阅读说明：本技术 一种基于改进pso算法的城市区域交通配时优化系统 (Urban area traffic timing optimization system based on improved PSO algorithm ) 是由 王卫 谢翔 熊峰 刘贵 陈习苓 王琨 刘胜 章丹 于 2021-07-05 设计创作，主要内容包括：本发明公开了一种基于改进PSO算法的城市区域交通配时优化系统,包括信息优化模块、信息处理模块、改进PSO算法模块、道路选择模块和信息采集模块,所述道路选择模块能够通过网络模块与交通指挥大厅的控制模块或区域交通指挥人员的交通信号控制装置连接,道路选择模块采用可视化操作模式,区域交通指挥人员的交通信号控制装置由交通指挥大厅进行授权；所述红绿灯配时模块与信息优化模块连接,信息优化模块通过网络模块与信息处理模块连接。本发明能够自主的选择道路的区域范围,能够灵活的根据实际道路情况的反馈来对交通的局部区域交通信号灯进行配时；有两种道路区域选择能够使得更具有适用性。(The invention discloses an urban regional traffic timing optimization system based on an improved PSO algorithm, which comprises an information optimization module, an information processing module, an improved PSO algorithm module, a road selection module and an information acquisition module, wherein the road selection module can be connected with a control module of a traffic command hall or a traffic signal control device of regional traffic commanders through a network module, the road selection module adopts a visual operation mode, and the traffic signal control device of the regional traffic commanders is authorized by the traffic command hall; the traffic light timing module is connected with the information optimization module, and the information optimization module is connected with the information processing module through the network module. The method can autonomously select the area range of the road, and can flexibly time the traffic signal lamp of the local area of the traffic according to the feedback of the actual road condition; two road region options can be made more applicable.)

1. An urban area traffic timing optimization system based on an improved PSO algorithm is characterized by comprising an information optimization module, an information processing module, an improved PSO algorithm module, a road selection module and an information acquisition module, wherein the information acquisition module is arranged on each road, and the information acquisition modules on a plurality of roads are connected with the information processing module through a network module;

the information processing module can be connected with the information optimization module through a network module, and the information processing module is used for judging and predicting the future traffic flow of the lane according to the information such as real-time traffic flow, lane congestion condition, traffic light duration and the like;

the road selection module can be connected with a control module of a traffic command hall or a traffic signal control device of regional traffic commanders through a network module, the road selection module adopts a visual operation mode, and the traffic signal control device of the regional traffic commanders is authorized by the traffic command hall;

the improved PSO algorithm module is used for selecting each traffic light as a particle, selecting an index vector of the traffic light as position information of the particle, selecting points of a weight vector of the traffic light and the index vector as standards for measuring the quality of the position of the particle, and applying the points to the improved PSO algorithm;

the traffic light timing module is connected with the information optimization module, the information optimization module is connected with the information processing module through the network module, and the information optimization module can perform global optimization on the timing strategy of the traffic light and issue the instruction to the traffic light timing module for processing.

2. The improved PSO algorithm-based urban area traffic timing optimization system according to claim 1, wherein the information collection module comprises noise collection, lane traffic collection, vehicle speed collection, and current traffic light time collection, wherein the lane traffic collection comprises traffic flow statistics of a left-turn lane, a straight-going lane, and a right-turn lane; the vehicle speed collection and the noise collection are combined with the traffic flow collection, so that the congestion condition of each lane at the current actual road junction can be accurately reflected in real time; and the traffic light time acquisition comprises the current traffic light state acquisition.

3. The system of claim 1, wherein the road selection module comprises a main road selection module and an adjacent area road selection module, and the selection information of the road is mainly summarized according to manual report information such as an information acquisition module or a traffic police, and then the road is selected according to actual requirements.

4. The system for optimizing urban regional traffic distribution based on the improved PSO algorithm as claimed in claim 1, wherein the improved PSO algorithm module comprises a particle selection module, a particle movement module, an iteration module, and a list storage module; the particle selection module is used for selecting each traffic light as a particle, selecting an index vector of the traffic light as position information of the particle, and selecting a weight vector of the traffic light and a point of the index vector as a standard for measuring the quality of the position of the particle; the particle moving module is used for sequencing each particle according to the map position information and then moving the particle to a nearest position; the iteration module is used for iteratively executing the movement of the particle movement module; and the list storage module is used for storing all traffic light position information meeting the preset conditions in the iteration process into the information processing module.

5. The improved PSO algorithm-based urban area traffic timing optimization system according to claim 1, wherein the road selection module comprises two selection modes, one is to select timing area from main according to road name; one is based on the divergent radiating timing zone selection of the central road intersection.

6. The system of claim 1, wherein the improved PSO algorithm is a PSO algorithm that depends in part on location information of worst particles; the method mainly comprises the following steps: firstly, judging whether the algorithm convergence criterion isIf yes, output fopt is min { p ═ if yes_g(i) Fourthly, the algorithm is ended; if not, comparing G with delta; the delta represents a threshold value of the times of continuously finding the optimal solution, and the G represents an actual numerical value of the continuously finding-less optimal solution in the calculation; calculate G (where f (p)_g(0))＝0)；

Judging the relation between G and delta; if G is not less than Δ, then v is_jd＝wv_jd+c₂r₂(p_wd-x_jd) Updating the position of the particle; if G <. DELTA, updating the position and velocity of the particle according to equations (1) and (2);

v_id＝wv_id+c₁r₁(p_id-x_id)+c₂r₂(p_gd-x_id) (1)；

x_id＝x_id+v_id(2) (ii) a Equations (1) and (2) are basic PSO algorithm iterative equations.

Technical Field

The invention relates to the technical field of urban traffic timing, in particular to an urban regional traffic timing optimization system based on an improved PSO algorithm.

Background

Currently, in an urban traffic system, timing control of traffic lights is a main way for adjusting, improving and inducing traffic flow. Particle Swarm Optimization (PSO for short) is an Optimization algorithm for simulating intelligent behaviors of a group. The concept is derived from the research on the predation behavior of the bird colony, and compared with the genetic algorithm and the ant colony algorithm, the method has the characteristics of simple algorithm, easy realization, few adjustable parameters and the like, so the method is widely applied to engineering optimization problems of structural design, electromagnetic field, task scheduling and the like. The existing patent has an off-line traffic timing method based on a PSO algorithm, but the term of the prior art is the first generation technology of signal control.

Entropy is a measure of the degree of order or chaos of a system. The chaos degree of the system and the entropy of the system are in a direct proportional relation, namely the larger the chaos degree of the system is, the larger the entropy of the system is; the larger the entropy of the system, the greater the degree of chaos of the system. Entropy is a state function. The entropy of the PSO system is changed from moment to moment in the process of searching the optimal solution, and the more ordered the particles are, the smaller the entropy of the system is, the more unfavorable the global search is.

The existing traffic timing system, especially in the urban mass traffic system, is in the traffic control of short time or limited time of the local area. In actual control, the timing is mostly optimized by adjusting the green light duration of each traffic phase, the adjustment method is complex, and the existing regional traffic timing adjustment is mostly a fixed local region, and the region real-time selection and division cannot be performed according to the traffic condition in real time.

Disclosure of Invention

The invention aims to provide an urban area traffic timing optimization system based on an improved PSO algorithm, so as to solve the problems in the background technology.

In order to achieve the purpose, the invention provides the following technical scheme:

an urban area traffic timing optimization system based on an improved PSO algorithm comprises an information optimization module, an information processing module, an improved PSO algorithm module, a road selection module and an information acquisition module, wherein the information acquisition module is arranged on each road, particularly the most collectors at road intersections, and the information acquisition modules on a plurality of roads are connected with the information processing module through a network module; the information processing module can be connected with the information optimization module through a network module, and the information processing module is used for judging and predicting the future traffic flow of the lane according to the information such as real-time traffic flow, lane congestion condition, traffic light duration and the like; the road selection module can be connected with a control module of a traffic command hall or a traffic signal control device of regional traffic commanders through a network module, the road selection module adopts a visual operation mode, and the traffic signal control device of the regional traffic commanders is authorized by the traffic command hall; the improved PSO algorithm module is used for selecting each traffic light as a particle, selecting an index vector of the traffic light as position information of the particle, selecting points of a weight vector of the traffic light and the index vector as standards for measuring the quality of the position of the particle, and applying the points to the improved PSO algorithm; the traffic light timing module is connected with the information optimization module, the information optimization module is connected with the information processing module through the network module, and the information optimization module can perform global optimization on the timing strategy of the traffic light and issue the instruction to the traffic light timing module for processing.

The information acquisition module comprises noise acquisition, lane flow acquisition, vehicle speed acquisition and current traffic light time acquisition, wherein the lane flow acquisition comprises traffic flow statistics of a left-turn lane, a straight-going lane and a right-turn lane; the vehicle speed collection and the noise collection are combined with the traffic flow collection, so that the congestion condition of each lane at the current actual road junction can be accurately reflected in real time; and the traffic light time acquisition comprises the current traffic light state acquisition.

The road selection module comprises a main road selection module and a neighboring area road selection module, wherein the selection information of the road is mainly summarized according to an information acquisition module or manual reporting information such as traffic police, and then the road is selected according to actual requirements, and the road can be selected in a mode of selecting a main road intersection and then diverging all around. Such as: selecting a center to a junction A, and then selecting an outward-divergent normal-circular area with n traffic lights away from the junction A according to the actual traffic condition, wherein n and A can be selected independently; in addition, local division can be selected directly according to the names of roads; the selection of the one-sided area is not limited to one road, and may be a boundary road composed of a plurality of roads.

The improved PSO algorithm module comprises a particle selection module, a particle moving module, an iteration module and a list storage module; the particle selection module is used for selecting each traffic light as a particle, selecting an index vector of the traffic light as position information of the particle, and selecting a weight vector of the traffic light and a point of the index vector as a standard for measuring the quality of the position of the particle; the particle moving module is used for sequencing each particle according to the map position information and then moving the particle to a nearest position; the iteration module is used for iteratively executing the movement of the particle movement module; and the list storage module is used for storing all traffic light position information meeting the preset conditions in the iteration process into the information processing module.

Compared with the prior art, the invention has the advantages that: the method can autonomously select the area range of the road, and can flexibly time the traffic signal lamp of the local area of the traffic according to the feedback of the actual road condition; two road area selections can make the road more applicable; the improved PSO algorithm is a PSO algorithm partially dependent on the position information of the worst particle, and from the perspective of system entropy, the worst position information in the particle swarm is added, so that the total entropy of the system is increased, the individual clustering performance is reduced, and the particles are easy to perform global optimization.

Drawings

Fig. 1 is a block diagram of an urban area traffic timing optimization system based on an improved PSO algorithm.

Fig. 2 is a schematic diagram of a framework of a road selection module according to the present invention.

Detailed Description

The technical solution of the present patent will be described in further detail with reference to the following embodiments.

Referring to fig. 1, an urban regional traffic timing optimization system based on an improved PSO algorithm includes an information optimization module, an information processing module, an improved PSO algorithm module, a road selection module, and an information acquisition module, where the information acquisition module is disposed on each road, especially the most collectors at intersections of the roads, and the information acquisition modules on the multiple roads are connected to the information processing module through a network module; the information processing module can be connected with the information optimization module through a network module, and the information processing module is used for judging and predicting the future traffic flow of the lane according to the information such as real-time traffic flow, lane congestion condition, traffic light duration and the like; the road selection module can be connected with a control module of a traffic command hall or a traffic signal control device of regional traffic commanders through a network module, the road selection module adopts a visual operation mode, and the traffic signal control device of the regional traffic commanders is authorized by the traffic command hall; the improved PSO algorithm module is used for selecting each traffic light as a particle, selecting an index vector of the traffic light as position information of the particle, selecting points of a weight vector of the traffic light and the index vector as standards for measuring the quality of the position of the particle, and applying the points to the improved PSO algorithm; the traffic light timing module is connected with the information optimization module, the information optimization module is connected with the information processing module through the network module, and the information optimization module can perform global optimization on the timing strategy of the traffic light and issue the instruction to the traffic light timing module for processing.

The information acquisition module comprises noise acquisition, lane flow acquisition, vehicle speed acquisition and current traffic light time acquisition, wherein the lane flow acquisition comprises traffic flow statistics of a left-turn lane, a straight-going lane and a right-turn lane; the vehicle speed collection and the noise collection are combined with the traffic flow collection, so that the congestion condition of each lane at the current actual road junction can be accurately reflected in real time; and the traffic light time acquisition comprises the current traffic light state acquisition.

As shown in fig. 2, the road selection module includes a main road selection module and a neighboring area road selection module, and the selection information of the road is mainly summarized according to the manual reporting information such as the information acquisition module or the traffic police, and then the road is selected according to the actual requirement, and the selection of the road may be performed by selecting a main road intersection and then selecting the main road intersection in a manner of diverging all around. Such as: selecting a center to a junction A, and then selecting an outward-divergent normal-circular area with n traffic lights away from the junction A according to the actual traffic condition, wherein n and A can be selected independently; in addition, local division can be selected directly according to the names of roads; the selection of the one-sided area is not limited to one road, and may be a boundary road composed of a plurality of roads.

The improved PSO algorithm module comprises a particle selection module, a particle moving module, an iteration module and a list storage module; the particle selection module is used for selecting each traffic light as a particle, selecting an index vector of the traffic light as position information of the particle, and selecting a weight vector of the traffic light and a point of the index vector as a standard for measuring the quality of the position of the particle; the particle moving module is used for sequencing each particle according to the map position information and then moving the particle to a nearest position; the iteration module is used for iteratively executing the movement of the particle movement module; and the list storage module is used for storing all traffic light position information meeting the preset conditions in the iteration process into the information processing module.

The improved PSO algorithm is a PSO algorithm that depends in part on location information of the worst particle; the algorithm mainly comprises the following steps: firstly, judging whether an algorithm convergence criterion is met, and if so, outputting fopt to min { p ═_g(i) Fourthly, the algorithm is ended; if not full ofIf yes, comparing G with delta; the delta represents a threshold value of the times of continuously finding the optimal solution, and the G represents an actual numerical value of the continuously finding-less optimal solution in the calculation; calculate G (where f (p)_g(0))＝0)；

Judging the relation between G and delta; if G is not less than Δ, then v is_jd＝wv_jd+c₂r₂(p_wd-x_jd) Updating the position of the particle; if G <. DELTA, updating the position and velocity of the particle according to equations (1) and (2);

v_id＝wv_id+c₁r₁(p_id-x_id)+c₂r₂(p_gd-x_id) (1)；

x_id＝x_id+v_id (2)；

wherein i is 1,2, …, m; d is 1,2, … D; learning factor c₁,c₂Is a non-negative constant; r is₁,r₂Is [0,1 ]]Random number of between, v_id＝[-v_max,v_max]；v_maxIs a constant; w is an inertia coefficient, is a non-negative number, and the ith particle is represented by a vector x of dimension D_i＝(x_i1,x_i2,…,x_iD) Denotes its flying speed in space, which is expressed by v_i＝(v_i1,v_i2,…,v_iD) Represents; p for the optimum position of the ith particle searched so far_i＝(p_i1,p_i2,…,p_iD) Indicating that the entire particle group has been searched for the optimal position p_g＝(p_g1,p_g2,…,p_gD) Represents; equations (1) and (2) are basic PSO algorithm iterative equations.

Although the preferred embodiments of the present patent have been described in detail, the present patent is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present patent within the knowledge of those skilled in the art.