Conventional MCP (Measure Correlate Predict) techniques often employ linear regression to model the relationship between wind speeds at two sites and use this model to predict the long term wind regime at one site from the long term wind regime at the other. In considering sites whose wind speeds are Weibull distributed it can be demonstrated analytically that linear relationships do not, in fact, hold. The general relationship is found to be of the form y = mxα + c where α is the ratio of the shape parameters of the Weibull distributions. Linearity prevails only when the shape parameters are equal. This is seen to have implications for MCP analysis.
展开▼
