Distributed power supply optimal configuration method and system

Abstract

The invention discloses a distributed power supply optimal configuration method and system. The method comprises the steps: carrying out the modeling of the uncertainty of the output of a distributedpower supply based on a conditional depth convolution generative adversarial network model, and adding month label information into the model to generate a wind and light output scene; determining anupper limit and a lower limit of wind-solar output corresponding to the month label information based on a Gaussian mixture model, and generating a distributed power supply limit scene; establishing adistributed power supply double-layer optimal configuration model according to the distributed power supply limit scene, and solving the model; and verifying and analyzing the distributed power supply double-layer optimal configuration model based on an IEEE33 node system. In the embodiment of the invention, the access capacity of the distributed power supply is improved, the total social cost iseffectively reduced, and the economical efficiency of power distribution network operation is improved.

Description

technical field [0001] The present invention relates to the technical field of power supply optimization, in particular to a method and system for optimal configuration of distributed power supplies. Background technique [0002] With the continuous consumption of traditional fossil energy and other resources, the energy crisis and environmental pollution problems are becoming more and more serious. The development of clean and sustainable energy has become an important strategy for energy development in countries all over the world. The wind and solar energy resources in nature are abundant and can be obtained continuously, providing effective support for the formation of a new global energy development pattern. However, the randomness and fluctuation characteristics of wind power and photovoltaic power generation also bring great challenges to the planning and operation of distribution network, and become the main obstacle to the vigorous development of distributed generat...

AI Technical Summary

Problems solved by technology

[0003] At present, there are mainly traditional probabilistic modeling methods, robust optimization methods, and scene generation technology for modeling the uncertainty of distributed generation technology output; while traditional probabilistic modeling methods need to accurately describe uncertain factors, and actual engineering Only part of the statistical information can be obtained, it is difficult to obtain accurate probability distribution and this method ignores the timing characteristics of distributed power output; the robust optimization method has the disadvantage of being too conservative, and cannot balance the economy and security of the planning scheme well ; Traditional scene generation technology is difficult to capture the nonlinear characteristics of high-dimensional data, there are certain limitations, and it may deviate from the actual planning scene

Images