利索-全球专利检索

  1. 登录
  2. 注册
发明公开
CN103942618A 采用复合数据源的基于自学习多项式核函数支持向量机的光伏发电功率短期预测方法 无效 - 驳回

采用复合数据源的基于自学习多项式核函数支持向量机的光伏发电功率短期预测方法
摘要：
本发明公开了采用复合数据源的基于自学习多项式核函数支持向量机的光伏发电功率短期预测方法，主要包括：采用基于自学习多项式核函数支持向量机的复合数据源，对待测光伏发电功率预测模型进行训练；基于待测光伏发电功率预测模型的训练结果，对待测光伏发电功率进行短期预测。本发明所述采用复合数据源的基于自学习多项式核函数支持向量机的光伏发电功率短期预测方法，可以克服现有技术中光伏发电功率短期预测精度低等缺陷，以实现高精度的光伏发电功率短期预测的优点。
摘要（英）：

The invention discloses a photovoltaic power generation power short-term prediction method using a composite data source based on a self-learning polynomial kernel function support vector machine. The method mainly comprises the steps that the composite data source based on the self-learning polynomial kernel function support vector machine is adopted to train a prediction model of photovoltaic power generation power to be detected; short-term prediction is performed on the photovoltaic power generation power to be detected on the basis of training result of the prediction model of the photovoltaic power generation power to be detected. The photovoltaic power generation power short-term prediction method using the composite data source based on the self-learning polynomial kernel function support vector machine has the advantages of being capable of overcoming the defect that short-term prediction accuracy of photovoltaic power generation power is low in the prior art, and achieving high-accuracy short-term prediction of the photovoltaic power generation power.

0/0