A Pragmatic Method to Determine Transient Stability Constrained with Interface Real Power Flow Limits via Power System Scenario Similarity

In practical power systems,operators generally keep interface flowing under the transient stability constrained with interface real power flow limits(TS-IRPFL)to guarantee transient stability of the system.Many methods of computing TS-IRPFL have been proposed.However,in practice,the method widely used to determine TS-IRPFL is based on selection and analysis of typical scenarios as well as scenario matching.First,typical scenarios are selected and analyzed to obtain accurate limits,then the scenario to be analyzed is matched with a certain typical scenario,whose limit is adopted as the forecast limit.In this paper,following the steps described above,a pragmatic method to determine TS-IRPFL is proposed.The proposed method utilizes data-driven tools to improve the steps of scenario selection and matching.First of all,we formulate a clear model of power system scenario similarity.Based on the similarity model,we develop a typical scenario selector by clustering and a scenario matcher by nearest neighbor algorithm.The proposed method is pragmatic because it does not change the existing procedure.Moreover,it is much more reasonable than the traditional method.Test results verify the validity of the method.

Recognition of Similar Weather Scenarios in Terminal Area Based on Contrastive Learning

In order to improve the recognition accuracy of similar weather scenarios(SWSs)in terminal area,a recognition model for SWS based on contrastive learning(SWS-CL)is proposed.Firstly,a data augmentation method is designed to improve the number and quality of weather scenarios samples according to the characteristics of convective weather images.Secondly,in the pre-trained recognition model of SWS-CL,a loss function is formulated to minimize the distance between the anchor and positive samples,and maximize the distance between the anchor and the negative samples in the latent space.Finally,the pre-trained SWS-CL model is fine-tuned with labeled samples to improve the recognition accuracy of SWS.The comparative experiments on the weather images of Guangzhou terminal area show that the proposed data augmentation method can effectively improve the quality of weather image dataset,and the proposed SWS-CL model can achieve satisfactory recognition accuracy.It is also verified that the fine-tuned SWS-CL model has obvious advantages in datasets with sparse labels.