Power macro-modelling using an iterative LS-SVM method

We propose a new method for power macromodelling of functional units for high-level power estimation based on Least-Squares Support Vector Machines (LS-SVM). Our method improves the already good modelling capabilities of the basic LS-SVM method in two ways. First, a modified norm is used that is able to take into account the weight of each input for global power consumption in the computation of the kernels. Second, an iterative method is proposed where new data-points are selectively added as support-vectors to increase the generalization of the model. The macromodels obtained provide not only excellent accuracy on average (close to 1% error), but more importantly, thanks to our proposed modified kernels, we were able to reduce the maximum error to values close to 10%.