Dragan Mlakić
Electric power company HZ-HB Inc. Mostar

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

An Adaptive Neuro-Fuzzy Inference System in Assessment of Technical Losses in Distribution Networks Dragan Mlakić; Srete N Nikolovski; Goran Knežević
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 3: June 2016
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (727.822 KB) | DOI: 10.11591/ijece.v6i3.pp1294-1304

Abstract

The losses in distribution networks have always been key elements in predicting investment, planning work, evaluating the efficiency and effectiveness of a network. This paper elaborates on the use of fuzzy logic systems in analyzing the data from a particular substation area predicting losses in the low voltage network. The data collected from the field were obtained from the Automatic Meter Reading (AMR) and Automatic Meter Management (AMM) systems. The AMR system is fully implemented in EPHZHB and integrated within the network infrastructure at secondary level substations 35/10kV and 10(20)/0.4 kV. The AMM system is partially implemented in the areas of electrical energy consumers; precisely, in accounting meters. Daily information gathered from these systems is of great value for the calculation of technical and non-technical losses. Fuzzy logic in combination with the Artificial Neural Networks implemented via the Adaptive Neuro-Fuzzy Inference System (ANFIS) is used. Finally, FIS Sugeno, FIS Mamdani and ANFIS are compared with the measured data from smart meters and presented with their errors and graphs.