Urban power network planning method based on pseudo-crossover taboo hybrid genetic algorithm

Abstract

The invention discloses an urban power network planning method based on a pseudo-crossover taboo hybrid genetic algorithm. The urban power network planning method includes the steps: (1) performing genetic encoding for all cities; (2) establishing a target function of each individual, and calculating a fitness function of each individual; (3) randomly selecting two individuals in a parent group by the aid of a pseudo-crossover operator, and performing air extension by two randomly generated crossover points; (4) combining a taboo search operator with the genetic algorithm to form the pseudo-crossover taboo hybrid genetic algorithm. The pre-crossover individual is rearranged according to arrangement information of another individual by the aid of the pseudo-crossover operator, the operator can avoid repetition of elements in the individuals, and an optimal power network planning scheme can be rapidly and accurately searched within a wider range by means of taboo search optimization and by jumping out of locally optimal solutions.

Description

technical field [0001] The invention relates to a power grid planning method, in particular to a power grid planning method for multiple specific cities. Background technique [0002] With the development of society, the use of electricity is closely related to the development of human society. Low-cost and high-efficiency electricity use is a very practical issue. The grid planning between cities is of great importance. Effective grid planning can reduce laying costs and power loss. How to lay the power grid among several cities to make the distance the shortest is actually a TSP problem. For this kind of problem, experts and scholars' solutions to such problems can be roughly divided into: [0003] 1. The method of finding the best route based on the simulated annealing algorithm, such as: the realization of the traveling salesman problem based on the simulated annealing algorithm. Guo Lexin. Modern Computer, 2012, (2). [0004] 2. The method of finding the best route ba...

AI Technical Summary

Problems solved by technology

[0007] 1. The method of finding the best route based on the simulated annealing algorithm. If the cooling process is slow enough, the performance of more solutions will be better, but in contrast to this, the convergence speed is too slow; if the cooling process is too fast, it is likely that no global optimal solution

[0008] 2. The method of finding the best route based on the ant colony algorithm is affected by the location of the start and end points and the distribution of obstacles. When the environment is complex, ants are prone to fall into unfeasible points, and even path detours and deadlocks occur

[0009] 3. The method of finding the best route based on the artificial fish swarm algorithm. When the search area is relatively flat, the random moving artificial fish cannot jump out of the flat area, which reduces the speed of global convergence; because some parameters take fixed values, the algorithm is generally in the process of optimization. The initial convergence speed is fast, but it often slows down later, and the optimization accuracy is also affected to a certain extent.

Images