论文标题
使用AI减轻网络延迟在基于云的智能交通信号控制中的影响
Using AI for Mitigating the Impact of Network Delay in Cloud-based Intelligent Traffic Signal Control
论文作者
论文摘要
云服务，物联网（IoT）和蜂窝网络的最新进步使云计算成为智能交通信号控制（ITSC）的有吸引力的选择。这种方法大大降低了电缆，安装，所使用的设备数量和维护的成本。基于云计算的ITC系统降低了ITSC系统的成本，并通过利用现有强大的云平台来扩展系统。 尽管此类系统具有巨大的潜力，但应解决的关键问题之一是网络延迟。众所周知，消息传播的网络延迟很难预防，这可能会降低系统的性能，甚至可能在交叉路口为车辆造成安全问题。 在本文中，我们基于强化学习介绍了一种新的流量信号控制算法，即使在严重的网络延迟下，该算法的性能也很好。本文介绍的框架对所有基于代理的系统使用远程计算资源可能会有所帮助，因为网络延迟可能是一个关键问题。对于不同方案获得的广泛模拟结果显示了设计算法的生存能力，以应对网络延迟。
The recent advancements in cloud services, Internet of Things (IoT) and Cellular networks have made cloud computing an attractive option for intelligent traffic signal control (ITSC). Such a method significantly reduces the cost of cables, installation, number of devices used, and maintenance. ITSC systems based on cloud computing lower the cost of the ITSC systems and make it possible to scale the system by utilizing the existing powerful cloud platforms. While such systems have significant potential, one of the critical problems that should be addressed is the network delay. It is well known that network delay in message propagation is hard to prevent, which could potentially degrade the performance of the system or even create safety issues for vehicles at intersections. In this paper, we introduce a new traffic signal control algorithm based on reinforcement learning, which performs well even under severe network delay. The framework introduced in this paper can be helpful for all agent-based systems using remote computing resources where network delay could be a critical concern. Extensive simulation results obtained for different scenarios show the viability of the designed algorithm to cope with network delay.
