INVESTIGATION INTO AN ARTIFICIAL NEURAL-NETWORK-BASED ONLINE CURRENT CONTROLLER FOR AN HVDC TRANSMISSION LINK

An artificial neural network (ANN) based current controller for a HVDC transmission link is described in this paper, Different ANN architect ures and activation functions (AFs) are investigated for this ANN cont roller. Small (set current change) and large (de-line fault) signal pe rturbations are applied to optimize the learning parameters for the co ntroller. Performance evaluation of the ANN controller under noise con ditions is studied. A comparison between a traditional PI and the prop osed ANN controller is made for various system contingencies and it is shown that the latter has many attractive features.