A dynamic weight adjustment model for enhancing dispatching efficiency and delay prediction in power grids

This paper proposes a novel delay prediction model tailored for power grid dispatching, leveraging dynamic weight adjustment and multimodal data analysis. The model integrates historical and real-time data through a dynamic weighting mechanism to enhance delay prediction and operational efficiency. A key feature is the use of a random forest algorithm for constructing a delay prediction framework, which improves accuracy by incorporating diverse data sources such as equipment status, environmental factors, and task histories. Additionally, the system provides comprehensive monitoring, efficiency evaluation, and feedback mechanisms to optimize task scheduling and minimize delays. The proposed methodology demonstrates significant improvements in predictive accuracy and operational performance, offering a scalable and intelligent solution for modern power grid management.