In application of neural networks based short-term load forecasting model, the main problems are over many training samples, thus resulting long training time and slow convergence speed.

在神经网络负荷预测实际应用中，突出的问题是训练样本大、训练时间长、收敛速度慢。

youdao

Using the information of rice phenology observed in Kai- yuan City and with the method of multiple regression, a long term forecasting model for rice yield was established.

本文以辽宁省开原市水稻物候观测实际资料为例，采用多重回归的方法，建立了影响水稻产量的多时效预报模式。

youdao

Because of the inherent bias in the traditional grey-forecasting model and the fixed choice of its parameter, the forecast precision is relatively low and unsuitable to the long-term forecasting.

由于传统灰色预测模型固有的偏差和模型参数的固定选择，导致预测精度较低，不适应中长期负荷预测。

youdao