应用时间序列法对厦门城市日供水量进行预测和误差分析，具有较强的实用价值。
The time sequence method which is quite valuable for use, is applied to the forecast and error analysis of daily water supply amount in Xiamen City.
又以预测误差平方和SSE最小为目标，构造了优选并自动生成最佳平滑参数使平滑模型得以优化的最速下降算法，增强了指数平滑模型对时间序列的适应能力。
Aiming the square sum of error (SSE), we construct the algorithm to iterate and select an optimal parameter for optimizing the new models, which ADAPTS the model to time series more.
与随机时间序列分析方法预测结果比较，神经网络方法可以提高预测精度，预测误差也呈现出随季节发生变化的规律。
Compared to the prediction results of time series method, the prediction results of ANN method are of higher precision. The prediction errors varied with seasons.
与随机时间序列分析方法预测结果比较，神经网络方法可以提高预测精度，预测误差也呈现出随季节发生变化的规律。
Compared to the prediction results of time series method, the prediction results of ANN method are of higher precision. The prediction errors varied with seasons.
应用推荐