Integrating Classification and Regression Tree Algorithm for Operational Optimization in AC-DC Hybrid Power System Planning: A Novel Approach

Yuyao Yang, Boyuan Zhang, Jun Zhang, Guoxian Gong, Feng Pan, Lei Feng, Yi Zheng and Peng Wang ()
Additional contact information
Yuyao Yang: Metrology Center of Guangdong Power Grid Co., Ltd., Qingyuan 511545, China
Boyuan Zhang: Department of Electrical Engineering, Tsinghua University, Beijing 100190, China
Jun Zhang: Metrology Center of Guangdong Power Grid Co., Ltd., Qingyuan 511545, China
Guoxian Gong: Department of Electrical Engineering, Tsinghua University, Beijing 100190, China
Feng Pan: Metrology Center of Guangdong Power Grid Co., Ltd., Qingyuan 511545, China
Lei Feng: Metrology Center of Guangdong Power Grid Co., Ltd., Qingyuan 511545, China
Yi Zheng: Department of Electrical Engineering, Tsinghua University, Beijing 100190, China
Peng Wang: Department of Electrical Engineering, Tsinghua University, Beijing 100190, China

Energies, 2025, vol. 18, issue 4, 1-22

Abstract: The increasing demand for electricity and the imperatives of climate change have made the optimization of power system planning critical for the energy transition and grid efficiency. This study presents an innovative planning method for inter-regional AC-DC hybrid power systems, leveraging the Classification and Regression Tree (CART) algorithm to optimize the operational characteristics of direct current (DC) channels. By designing a closed-loop iteration, precise operational constraints are considered by the CART algorithm, which immerged into the planning model to achieve safe and economic optimization. Based on the empirical analysis of the HRP-38 system, this study concludes that the CART algorithm offers a constructive approach to managing the operational complexities of modern power grids. By optimizing and refining DC operational characteristics based on actual system requirements, the algorithm contributes to improvements in safety, economic efficiency, and environmental sustainability within the confines of the HRP-38 node system. Consequently, the effectiveness of the CART optimization approach could be corroborated. Meanwhile, this study also acknowledges the limitations in generalizing these results to other power grid configurations and the need for further exploration in developing environmentally conscious planning methods.

Keywords: AC-DC hybrid power systems; machine learning; CART algorithm; power system optimization (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/4/783/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/4/783/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:4:p:783-:d:1586155

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().