Abstract:
The automatic association technology of virtual terminals is a key link in the establishment of virtual circuits in digital substations, which is particularly important for the safe operation of the system. The current manual association of virtual terminals has obvious inefficiency problems, and the limitations of the association method also lead to the problems of low efficiency and low accuracy of virtual terminal identification. This paper utilizes the FastText model to encode the virtual terminal information and maps it to a high-dimensional vector space, which can realize the extraction of the key features in the description file of the virtual terminals in order to improve the efficiency of the subsequent matching work; the longest common subsequence (LCS) algorithm is introduced to compare the encoded virtual terminal information and find the best matching correspondence. The accuracy of the association is ensured by checking and correcting the matching results. The validation of the algorithm on the actual substation dataset shows that the text representation capability of the FastText model and the string matching advantage of the LCS algorithm effectively improve the accuracy and computational efficiency of the automatic association of dummy terminals, which can be a reference for the development of substation digitalization transformation technology.