本文關(guān)鍵詞： 交通工程 信號(hào)控制交叉口 定周期Q學(xué)習(xí)配時(shí) 不定周期Q學(xué)習(xí)配時(shí)　出處：《長(zhǎng)沙理工大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：為了優(yōu)化交叉口信號(hào)配時(shí),本文通過建立Excel Vba-Vissim-Matlab集成仿真平臺(tái),建立了以總關(guān)鍵排隊(duì)長(zhǎng)度之差最小為優(yōu)化目標(biāo)的單交叉口在線Q學(xué)習(xí)模型。在線模型分為定周期Q學(xué)習(xí)配時(shí)模型、不定周期Q學(xué)習(xí)配時(shí)模型。針對(duì)控制性能指標(biāo)相對(duì)于臨近的配時(shí)方案不敏感的特點(diǎn),提出了以平均總關(guān)鍵排隊(duì)長(zhǎng)度之差作為基本單位重新構(gòu)造獎(jiǎng)勵(lì)函數(shù),目的是拉大各行為對(duì)應(yīng)的Q值差距,提高模型的收斂速度和魯棒性。定周期兩相位Q學(xué)習(xí)模型算例表明Q學(xué)習(xí)模型的正確性,能夠隨著流量變化動(dòng)態(tài)優(yōu)化,而且利用經(jīng)驗(yàn)可以縮短學(xué)習(xí)時(shí)間。通過對(duì)猴子石大橋交通狀況的模擬測(cè)試,表明模型具有很好的實(shí)際應(yīng)用能力。通過定周期Q學(xué)習(xí)配時(shí)方案、不定周期Q學(xué)習(xí)配時(shí)方案與Transyt配時(shí)方案的對(duì)比,結(jié)果表明以總關(guān)鍵排隊(duì)長(zhǎng)度之差作為優(yōu)化目標(biāo)能夠優(yōu)化整個(gè)交叉口的時(shí)空資源,本論文建立的在線Q學(xué)習(xí)模型具有較高的準(zhǔn)確性、魯棒性和學(xué)習(xí)能力,通過學(xué)習(xí)能夠?qū)崿F(xiàn)優(yōu)化目標(biāo)。同時(shí)還探討了流量變化情況下定周期、不定周期Q學(xué)習(xí)配時(shí)模型的性能。
[Abstract]:In order to optimize intersection signal timing, this paper establishes an online Q learning model of single intersection with minimum critical queue length difference as the optimization objective by establishing Excel Vba-Vissim-Matlab integrated simulation platform. The online model is divided into fixed period Q learning timing model. According to the insensitivity of the control performance index to the adjacent timing scheme, a reward function based on the difference of the average total critical queue length as the basic unit is proposed. The purpose of this paper is to widen the Q-value gap corresponding to different behaviors and to improve the convergence speed and robustness of the model. An example of the two-phase Q-learning model with fixed period shows that the Q-learning model is correct and can be dynamically optimized with the flow rate. Moreover, the learning time can be shortened by using experience. By simulating the traffic conditions of the Monkey Stone Bridge, it is shown that the model has good practical application ability. The comparison between the uncertain periodic Q learning timing scheme and the Transyt timing scheme shows that the space-time resources of the intersection can be optimized by using the difference of the total critical queue length as the optimization objective. The online Q learning model established in this paper has high accuracy, robustness and learning ability, and it can achieve the optimization goal by learning. At the same time, the performance of the Q learning timing model with fixed period and variable period under the condition of flow change is also discussed.
【學(xué)位授予單位】：長(zhǎng)沙理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：U491.54
，

本文編號(hào)：1555026