Optimasi Peramalan Beban Listrik dengan Regresi Linear Berganda Berbasis Algoritma Genetika: Studi Kasus Kabupaten Soppeng
Abstract
Electricity is a crucial infrastructure supporting economic and social development, thus requiring reliable supply planning. In Soppeng Regency, historical data from 2019–2023 show population growth from 226,992 to 240,955 people and GRDP increase from 10,938 to 14,909 billion rupiah, driving higher electricity demand. Customer numbers rose in the household sector from 29,438 to 34,376 and in industry from 33 to 58, with similar upward trends in connected load and energy use. This study addresses the challenge of accurate forecasting by applying Multiple Linear Regression (MLR) optimized with Genetic Algorithm (GA). Forecasting results up to 2028 predict household customers reaching 40,449 and industrial customers 89, while connected load grows from 35.7 to 34.0 million VA in households and from 8.6 to 17.4 million VA in industry. Electricity consumption is projected to exceed 41.8 million kWh in households and 13.5 million kWh in industry by 2028. Model evaluation using Mean Absolute Percentage Error (MAPE) confirms reliable accuracy, making the MLR–GA approach effective for future capacity planning.
References
AL-Qaysi, A. M. M., Bozkurt, A., & Ates, Y. (2023). Load Forecasting Based on Genetic Algorithm–Artificial Neural Network-Adaptive Neuro-Fuzzy Inference Systems: A Case Study in Iraq. Energies, 16(6). https://doi.org/10.3390/en16062919
Damanik, D., Damanik, P., & Nopeline, N. (2024). Analisis Pengaruh Infrastruktur Jalan dan Infrastruktur Listrik Terhadap Pertumbuhan Ekonomi di Kota Pematang Siantar. Jurnal KAFEBIS, 2(1), 59–67. https://doi.org/10.51622/kafebis.v2i1.2378
Jamilatun, S., Rhomadoni, F. R., Astuti, E., Setya, B., Idris, M., & Auliasari, P. A. (2025). Peran Manajemen Energi terhadap Efisiensi Konsumsi Listrik Rumah Tangga di Indonesia. 1–12.
Kurniawan, E., Purwoharjono, & Abidin, Z. (2022). Peramalan Beban Pada Gardu Induk PT.PLN (Persero) UP3B Kalimantan Barat. 4–12.
Lingga Pradipika, C., Handoko, S., & Winardi, B. (2017). Peramalan Beban Puncak Harian Pada Sistem Pt.Pln Apb Jawa Tengah Dan Diy Menggunakan Metode Jaringan Saraf Tiruan-Algoritma Genetika. Transmisi: Jurnal Ilmiah Teknik Elektro, 19(1), 28–34.
Loway, A. I. J., Silimang, S., & Tumaliang, H. (2025). Forecasting Load Growth and Electricity Availability in 2023 - 2037 in North Sulawesi. Jurnal Teknik Elektro Dan Komputer, 14(1), 1–8.
Muchmad Bayu, Purowharjono, R. G. (2025). Studi Perkiraan Beban Listrik Universitas Tanjungpura Menggunakan Metode Regresi Linier Berganda. 8(6), 1–23. https://doi.org/10.8734/Kohesi.v1i2.365
Muhammad Khaidir, Rahman, F., & Mustafa, S. (2025). Pengembangan PLTMH dengan Model Multipowerhouse (MPH) untuk Optimalisasi Air Buangan Turbin PLTMH Garassik di Sungai Garassik Kab. Enrekang. Jurnal Mosfet, 5(1), 104–118. https://doi.org/10.31850/jmosfet.v5i1.3510
Nti, I. K., Teimeh, M., Nyarko-Boateng, O., & Adekoya, A. F. (2020). Electricity load forecasting: a systematic review. Journal of Electrical Systems and Information Technology, 7(1). https://doi.org/10.1186/s43067-020-00021-8
Purnomo, H., Suyono, H., & Hasanah, R. N. (2021). Peramalan Beban Jangka Pendek Sistem Kelistrikan Kota Batu Menggunakan Deep Learning Long Short-Term Memory. Transmisi, 23(3), 97–102. https://doi.org/10.14710/transmisi.23.3.97-102
Sa, A., & Amir, F. (2021). Perilaku Masyarakat Menggunakan Energi Listrik yang Berwawasan Lingkungan di Kabupaten Soppeng. 2199–2208.
Sholeh, I., Situmeang, U., & Monice. (2021). Studi Peramalan Beban Pada Gardu Induk TeLuk Lembu Uip3bs Upt Pekanbaru PT. PLN (PERSERO). Senkim, 1(1), 11–26.
Wijaya, A. H. (2019). Artificial Neural Network Untuk Memprediksi Beban Listrik Dengan Menggunakan Metode Backpropagation. Jurnal CoreIT, 5(2), 61–70.
