SARIMA-Based water consumption forecasting for distribution planning and performance evaluation at padang municipal waterworks

Nelvidawati Nelvidawati (Institut Teknologi Padang)
Firdaus Firdaus (Teknik Telekomunikasi, Jurusan Teknik Elektro, Politeknik Negeri Padang, Jl. Kampus Limau Manis, Kec. Pauh, Kota Padang, Sumatera Barat, Indonesia 25176)

TEKNOSAINS: Jurnal Sains, Teknologi dan Informatika
Vol 14 No 1 (2027): TEKNOSAINS: Jurnal Sains, Teknologi dan Informatika

This study develops a forecasting model for water consumption at the Padang Municipal Waterworks using the Seasonal Autoregressive Integrated Moving Average (SARIMA) approach to enhance water distribution planning. Monthly consumption data from 2007 to 2024 were analyzed using time-series techniques. The results identify SARIMA (1,1,1)(1,1,1)₁₂ as the optimal model, effectively capturing both long-term trends and seasonal fluctuations. The model demonstrates high predictive accuracy with a Mean Absolute Percentage Error (MAPE) of 5.26%. While the Root Mean Square Error (RMSE) of 238,967.70 m³ suggests limited robustness against extreme data anomalies, the model remains highly effective for forecasting under normal operational conditions. These findings provide a data-driven foundation for Padang City’s water resource management, offering a more precise tool for anticipating demand cycles. Future research should consider incorporating external variables to better account for non-seasonal volatility.