IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v18y2025i10p2450-d1652966.html
   My bibliography  Save this article

DTCformer: A Temporal Convolution-Enhanced Autoformer with DILATE Loss for Photovoltaic Power Forecasting

Author

Listed:
  • Quanhui Qiu

    (Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China
    University of Chinese Academy of Sciences, Beijing 100049, China)

  • Dejun Ning

    (Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China
    University of Chinese Academy of Sciences, Beijing 100049, China)

  • Qiang Guo

    (HCIG AVIC Saihan Green Energy Technology Development Co., Ltd., Chengde 067400, China)

  • Jiang Wei

    (HCIG AVIC Saihan Green Energy Technology Development Co., Ltd., Chengde 067400, China)

  • Huichang Chen

    (HCIG AVIC Saihan Green Energy Technology Development Co., Ltd., Chengde 067400, China)

  • Lihui Sui

    (HCIG AVIC Saihan Green Energy Technology Development Co., Ltd., Chengde 067400, China)

  • Yi Liu

    (HCIG AVIC Saihan Green Energy Technology Development Co., Ltd., Chengde 067400, China)

  • Zibing Du

    (HCIG AVIC Saihan Green Energy Technology Development Co., Ltd., Chengde 067400, China)

  • Shipeng Liu

    (Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China
    University of Chinese Academy of Sciences, Beijing 100049, China)

Abstract

Photovoltaic power forecasting plays a crucial role in the integration of renewable energy into the power grid. However, existing methods suffer from issues such as cumulative multi-step prediction errors and the limitations of traditional evaluation metrics (e.g., MSE, MAE). To address these challenges, this study introduces DTCformer, a generative forecasting model based on Autoformer. The proposed model integrates a Temporal Convolution Feedforward Network module and a Variable Selection Embedding module, effectively capturing inter-variable dependencies and temporal periodicity. Furthermore, it incorporates the DILATE loss function, which significantly enhances both forecasting accuracy and robustness. Experimental results on publicly available datasets demonstrate that DTCformer surpasses mainstream models, improving overall performance metrics (DILATE values) by 5.0–42.3% in 24 h, 48 h, and 72 h forecasting tasks.

Suggested Citation

  • Quanhui Qiu & Dejun Ning & Qiang Guo & Jiang Wei & Huichang Chen & Lihui Sui & Yi Liu & Zibing Du & Shipeng Liu, 2025. "DTCformer: A Temporal Convolution-Enhanced Autoformer with DILATE Loss for Photovoltaic Power Forecasting," Energies, MDPI, vol. 18(10), pages 1-16, May.
    • Handle: RePEc:gam:jeners:v:18:y:2025:i:10:p:2450-:d:1652966
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/18/10/2450/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/18/10/2450/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Chu Donatus Iweh & Samuel Gyamfi & Emmanuel Tanyi & Eric Effah-Donyina, 2021. "Distributed Generation and Renewable Energy Integration into the Grid: Prerequisites, Push Factors, Practical Options, Issues and Merits," Energies, MDPI, vol. 14(17), pages 1-34, August.
    2. S. Yakowitz, 1987. "Nearest‐Neighbour Methods For Time Series Analysis," Journal of Time Series Analysis, Wiley Blackwell, vol. 8(2), pages 235-247, March.
    3. Mahmoud Dhimish & Pavlos I. Lazaridis, 2022. "Approximating Shading Ratio Using the Total-Sky Imaging System: An Application for Photovoltaic Systems," Energies, MDPI, vol. 15(21), pages 1-16, November.
    4. Zagouras, Athanassios & Pedro, Hugo T.C. & Coimbra, Carlos F.M., 2015. "On the role of lagged exogenous variables and spatio–temporal correlations in improving the accuracy of solar forecasting methods," Renewable Energy, Elsevier, vol. 78(C), pages 203-218.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Fernando Venâncio Mucomole & Carlos Augusto Santos Silva & Lourenço Lázaro Magaia, 2025. "Parametric Forecast of Solar Energy over Time by Applying Machine Learning Techniques: Systematic Review," Energies, MDPI, vol. 18(6), pages 1-51, March.
    2. Rodríguez-Vargas, Adolfo, 2020. "Forecasting Costa Rican inflation with machine learning methods," Latin American Journal of Central Banking (previously Monetaria), Elsevier, vol. 1(1).
    3. Elsinga, Boudewijn & van Sark, Wilfried G.J.H.M., 2017. "Short-term peer-to-peer solar forecasting in a network of photovoltaic systems," Applied Energy, Elsevier, vol. 206(C), pages 1464-1483.
    4. Nonnenmacher, Lukas & Kaur, Amanpreet & Coimbra, Carlos F.M., 2016. "Day-ahead resource forecasting for concentrated solar power integration," Renewable Energy, Elsevier, vol. 86(C), pages 866-876.
    5. Yousef Alharbi & Ahmed Darwish & Xiandong Ma, 2023. "A Comprehensive Review of Distributed MPPT for Grid-Tied PV Systems at the Sub-Module Level," Energies, MDPI, vol. 16(14), pages 1-23, July.
    6. Gustavo Adolfo Gómez-Ramírez & Carlos Meza & Gonzalo Mora-Jiménez & José Rodrigo Rojas Morales & Luis García-Santander, 2023. "The Central American Power System: Achievements, Challenges, and Opportunities for a Green Transition," Energies, MDPI, vol. 16(11), pages 1-20, May.
    7. Dominique Guegan & Patrick Rakotomarolahy, 2010. "A Short Note on the Nowcasting and the Forecasting of Euro-area GDP Using Non-Parametric Techniques," PSE-Ecole d'économie de Paris (Postprint) halshs-00460472, HAL.
    8. Laurent Ferrara & Dominique Guégan & Patrick Rakotomarolahy, 2010. "GDP nowcasting with ragged-edge data: a semi-parametric modeling," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 29(1-2), pages 186-199.
    9. Rob Shipman & Rebecca Roberts & Julie Waldron & Chris Rimmer & Lucelia Rodrigues & Mark Gillott, 2021. "Online Machine Learning of Available Capacity for Vehicle-to-Grid Services during the Coronavirus Pandemic," Energies, MDPI, vol. 14(21), pages 1-16, November.
    10. Servín-Campuzano, Hermelinda & Domínguez-Pérez, Valeria Monserrat & Marín-Mendoza, Pablo César & Panales-Pérez, Alexander & Fuentes-Cortés, Luis Fabián, 2024. "The role of storage in energy security performance based on diversification and concentration for distributed energy systems," Renewable Energy, Elsevier, vol. 229(C).
    11. Aguiar, L. Mazorra & Pereira, B. & Lauret, P. & Díaz, F. & David, M., 2016. "Combining solar irradiance measurements, satellite-derived data and a numerical weather prediction model to improve intra-day solar forecasting," Renewable Energy, Elsevier, vol. 97(C), pages 599-610.
    12. Piotr Powroźnik & Paweł Szcześniak & Krzysztof Piotrowski, 2021. "Elastic Energy Management Algorithm Using IoT Technology for Devices with Smart Appliance Functionality for Applications in Smart-Grid," Energies, MDPI, vol. 15(1), pages 1-23, December.
    13. Wassim Daher & Jihad Elnaboulsi & Mahelet G Fikru & Luis Gautier, 2024. "An Analysis of Mergers in the Presence of Uncertainty in Renewable Energy Integration Costs," Working Papers hal-04682056, HAL.
    14. Dominique Guegan & Justin Leroux, 2009. "Local Lyapunov Exponents: A new way to predict chaotic systems," PSE-Ecole d'économie de Paris (Postprint) halshs-00511996, HAL.
    15. Ayuketah, Yvan & Gyamfi, Samuel & Diawuo, Felix Amankwah & Dagoumas, Athanasios S., 2023. "A techno-economic and environmental assessment of a low-carbon power generation system in Cameroon," Energy Policy, Elsevier, vol. 179(C).
    16. Nalini Karchi & Deepak Kulkarni & Rocío Pérez de Prado & Parameshachari Bidare Divakarachari & Sujata N. Patil & Veena Desai, 2022. "Adaptive Least Mean Square Controller for Power Quality Enhancement in Solar Photovoltaic System," Energies, MDPI, vol. 15(23), pages 1-19, November.
    17. Chu, Yinghao & Li, Mengying & Pedro, Hugo T.C. & Coimbra, Carlos F.M., 2015. "Real-time prediction intervals for intra-hour DNI forecasts," Renewable Energy, Elsevier, vol. 83(C), pages 234-244.
    18. Joel Alpízar-Castillo & Laura Ramirez-Elizondo & Pavol Bauer, 2022. "Assessing the Role of Energy Storage in Multiple Energy Carriers toward Providing Ancillary Services: A Review," Energies, MDPI, vol. 16(1), pages 1-31, December.
    19. Mikhail V. Kozhevnikov & Artem A. Dvinyaninov & Nikita G. Sapozhnikov, 2024. "Institutional barriers to the development of small-scale power generation in Russia," Journal of New Economy, Ural State University of Economics, vol. 25(1), pages 110-130, April.
    20. Kück, Mirko & Freitag, Michael, 2021. "Forecasting of customer demands for production planning by local k-nearest neighbor models," International Journal of Production Economics, Elsevier, vol. 231(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:18:y:2025:i:10:p:2450-:d:1652966. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.