On-line Voltage Stability Assessment by a New Neural Network

Voltage stability problems have been one of the major concerns for electric utilities as a result of system heavy loading. This paper reports on an investigation on the application of a new neural network (NN) in on-line voltage stability assessment. The proposed NN is a functional link net with an efficient functional expansion model for learning. This NN is used for estimation of voltage stability margins (VSM). A comparison between the proposed NN and a multi-layer perceptron (MLP) with standard error back-propagation learning (EBPL) is presented, which indicates efficiency of this NN. Based on the energy method, a direct mapping relation between system loading onditions and the VSMs is set up via the designed NN. A systematic method for selecting the NN's input variables was developed using sensitivity analysis. The proposed method has been tested on the WEE test systems and a portion of the Iran's power system network. Obtained results confirm the validity of thedeveloped approach.

کلیدواژه ها:

Voltage Stability ، Neural Network ، Energy Method