This paper proposes a novel method for load forecast, which integrates wavelet transform and extreme learning machine. In order to capture more internal features, wavelet transform is used to decompose the load series into a set of subcomponents, which are more predictable. Then all the components are separately processed by extreme learning machine. Numerical testing shows that the proposed me...

— A method to extract unique features from measured waveforms of non-linear loads is presented. These features can be used for the identification of loads connected to the grid. The method is based on the currents' physical components (CPC) electric power transport theory combined with the Z-transform (for implementation using digital signal processing (DSP). A set of admittance-based Z-transfo...

The advent of modern rare-earth permanent magnets, which have a magnetic energy product up to an order of magnitude greater than those of Alnico and ferrite magnets, with high remanence and coercive force, has resulted in improved performance of many devices and products. Modern rare-earth magnets, especially neodymium-iron-boron, when combined with technological advances in power and control e...