COMPARATIVE STUDY OF LSTM-BASED MODELS WITH HYPERPARAMETER OPTIMIZATION FOR SHORT-TERM ELECTRICITY LOAD FORECASTING

This research is focused on the development and comparison of time series models for short-term electrical load forecasting, utilizing several variants of Long Short-Term Memory (LSTM) networks. The specific LSTM variants employed in this study include Vanilla LSTM, Stacked LSTM, Bidirectional LSTM, and Convolutional Neural Network LSTM (CNN-LSTM). We used five years (2016-2020) of daily electricity load data from the Central Java-DIY system, provided by PT PLN (Persero). The primary objective is to ascertain the accuracy and evaluate the performance of these LSTM variants in the context of short-term load forecasting. This is achieved quantitatively through the computation of various error metrics, namely Mean Square Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared. The results of the study reveal that the CNN-LSTM method outperforms the other variants in terms of the calculated metrics. Specifically, the CNN-LSTM method achieved the lowest values for all metrics: an MSE of 0.007 for training and 0.0010 for testing, an MAE of 0.0050 for training and 0.0062 for testing, and an RMSE of 0.083 for training and 0.099 for testing. Among the evaluated models, CNN-LSTM demonstrates the best trade-off between predictive accuracy and training efficiency, making it the most recommended for short-term electricity load forecasting. While BiLSTM achieves higher accuracy, particularly in terms of MAE, it requires a longer training time. In contrast, Stacked LSTM converges faster with slightly lower accuracy, making it a strong alternative when computational efficiency is prioritized..