Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 10, Issue 2, 2026

A Rolling Error Correction Framework for Short-Term Photovoltaic Power Forecasting under Complex Weather Conditions

Download as PDF

DOI: 10.23977/acss.2026.100211 | Downloads: 2 | Views: 87

Author(s)

Shaoyi Sun 1, Chunyu Ma 1

Affiliation(s)

1 School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China

Corresponding Author

Shaoyi Sun

ABSTRACT

To address the issues of photovoltaic (PV) power generation being significantly affected by meteorological factors, exhibiting strong output sequence volatility, and having short-term prediction accuracy susceptible to error accumulation, this paper proposes a short-term PV power prediction method based on Stacking-Convolutional Neural Network (CNN)-Temporal Convolutional Network-Attention (TCN). This method first employs a Stacking ensemble learning model to integrate the prediction advantages of multiple base learners to obtain initial power prediction results. Then, CNN-TCN error correction network is constructed to perform deep feature learning on the initial prediction error. The CNN captures local fluctuation features, the Temporal Convolutional Network extracts temporal dependency information, and the Attention mechanism enhances the weight representation of key error segments. Finally, a rolling iteration strategy is combined to achieve continuous multi-step prediction. Experimental results show that this method exhibits high prediction accuracy and stability in typical daily predictions, comparisons with different models, and monthly error analysis, effectively improving the short-term PV power prediction performance under complex weather conditions.

KEYWORDS

Photovoltaic power forecasting; short-term forecasting; stacking ensemble learning; error correction

CITE THIS PAPER

Shaoyi Sun, Chunyu Ma. A Rolling Error Correction Framework for Short-Term Photovoltaic Power Forecasting under Complex Weather Conditions. Advances in Computer, Signals and Systems (2026). Vol. 10, No. 2, 98-110. DOI: http://dx.doi.org/10.23977/acss.2026.100211.

REFERENCES

[1] Punjwani M R. renewable and sustainable energy systems for a low-carbon future: sources, sustainability dimensions, and future challenges[J]. Spectrum of Engineering Sciences, 2026, 4(4): 1003-1014.
[2] Tang X. Synergistic development pathways: an exploratory study on the urban–rural mutual assistance model and low-carbon transformation of henan’s power supply industry towards dual-carbon goals[J]. Energies, 2024, 17(24): 6497.
[3] Arshad M. Sustainability of renewable energy options as compared to coal-fired power plants in Pakistan[J]. Green and Low-Carbon Economy, 2024, 2(3): 162-173.
[4] Olujobi O J. RETRACTED: Legal responses to energy security and sustainability in Nigeria's power sector amidst fossil fuel disruptions and low carbon energy transition[J]. Heliyon, 2023, 9(7).
[5] Markovics D, Mayer M J. Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction[J]. Renewable and Sustainable Energy Reviews, 2022, 161: 112364.
[6] Gaboitaolelwe J. Machine learning based solar photovoltaic power forecasting: A review and comparison[J]. IEEE Access, 2023, 11: 40820-40845.
[7] Abotaleb M, Dutta P K. Optimizing gated recurrent unit networks for univariate time series forecasting[J]. Hybrid Information Systems: Non-Linear Optimization Strategies with Artificial Intelligence, 2024: 473.
[8] Kim J. A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges[J]. Artificial Intelligence Review, 2025, 58(7): 216.
[9] Karthikeyan G, Jagadeeshwaran A. Enhancing solar energy generation: a comprehensive machine learning-based PV prediction and fault analysis system for real-time tracking and forecasting[J]. Electric Power Components and Systems, 2024, 52(9): 1497-1512.
[10] Tian B. Enhancing solar irradiance prediction precision: A stacked ensemble learning-based correction paradigm[J]. Next Energy, 2025, 8: 100306.
[11] Shantal M, Othman Z, Abu Bakar A. Missing data imputation using correlation coefficient and min-max normalization weighting[J]. Intelligent Data Analysis, 2025, 29(2): 372-384.
[12] Sujon K M. When to use standardization and normalization: Empirical evidence from machine learning models and XAI[J]. IEEE access, 2024, 12: 135300-135314.
[13] Yang T. Integrated thermal error modeling and compensation of machine tool feed system using subtraction-average-based optimizer-based CNN-GRU neural network[J]. The International Journal of Advanced Manufacturing Technology, 2024, 131(12): 6075-6089.
[14] Xu Z. Research on parking space detection and prediction model based on CNN-LSTM[J]. IEEE Access, 2024, 12: 30085-30100.
[15] Chen J. An error-corrected deep Autoformer model via Bayesian optimization algorithm and secondary decomposition for photovoltaic power prediction[J]. Applied Energy, 2025, 377: 124738.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 49671
Visits: 1141851

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.