Research on Greenhouse Energy Consumption Simulation and Yield Prediction Model Based on Time Series Analysis

In order to propose a method of predicting fruit yield and output value at room temperature based on seasonal time series, which provides an important basis for vegetable industry to make a reasonable plan, the stationarity of fruit yield sequence was tested using ARIMA model test method. Compared with the traditional BP model and WNN model, the seasonal time series model can not only predict the number of iterations of the model, but also analyze and predict the fruit yield faster, with higher prediction accuracy. The experimental results show that the seasonal series model can predict the cycle and trend of room temperature on fruit yield and output value well, and can improve the prediction accuracy to a large extent. This can provide a basis for fruit production to make yield plans (the average relative error of fruit yield prediction from 2019 to 2021 of the time series analysis model is 0.56%, indicating a high accuracy of the model).