Abstract

ABSTRAK Teknik Non-Intrusive Load Monitoring (NILM) digunakan dalam pemantauan konsumsi energi. Variabel pengukuran yang digunakan yaitu Real Power dan Reactive Power. klasifikasi beban listrik menjadi acuan dalam mengurangi tagihan energi. Namun, data pengukuran sering kali terpengaruh oleh noise. Penelitian ini bertujuan untuk menganalisis pengaruh noise terhadap performa algoritma k-Nearest Neighbors (k-NN) dalam klasifikasi beban listrik. Berbagai tingkat noise secara rundom diberikan pada data pengukuran yang diperoleh. Selanjutnya, model k-NN dilatih dan dievaluasi dengan nilai k = 1 sampai 9 dan 15 tipe jarak. Hasil eksperimen menunjukkan bahwa penambahan noise pada data pengukuran secara signifikan mempengaruhi performa algoritma k-NN dalam mengklasifikasikan beban listrik. Pengaruh ini terlihat pada nilai akurasi tertinggi mayoritas pada k = 3 dan Tipe jarak Cambera menghasilkan nilai akurasi di atas rata-rata. Kata kunci: NILM, Real Power, Reactive Power, noise, k-NN ABSTRACT The Non-Intrusive Load Monitoring (NILM) technique is used in monitoring energy consumption. The measurement variables used are Real Power and Reactive Power. Electric load classification serves as a reference in reducing energy bills. However, measurement data is often affected by noise. This study aims to analyze the influence of noise on the performance of the k-Nearest Neighbors (k-NN) algorithm in electric load classification. Various levels of noise are randomly added to the obtained measurement data. Subsequently, the k-NN model is trained and evaluated with values of k = 1 to 9 and 15 distance types. The experimental results show that the addition of noise to the measurement data significantly affects the performance of the k-NN algorithm in classifying electric loads. This influence is observed in the highest accuracy values, mostly at k = 3, and the Canberra distance type yields accuracy values above average. Keywords: NILM, Real Power, Reactive Power, noise, k-NN

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.