Electricity Consumption Forecasting in Algeria using ARIMA and Long Short-Term Memory Neural Network

Sahed Abdelkader () and Kahoui Hacene ()
Additional contact information
Sahed Abdelkader: University Centre of Maghnia
Kahoui Hacene: University Centre of Maghnia

Post-Print from HAL

Abstract: Forecasting electricity consumption is necessary for electric grid operation and utility resource planning, as well as to improve energy security and grid resilience. Thus, this research aims to investigate the prediction performance of the ARIMA and LSTM neural network model using electricity consumption data during the period 1990 to 2020. The time series for electricity consumption is divided into 70% for training data and 30% for test data. The results showed that the LSTM model provided improved forecasting accuracy than the ARIMA model.

Keywords: Electricity Consumption ARIMA LSTM Algeria. JEL Classification Codes: Q47; C53; C45; Electricity Consumption; ARIMA; LSTM; Algeria. JEL Classification Codes: Q47 (search for similar items in EconPapers)
Date: 2023-06-04
New Economics Papers: this item is included in nep-ara, nep-cmp, nep-ene, nep-for and nep-ger
Note: View the original document on HAL open archive server: https://cnrs.hal.science/hal-04183403v1
References: Add references at CitEc
Citations:

Published in International Journal of Economic Performance - المجلة الدولية للأداء الاقتصادي, 2023, 06 (01)

Downloads: (external link)
https://cnrs.hal.science/hal-04183403v1/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04183403

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().