Akademik Veri Yönetim Sistemi
TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, cilt.32, sa.4, 2024 (SCI-Expanded, Scopus, TRDizin)
This paper explores the determination of any load or load combination in a power system at any moment. This process requires measurements at the main electric utility service entry of a house, known as nonintrusive measurement. To accurately identify loads, total harmonic distortion, RMS, third harmonic currents, and power consumption are considered their fingerprints. Based on these fingerprints, an algorithm called the competitive decision process is developed and integrated into an embedded system. This algorithm has a two-level decision mechanism. In the first stage, the winner loads with the highest similarity scores from each feature are determined, and the loads with a similarity score higher than 90 move to the second stage to be evaluated. Loads that do not pass the first stage in all features are not considered for the next one. In the second stage, the scores from each feature of the loads passed to this stage are summed, and the load with the highest score is determined. It is experimentally validated that the method significantly detects correct load or load combinations for six residential appliances. Fifty-six type-tests are performed, and each type-test contains ten measurements. As a result, a total success rate of over 97 percent is obtained in all metrics.