EnergyPatchTST: Multi-scale Time Series Transformers with Uncertainty Estimation for Energy Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Wei, Wang, Zixin, Sun, Qizheng, Gao, Qixiang, Yang, Fenglei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912525896908800
author Li, Wei
Wang, Zixin
Sun, Qizheng
Gao, Qixiang
Yang, Fenglei
author_facet Li, Wei
Wang, Zixin
Sun, Qizheng
Gao, Qixiang
Yang, Fenglei
contents Accurate and reliable energy time series prediction is of great significance for power generation planning and allocation. At present, deep learning time series prediction has become the mainstream method. However, the multi-scale time dynamics and the irregularity of real data lead to the limitations of the existing methods. Therefore, we propose EnergyPatchTST, which is an extension of the Patch Time Series Transformer specially designed for energy forecasting. The main innovations of our method are as follows: (1) multi-scale feature extraction mechanism to capture patterns with different time resolutions; (2) probability prediction framework to estimate uncertainty through Monte Carlo elimination; (3) integration path of future known variables (such as temperature and wind conditions); And (4) Pre-training and Fine-tuning examples to enhance the performance of limited energy data sets. A series of experiments on common energy data sets show that EnergyPatchTST is superior to other commonly used methods, the prediction error is reduced by 7-12%, and reliable uncertainty estimation is provided, which provides an important reference for time series prediction in the energy field.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05454
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EnergyPatchTST: Multi-scale Time Series Transformers with Uncertainty Estimation for Energy Forecasting
Li, Wei
Wang, Zixin
Sun, Qizheng
Gao, Qixiang
Yang, Fenglei
Machine Learning
Artificial Intelligence
Accurate and reliable energy time series prediction is of great significance for power generation planning and allocation. At present, deep learning time series prediction has become the mainstream method. However, the multi-scale time dynamics and the irregularity of real data lead to the limitations of the existing methods. Therefore, we propose EnergyPatchTST, which is an extension of the Patch Time Series Transformer specially designed for energy forecasting. The main innovations of our method are as follows: (1) multi-scale feature extraction mechanism to capture patterns with different time resolutions; (2) probability prediction framework to estimate uncertainty through Monte Carlo elimination; (3) integration path of future known variables (such as temperature and wind conditions); And (4) Pre-training and Fine-tuning examples to enhance the performance of limited energy data sets. A series of experiments on common energy data sets show that EnergyPatchTST is superior to other commonly used methods, the prediction error is reduced by 7-12%, and reliable uncertainty estimation is provided, which provides an important reference for time series prediction in the energy field.
title EnergyPatchTST: Multi-scale Time Series Transformers with Uncertainty Estimation for Energy Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.05454