Urban Traffic Dynamics Prediction—A Continuous Spatial-temporal Meta-learning Approach

Urban traffic status (e.g., traffic speed and volume) is highly dynamic in nature, namely, varying across space and evolving over time. Thus, predicting such traffic dynamics is of great importance to urban development and transportation management. However, it is very challenging to solve this problem due to spatial-temporal dependencies and traffic uncertainties. In this article, we solve the traffic dynamics prediction problem from Bayesian meta-learning perspective and propose a novel continuous spatial-temporal meta-learner (cST-ML), which is trained on a distribution of traffic prediction tasks segmented by historical traffic data with the goal of learning a strategy that can be quickly adapted to related but unseen traffic prediction tasks. cST-ML tackles the traffic dynamics prediction challenges by advancing the Bayesian black-box meta-learning framework through the following new points: (1) cST-ML captures the dynamics of traffic prediction tasks using variational inference, and to better capture the temporal uncertainties within tasks, cST-ML performs as a rolling window within each task; (2) cST-ML has novel designs in architecture, where CNN and LSTM are embedded to capture the spatial-temporal dependencies between traffic status and traffic-related features; (3) novel training and testing algorithms for cST-ML are designed. We also conduct experiments on two real-world traffic datasets (taxi inflow and traffic speed) to evaluate our proposed cST-ML. The experimental results verify that cST-ML can significantly improve the urban traffic prediction performance and outperform all baseline models especially when obvious traffic dynamics and temporal uncertainties are presented.

An efficient routing strategy for coupled spatial networks

The study of traffic dynamics on couple networks is important for the design and management of many real systems. In this paper, an efficient routing strategy on coupled spatial networks is proposed, considering both traffic characteristics and network topology information. With the routing strategy, the traffic capacity can be greatly improved in both scenarios of identical and heterogeneous node capacity allocation. Heterogeneous allocation strategy of node delivery capacity performs better than identical capacity allocation strategy. The study can help to improve the performance of real-world multi-modal traffic systems.

The self-adaptive routing strategy to alleviate packet loss in finite buffer networks

In real communication or transportation systems, loss of agents is very common due to finite storage capacity. We study the traffic dynamics in finite buffer networks and propose a routing strategy motivated by a heuristic algorithm to alleviate packet loss. Under this routing strategy, the traffic capacity is further improved, comparing to the shortest path routing strategy and efficient routing strategy. Then we investigate the effect of this routing strategy on the betweenness of nodes. Through dynamic routing changes, the maximum node betweenness of the network is greatly reduced, and the final betweenness of each node is almost the same. Therefore, the routing strategy proposed in this paper can balance the node load, thereby effectively alleviating packet loss.

Enhancing traffic capacity for multilayer networks by link rewiring

The traffic dynamics of complex networks is closely related to network structure. By changing network structure, the traffic dynamics behavior can be optimized. Faced with the network congestion problem, we focus on the relationship between network traffic capacity and its structure. The multilayer networks are studied, which are composed of high-speed and low-speed layers. A link rewiring strategy is proposed to change the low-speed layer structure and improve the network traffic capacity. Compared with the random link rewiring strategy, the purposeful link rewiring strategy can improve network traffic capacity. A large number of simulations are carried out under the effective traffic-flow assignment strategy to prove the effectiveness of the link rewiring strategy. This strategy improves packet transmission efficiency of low-speed layer, and reduces the average length of effective path, which indicates that adjustment of low-speed layer structure can improve traffic capacity of multilayer networks.