粗糙集的过饱和多交叉口协同优化模型研究

为解决现有模糊智能控制方法仅适用于单交叉口非饱和状态,满足区域交通过饱和多交叉口信号协同联动控制的需要,提出了高峰时期主通道优化控制策略。在粗糙集知识推理基础上,构建了以多交叉口状态信息为条件属性,以绿灯延长方式、绿灯延长相位和绿灯延长时间3个参数为决策属性的多决策属性模糊控制模型。运用可辨识矩阵与属性频度的属性约简方法对模型进行约简,提取决策规则。实例分析表明:多交叉口主通道绿灯时间延长3~8 s能够有效提高区域交通整体通行效能,同时延长时间不仅与过饱和状态车辆最大排队长度有关,还与绿灯延长方式、绿灯延长相位存在关联,这与交警经验总结的控制规律一致。

Collaborative optimization model for oversaturated multiple intersections based on the rough set theory

To solve the defect that the existing fuzzy intelligent control method is only suitable for a single intersection under unsaturated state, and to meet the need of coordination control of regional traffic for oversaturated multiple intersections, an optimization control strategy for main channel at peak time was proposed. The fuzzy control model with multiple decision attributes was established on the basis of knowledge reasoning in rough sets theory. It took multiple intersections state information as condition attributes, and the elongation mode, phase, and green light timing, as decision attributes. The methods of attribute reduction of the discernibility matrix and the frequency of attribute were used in the model, then some decision rules were extracted. The results show that the efficiency of regional traffic was improved via 3-8 more seconds of green light signal at the main channel. In addition, the extension time is not only related to the maximum queue length of vehicles under oversaturated vehicle conditions, but also the extension mode and phase of green light, which is consistent with the experience of traffic police.