will be available at the utilities end, which can be used to detect illegal consumers. This dissertation presents an encoding technique that simplifies the received customer energy consumption readings (patterns) and maps them into corresponding irregularities in consumption. The encoding technique preserves the exclusivity in the energy consumption patterns. The encoding technique saves significant CPU time in the real-time analysis and classification of customers, in addition to decreasing the memory required to store historical data. Then, this dissertation elucidates operation of intelligent classification techniques on customer energy consumption data to classify genuine and illegal consumers. These classification models are applied on regular energy consumption data as well as the encoded data to compare corresponding classification accuracies and computational overhead. Further, performance and scope of the proposed algorithms is enhanced in two directions - reducing the overall computation time, and including more real-time parameters using High Performance Computers (HPC). The encoding and classification algorithms are parallelized (in both Task Parallel and Data Parallel approaches). On the other hand, impact of Time-Based Pricing (TBP) and Distributed Generation (DG) on illegal consumers as well as the algorithms used for detection of illegal consumers are analyzed. Economics involved in terms of losses due to illegal consumption of electricity is also explained.
Lingfeng Wang, PhD (Committee Chair)
Vijay Devabhaktuni, PhD (Committee Co-Chair)
Mansoor Alam, PhD (Committee Member)
Mohamed Samir Hefzy, PhD (Committee Member)
Roger King, PhD (Committee Member)
Electrical Engineering
Non-Technical Losses; Detection of Electricity Theft; Neural Network; SVM; Data Classification; Rule Engine; Smart Grid; Smart Meter; Power Grid; Fraud/Illegal consumption of electricity; HPC; DG;

Recommended Citations

Citations

  • Depuru, S. S. (2012). Modeling, Detection, and Prevention of Electricity Theft for Enhanced Performance and Security of Power Grid [Doctoral dissertation, University of Toledo]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1341522225

    APA Style (7th edition)

  • Depuru, Soma Shekara. Modeling, Detection, and Prevention of Electricity Theft for Enhanced Performance and Security of Power Grid. 2012. University of Toledo, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=toledo1341522225.

    MLA Style (8th edition)

  • Depuru, Soma Shekara. "Modeling, Detection, and Prevention of Electricity Theft for Enhanced Performance and Security of Power Grid." Doctoral dissertation, University of Toledo, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1341522225

    Chicago Manual of Style (17th edition)

toledo1341522225
22,715
© 2012, all rights reserved.
This open access ETD is published by University of Toledo and OhioLINK.