A Hybrid Method for Fault Location in HVDC-Connected Wind Power Plants Using Optimized RBF Neural Network and Efficient Features

High voltage direct current (HVDC) transmission system is going to become the most economical and efficient way of power delivery for large and remote offshore wind power plants. Designing an accurate and fast fault location method in HVDC-connected wind power plants is necessary to maintain uninterrupted power delivery and protect sensitive devices of these systems. This paper proposes a hybrid method for fault location on voltage source converter HVDC (VSC-HVDC) transmission line which connects the wind power plant to the main AC grids using one terminal current data. The proposed method includes three main modules: the feature extraction module, the estimator module and learning algorithm module. In the feature extraction module, frequency feature are extracted using wavelet transform. In the estimator module, radial basis function neural network (RBFNN) is used. In RBFNN, learning algorithm has a high impact on the network performance. Therefore, a new learning algorithm based on the bee s algorithm (BA) has been used in the learning module. The proposed method is tested on 250 km VSC-HVDC transmission line. The obtained results have shown that combination of proposed feurears and Bee-RBF has accuracy in fault location in HVDC systems