Design of a Web-Based Household Electricity Usage Prediction System Using the Sarima Method
Abstract
Pada sektor rumah tangga, tingkat kesadaran untuk mengontrol besar penggunaan listrik belum tinggi sehingga pemakaiannya tidak dapat diprediksi. Ketidaktahuan ini akan menyebabkan pembengkakan tagihan listrik yang tidak dapat dihindari atau dicegah. Untuk itu dibutuhkan sistem prediksi penggunaan listrik yang dpat digunakan acuan konsumen mengenai konsumsi listrik rumah tangga. Pada penelitian ini dirancang sebuah sistem yang bisa memprediksi penggunaan beban listrik pada sektor rumah tangga, dengan metode SARIMA (Seasonal Autoregressive Integrated Moving Average) yang menggunakan data penggunaan listrik sebelumnya sebagai acuan prediksi penggunaan listrik dalam tujuh hari kedepan. Sistem ini kemudian akan diaplikasikan melalui web dengan framework flask. Sistem ini diharapkan dapat dimanfaatkan sebagai media prediksi penggunaan beban listrik dalam sektor rumah tangga. Data yang digunakan dalam sistem prediksi adalah besar penggunaan daya listrik harian dalam hitungan jam selama 37 hari, sejak tanggal 22 Maret 2020 sampai 27 April 2020. Hasil prediksi yang didapat yaitu besar total penggunaan daya listrik untuk 7 hari dari tanggal 21 April sampai 27 April 2020 dengan nilai MAPE (Mean Percetage Error) sebesar 14,995%.
Kata kunci : Beban Listrik, Metode Prediksi, ARIMA (Autoregressive Integrated Moving Average), Web.
References
Q. Chen, A. Balian, M. Kyzym, T. Salashenko, I. Gryshova and V. Khaustova, "Electricity Markets Instability: Causes of Price Dispersion.," Sustainability, vol. 13, no. 12343, 2013.
R. Weron, "Electricity price forecasting: A review of the state-of-the-art with a look into the future," Int. J. Forecast, vol. 3, pp. 1030-1081, 2014.
J. Lago, G. Marcjasz, B. De Schutter and R. Weron, "Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an openaccess benchmark," Appl. Energy, vol. 293, no. 1169833, 2021.
K. Funahashi and Y. Nakamura, "Approximation of dynamical systems by continuous time recurrent neural networks," Neural Network, no. 6, pp. 801- 806, 1993.
F. R. Alharbi and D. Csala, "Short-Term Wind Speed and Temperature Forecasting Model Based on Gated Recurrent Unit Neural Networks.," in The 2021 3rd Global Power, Energy and Communication Conference (GPECOM), Antalya, Turkey, 2021.
M. Valipour, "Long-term runoff study using SARIMA and ARIMA models in the United States," METEOROLOGICAL APPLICATIONS, vol. 22, pp. 592-598, 2015.
"Modelling and Forecasting of Rainfall Time Series Using SARIMA," Environ. Process., vol. 4, pp. 399- 419, 2017.
R. W. Divisekara, G. J. M. S. R. Jayasinghe and K. W. S. N. Kumari, "Forecasting the red lentils commodity market price using SARIMA models," SN Bus Econ, vol. 1, no. 20, 2021.
"Sarima Modelling Approach for Railway Passenger Flow Forecasting," Transport, vol. 33, no. 5, pp. 1113- 1120, 2016.
A. E. Permanasari, I. Hidayah and I. A. Bustoni, "SARIMA (Seasonal ARIMA) Implementation on Time Series to Forecast The Number of Malaria Incidence," International Conference on Information Technology and Electrical Engineering (ICITEE), Yogyakarta, Indonesia, pp. 203-207, 2013.
Z. Xinxiang, Z. Bo and F. Huijuan, "A Comparison Study of Outpatient Visits Forecasting Effect between ARIMA with Seasonal Index and SARIMA," International Conference on Progress in Informatics and Computing (PIC), Nanjing, China, pp. 362-366, 2017.
D. N. Pradini, M. Astiningrum and A. Y. Ananta, "Sistem Peramalan Dan Pemantauan Jumlah Produksi Ikan Berbasis Web Dengan Metode Seasonal Autoregressive Integrated Moving Average(SARIMA) (STUDI KASUS DINAS PERIKANAN KAB.MALANG )," Teknologi Informasi, Politeknik Negri Malang, 2020.
C. G. K. Simatupang, W. Swastika and T. R. Suganda, "Perancangan Aplikasi Berbasis Web Untuk Prediksi Harga Saham Dengan Metode LTSM," Sainsbertek Jurnal Ilmiah Sains dan Teknologi, vol. 3, no. 1, pp. 1- 8, 2022.
D. Suswanto, Sistem Distribusi Tenaga Listrik, 2010.
R. T. Jurnal, "Analisis Pengaruh Jenis Beban Listrik Terhadap Kinerja Pemutus Daya Listrik Di Gedung Cyber Jakarta," Energi & Kelistrikan, vol. 7, no. 2, pp. 108-117, 2015.
S. Pers, "web.pln.co.id," PT. PLN (Persero), 27 Juni 2023. [Online]. Available: https://web.pln.co.id/media/siaran- pers/2023/06/tariflistrik-triwulan-iii-tetap-pln- pastikan-listrik-andaluntuk-dorong-perekonomian. [Accessed 22 Agustus 2023].
Science Direct, "Forecasting: theory and practice," International Journal of Forecasting, vol. 38, no. 3, pp. 705-871, 2022.
I. K. Putri and S. , "Deteksi Outlier pada Model ARIMA Musiman Ganda untuk Peramalan Beban Listrik Jangka Pendek di Jawa Timur," Jurnal Sains dan Seni ITS, vol. 4, no. 1, pp. 2337-3520, 2015.
E. T. K. Dewi, A. Agoestanto and S. , "Metode Least Trimmed Square (LTS) dan MM-Estimation Untuk Mengestimasi Parameter Regresi Ketika Terdapat Outlier," UNNES Journal of Mathematics, vol. 5, no. 1, pp. 47-54, 2016.
G. E. P. Box, G. M. Jenkins and G. C. Reinsel, Time Series Analysis, Forecasting and Control, Holden- Day. Series G, 1976.
J. E. Hanke and D. W. Wichern, "Business Forecasting," Prentice Hall, New York City, 2005.
I. Aksan and K. Nurfadilah, "Aplikasi Metode Arima Box-Jenkins Untuk Meramalkan Penggunaan Harian Data Seluler," Journal of Mathematics:: Theory and Applications, vol. 2, no. 1, pp. 2722- 2705, 2020.
S. Makridakis, S. C. Wheelwright and V. E. McGee, Metode dan Aplikasi Peramalan. Ed. ke-2.Terjemahan Ir.Hari Suminto, Jakarta: Binarupa Aksara, 1999.
Python Software Foundation, "docs.python.org," 2001. [Online]. Available: https://docs.python.org/3/library/pickle.html. [Accessed 1 November 2023].
N. Loubser, "Software Engineering for Absolute Beginners," in Creating a RESTful API: Flask, Berkeley, CA, Apress, 2021, pp. 193-233.[26] P.-C. Chang, Y.-W. Wang and C.-H. Liu, "The development of a weighted evolving fuzzy neural network for PCB sales forecasting," Expert Systems with Applications, vol. 32, no. 1, pp. 86-96, 2007.
D. A. R. Poespitasari, C. Ekaputri and D. K. Silalahi, "Prediksi Konsumsi Listrik Rumah Berdasarkan Pola Penggunaan Beban Listrik," 2021.
A. Krizhevsky, I. Sutskever and G. Hinton, "Imagenet classification with deep convolutional neural networks," Communication ACM, no. 60, pp. 84-90, 2017.
S. Vagropoulos, G. Chouliaras, E. Kardakos, C. Simoglou and A. Bakirtzis, "Comparison of SARIMAX, SARIMA, modified SARIMA and ANN-based models for short-term PV generation forecasting," in the 2016 IEEE International Energy Conference (ENERGYCON), Leuven, Belgium, 2016.
N. Elamin and M. Fukushige, "Modeling and Forecasting Hourly Electricity Demand by SARIMAX with Interactions," Energy, vol. 165, pp. 257-268, 2018.
