Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.12682 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915449040535552 |
|---|---|
| author | Shi, Jinquan Cheng, Yingying Zhang, Fan Jiang, Miao Lin, Jun Shen, Yanbai |
| author_facet | Shi, Jinquan Cheng, Yingying Zhang, Fan Jiang, Miao Lin, Jun Shen, Yanbai |
| contents | The global shift towards renewable energy presents unprecedented challenges for the electricity industry, making regulatory reasoning and compliance increasingly vital. Grid codes, the regulations governing grid operations, are complex and often lack automated interpretation solutions, which hinders industry expansion and undermines profitability for electricity companies. We introduce GridCodex, an end to end framework for grid code reasoning and compliance that leverages large language models and retrieval-augmented generation (RAG). Our framework advances conventional RAG workflows through multi stage query refinement and enhanced retrieval with RAPTOR. We validate the effectiveness of GridCodex with comprehensive benchmarks, including automated answer assessment across multiple dimensions and regulatory agencies. Experimental results showcase a 26.4% improvement in answer quality and more than a 10 fold increase in recall rate. An ablation study further examines the impact of base model selection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12682 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GridCodex: A RAG-Driven AI Framework for Power Grid Code Reasoning and Compliance Shi, Jinquan Cheng, Yingying Zhang, Fan Jiang, Miao Lin, Jun Shen, Yanbai Artificial Intelligence The global shift towards renewable energy presents unprecedented challenges for the electricity industry, making regulatory reasoning and compliance increasingly vital. Grid codes, the regulations governing grid operations, are complex and often lack automated interpretation solutions, which hinders industry expansion and undermines profitability for electricity companies. We introduce GridCodex, an end to end framework for grid code reasoning and compliance that leverages large language models and retrieval-augmented generation (RAG). Our framework advances conventional RAG workflows through multi stage query refinement and enhanced retrieval with RAPTOR. We validate the effectiveness of GridCodex with comprehensive benchmarks, including automated answer assessment across multiple dimensions and regulatory agencies. Experimental results showcase a 26.4% improvement in answer quality and more than a 10 fold increase in recall rate. An ablation study further examines the impact of base model selection. |
| title | GridCodex: A RAG-Driven AI Framework for Power Grid Code Reasoning and Compliance |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.12682 |