Transverse time axis clustering method in generalized load modeling on basis of time periods

Abstract

The invention discloses a transverse time axis clustering method in generalized load modeling on the basis of time periods. According to the method, root bus data formed by wind power and loads of the whole year are obtained; the data are processed, all the processed data are connected end to end, the data in rows form the transverse continuous data which are divided into M sections according to transverse time units THN, and all the data are transversely clustered; based on the transverse cluster result, a sample data source to be analyzed is divided into q transverse classes, and each class is represented by the respective clustering center; feature vectors are intersected and matched. The classes to which samples belong are judged through intersecting and matching of the feature vectors, generalized load modeling is utilized for setting up an accurate model and testing the effectiveness of the clustering strategy, and the simulation result shows that generalized load modeling carried out after clustering analysis makes the model practical on the basis of meeting the requirement for accuracy, and is beneficial for improving the simulation accuracy and the simulation effectiveness of an electrical power system.

Description

technical field [0001] The invention relates to a time-based horizontal time axis clustering method in generalized load modeling. Background technique [0002] As an intermittent energy source, wind power has a great impact on the security and stability of the power system due to its randomness and volatility, and also brings great challenges to generalized load modeling. With the increase of wind power capacity, generalized load nodes sometimes show power supply characteristics and sometimes load characteristics. Different characteristics correspond to different models, which will have qualitative changes to the power system simulation calculation. Therefore, the generalized load modeling considering wind power uncertainty is analyzed for Power system analysis is very important. [0003] In measurement-based load modeling, time-varying is the biggest obstacle to its application. However, the uncertainty caused by the access of wind power increases the difficulty of the ori...

AI Technical Summary

Problems solved by technology

The above-mentioned literature can solve the time-varying problem well through a reasonable classification and synthesis method, but the clustering method used in some literature needs to artificially set the number of clusters, cluster centers, etc., which cannot exclude subjective factors, and is not universal in the new situation. Applicability; In addition, due to the small sample size of the analysis object, the clustering strategy is relatively simple. It is only necessary to determine the appropriate clustering method and feature vector for clustering to be divided into categories with clear boundaries. In the face of the whole year (or longer time ) for large sample data of wind power and load, the simple clustering strategy cannot reasonably classify all the sample data; in addition, limited to traditional application scenarios, the above literature does not consider the impact of time period continuity on the model, due to human activities and natural laws Both are long-term periodic gradual changes, so considering the continuity of training samples in time will make the model more accurate and complete

Therefore, the literature [11] considers the continuous time information, but this method takes the day as the minimum analysis interval, and does not consider the similarity of time period and the difference between days. For generalized load modeling, the scale is too large to give Reasonable Models for Determining Time Periods

Images