Power grid planning lean analysis method based on big data

Abstract

The invention discloses a power grid planning lean analysis method based on big data.step 1, constructing a power grid planning lean analysis platform; step 2, carrying out dynamic load distribution and prediction by utilizing a power grid planning lean analysis platform; 3, performing space-time visualization on the power grid supply capability; and step 4, automatically diagnosing, evaluating and analyzing power grid problems. According to the method, physical service of a power supply company is taken as an entry point, on the basis of geographic position information and on the basis of data fusion and penetration, regional power grid load distribution and power grid supply capacity are displayed dynamically in a multi-dimensional mode through a data visualization technology, and planners are assisted in finding load distribution rules and power grid weak points quickly. And constructing a load prediction model based on load characteristic analysis by using a big data analysis mining method, and supporting power grid project and operation mode arrangement.

Description

technical field [0001] The invention relates to a lean analysis method for power grid planning based on big data, and belongs to the technical field of power grid planning. Background technique [0002] The distribution network is an important part of the power system and an important infrastructure on which the development of the national economy depends. It plays a vital role in the safe operation of the power system and the improvement of the economic benefits of enterprises. The construction and management level of the distribution network directly affects the safe operation, economic and social benefits of the power grid. Due to the imperfection of the system and technical limitations, the distribution network-related equipment assets have more or less not matched the actual electricity demand. [0003] Grid planning is the primary link in the development and construction of smart grids. It plays an important role in predicting power demand development, rationally plan...

AI Technical Summary

Problems solved by technology

In addition, the traditional load forecasting work is relatively extensive. It is generally carried out according to the area of ​​the plot and the corresponding load density. The consideration factors are relatively single, and the calibration and correction are rarely carried out. It does not meet the requirements of refined load forecasting. It is urgent to combine the development needs of the unit system distribution network. Explore a refined load forecasting method

[0005] The method of using historical load data and related factors for load forecasting is gradually emerging. Machine learning algorithms and big data computing platforms have become important means to solve practical problems in power systems. However, the current methods are all effective in specific environments and constraints. However, there are the following problems: 1) The values ​​of parameters such as load density, demand coefficient, and growth rate tend to be uniform, without considering the differences between regions and users; 2) The degree of refinement is not enough, and generally only specific load values ​​are predicted. Rarely carry out load distribution forecasting; 3) Failure to fully mine the laws of the massive data of lines, stations, and users

Images