本文關鍵詞： 粒子群算法 遺傳算法 交通流量控制 交叉操作 變異操作　出處：《長安大學》2015年碩士論文　論文類型：學位論文

【摘要】：隨著城市規(guī)模的擴大和汽車保有量的不斷壯大,針對有限的城市交通資源和急劇增加的汽車數(shù)量,在保證交通流量合理有序的前提下,如何最大限度地發(fā)揮現(xiàn)有城市交通網(wǎng)絡的通行能力,是當前交通控制研究的重點和難點。首先,本文針對粒子群算法存在局部最優(yōu)的問題,將遺傳算法的交叉操作和變異操作引入粒子群算法對其進行改進,詳細闡述了改進粒子群算法的算法流程。四個標準測試函數(shù)收斂圖對比發(fā)現(xiàn),在收斂速度和穩(wěn)定性方面,改進的粒子群算法優(yōu)于遺傳算法和粒子群算法。其次,為了提高交通流量控制和優(yōu)化的精度,將混沌理論引入PSO對LS-SVM的核參數(shù)和懲罰系數(shù)進行優(yōu)化選擇,提出一種ECLS-SVM交通流量預測模型。通過基于ECLS-SVM算法的單步、3步、5步和7步預測結(jié)果和不同模型的預測時間和預測均方誤差的對比結(jié)果可知,ECLS-SVM算法可以有效提高交通流量預測的精度和效率,對指導交通網(wǎng)絡資源的合理分配和規(guī)劃具有重要的理論意義和實際價值。在交通流量預測的基礎上,運用粒子群算法實現(xiàn)城市單交叉路口和雙交叉路口交通信號燈的優(yōu)化控制,達到緩解城市交通擁堵的壓力和提高城市交通效率的目的。針對交通信號控制的具體實例,建立單交叉路口和雙交叉路口交通控制數(shù)學模型。再次,針對標準PSO算法存在局部最優(yōu)和約束條件的問題,運用GA算法對標準PSO算法進行改進,之后將改進的粒子群算法GA-PSO應用于交通控制上。在單個交叉路口模型的基礎上,結(jié)合以往交通控制模型,運用改進的粒子群算法對交通控制算法進行優(yōu)化并與未改進的PSO算法進行對比,發(fā)現(xiàn)改進的粒子群算法更優(yōu)。在此基礎上,研究雙交叉路口,建立交通協(xié)調(diào)優(yōu)化模型,再運用改進的粒子群算法對該模型進行優(yōu)化,并與標準PSO算法進行對比。最后,通過標準PSO和改進的GA-PSO算法的交通控制算法對比研究發(fā)現(xiàn),引入交叉操作、變異操作的粒子群算法,可以增加全局搜索能力,同時可以避免陷入局部最優(yōu)解。改進的PSO算法較標準PSO算法在解決交通流量控制問題的時候,完全避免了標準化誤差、統(tǒng)計不完善、局部收斂等問題,能夠很好地實現(xiàn)交通流量最優(yōu)化控制。
[Abstract]:With the expansion of the city scale and the continuous expansion of the vehicle ownership, the limited urban traffic resources and the rapidly increasing number of vehicles, under the premise of ensuring a reasonable and orderly traffic flow, How to maximize the capacity of the existing urban traffic network is the focus and difficulty of current traffic control research. Firstly, the particle swarm optimization algorithm has the problem of local optimization. The crossover operation and mutation operation of genetic algorithm are introduced into the particle swarm optimization algorithm to improve it, and the algorithm flow of the improved particle swarm optimization algorithm is described in detail. By comparing the convergence diagrams of four standard test functions, it is found that the convergence speed and stability of the improved particle swarm optimization algorithm are analyzed. The improved particle swarm optimization algorithm is superior to genetic algorithm and particle swarm optimization algorithm. Secondly, in order to improve the accuracy of traffic flow control and optimization, chaotic theory is introduced into PSO to optimize the kernel parameters and penalty coefficients of LS-SVM. This paper presents a ECLS-SVM traffic flow forecasting model. By comparing the prediction results of three steps, five steps and seven steps based on ECLS-SVM algorithm with the prediction time and mean square error of different models, it can be seen that ECLS-SVM algorithm can effectively improve traffic performance. Accuracy and efficiency of flow forecasting, It is of great theoretical and practical value to guide the rational allocation and planning of traffic network resources. On the basis of traffic flow prediction, the particle swarm optimization algorithm is used to realize the optimal control of traffic lights at single and double intersections. To alleviate the pressure of urban traffic congestion and improve urban traffic efficiency. In view of the specific example of traffic signal control, the mathematical model of traffic control at single intersection and double intersection is established. In order to solve the problem of local optimization and constraint in standard PSO algorithm, GA algorithm is used to improve the standard PSO algorithm, and then the improved particle swarm optimization (GA-PSO) algorithm is applied to traffic control. On the basis of a single intersection model, the improved particle swarm optimization algorithm (GA-PSO) is applied to traffic control. Combined with the previous traffic control model, the improved particle swarm optimization algorithm is used to optimize the traffic control algorithm and compared with the unimproved PSO algorithm. It is found that the improved particle swarm optimization algorithm is better. The traffic coordination optimization model is established, and then the improved particle swarm optimization algorithm is used to optimize the model, and compared with the standard PSO algorithm. Finally, through the comparison of traffic control algorithm between standard PSO and improved GA-PSO algorithm, it is found that, The particle swarm optimization algorithm with crossover operation and mutation operation can increase the global search ability and avoid falling into the local optimal solution. The improved PSO algorithm is better than the standard PSO algorithm in solving the traffic flow control problem. The problems of standardization error, statistical imperfection and local convergence can be avoided completely, and the optimal traffic flow control can be realized well.
【學位授予單位】：長安大學
【學位級別】：碩士
【學位授予年份】：2015
【分類號】：U491.54;TP18

【參考文獻】

相關期刊論文 前4條

1 趙建有,趙麗平;基于多智能體的城市交通流控制原型系統(tǒng)[J];交通運輸工程學報;2003年03期

2 歐海濤,張衛(wèi)東,許曉鳴;基于RMM和貝葉斯學習的城市交通多智能體系統(tǒng)[J];控制與決策;2001年03期

3 承向軍,賀振歡,楊肇夏;基于遺傳算法的交通信號機器學習控制方法[J];系統(tǒng)工程理論與實踐;2004年08期

4 馬東方;王殿海;宋現(xiàn)敏;金盛;;進出口道綜合效率最優(yōu)的交叉口配時參數(shù)優(yōu)化方法[J];中南大學學報(自然科學版);2012年04期

，

本文編號：1551044