The objective of electrical load forecasting is to satisfactorily and accurately predict the electrical demand that could increase or decrease in the future. A large number of engineering applications have accurate and reliable electricity demand forecasting models. Accurate load forecasting helps to plan the capacity and operation of different utilities to reliably supply power to consumers. The present work establishes the collection of annual and monthly historical data, obtained from the Ecuadorian electricity regulation and control agency. This study is focused on the comparison of the SARIMA regression model that considers the seasonality of electrical demand data, providing an evaluation of the model based on the Akaike information criterion. The input data have been divided into two data sets, one annual and one monthly, to build the forecasting model. By simulating the actual data, removing the last 5 years of data in the annual case and 2 years in the monthly case, the simulation results are checked against the actual data. The accuracy of the prediction models has been evaluated using different error matrices. R software was used for the prediction analysis having results with an error of less than 5% when comparing actual and estimated electrical demand.
|Title of host publication||Communication, Smart Technologies and Innovation for Society - Proceedings of CITIS 2021|
|Editors||Álvaro Rocha, Paulo Carlos López-López, Juan Pablo Salgado-Guerrero|
|Publisher||Springer Science and Business Media Deutschland GmbH|
|Number of pages||11|
|State||Published - 2022|
|Event||7th International Conference on Science, Technology and Innovation for Society, CITIS 2021 - Virtual, Online|
Duration: 26 May 2021 → 28 May 2021
|Name||Smart Innovation, Systems and Technologies|
|Conference||7th International Conference on Science, Technology and Innovation for Society, CITIS 2021|
|Period||26/05/21 → 28/05/21|
Bibliographical notePublisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
- Demand forecasting
- Time-series analysis