A Big Data Federated Learning-Based Traffic Optimization Routing Scheme for Emergency Services Provision in Autonomous Vehicles Environment
Year: 2025
Type: conference-paper
Abstract: Most of the future intelligent transportation services will rely on onboard sensing and communication protocols used in modern vehicles for providing uninterrupted services such as lane change, on demand audio-video entertainment, and emergency services to end users. Most of these services generate a huge amount of big data used for analytics to take intelligent decisions. However, keeping in view of the complex decision making and limited resources, the deployment and use of these services has various challenges and constraints including data safety, intelligent decision making, and route planning. Specifically, handling emergency situations for the end users traveling on road can be considered as an interesting problem which requires an efficient solution resilient to the aforementioned constraints and challenges. Motivated from the above, in this paper, we propose a prioritize route selection strategy using Federated learning (FL). The proposed scheme first envisions a futuristic road network scenario in which vehicles rely on an onboard intelligent route movement algorithm for reaching to its destination. By assigning higher priority to vehicles on emergency duties, the proposed scheme provides an uninterrupted route discovery by facilitating them to reach their destination on time. The proposed scheme has been validated using simulations on benchmark data sets traces using various performance evaluation metrics in comparison to the other existing state-of-the-art proposals. Results obtained prove the efficacy of the proposed solution on comparison with other existing schemes in literature.
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414539263