IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v17y2024i24p6234-d1541180.html
   My bibliography  Save this article

Hybrid Proximal Policy Optimization—Wasserstein Generative Adversarial Network Framework for Hosting Capacity Optimization in Renewable-Integrated Power Systems

Author

Listed:
  • Jun Han

    (State Grid Jiangsu Electric Power Economic and Technological Research Institute, No. 251 Zhongshan Road, Gulou District, Nanjing 210009, China)

  • Chao Cai

    (State Grid Jiangsu Electric Power Economic and Technological Research Institute, No. 251 Zhongshan Road, Gulou District, Nanjing 210009, China)

  • Wenjie Pan

    (State Grid Jiangsu Electric Power Economic and Technological Research Institute, No. 251 Zhongshan Road, Gulou District, Nanjing 210009, China)

  • Hong Liu

    (School of Electrical and Information Engineering, Tianjin University, No. 92 Weijin Road, Nankai District, Tianjin 300072, China)

  • Zhengyang Xu

    (School of Electrical and Information Engineering, Tianjin University, No. 92 Weijin Road, Nankai District, Tianjin 300072, China)

Abstract

The rapid integration of distributed energy resources (DERs) such as photovoltaics (PV), wind turbines, and energy storage systems has transformed modern power systems, with hosting capacity optimization emerging as a critical challenge. This paper presents a novel Hybrid Proximal Policy Optimization-Wasserstein Generative Adversarial Network (PPO-WGAN) framework designed to address the temporal-spatial complexities and uncertainties inherent in renewable-integrated distribution networks. The proposed method combines Proximal Policy Optimization (PPO) for sequential decision-making with Wasserstein Generative Adversarial Networks (WGAN) for high-quality scenario generation, enabling robust hosting capacity enhancement and operational efficiency. Simulation results demonstrate a hosting capacity improvement of up to 128.6% in high-penetration scenarios (90% renewable), with average operational cost reductions of 22%. Voltage deviations are minimized to within ±5% of nominal levels, while energy losses are reduced by 18%. Scenario quality, evaluated using the Wasserstein metric, achieved convergence with an average score of 0.95 after 80 iterations, highlighting the WGAN’s ability to generate realistic and diverse scenarios. This study advances the state of the art in distribution network optimization by integrating machine learning techniques with robust mathematical modeling. The PPO-WGAN framework enhances scalability, ensures grid stability, and promotes efficient renewable integration, providing a robust foundation for future applications in modern power systems.

Suggested Citation

  • Jun Han & Chao Cai & Wenjie Pan & Hong Liu & Zhengyang Xu, 2024. "Hybrid Proximal Policy Optimization—Wasserstein Generative Adversarial Network Framework for Hosting Capacity Optimization in Renewable-Integrated Power Systems," Energies, MDPI, vol. 17(24), pages 1-22, December.
  • Handle: RePEc:gam:jeners:v:17:y:2024:i:24:p:6234-:d:1541180
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/17/24/6234/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/17/24/6234/
    Download Restriction: no
    ---><---

    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:17:y:2024:i:24:p:6234-:d:1541180. 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.

    We have no bibliographic references for this item. You can help adding them by using 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.