基于组合预测模型的水质数据预测研究

Prediction for Time Series Data of Water Quality Based on Combination Prediction Model

对时间序列水质预测问题进行研究,提出了基于最优加权法的组合预测模型。综合利用了ARIMA预测模型、人工神经网络模型和指数平滑法对水质数据进行预测,再将它们的结果利用最优加权组合法进行组合,得到组合预测模型结果。将组合预测模型应用到广州长洲水质预测工作中,得到了较好的预测结果。组合预测模型结果的精度高于单一模型结果。组合预测模型能平衡单一模型的偏差,具有更好的适用性和更高的精度。

For the issue of prediction for time series data of water quality, a combination prediction model based on optimal weighting method was presented. The ARIMA model, ANNs model and exponential smoothing model was used to predict the data of water quality. The results of the three methods were combined with the weights from optimal weighting method. Thus the combination prediction results were obtained. The combination prediction model was used to predict the data of water quality of Changzhou in Guangzhou, and good prediction results were ob- tained. The accuracy of the results of the combination forecasting model was higher than that of each single model. The combined forecasting model could balance the deviation of each single model, and had better applicability and higher accuracy.