一种区域可再生能源的适宜性布局评价方法及评价系统
By employing techniques such as ARIMA models, Kriging interpolation, CatBoost, and XGBoost algorithms, the problems of weak variable explanatory power and insufficient spatial accuracy in renewable energy consumption assessment have been solved. Nonlinear modeling and multi-energy complementarity analysis have been achieved, improving the accuracy and interpretability of the assessment and supporting policy and engineering applications.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XI AN JIAOTONG UNIV
- Filing Date
- 2025-11-05
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for assessing renewable energy consumption suffer from problems such as weak variable explanatory power, lack of marginal effects and threshold identification, insufficient spatial accuracy, and poor model interpretability, making it difficult to achieve refined planning.
The ARIMA model is used to impute missing values in time series, Kriging interpolation and kernel density estimation are used to obtain spatial distribution, a nonlinear correlation model is established by combining CatBoost and XGBoost algorithms, the marginal effect curve is identified by the SHAP model, and spatial clustering is performed by the improved Getis-Ord Gi* and local Moran's I algorithms to achieve suitability mapping.
It achieves nonlinear and threshold modeling, significantly improving spatial accuracy and applicability. It can identify the optimal threshold range of key variables, support policy evaluation and regional energy layout optimization, provide multi-energy complementarity analysis, and provide a basis for the coupling of multi-energy systems.
Smart Images
Figure CN121543869B_ABST