Faculty of Computer Science and Mathematics – University of Kufa Official Site – Faculty of Computer Science and Mathematics
The Faculty of Computer Science and Mathematics, Computer Science Department, discussed the doctoral thesis titled ” Energy Theft Detection Based on CNN Approach ” by the student Maali Hashim Alameedi. The thesis presented a study on the use of deep learning techniques in analyzing and distinguishing abnormal consumer behavior.
The study was on the dataset of State Grid Corporation of China (SGCC), which was collected from 42,372 networked smart homes. The data were
processed using the linear interpolation algorithm to process missing values, then ADAptive SYNthetic (ADASYN) algorithm for an unbalanced class is applied.
The main objective of this study is to design and implement an effective electric power theft detection system using effective statistical features to distinguish between the house in which the theft occurred or not, and to determine the days in which the theft occurred.
A convolutional neural network (CNN) model was proposed for the automatic detection of electricity theft, after which extensive and detailed tests were carried out to compare the performance of the proposed model.
The achieved calculated accuracy was close to 99.54, and the thesis was successfully accepted.
