基于指数平滑法的动态预测机制

A Dynamic Prediction Mechanism Based on Exponential Smoothing Method

对数据进行实时预测,从而制定下阶段的工作计划,对于生活中的工作生产具有很大意义。现阶段存在很多预测模型,其中,指数平滑法在短期预测中应用较为广泛。针对传统预测模型中存在的方法单一,预测模式固定,不能更好地追随数据的变化趋势,具有局限性等问题,提出了一种基于传统模型的动态预测机制。该预测机制在预测过程中选取一定步长的数据,根据数据的实际变化趋势得到可变的平滑系数,此平滑系数能够根据实际数据的变化趋势进行自动调整,使预测模型在预测过程中能追踪到数据的实际走势,具有更高的自适应性。在仿真实验中,以某高校多媒体教室的实际使用频率作为实验数据,对修正后的模型和传统模型进行对比,结果显示,修正后的动态预测机制具有更高的预测精度,且模型简单易用,能够满足实际情况的需要。

Real time prediction for data and developing the work plan in next phase is significant for the production of life. There are many prediction models in the present stage in which the exponential smoothing method is widely used in short-term forecasting. In view of problems of the traditional forecasting model like single way, fixed forecasting mode, not better following the trend of the change of the data and the limitation and so on, a dynamic prediction mechanism based on the traditional model is proposed. It selects a certain step of data in the prediction process and acquires variable smoothing coefficient according to the actual changes of data. The smoothing coeffi- cient can be adjusted automatically according to the change trend of the actual data, making the forecast model can be traced to the actual trend of the data in the prediction process, which has a higher adaptability. In the simulation experiment, the actual usage frequency of the multimedia classroom in a college is used as the experimental data to compare the modified model and the traditional model. The result shows that the modified dynamic prediction mechanism has higher prediction accuracy, and the model is simple and easy to use, and can meet the needs of the actual situation.