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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Veluru, Suhasnadh Reddy, Erukude, Sai Teja, Marella, Viswa Chaitanya
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917319215677440
author Veluru, Suhasnadh Reddy
Erukude, Sai Teja
Marella, Viswa Chaitanya
author_facet Veluru, Suhasnadh Reddy
Erukude, Sai Teja
Marella, Viswa Chaitanya
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06622
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From ARIMA to Attention: Power Load Forecasting Using Temporal Deep Learning
Veluru, Suhasnadh Reddy
Erukude, Sai Teja
Marella, Viswa Chaitanya
Machine Learning
Artificial Intelligence
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.
title From ARIMA to Attention: Power Load Forecasting Using Temporal Deep Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.06622