Sales Forecast Of Solar Water Heater Based On Exponential Smoothing And Neural Network Model

With the country's emphasis on new energy,solar water heater industry is developing rapidly and increasing competition among industry. In order to increase the market share in the fierce competition, enterprises need to accurately predicting China's solar water heater market for the purpose of reasonable arrange the production plan of the enterprise. So as to finding a forecasting model with high prediction accuracy,this paper is based on the trend of sales of solar water heaters in China.Firstly, the exponential smoothing model in the linear trend forecasting model is used to predict the sales volume of the water heater. The secondary exponential smoothing model is selected according to the characteristics of the sales scatter plot. The predicted result is obvious from the actual value and the prediction error is large.Considering the trend of non-linear change of market demand, the most widely used BP neural network model in neural network is used to predict the sales volume of water heater. The most powerful function of BP neural network is its Self-learning,self-organization, self-organizing ability and nonlinear function approximation ability.By comparing the prediction results of the two models, it is found that the BP neural network model is better than the effect of the exponential smoothing model, The model is prone to fit the phenomenon. Therefore, the exponential smoothing neural network model is introduced, and the quadratic exponential smoothing sequence obtained by quadratic exponential smoothing is used as the input value of BP neural network. The BP neural network model is used to predicting the model. The model combines the advantages of the two models. Which improves the accuracy of the forecast and provides a reference for the selection of the forecasting methods of each enterprise.