Evaluation and Planning Method for Renewable Energy Carrying Capacity of Novel Power Systems Based on Deep Spatiotemporal Feature Learning and Inter-Provincial Mutual Assistance Synergy
Abstract
INTRODUCTION: With the in-depth advancement of novel power system construction, the randomness and volatility brought by high-proportion renewable energy grid connections pose severe challenges to long-term planning. Traditional methods struggle with extracting complex non-linear features from massive data and face limited flexible resources within a single region.
Objectives
This paper aims to propose a dynamic evaluation and collaborative planning method driven by deep spatiotemporal feature learning and inter-provincial power mutual assistance to accurately assess and expand the overall accommodation space.
Methods
Techniques derived from deep learning and graph neural networks are employed to conduct this research. Based on multi-source heterogeneous power grid operation measurement data, a spatial-temporal graph convolutional network (STGCN) model is constructed. Unlike traditional noise reduction methods, this model actively observes and compensates for the complex nonlinear coupling terms among source-grid-load. Subsequently, a two-stage collaborative planning model is established, utilizing the dynamic carrying boundaries output by the STGCN for grid expansion and operation simulation.
Results
The main results obtained in this paper are the following. Simulations on a certain provincial grid in China demonstrate that the STGCN model significantly improves computational efficiency and accuracy in extracting spatial-temporal features. Furthermore, the inter-provincial mutual assistance mechanism effectively optimizes resource allocation under the boundaries provided by the deep learning model.
Conclusion
These are the conclusions of this paper: The integration of deep spatiotemporal learning with cross-regional mechanisms provides a highly accurate, data-driven computational framework for renewable energy carrying capacity evaluation and grid planning.
