For the monthly load with double trends of increasing and fluctuating, the integrated optimum gray neural network model of monthly load forecasting is proposed in the paper for the first time. In the model, we regard vertical historical data as the primitive array to forecast increasing trend by the gray model, and regard horizontal historical data as the primitive array to forecast fluctuating trend by the . Based on that, the concept of the optimum credibility is introduced, and the integrated optimum model is built in the paper. In the model, the double trends of monthly load are considered at the same time and the two models’ modeling characters are given attention. So the integrated model is superior to the model of single trend forecasting. An application case of the power load forecasting is given. Through the analysis to the monthly supplying electric capacity in LiaoNing power system, the corresponding integrated optimum gray neural network model is built. It is compared with other algorithms. The calculation results prove that this method raises accuracy of the monthly load forecasting greatly. For the weekly and seasonal load with the same double trends, the method has same suitability to them.
Integrated Optimum Gray Neural Network Model of Monthly Power Load Forecasting Based on Optimum Credibility
- Views Icon Views
- Share Icon Share
- Search Site
Niu, D, Lu, J, & Li, Y. "Integrated Optimum Gray Neural Network Model of Monthly Power Load Forecasting Based on Optimum Credibility." Proceedings of the ASME 2005 Power Conference. ASME 2005 Power Conference. Chicago, Illinois, USA. April 5–7, 2005. pp. 397-400. ASME. https://doi.org/10.1115/PWR2005-50313
Download citation file: