A hybrid method of optimal data mining and artificial neural network for voltage stability assessment

This paper proposes a new method for voltage stability assessment in power systems. The proposed method is based on a hybrid method of optimal data mining and an artificial neural network (ANN). Voltage stability is of main concern in power system operation and planning. In recent years, the deregulated power market brings about the uncertain events and increases the degree of uncertainty. As a result, power system operators are faced with more complicated power system operation and planning. To understand power system conditions appropriately, they need the feature extraction of power system conditions with an index. In this paper, a hybrid method of optimal data mining and an artificial neural network is proposed to estimate a voltage stability index and extract the rules. Optimal data mining is based on optimizing the regression tree with respect to the splitting value of the splitting conditions. Particle swarm optimization (PSO) of swarm intelligence is used to optimize the combination of splitting values. As ANN, the multi-layer perceptron (MLP) is employed to estimate the voltage stability index at each cluster. The proposed method makes use of data similarity of power system conditions to estimate the voltage stability index so that MLP becomes more accurate estimator. The effectiveness of the proposed method is demonstrated in a sample system.