Power distribution network load missing data recovery method based on approximate low-rank matrix completion

Abstract

The invention discloses a power distribution network load missing data recovery method based on approximate low-rank matrix completion. The power distribution network load missing data recovery methodcomprises the following steps: S1, dividing load historical data into two types including a data loss vector and a data integrity vector; S2, forming an original matrix; S3, performing interpolationon the missing elements to form a preliminary recovery matrix; S4, solving a Pearson correlation coefficient matrix for the preliminary recovery matrix, and screening out a vector with high correlation with a data missing vector; s5, performing Pearson correlation coefficient matrix screening on the original vectors containing data loss to obtain vectors; s6, performing recovery completion on missing elements in the recovery matrix by using a singular value threshold shrinkage algorithm; and S7, taking out the next vector with data loss, and repeating the above steps. Compared with a traditional low-rank matrix completion algorithm, the improved algorithm provided by the invention has the advantages that a better overall recovery effect and stability are achieved, and the improved algorithm is more excellently applied to completion of the load missing data of the power distribution network.

Description

technical field [0001] The invention relates to the restoration of missing data of distribution network load, in particular to a method for restoring missing data of distribution network load based on approximate low-rank matrix completion. Background technique [0002] For the power grid company, there are a large amount of user historical power consumption data in the electric energy metering system (TMRS) of the power grid company's metering center, and the hidden information in the data can be mined for load modeling, load forecasting or energy consumption analysis, which can be used for power grid The company brings greater benefits. However, due to the failure of the collection terminal and the unreliability of the transmission channel, the data loss and incompleteness of the distribution network metering data occur from time to time, which brings great inconvenience to the subsequent data mining and analysis. [0003] References To deal with the missing electrical qu...

AI Technical Summary

Problems solved by technology

(3) Learning methods based on input-output relations, such as neural network methods (Yang Mao, Sun Yong, Mu Gang, etc. Completion of missing wind power data based on adaptive neuro-fuzzy reasoning system[J]. Power system automation ,2014,38(19):16-21+46.], [Ding Feng. Research on power load forecasting algorithm under the condition of missing data [D]. Wuhan: Huazhong University of Science and Technology, 2016.], [Wu Jun. Based on neural Research on network power load data cleaning model [D]. Dalian: Dalian University of Technology, 2010.]), but the mathematical mechanism of this type of method is not clear, the interpretability is poor, and the recovery accuracy is closely related to the parameter setting and the training process

Images