Traffic planning system based on swarm intelligence evolutionary ant colony algorithm

• Main Authors: LIU TIANXING, QI XIAOYA, GAN ZHONGXUE, LI WEI, XU ZHENG, TIAN XIAOHE
• Format: Patent
• Language: Chinese; English
• Published: 06.04.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS; SIGNALLING; TRAFFIC CONTROL SYSTEMS

The invention provides a traffic planning system based on a swarm intelligence evolutionary ant colony algorithm, which is used for optimizing controllable signal lamps involved in traffic and driving paths of vehicles to obtain the shortest global traffic average time. The method comprises the following steps that an action selection part calculates the action probability of ants according to pheromones and a strategy neural network, and determines an ant selection strategy according to the action probability; the global updating part updates global pheromones according to the individual optimal strategy of each ant; the global optimal part calculates the global pheromones to obtain a global optimal strategy as a global optimal strategy; the individual loss construction unit constructs individual loss on the basis of the global optimal strategy. According to the traffic planning system, individual optimization is firstly carried out on fine traffic components such as signal lamps and vehicles, then global op