Clustering Indonesian Provinces Based on Per Capita Energy Consumption Using the K-Means Algorithm
DOI:
https://doi.org/10.30865/ijics.v9i1.8875Keywords:
K-Means Clustering, Energy Consumption, Indonesia's Provincial Per Capita,Abstract
Per capita energy consumption is a crucial indicator for assessing the level of development and energy needs of communities in any region. This research aims to group Indonesian provinces based on their average per capita energy consumption in 2014-2024. The method used is the K-Means Clustering algorithm, an effective data mining technique for identifying hidden patterns and structures in numerical data. The data utilized consists of per capita energy consumption values from each province, which were then processed and analyzed to form several clusters of provinces with similar energy consumption characteristics. The results of the clustering process show that Indonesian provinces can be grouped into three main clusters: provinces with low, medium, and high consumption levels. These findings can serve as a reference for the government in designing more targeted and equitable energy policies, as well as a basis for strategic decision-making in the energy sector and regional development. This study concludes that Indonesia's provincial per capita energy consumption varies significantly across regions and over time, and such variation can be systematically grouped into three distinct clusters—low, medium, and high consumption—using the K-Means Clustering algorithm. The analysis of data from 2018 to 2024, consisting of 238 records across 34 provinces, shows that the majority of provinces (135 out of 238 entries) fall into the medium consumption cluster, with an average of 2,075.85 kcal/capita/day, indicating a relatively stable and balanced energy use that aligns with national standards. In contrast, Cluster 0 represents provinces with lower energy consumption, averaging 1,878.93 kcal, often linked to limited access to modern energy sources and lower economic activity. Meanwhile, Cluster 2, with the highest average of 2,248.75 kcal, comprises industrialized or highly urbanized provinces with more intensive energy needs.References
R. Susetyoko, E. Satriyanto, A. Fadliana, and M. Syahfitra, “APPLICATION OF MULTISTAGE CLUSTERING FOR MAPPING ECONOMIC POTENTIAL IN EAST JAVA PROVINCE,” J. Ilm. Kursor, vol. 12, no. 1, pp. 11–22, 2023.
N. Malik, I. Zuhroh, M. S. W. Suliswanto, and M. Rofik, “Sustainable Development Clustering in East Java Using the K-means Method,” in Sixth Padang International Conference On Economics Education, Economics, Business and Management, Accounting and Entrepreneurship (PICEEBA 2020), 2021, pp. 114–123.
S. Robiati, D. Fitria, D. Vionanda, and D. Sulistiowati, “Comparison of K-Means and K-Medoids in Clustering Regency/City in West Sumatra Province Based on Environmental Indicators,” Indones. J. Stat. Its Appl., vol. 8, no. 2, pp. 191–201, 2024.
S. N. Huda, “Cluster Analysis of Indonesian Province Based on Household Primary Cooking Fuel Using K-Means,” in IOP Conference Series: Materials Science and Engineering, 2017, p. 12016.
T. R. Noviandy et al., “Environmental and economic clustering of indonesian provinces: insights from K-Means analysis,” Leuser J. Environ. Stud., vol. 2, no. 1, pp. 41–51, 2024.
A. V. D. Sano and H. Nindito, “Application of K-means algorithm for cluster analysis on poverty of provinces in Indonesia,” ComTech Comput. Math. Eng. Appl., vol. 7, no. 2, pp. 141–150, 2016.
T. S. Alasi, Ilmu Komputer, 1st ed. Deli Serdang, 2024. [Online]. Available: https://www.media-publikasi-idpress.my.id/2023/12/ilmu-komputer.html
S. Y. Prayogi, T. S. Alasi, and R. F. Rahmat, Pengantar Machine Learning, 1st ed. Deli Serdang: Media Publikasi Idpress, 2025. [Online]. Available: https://www.media-publikasi-idpress.my.id/2025/03/4.html
B. Meng, F. Li, F. Yang, and Q. Gao, “Centroid-free k-means with balanced clustering,” IEEE Signal Process. Lett., 2025.
K. Song, H. Zhang, H. Ma, Y. Sun, and L. Yan, “Design and implementation of parallel k-means algorithm based on ternary optical computer,” J. Supercomput., vol. 81, no. 4, p. 536, 2025.
B. Triwijaya, S. Wibowo, and N. L. D. M. Sari, “Performance Comparison of K-Means Algorithm and BIRCH Algorithm in Clustering Earthquake Data in Indonesia with Web-Based Map Visualization,” J. Teknol. dan Open Source, vol. 8, no. 1, pp. 278–287, 2025.
S. H. Abdullah and Z. Fatah, “Analisis Produksi Cabai Rawit Indonesia Menggunakan Algoritma K-Means Clustering,” J. Ilm. SAINS Teknol. DAN Inf., vol. 3, no. 1, pp. 66–74, 2025.
L. Bayuaji, N. J. Perdana, T. Handhayani, and others, “Mapping Indonesia’s Regions Based on Carbon Emissions Using the K-Means Algorithm,” in 2025 International Conference on Computer Sciences, Engineering, and Technology Innovation (ICoCSETI), 2025, pp. 200–205.
I. Rinaldi and H. Harmayani, “PENGGUNAAN ALGORITMA CLUSTERING K-MEANS UNTUK MENGELOMPOKKAN POLA CUACA,” J. Sci. Soc. Res., vol. 8, no. 1, pp. 343–348, 2025.
O. Kisi, S. Heddam, K. S. Parmar, A. Petroselli, C. Külls, and M. Zounemat-Kermani, “Integration of Gaussian process regression and K means clustering for enhanced short term rainfall runoff modeling,” Sci. Rep., vol. 15, no. 1, p. 7444, 2025.
A. S. Manalu and M. A. Hanafiah, “Implementasi Clustering Dalam Pengelompokan Jumlah Keluarga Penerima Manfaat Di Provinsi Sumatera Utara,” Peningkatan Prof. Diri di Era Soc. 5.0, p. 91, 2025.
A. H. Hidayah, D. Novitasari, R. Kamila, M. Nasrudin, and others, “Cluster Modeling with K-Means on Provincial Data in Indonesia Based on Environmental Indicators,” J. Artif. Intell. Eng. Appl., vol. 4, no. 3, pp. 2245–2249, 2025.
A. S. Sembiring, T. S. Alasi, and others, “Penerapan Data Mining Menggunakan Algoritma Apriori Pada Peminjaman Buku di Perpustakaan Pada Pesantren Babul Ulum,” J. Armada Inform., vol. 7, no. 2, pp. 323–327, 2023.
H. Lai, T. Huang, B. Lu, S. Zhang, and R. Xiaog, “Silhouette coefficient-based weighting k-means algorithm,” Neural Comput. Appl., vol. 37, no. 5, pp. 3061–3075, 2025.
K. Niswatin, C. Andreas, P. F. A. Oktavia Hans, and M. Mardianto, “Clustering of districts and cities in Indonesia based on poverty indicators using the K-means method,” in International Conference on Computing, Mathematics and Statistics (iCMS 2021), 2021, pp. 225–232.
