[공지사항]을 빙자한 안부와 근황 
Show more

Daily Arxiv

This is a page that curates AI-related papers published worldwide.
All content here is summarized using Google Gemini and operated on a non-profit basis.
Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.

Large Language Model as An Operator: An Experience-Driven Solution for Distribution Network Voltage Control

Created by
  • Haebom

Author

Xu Yang, Chenhui Lin, Haotian Liu, Qi Wang, Wenchuan Wu

Outline

This paper proposes a novel method for generating autonomous distributed control strategies for power systems by utilizing large-scale language models (LLMs). In particular, we apply LLMs to experience-based voltage control solutions for distributed networks, enabling self-evolution of LLM-based voltage control strategies through interactions among experience storage, retrieval, generation, and modification modules. Experimental results demonstrate the effectiveness of the proposed method and the applicability of LLMs to solving distributed control problems in power systems.

Takeaways, Limitations

•
Takeaways:
◦
A novel distributed power system control strategy using LLM
◦
Verification of the feasibility of implementing an LLM-based self-evolutionary voltage control system
◦
Verification of the applicability of LLM to solving distributed control problems in power systems
•
Limitations:
◦
Additional validation needed for practical field application
◦
Possible performance degradation depending on the quality and quantity of LLM learning data
◦
LLM computational cost and energy consumption issues need to be considered
◦
Insufficient response measures to unpredictable situations
👍
Made with Slashpage