From ARIMA to Attention: Power Load Forecasting Using Temporal Deep Learning

Accurate short-term power load forecasting is important to effectively manage, optimize, and ensure the robustness of modern power systems. This paper performs an empirical evaluation of a traditional statistical model and deep learning approaches for predicting short-term energy load. Four models, namely ARIMA, LSTM, BiLSTM, and Transformer, were leveraged on the PJM Hourly Energy Consumption data. The data processing involved interpolation, normalization, and a sliding-window sequence method. Each model’s forecasting performance was evaluated for the 24-hour horizon using MAE, RMSE, and MAPE. Of the models tested, the Transformer model, which relies on self-attention algorithms, produced the best results with 3.8 percent of MAPE, with performance above any model in both accuracy and robustness. These findings underscore the growing potential of attention-based architectures in accurately capturing complex temporal patterns in power consumption data.

💡 Research Summary

**
This paper presents a systematic empirical comparison of four forecasting approaches—ARIMA, LSTM, BiLSTM, and a vanilla Transformer—applied to the PJM Hourly Energy Consumption dataset, a publicly available record of total system load in megawatts for the Eastern United States. The authors first preprocess the raw series by linearly interpolating any missing timestamps, scaling the values to the