An RT-KDE Approach for Constructing Robust Renewable Energy Capacity Factor Databases

DOI

10.2991/978-94-6463-902-5_43How to use a DOI?

Keywords

Capacity factor database construction; Regression tree; Gaussian Kernel Density Estimation; Power system dispatch

Abstract

With the increasing penetration of renewable energy, accurately assessing power output is crucial for grid stability and economic operation. Traditional forecasting models, however, are susceptible to outliers and often fail to reflect the true central tendency of power output. This paper presents a novel method to construct a high-precision capacity factor database using Regression Trees (RT) and Gaussian Kernel Density Estimation (KDE). By training RT models for discrete time intervals, the method captures complex non-linear relationships between meteorological conditions and capacity factors. Its core innovation is using the KDE peak value to determine the output for each tree's leaf node, which enhances the forecast’s representativeness and robustness compared to the traditional arithmetic mean. A case study with real-world photovoltaic data validates the approach. Results confirm that the proposed RT-KDE model significantly improves forecasting accuracy and stability, reducing the MAE by 18.05% and the RMSE by 18.92% compared to the traditional regression tree baseline. The resulting database offers reliable data support for power system operations, planning, and market activities, advancing the data asset management of renewable energy.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Qiaoyu Zhang
AU  - Guobing Wu
AU  - Kai Dong
AU  - Qiuna Ca
AU  - Zhongfei Chen
PY  - 2025
DA  - 2025/12/16
TI  - An RT-KDE Approach for Constructing Robust Renewable Energy Capacity Factor Databases
BT  - Proceedings of the 2025 7th International Conference on Civil Engineering, Environment Resources and Energy Materials (CCESEM 2025)
PB  - Atlantis Press
SP  - 431
EP  - 441
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-902-5_43
DO  - 10.2991/978-94-6463-902-5_43
ID  - Zhang2025
ER  -