7 papers
Grid-Oriented Probabilistic Load Forecasting for AI Data Centers
Qingyi Yao, Ding Lin, Tianqiao Zhao +2
Probabilistic load forecasts for AI data centers need to represent both uncertainty under changing workloads and temporal dependence to support grid operations. This paper develops…
Identifiability-Guided Composite Load Modeling of AI Data Centers
Ding Lin, Jianhui Wang, Meng Yue +1
The rapid growth of AI data centers introduces large, workload-dependent loads whose protection and reconnection behavior can affect power-system transient stability. Calibrating d…
Task-Conditional Faithfulness Auditing of Multimodal LLMs for Grid Diagnosis
Tianqiao Zhao, Meng Yue, Jianhui Wang
Multimodal large language models (LLMs) can combine topology, measurements, and incident text for grid diagnosis, yet answer accuracy does not establish that task-appropriate evide…
From Natural Language to Solver-Ready Power System Optimization: An LLM-Assisted, Validation-in-the-Loop Framework
Yunkai Hu, Tianqiao Zhao, Meng Yue
This paper introduces a novel Large Language Models (LLMs)-assisted agent that automatically converts natural-language descriptions of power system optimization scenarios into comp…
A Deep Reinforcement Learning Method for Multi-objective Transmission Switching
Ding Lin, Jianhui Wang, Tianqiao Zhao +1
Transmission switching is a well-established approach primarily applied to minimize operational costs through strategic network reconfiguration. However, exclusive focus on cost re…
Reinforcement Learning Based Symbolic Regression for Load Modeling
Ding Lin, Han Guo, Jianhui Wang +2
With the increasing penetration of renewable energy sources, growing demand variability, and evolving grid control strategies, accurate and efficient load modeling has become a cri…
Diffusion Model-based Parameter Estimation in Dynamic Power Systems
Feiqin Zhu, Dmitrii Torbunov, Zhongjing Jiang +4
Parameter estimation, which represents a classical inverse problem, is often ill-posed as different parameter combinations can yield identical outputs. This non-uniqueness presents…