Optimization Method of Traffic Signal Timing Based on Principal Component Analysis and Improved Genetic Algorithm

Abstract

Provided is a traffic signal timing optimization method based on a principal component analysis improvement genetic algorithm. The algorithm is provided by analyzing internal relation among the genetic algorithm, image processing and model recognition and can be used for solving various function optimization problems. By means of the algorithm, principal component analysis is conducted on population individuals to analyze design cross and a mutation operator. The mutation operator can avoid the cross position where ineffective cross may be generated easily according to similar genes of parent individuals counted by PCA, useless cross is reduced, and algorithm search efficiency is improved. The mutation operator conducts self-adaptation mutation probability adjustment according to the similar genes counted by PCA to protect the good mode and improve the local research efficiency of the algorithm. The algorithm is applied to single-crossing signal timing optimization. By means of testing comparison with the existing algorithm, the method improves algorithm generality and efficiency, effective timing time is acquired, and the number of the queuing vehicles in front of a crossing is reduced.

Description

technical field [0001] The invention belongs to the technical field of urban traffic control signal timing. The algorithm of genetic algorithm and biometric identification technology intersecting field (specifically involving classical genetic algorithm and principal component analysis PCA) is used to realize the signal timing control of urban single intersection. Background technique [0002] With the rapid development of my country's economy and the continuous acceleration of the urbanization process, the number of motor vehicles has also increased rapidly, the traffic volume has increased greatly, the transportation supply is seriously insufficient, and the contradiction between supply and demand is prominent. Take Beijing as an example. At present, the number of motor vehicles in Beijing has exceeded 2 million. The annual growth rate of urban roads is 3%, while the growth rate of vehicles is 15%, and the annual growth rate of traffic volume has reached 18%. [0003] As ...

AI Technical Summary

Problems solved by technology

Song Xuehua and others invented a single intersection signal timing optimization method based on genetic algorithm. The genetic algorithm used in this invention is a standard genetic algorithm, in which the optimal retention strategy is added to the selection strategy, but the local search ability of the standard genetic algorithm is not strong. prone to premature convergence

Images