| 引用本文: | 宋小会,郭志忠,郭华平,等.一种基于森林模型的光伏发电功率预测方法研究[J].电力系统保护与控制,2015,43(2):13-18.[点击复制] |
| SONG Xiaohui,GUO Zhizhong,GUO Huaping,et al.A new forecasting model based on forest for photovoltaic power generation[J].Power System Protection and Control,2015,43(2):13-18[点击复制] |
|
| 摘要: |
| 为了有效预测光伏发电站发电功率，提高预测精度，给出一种基于森林预测模型FPPG (Forest for Photovoltaic Power Generation)。FPPG是一个由多个回归树组成的集合预测模型。在学习阶段，FPPG首先随机抽样方法构建有差异的训练数据集，进而在不同的训练集上构建有差异的回归树。在预测阶段，首先，FPPG将输入信息沿着每棵树的某条路径分派到相应的叶结点，使用这些叶结点预测发电量，然后，平均这些预测结果得到FPPG对发电厂系统发电量的预测。在实测运行数据集上的实验结果表明，较之于神经网络，FPPG同时表现出更高的预测准确性，从而提高了光伏发电功率预测精度。 |
| 关键词: 回归树 森林预测模型 发电功率预测 神经网络 光伏发电 |
| DOI：10.7667/j.issn.1674-3415.2015.02.003 |
| 投稿时间：2014-04-11修订日期：2014-05-30 |
| 基金项目:河南科技厅研究项目(14A520016, 14B520045, 12A520035) |
|
| A new forecasting model based on forest for photovoltaic power generation |
| SONG Xiaohui,GUO Zhizhong,GUO Huaping,WU Shuanghui,WANG Zhaoqing,WU Changan |
| (Department of Electrical Engineering, Harbin Institute of Technology, Harbin 150001, China;Xinyang Normal University, Xinyang 464000, China;XJ Electric Co., Ltd., Xuchang 461000, China) |
| Abstract: |
| A novel model called forest for photovoltaic power generation (FPPG) is proposed to effectively predict the generation power of photovoltaic power generation. FPPG is an assembly predict model composed by multi regression tree. In learning stage, FPPG first obtains training sets with diversity using random sample technique, and then, constructs regression trees with diversity. For prediction stage, the leaf that the has been assigned input information along the path of each tree predicts the power generation. Then FPPG obtains the corresponding prediction by averaging the predictions of the corresponding leaves. Experimental results show that, compared with neural network, FPPG performs better generated power forecasting. |
| Key words: regression tree FPPG generated power forecasting neural network photovoltaic power generation |
