Emission-Forecasting-Based Spatial-Temporal Carbon Response: A Multi-Agent Attention-Enhanced Deep Learning Framework

2026-07-29

AI Summary

This study addresses the limitations of traditional node-specific carbon intensity estimation, which relies on ex post accounting and is ill-suited for real-time low-carbon dispatch under high renewable energy variability. To overcome this, the authors propose a day-ahead spatiotemporal carbon response framework that integrates a novel two-stage attention mechanism with a large language model–driven multi-agent coordination system to achieve high-accuracy forecasting of nodal carbon intensity. The framework further optimizes dispatch strategies by incorporating geographically dispatchable loads, including mobile energy storage and distributed data centers. Validated on the IEEE 33-node test system, the approach reduces carbon scheduling latency by one hour and cuts system-wide emissions by over 30%, significantly enhancing the power grid’s proactive, low-latency decarbonization capability.

Abstract

As a major contributor to carbon emissions, the decarbonization of power systems has garnered significant societal attention. Nodal carbon intensity (NCI), a critical factor in carbon-oriented demand response, has traditionally been determined through ex-post calculations. However, this ex-post approach introduces latency in low-carbon dispatch. To address this, this paper presents a proactive ex-ante spatial-temporal carbon response framework. At its core, we develop a novel deep learning-based hierarchical design, enhanced by a dual-stage attention mechanism and a large language model (LLM)-based multi-agent cooperation system, to accurately forecast day-ahead NCI. This design effectively mitigates the impact of renewable energy uncertainty and enhances predictive resilience. On the demand side, the framework proposes a spatial-temporal carbon scheduling model that integrates geographically dispatchable loads (GDLs), including mobile energy storage systems (MESSs) and distributed data centers (DDCs). Leveraging high-accuracy day-ahead NCI predictions, the framework can effectively reduce system emissions by quickly responding to carbon intensity fluctuations. The proposed framework is tested on the modified IEEE 33-bus system. According to the simulation results, the impacts of proposed framework on dispatching latency and emission outcomes are analyzed. The results demonstrate that under a one-hour reduction in carbon scheduling latency, the proposed model and methodology can achieve over 30% emission reduction. This research breaks through the limitations of passive carbon accounting, advancing toward proactive carbon management. It offers an intelligent solution that accelerates the transition to cleaner power systems while directly supporting sustainable production goals.

Problem

• nodal carbon intensity
• carbon emission forecasting
• low-carbon dispatch
• spatial-temporal carbon response
• decarbonization of power systems

Innovation

• nodal carbon intensity forecasting
• multi-agent attention mechanism
• large language model (LLM)
• spatial-temporal carbon scheduling
• proactive carbon management