论文部分内容阅读
为准确预测太阳辐射量,提出一种基于变分模态分解和粒子群优化算法的最小二乘支持向量机组合预测模型。针对太阳辐射量序列具有不稳定性的特点,首先利用变分模态分解将历史太阳辐射量数据分解成一系列相对稳定的分量序列,再应用粒子群优化最小二乘支持向量机参数,以预测各分量序列,将各分量太阳辐射量预测值集成,从而得到最终太阳辐射量预测值。实例分析和对比研究表明,该模型预测太阳辐射量有效可行,具有较高的预测精度。研究成果可为太阳辐射量预测提供参考。
In order to accurately predict the amount of solar radiation, a least squares support vector machine (SVM) combined forecasting model based on variational mode decomposition and particle swarm optimization is proposed. Aiming at the instability of solar radiation sequence, firstly, the data of historical solar radiation are decomposed into a series of relatively stable component sequences by using the variational mode decomposition, and then the parameters of the least squares support vector machine (SVM) Component sequence, the components of the solar radiation amount of the integrated forecast, resulting in the final amount of solar radiation forecast. Case studies and comparative studies show that this model is effective and predictable for solar radiation and has high prediction accuracy. The research results can provide a reference for the prediction of solar radiation.