计算机与现代化 ›› 2023, Vol. 0 ›› Issue (09): 44-50.doi: 10.3969/j.issn.1006-2475.2023.09.007

• 数据库与数据挖掘 • 上一篇    下一篇

贝叶斯优化梯度提升树的室内日光照度分布预测

  

  1. (山东建筑大学信息与电气工程学院,山东 济南 250101)
  • 出版日期:2023-09-28 发布日期:2023-10-10
  • 作者简介:冀心成(1998—),女,山西原平人,硕士研究生,研究方向:建筑室内光环境建模与优化,E-mail: xincheng_ji@163.com; 汪衍凯(1996—),男,硕士研究生,研究方向:智能环境与网络化控制,E-mail: 825601197@qq.com; 张迎(1997—),男,硕士研究生,研究方向:智能环境与网络化控制,E-mail: 1196162538@qq.com。
  • 基金资助:
    国家自然科学基金资助项目(62073201)

Prediction of Bayesian Optimized Gradient Boosting Tree for Interior Natural Illuminance Distribution

  1. (School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, China)
  • Online:2023-09-28 Published:2023-10-10

摘要: 透过窗户照射进室内的自然光随时间非线性变化,且在空间上的分布呈现不均匀性,导致照度模型预测误差大。在数据量有限的情况下,如何实现自然光下的室内光环境高精度建模是一项巨大的挑战。针对上述问题,提出一种主成分分析与贝叶斯优化梯度提升回归树的室内照度预测算法。该算法首先利用哑变量处理样本数据,通过主成分分析法充分考虑照度数据多特征之间的内在相关性并进行特征重塑;然后利用随机森林确定梯度提升回归树的初始参数,提高其收敛速度和稳定性;最后融合交叉验证和贝叶斯优化算法自适应确定梯度提升回归树的超参数组合,从而进一步提升该模型对室内照度分布的预测性能。实验结果表明,在不同气象、时间条件下,该算法对600个测试样本的照度的R2、MAE和RMSE分别为0.9912、18 lx和40 lx,均优于其他几种算法,且能够显著降低样本偏差值。

关键词: 日光预测模型, 梯度提升回归树, 贝叶斯优化

Abstract:  Large prediction errors in lighting models are caused by the nonlinear temporal variation and non-uniform spatial distribution of the natural light that enters the room through the window. In the case of limited data, how to achieve high-precision modeling of interior light environment under natural light is a huge challenge. To solve these problems, an interior illuminance prediction technique using principal component analysis and Bayesian optimized gradient boosting regression tree is proposed. Firstly, the algorithm performs feature reshaping by principal component analysis, fully takes into account the intrinsic correlation between various illuminance data features and preprocesses the sample data using Dummy variable. Then the random forest is used to determine the initial parameters of GBRT to improve its convergence speed and stability. Finally, cross-validation and Bayesian optimization algorithm are integrated to determine the hyperparameter combination of GBRT, so as to further improve the prediction ability of the model for indoor illumination distribution. The experimental results show that under different weather and time conditions, the R2, MAE and RMSE of 600 test samples with illuminance are 0.9912, 18 lx and 40 lx, respectively, which are superior to other algorithms and can significantly reduce sample deviation value.

Key words: daylighting prediction model, gradient boosting regression tree(GBRT), Bayesian optimization

中图分类号: