Abstract: The issue of obtaining reliable forecasting methods for electricity consumption has been widely discussed by the past research work. This is due to increased demand for electricity and as a result, the development of efficient pricing model. Several techniques have been used in past research for forecasting electricity consumption. In this paper, auto-regressive integrated moving average (ARIMA) and artificial neural network (ANN) models are utilized to formulate a forecasting model of the monthly electricity consumption of Cagayan de Oro City. ARIMA and ANN were used to forecast the monthly electricity consumption of Cagayan de Oro City. Other variables like number of consumers, gross domestic product, effective rate of consumers, average monthly rainfall, and average monthly temperature were used as input variables for ANN. The accuracy of the ARIMA and ANN models is being compared using the actual data with the predicted values obtained in the forecasting process using mean absolute percentage error (MAPE). Based on the results of ARIMA and ANN on MAPE, feed-forward neural network (FFNN) of ANN model has the least mean absolute percentage error. Hence, FFNN was used to forecast the monthly electricity consumption of the Cagayan de Oro City.
|
Keywords and phrases: monthly electricity consumption, forecasting, autoregressive integrated moving average, artificial neural network.
Received: May 31, 2022; Accepted: June 25, 2022; Published: July 20, 2022
How to cite this article: Noel G. Cuarteros Jr., Forecasting a monthly electricity consumption using auto-regressive integrated moving average (ARIMA) and artificial neural network (ANN) models, Advances and Applications in Statistics 79 (2022), 55-66. http://dx.doi.org/10.17654/0972361722059
This Open Access Article is Licensed under Creative Commons Attribution 4.0 International License
References:
[1] D. Aydin and H. Toros, Prediction of short-term electricity consumption by artificial neural network using temperature variables, European Journal of Science and Technology No. 14 (2018), 393-398. [2] K. Cuarteros and N. Cuarteros, Forecasting the electricity consumption using auto-regressive integrated moving average, Sci. Int. (Lahore) 33(6) (2021), 463-466. [3] M. Hagan, H. Demuth, M. Beale and O. De Jesus, Neural Network Design, 2nd ed., PWS Publishing Co., 2007. hagan.okstate.edu/nnd.html. [4] K. Hornik, M. Stinchcombe and H. White, Multilayer feedforward networks are universal approximators, Neural Network 2 (1989), 359-366. [5] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 2nd Edition Textbook, OTexts, 2018, 384 pp. [6] K. Kandananond, Forecasting electricity demand in Thailand with an artificial neural network approach, Energies 4(8) (2011), 1246-1257.
|