On improving the regional transportation efficiency based on federated learning

Abstract

In recent years, regional traffic congestion has become increasingly frequent, which seriously affects the safety and efficiency of urban vehicles. Therefore, traffic flow prediction methods based on artificial intelligence are widely used in traffic management. However, the existing traffic flow prediction methods need to collect raw data, which involves risks of vehicle privacy leakage. Federated learning, which shares model updates without exchanging local data, has gradually become an effective solution to achieve privacy protection. A federated learning traffic flow prediction model for regional transportation systems is proposed in this paper. At the same time, due to the emergence of highly intelligent automatic driving vehicles, a vehicle scheduling system, which can control the departure and routes of vehicles in urban regions is developed in the proposed approach. A road weight measurement method combined with real time traffic information is introduced to optimize the driving routes of vehicles to reduce the average travel time. Additionally, departure strategy, is another factor that has a great influence on traffic efficiency, but is usually ignored in the past, and is also carefully compared and studied in this paper. The numerical results illustrate that the proposed schemes can effectively improve the privacy protection ability of model updates, reduce the scheduling completion time by using the traffic flow prediction model, and realize the comparative research between departure strategies, which provides a reference for developing a safe and efficient regional transportation system.