Design technology for virtual circuit automatic generation in intelligent substations based on substation configuration description

Abstract

The intelligent substation project has a high workload, high error rate, and low efficiency in SCD virtual terminal connection. A technique for automatically generating virtual circuits has been proposed to improve the efficiency of SCD virtual terminal connections. Using the virtual circuit design template, this article first uses the K-nearest neighbor learning method to automatically match virtual terminals. On the basis of training data, a weight vector optimization model will be constructed, with weight vectors as optimization parameters and appropriate objective functions set. By using an improved simulated annealing algorithm to solve the weight optimization model, the optimal solution of the distance weight vector is obtained. The verification through examples shows that compared to existing technologies, this method obtains more accurate virtual terminal connection results and higher matching efficiency.