Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : bulletin of informatics and data science

Analysis of Electricity Consumption Patterns a Hybrid Algorithm K-Means Clustering and Support Vector Machine Fika Saputri; Asminar Asminar; Tambi Tambi; Mustarum Musaruddin; Muhammad Nadzirin Anshari Nur; Adhi Setiawan Samsul
Bulletin of Informatics and Data Science Vol 5, No 1 (2026): May 2026
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v5i1.155

Abstract

Fluctuations in electricity consumption make it difficult to manage and control energy use efficiently. Therefore, an analytical method capable of accurately identifying electricity consumption patterns is needed. Previous studies have generally applied clustering and classification separately and relied mainly on historical data, limiting their ability to capture dynamic electricity consumption patterns and classify new observations. This study aims to analyze electricity consumption patterns using a machine learning approach based on K-Means Clustering and Support Vector Machine (SVM). The data used consist of historical data and 24-hour real-time data obtained from PT PLN (Persero) UP3 Kendari. The research stages include data preprocessing, feature engineering, standardization using Z-scores, the clustering process using K-Means, and classification using SVM in a hybrid approach. The novelty of this study lies in using K-Means cluster labels as target classes for SVM while combining historical and real-time data. The results show the formation of four clusters: Cluster 0 representing stable moderate consumption, Cluster 1 representing high consumption, Cluster 2 representing low consumption, and Cluster 3 representing fluctuating consumption. Evaluation yielded a Silhouette Score of 0.5095 and a Davies-Bouldin Index of 0.6868, indicating fairly good cluster quality. The SVM model achieved an accuracy of 99.23% with high precision, recall, and F1-score values. These results demonstrate that the hybrid approach is effective in improving analysis performance and producing a reliable model for classifying new electricity consumption data
Co-Authors Abdul Djohar Abdul Djohar Abdul Djohar Abdul Kadir Achmad Nur Aliansyah Adhi Setiawan Samsul Adhi Setiawan Samsul Aditya Rachman Agustinus Lolok Agustinus Lolok Agustinus Lolok Agustinus Lolok Ahmad Munawir Ahmad Nur Aliansyah Akhyar Muchtar Alhidayat Anshari Nur, Muh. Nadzirin Asminar Asminar Bambang Pramono Briam Harpah Matana Brian Dwijayanto Sarira Bunyamin Bunyamin Bunyamin Cindy Puspitafuri DANU SALAM Diah A.P, Zahwa Dickey Ansharullah Hamid Didin Eng. Lukas Kano Manggalla Faldin Fidmasari, Rezki Fika Saputri Gamal Abdel Nasser Masikki Gamal Abdel Nasser Maskki Hasmin Tari Mokui Hasmina Tari Mokui Hasmina Tari Mokui Hazen Masrafat Holis Hermansyah Indra Indrayati Galugu Isnawaty Isnawaty, Isnawaty Jaelani, Muhammad Ishak Kalimin Kansil, Fiani Karangan, Rishan Koedoes, Y.A. Labiran, Tommy Rekza Lolok, Agustinus Lukas Kano Mangalla, Lukas Kano Malikurrahim Mansur Mardawia Mabe Parenreng Muh. Saparun Muhamad Faza Almaliki Muhammad Fiqran Rusydi Muhammad Hasbi Muhammad Safaat Munawir, Ahmad Nazrayan, Nazrayan Nita Zelfia Dinianti Luzi Mulyawati Nur Rahmadani Nurtaufiq Nurul Khaerani Hamzidah Pagiling, luther Pebi Wahyudin Rayadin, Muhamad Amhar Rifki Rifki Rifki Rifki Rizal Adi Saputra Ronni Rustam Sahabuddin Hay Sahabuddin Hay, Sahabuddin Samuel Jie Sarita, Muh Ihsan Sarita, Muhammad Ihsan St. Nawal Jaya Sukardi Sukardi Tachrir Tachrir, Tachrir Tahir, Zulqifli Tambi Tambi Tari Mokui, Hasmina Wa Ode Siti Nur Alam Wahyuddin Zhafirah Majdiyah Mustarum Zulkaida, Wa Ode