Short, Medium and Long Term Load Forecasting Model and Virtual Load

6766 Words Oct 5th, 2012 28 Pages
Electrical Power and Energy Systems 32 (2010) 743–750

Contents lists available at ScienceDirect

Electrical Power and Energy Systems journal homepage: www.elsevier.com/locate/ijepes

Short, medium and long term load forecasting model and virtual load forecaster based on radial basis function neural networks
Changhao Xia a,b,*, Jian Wang b,*, Karen McMenemy c a College of Electrical Engineering and Information Technology, China Three Gorges University, Yichang Hubei 443002, China School of Mechanical and Aerospace Engineering, Queen’s University, Belfast, Northern Ireland BT9 5AH, UK c School of Electronics, Electrical Engineering and Computer Science, Queen’s University, Belfast, Northern Ireland BT9 5AH, UK b a r t i c l
…show more content…
Traditional econometric approaches establish functional relationships between weather variables and current load demand for the forecasting function, often assuming a linear relationship. However, as Park et al. (1991) indicate, the econometric approach may not give sufficiently accurate results because of nonlinear and non-stationary relationships between the load data and weather variables. Therefore, an adaptable technique is needed [5]. An ANN can model any complicated nonlinear relationship and since STLF is a nonlinear problem the ANN forecasting method, which combines nonlinear and time series forecasting methods, is widely applied to STLF. However, it is rarely used in MLTLF since the variations within short-term load forecasting can be considered as a stable random process. The variations within medium to long term load forecasting are not usually random and can be attributed to important factors such as governance within a given country. Therefore, accurate MLTLF is a much more difficult problem because it is difficult to describe the forecasting pattern with obvious formula because of the different and various factors which

744

C. Xia et al. / Electrical Power and Energy Systems 32 (2010) 743–750

Nomenclature n a p w1 b1 w2 input of Gauss function output of Gauss function input vector of neural network weight vector between the input and the hidden layer bias of

Related Documents