Research On Analysis Method Of Power Quality Data Based On Dictionary Learning

With the large number of distributed power,electric vehicles and other non-linear equipment connected to the grid,various power quality disturbances have emerged.More and more power quality data are collected due to the application of smart meters and various intelligent acquisition devices.The generation of massive power quality data not only imposes a large burden on the data transmission and storage of the current power grid,but also complicates the analysis of power quality.In order to reduce the pressure on communication and the problem of storage at the collection end,the application of less data to realize effective analysis of power system is the development trend of smart grid.The processing and analysis of power quality data is critical to the operation of the power system.How to use less data to process it more quickly and accurately becomes a very important problem.For the characteristics of a large number of buses in the power system,this subject introduce distributed compressed sensing and dictionary learning to compress and reconstruct the power quality data.We built a distributed IEEE 14 bus system in PSCAD.This model was used to analyse the correlation and sparsity of power quality data and to obtain the four types of data that should be used in the latter simulation.To make the signal sparser,we constructed a distributed compressed sensing learning dictionary for power quality data.The simulation results show that the performance of the distributed compressed sensing learning dictionary constructed in this paper is more suitable for power quality data.The application of distributed compressed sensing in a power system can ensure the accuracy of reconstructed data when the quantity of data is reduced by 1/3,which greatly reduces the system storage space.Additionally,the speed of reconstruction also increases by 3/5.In addition,the existing power quality disturbance recognition methods generally suffer from slow recognition speed and low recognition accuracy.This subject proposes a simple yet effective recognition method,namely a fast recognition method of power quality disturbance based on unidirectional representation dictionary learning.First,train the training samples of the power quality data to obtain sub-dictionaries corresponding to each category,and propose a one-way constraint so that the directions of the sample's representation coefficients in the dictionary can be distinguished.Then,distinguished the category by calculating the direction and size of the representation coefficient of the test sample.The simulation results show that the method proposed in this paper not only has higher accuracy than the existing recognition methods,but also improves the calculation efficiency.