基于协整理论和误差修正模型的电网投资需求预测研究

Research on Prediction to Investment Demand of Power Grid Based on Co-integration Theory and Error Correction Model

电网投资需求预测对于合理安排电网建设资金的投入、减少资金成本等具有十分重要的意义,提出了一种基于协整理论和误差修正模型的电网投资需求预测模型。以某地区1981—2009年的统计数据为基础,通过ADF单位根检验、Johansen协整检验,逐步筛选变量,发现了电网投资与最大用电负荷之间具有长期均衡关系,并建立了2者的长期均衡模型。在长期均衡模型的基础上,通过误差修正模型构建了2者的短期调节关系模型,以提高短期预测精度。算例分析说明,上述长期均衡模型和短期调节关系模型具有较高的预测精度。

It is very important to predict the investment demand of power grid for reasonable input of the funds for power grid construction and reduce the fund cost. For this reason, a co-integration theory and error correction model （ECM） based model to predict the investment demand of power grid is proposed. Based on statistical data of a certain region from 1981 to 2009, the variables are screened in steps by advanced Dicker-Fuller unit root test and Johansen co-integration test, and itis discovered that there is a long-term equilibrium relationship between investment for power grid and peak load of power grid, and then a long-term equilibrium model for them is established and according to the long-term equilibrium model a short-term regulation relationship model for them is constructed to improve the accuracy of short-term prediction. Calculation example shows that the proposed long-term model and short-term model can offer prediction results with higher accuracy.