Fault location in power transmission line based on ISVR

The learning and generation performance of support vector regression (SVR) is determined to parameter selection, so an immune support vector regression (ISVR) for fault location was presented in the paper. The algorithm used immune algorithm to optimize the parameters of SVR in order to globally optimize parameters and reduce the blindness of man-made selection parameters and improve generation performance of SVR. Compared to the standard SVR, the parameters of this algorithm is a more specific theory to guide and accelerate the optimization the process. A large number of simulations show that the algorithm for fault location is of higher precision, stronger adaptability, smaller sample than the SVR and BP method; and it is free from influence of factors such as transition resistance and resistance changes in the side; and it eliminates false root in the conventional one-terminal algorithm and divergence in iteration.