Exploration of Multi-Element Collaborative Research and Application for Modern Power System Based on Generative Large Models
Lu Cheng, Qixiu Zhang, Beibei Xu, Zhiwei Huang, Cirun Zhang, Yanan Lyu, Fan Zhang
TL;DR
The paper addresses the challenge of operating modern power systems with high renewable penetration and carbon constraints by proposing Generative Large Models (GLMs) as a unifying, data-driven framework. It outlines how GLMs, leveraging multi-modal data, transformer-based forecasting, reinforcement learning, and causal inference, can optimize generation, grid operation, load, storage, and electricity carbon within a Source-Grid-Load-Storage-Carbon (SGLSC) context. The authors present a cross-domain synthesis of applications, including renewable forecasting, intelligent dispatch, load management, energy storage optimization, and carbon market participation, accompanied by an interaction analysis framework for SGLSC. They also discuss practical challenges and future directions, emphasizing scalability, interpretability, and integration with emerging technologies to enable efficient, resilient, and low-carbon power system operations.
Abstract
The transition to intelligent, low-carbon power systems necessitates advanced optimization strategies for managing renewable energy integration, energy storage, and carbon emissions. Generative Large Models (GLMs) provide a data-driven approach to enhancing forecasting, scheduling, and market operations by processing multi-source data and capturing complex system dynamics. This paper explores the role of GLMs in optimizing load-side management, energy storage utilization, and electricity carbon, with a focus on Smart Wide-area Hybrid Energy Systems with Storage and Carbon (SGLSC). By leveraging spatiotemporal modeling and reinforcement learning, GLMs enable dynamic energy scheduling, improve grid stability, enhance carbon trading strategies, and strengthen resilience against extreme weather events. The proposed framework highlights the transformative potential of GLMs in achieving efficient, adaptive, and low-carbon power system operations.