关键词: 天然气, 年负荷量, 灰色模型, 改进, 预测

Abstract: 　Three improved grey forecasting models are constructed to improve the accuracy of traditional forecasting methods. This paper took natural gas load of Beijing from 2007 to 2015 as raw data for modeling, and tested the predicting results of 2016.The traditional Grey Model and the three kind s of improved Grey Model were established to predict respectively，and the optimal model with best precision was chosen to combine with metabolism model which abandons the old data, constantly supplies new data, and repeats modeling. The optimal improved Grey Model was established to predict the annual gas load of Beijing from 2017 to 2020.The results show that the combined model can reduce the interference of the original data to the prediction system, the prediction accuracy meets the actual requirements, and the accuracy is much higher than the traditional gray model. It can truly reflect the development trend of annual natural gas load, and the prediction results are reliable and practical. It can provide reference for natural gas deployment and optimization of the pipeline network.

Key words: Gas, Annual load, Grey Model, Improvement, Prediction