基于误差校正的二次非线性能源需求预测

Research on nonlinear forecasting model of energy demand based on error correction

能源需求预测是能源规划和政策制定的基础。通过对影响能源需求的因素进行分析,建立了基于影响因素的二次非线性能源需求预测模型,并通过混沌遗传算法(CGA)求解模型的参数得到具体的预测模型。在模型基础之上,进一步研究了模型误差,通过数据变换技术对误差建立GM(1,1)预测模型。通过对二次非线性模型进行误差校正,进一步提高了模型的预测精度。依据1985-2014年的历史数据建立了基于误差校正的二次非线性能源需求预测模型,并预测了在经济新常态的形势下,2020年中国能源的需求量约为48.57亿t标准煤。

Energy demand forecast is the foundation for energy planning and policies formulation. Through the analysis of the factors affecting energy demand,the two time nonlinear energy demand forecasting model were established,and the parameters of the model were obtained by the chaos genetic algorithm（ CGA）. On the basis of the model,the model error was further studied,and the GM（ 1,1） forecasting model was established by the data transformation technology. The accuracy of the model was improved by the error correction of the two nonlinear model. According to the historical data of 1985-2014,the two time nonlinear energy demand forecasting model was established based on the error correction,and the energy demand of China is about 48. 57 tons of standard coal in 2020.