Previous Article in Journal
The Use of Coniferous Tree Cone Biomass as an Energy Source and a Reducing Agent in the Recycling of Metals from Oxide Secondary Raw Materials
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Energies
Volume 18
Issue 23
10.3390/en18236179
energies-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Temporal Convolutional Network with Adaptive Diffusion Model for Generation–Load Probabilistic Forecasting

by
Dengao Li
1,2,3,
Ting Wang
1,4,
Ding Feng
1,5,*,
Yu Zhou
1,2 and
Feng Ji
6
1
Shanxi Energy Internet Research Institute, Taiyuan 030000, China
2
College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan 030024, China
3
Key Laboratory of Data Governance and Intelligent Decision Making of Shanxi Province, Taiyuan 030024, China
4
Shanxi Key Laboratory of Integrated Energy System, Taiyuan 030000, China
5
College of Computer Science and Technology, Taiyuan Normal University, Jinzhong 030619, China
6
Department of Electronics and Communication Engineering, Shanxi Polytechnic College, Taiyuan 237016, China
*
Author to whom correspondence should be addressed.
Energies 2025, 18(23), 6179; https://doi.org/10.3390/en18236179
Submission received: 17 October 2025 / Revised: 17 November 2025 / Accepted: 24 November 2025 / Published: 25 November 2025
Versions Notes

Abstract

Accurate generation–load forecasting is essential for the stability and efficiency of modern power systems. However, large-scale renewable integration and diverse user demand introduce strong nonlinearity and uncertainty, making probabilistic forecasting challenging. To address this, we propose a Temporal Convolutional Network with Adaptive Diffusion for generation–load probabilistic forecasting, called TCN-AD. TCN-AD employs a temporal convolutional encoder to capture long-term dependencies and local variations. In addition, an adaptive diffusion mechanism dynamically adjusts noise intensity to model time-varying uncertainty. Notably, a multi-scale fusion module and periodic attention mechanism further enhance the perception of multi-scale and cyclical patterns. Finally, a TCN-based denoising decoder refines the reverse diffusion process to reconstruct temporal dependencies effectively. Experiments on real-world load, solar, and wind datasets show that TCN-AD consistently outperforms baselines in both deterministic and probabilistic forecasting.
Keywords: generation–load forecasting; probabilistic prediction; diffusion model; temporal convolutional network; uncertainty quantification generation–load forecasting; probabilistic prediction; diffusion model; temporal convolutional network; uncertainty quantification

Share and Cite

MDPI and ACS Style

Li, D.; Wang, T.; Feng, D.; Zhou, Y.; Ji, F. Temporal Convolutional Network with Adaptive Diffusion Model for Generation–Load Probabilistic Forecasting. Energies 2025, 18, 6179. https://doi.org/10.3390/en18236179

AMA Style

Li D, Wang T, Feng D, Zhou Y, Ji F. Temporal Convolutional Network with Adaptive Diffusion Model for Generation–Load Probabilistic Forecasting. Energies. 2025; 18(23):6179. https://doi.org/10.3390/en18236179

Chicago/Turabian Style

Li, Dengao, Ting Wang, Ding Feng, Yu Zhou, and Feng Ji. 2025. "Temporal Convolutional Network with Adaptive Diffusion Model for Generation–Load Probabilistic Forecasting" Energies 18, no. 23: 6179. https://doi.org/10.3390/en18236179

APA Style

Li, D., Wang, T., Feng, D., Zhou, Y., & Ji, F. (2025). Temporal Convolutional Network with Adaptive Diffusion Model for Generation–Load Probabilistic Forecasting. Energies, 18(23), 6179. https://doi.org/10.3390/en18236179

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop