Most traffic control systems are centralized, where all the collected data can be analyzed to make a decision. However, there are problems with computational complexity and, more seriously, real-time decision-making. This paper proposes a decentralized traffic routing system based on a new pheromone model of ant colony optimization algorithm and an automated negotiation technique in a connected vehicle environment. In particular, connected vehicles utilize a new pheromone model, namely the inverted pheromone model, which generates a repulsive force between vehicles and gives negative feedback to the congested roads. They also perform a collective learning-based negotiation process for distributing traffic flows throughout the road networks, reducing traffic congestion. Via extensive simulations based on the Simulation of Urban Mobility, the proposed system shows that it can significantly reduce travel time and fuel consumption compared to existing systems.

大多数交通控制系统都是集中式的，可以分析所有收集的数据以做出决策。然而，计算复杂性存在问题，更严重的是，实时决策存在问题。本文提出了一种基于蚁群优化算法的新信息素模型和车联网环境下的自动协商技术的分散式交通路由系统。特别是网联汽车利用了一种新的信息素模型，即反向信息素模型，它在车辆之间产生排斥力，对拥挤的道路产生负反馈。他们还执行基于集体学习的协商过程，以在整个道路网络中分配交通流量，从而减少交通拥堵。通过基于城市交通模拟的广泛模拟，