ABSTRACT: The rapid development of technology has led to an ever-increasing demand for electrical energy. In the context of Timor-Leste, which still relies on fossil energy sources with high operational costs and significant environmental impacts, electricity load forecasting is a strategic measure to support the energy transition towards the Net Zero Emission (NZE) target by 2050. This study aims to utilize historical electricity load data for the period 2013-2024, as well as data on external factors affecting electricity consumption, to forecast electricity load in Timor-Leste in the next 10 years (2025-2035). The forecasting results are expected to support efforts in energy distribution efficiency, reduce operational costs, and inform decisions related to the sustainable energy transition. The method used in this study consists of two main approaches: the causality method, represented by the econometric Principal Component Analysis (PCA) model, which involves external factors in the data processing process, and the time series method, utilizing the LSTM, XGBoost, and hybrid (LSTM+XGBoost) models. In the time series method, data processing is combined with two approaches: the sliding window and the rolling recursive forecast. The performance of each model is evaluated using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The model with the lowest MAPE (<10%) is considered the best-performing model, indicating the highest accuracy. Additionally, a Monte Carlo simulation with 50,000 iterations was used to process the data and measure the prediction uncertainty, as well as test the calibration of the electricity load projection data. The results showed that the hybrid model (LSTM+XGBoost) with a rolling forecast recursive approach is the best-performing model in predicting electricity load in Timor-Leste. This model yields an RMSE of 75.76 MW, an MAE of 55.76 MW, and an MAPE of 5.27%, indicating a high level of accuracy. In addition, the model is also indicated as one that fits the characteristics of electricity load in Timor-Leste, as it produces the lowest percentage of forecasting error in predicting electricity load. The integration of the best model with Monte Carlo Simulation, which yields a P-value of 0.565, suggests that the results of electricity load projections for the period 2025-2035 are well-calibrated, reliable, accurate, and unbiased.
Keywords: Load forecasting; econometric PCA; LSTM; XGBoost; Monte Carlo; sliding window; rolling forecast; recursive; retraining; Timor-Leste.