Novel power distribution network operation state portrait analysis method

Abstract

The invention relates to a novel power distribution network operation state portrait analysis method. The method comprises the steps that the first part is to obtain basic data from a marketing, distribution and dispatching related production and management system; the second part is to clean the acquired data; and the third part is to take the cleaned normal data as a characteristic quantity, construct an index system by referring to the urban power distribution network operation level and the power supply capability evaluation guide rule, perform evaluation by using an analytic hierarchy process, and perform adjustment of an evaluation result by combining historical experience data and actual production requirements, and the fourth part is to construct a neural network model, and carryout correlation analysis on indexes of all levels, and the fifth part is to establishing and analyzing a portrait. According to the method, the neural network training model is constructed by adoptingthe restricted Boltzmann machine (RBM), and the traditional index weight definition is abandoned and the portrait of the distribution network operation is constructed through the self-learning of themachine, so that the evaluation result is more objective and accurate.

Description

technical field [0001] The invention relates to the fields of distribution network, big data and artificial intelligence, in particular to a novel method for analyzing the image of distribution network operation status. Background technique [0002] With the continuous expansion of the distribution network scale in recent years, the continuous deepening of the construction of intelligent distribution network and the deep integration of the field of power distribution, the data collected by the terminal has increased sharply, and the data volume of power distribution has grown from TB level to PB level. The power distribution business is gradually developing in the direction of intelligence and leanness, and it is necessary to further improve the cross-business and cross-platform data analysis and processing capabilities. Portrait is a fast and accurate analysis method, which has been widely used in finance, telecommunications and other fields. At present, the portraits of t...

AI Technical Summary

Problems solved by technology

[0003] The existing distribution network operation evaluation system mostly uses graded index evaluation, and the analytic hierarchy process, expert method, entropy weight method or a combination of the above methods are used in the correlation analysis between indicators, and the evaluation results are relatively subjective and accurate. The shortcomings of low precision, and the lack of comparison between different distribution networks and the mining of weak points in operation

Images