Method for realizing self-adapting network reconfiguration at distribution network terminal

Abstract

The invention relates to the field of power supply and distribution technology, and discloses a method for realizing self-adapting network reconfiguration at a distribution network terminal. The method is characterized by comprising the followings steps of: (a) constructing an input vector and an output vector of a distribution network terminal neural network module; (b) initializing a neural network; (c) training the neural network by using samples; and (d) treating the distribution network for reconfiguration with the trained neural network module. The invention has the benefits of buildingthe corresponding relation between a dynamic distribution network load and an optimal network topology by using the nonlinear mapping relationship between the input and output of the neural network and the self adapting self-learning ability to realize the reconfiguration of the distribution network, thereby reducing the line loss of the distribution network and improving the system economy, balancing the loads, eliminating the overload, improving the voltage quality of supplied power, and further improving the reliability of the supplied power.

Description

technical field [0001] The invention relates to the technical field of electric power supply and distribution, in particular to a method for realizing adaptive network restoration and reconstruction at a distribution network terminal. Background technique [0002] Network reconfiguration is an important means of distribution system operation and control, and also an important part of distribution management system. Network reconfiguration is theoretically a complex multi-objective nonlinear combinatorial optimization problem. Since the 1980s, people have conducted extensive research on power distribution network reconfiguration, and formed relatively mature methods and theories of network reconfiguration. The background of the distribution network reconfiguration algorithm is that in the process of network reconfiguration, since the network loss and voltage of the distribution network have a nonlinear relationship, and there are other constraints, the analysis of the distri...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems in the prior art, the present invention provides a method for realizing adaptive network recovery and reconstruction at the distribution network terminal, which solves the problem that the network reconfiguration must rely on the distribution master station when the distribution network is reconfigured in the prior art , the network reconstruction of the distribution network cannot be realized when the control center fails, so as to achieve the purpose of power supply reliability

Images