小波变换-指数平滑法预测西藏畜牧业产值

Prediction of Animal Husbandry Output of Tibet Autonomous Region Based on Wavelet Transform and Exponential Smoothing Method

运用小波变换和指数平滑法相结合对西藏畜牧业产值进行了预测。首先对原始时间序列进行小波变换,通过信号重构去除原始信号中的噪声信号,然后利用3次指数平滑法对无噪信号进行预测,最后将指数平滑法的预测值与噪声信号相加,还原对原始时间序列的预测。结果显示:小波变换-指数平滑法的平均误差为0.715 6%,比传统3次指数平滑法的平均预测误差1.499 5%减小了52.277 4%,由模型预测得到2023年西藏自治区畜牧业产值为142.702 8亿元。

The combination of wavelet transform and exponential smoothing method was used to predict the output value of animal husbandry in Tibet autonomous region.Firstly,the original time series is subjected to wavelet transform,and noise signals are removed from the original signal through signal reconstruction.Then,the noiseless signal is predicted using the cubic exponential smoothing method.Finally,the predicted value of the expo-nential smoothing method is added to the noise signal to restore the prediction of the original time series.The results show that the average error of the wavelet transform and exponential smoothing method is 0.7156%,which is 52.2774%less than the average prediction error of the traditional cubic ex-ponential smoothing method of 1.4995%.This model predicted that the output value of animal husbandry in 2023 in Tibet autonomous region will be 14.27028 billion yuan.