Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm

• Main Authors: Yap K.S., Abidin I.Z., Ahmad A.R., Hussien Z.F., Pok H.L., Ismail F.I., Mohamad A.M.
• Other Authors: 24448864400
• Format: Conference Paper
• Published: 2023
• Subjects: Dual lagrangian optimization; Dynamic crossover point; Genetic algorithm; Pre-populated database; Support vector machine; Algorithms; Computer science; Computers; Database systems; Diesel engines; Genetic algorithms; Image retrieval; Intelligent systems; Learning systems; Multilayer neural networks; Neural networks; Vectors; 10 fold cross validations; And genetic algorithms; Classification techniques; Comparison results; Consumption patterns; Customer consumption datums; Detection accuracies; Distribution losses; Fraud detections; Gaussian; Generalization performances; Hybrid algorithms; Kernel parameters; Malaysia; Optimized solutions; RBF kernels; Support vectors; SVM classifications; Technical losses; Support vector machines

This paper presents an intelligent system to reduce Non Technical Loss (NTL) using hybrid Support Vector Machine (SVM) and Genetic Algorithm (GA). The main motivation for this research is to assist Sabah Electricity Sdn. Bhd. (SESB) to reduce their distribution loss, estimated around 15% at present...