论文信息 - The characteristic analysis and forecasting of mid-long term load based on spatial autoregressive model

The characteristic analysis and forecasting of mid-long term load based on spatial autoregressive model

Using spatial autoregressive model, the spatial characteristic between power demand and GDP is analyzed in this paper. And the combination model of forecasting in which the spatial characteristic between power requirement was considered is established. Simulations results show the distinct spatial dependence between power requirement and GDP, and the dependence between power requirementv and GDP is very strongly in space. The forecasting results show the error of the combination model of forecasting which was established in this paper is very small. Besides the combination model proposed in this paper is a effective forecasting method because of its strong adaptability.

[1] Chen Hong-min. Spatial Autoregression Model on the Income of Residents and City Economy , 2005 .

[2] R. Pace,et al. Sparse spatial autoregressions , 1997 .

[3] Xu Guang. Study on the improved method for mid-and long-term load forecasting of power system , 2002 .

[4] L. Anselin. Spatial Econometrics: Methods and Models , 1988 .

[5] Martin T. Hagan,et al. Neural network design , 1995 .

[6] M. K. Soni,et al. Artificial Neural Network-Based Peak Load Forecasting Using Conjugate Gradient Methods , 2002, IEEE Power Engineering Review.

[7] P. Moran,et al. A test for the serial independence of residuals. , 1950, Biometrika.