Search

With the rapid development of the intelligent grid technology and the arrival of the informationalized big data era, the application of computing method to power grid specialty will be a key step for the value of power grid data. Grid data record is not standard, the confusion caused by a device with multiple recording, professional equipment for power grid name recognition and use of data and algorithm based on identification service work will gradually replace artificial recognition, this paper presents a ENMTM algorithm with the grid raw data, which can identify accurately the same equipment with different names. The equipment name record is an important data of power grid business scenario, however, the same device is easy to describe in different situations or staff’s records, which causes data redundancy and equipment confusion caused by error identification of equipment name. The name recognition is to segment the device name string into a structured element unit which can be calculated by the computer, so as to realize the identification of multiple words with one meaning and devices with different names. In this paper, we study the recognition algorithm of recognition, the establishment of professional word library, segmentation and calculation of similarity recognition. The results show that the ENMFM result error rate is only 3.13%, on the basis of segmentation results and the confusion matrix of device name similarity can be seen that the positive samples has good prediction. In addition, in the experiment, the Top N items of higher similarity were given, which provided the staff with professional judgment to ensure the rigor of work. The calculation method to solve the name recognition of power equipment can greatly reduce the human work of identifying equipment, improve the work efficiency of power professional business scenarios, and lay a solid foundation for the unified data environment of intelligent grid.

With the development of the smart grid technology and the advent of the big data, it is highly desired to develop efficient computational methods for mining the values behind of huge volumes of data on the grid. However non-unified naming of the electronic devices from the de-centralized and heterogeneous power systems makes the procedure a hard problem. In the present work, we proposed a Ternary Search Trie based algorithm for recognizing the devices from the huge volumes of transaction data in the power grid. On the base of well-defined professional vocabulary of electronic devices, the algorithm scans and segments records having names of devices using the Ternary Search Trie method. An integrative scoring schema combing semantic and word order similarity is designed to evaluate the segments against the target device names. Experimental results indicate that the proposed method achieves only 3.13% error in parsing stage, and higher recognition rate. Moreover, the algorithm lists top-n matches for professional judgments to make the work more useful and rigorous.