Gross electricity consumption forecasting using LSTM and SARIMA approaches: A case study of Türkiye

Mehmet Bilgili and Engin Pinar

Energy, 2023, vol. 284, issue C

Abstract: Gross electricity consumption (GEC) forecasts are an essential tool for policymakers in developing countries. It is widely acknowledged that GEC forecasting models contribute significantly to more effective electricity management policies, behavioral changes within the energy supply industry, and reduced energy consumption. In this regard, it is essential to evaluate the approaches that allow users to anticipate their future energy usage based on their own consumption history data and other variables. This motivates researchers to develop efficient GEC forecasting models using historical time series data and appropriate estimation strategies. In this study, therefore, a machine-learning model employing a deep-learning technique based on a long short-term memory (LSTM) neural network was utilized to forecast GEC in Türkiye. The LSTM model was compared to the seasonal autoregressive integrated moving average (SARIMA) model to determine the amount of gross energy usage. Although the results are close to each other, the LSTM model outperformed the SARIMA model in general, with the lowest MAPE (2.42%), MAE (215.35 GWh), and RMSE (329.9 GWh) values and the greatest R-value (0.9992).

Keywords: Deep learning; Forecasting; Gross electricity consumption; Long short-term memory (LSTM); Seasonal autoregressive integrated moving-average (SARIMA) (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (8)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223019692
Full text for ScienceDirect subscribers only

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:eee:energy:v:284:y:2023:i:c:s0360544223019692

DOI: 10.1016/j.energy.2023.128575

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().