Scholarlink

This paper presents a hybrid Deep Learning model for short-term electricity load forecasting, combining Seasonal Autoregressive Integrated Moving Average (SARIMA) and Long Short-Term Memory (LSTM) networks. Using historical data from Ecuador’s National Interconnected System (SNI) between 1972 and 2023, the study evaluates the performance of SARIMA, LSTM, and the proposed hybrid model. Results demonstrate that the SARIMA-LSTM hybrid significantly improves forecasting accuracy, achieving an RMSE of 18.7 GWh, MAE of 12.3 GWh, and R2 of 0.96 for monthly demand prediction. The model successfully incorporates exogenous variables such as user growth, region, and extreme climate events (floods and droughts), reducing forecast error by 12%. These findings highlight the hybrid approach as a robust tool for supporting energy planning and decision-making in Ecuador’s electricity sector.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning Model for Short-Term Electricity Load Forecasting Based on SARIMA-LSTM Model with Data from Ecuador’s National Interconnected System

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Galo Valverde-Landívar,
  • Joffre León-Veas

摘要

This paper presents a hybrid Deep Learning model for short-term electricity load forecasting, combining Seasonal Autoregressive Integrated Moving Average (SARIMA) and Long Short-Term Memory (LSTM) networks. Using historical data from Ecuador’s National Interconnected System (SNI) between 1972 and 2023, the study evaluates the performance of SARIMA, LSTM, and the proposed hybrid model. Results demonstrate that the SARIMA-LSTM hybrid significantly improves forecasting accuracy, achieving an RMSE of 18.7 GWh, MAE of 12.3 GWh, and R2 of 0.96 for monthly demand prediction. The model successfully incorporates exogenous variables such as user growth, region, and extreme climate events (floods and droughts), reducing forecast error by 12%. These findings highlight the hybrid approach as a robust tool for supporting energy planning and decision-making in Ecuador’s electricity sector.