Edge-Based V2X Communications With Big Data Intelligence

Abstract

Vehicular Internet-of-Things applications require an efficient Vehicle-to-Everything (V2X) communication scheme. However, it is particularly challenging to achieve a high throughput and low latency with limited wireless resources in highly dynamic vehicular networks. In this article, we propose a scheme that enhances V2V communications through integration of vehicle edge-based forwarding and learning-based edge selection policy optimization. The proposed scheme has three main characteristics. First, the Hierarchical edge-based preemptive route creation is introduced to create hierarchical edges and conduct efficient packet forwarding as well as route aggregation. Second, Two-stage learning is introduced to select efficient edge nodes using big data driven traffic prediction and reinforcement learning-based edge node selection. Third, Context-aware edge selection is employed to improve the performance of edge-based forwarding in various contexts. We use real traffic big data and realistic vehicular network simulations to evaluate the performance of the proposed scheme and show the advantage over other baseline approaches. INDEX TERMS Edge computing, traffic big data, vehicular ad hoc networks, V2X communications.

Robust Autonomous Intersection Control Approach for Connected Autonomous Vehicles

“…QH is the set of queue heads of (lq 1 − CS) to (lq 8 − CS), and ST is the set that contains the top of stacks differentiate by lane which stores the vertex in CS. All operations will be done between the vertexes on either side of the line which separating ST and QH to satisfy the constraint (8). Then three kinds of neighborhood operations are defined:…”

“…In the research area, extensive studies have been done to improve link reliability and quality of service. In [7] and [8], V2X communication protocols with edge intelligence are proposed, which achieves high throughput and low latency and in highly dynamic V2X networks. With the current advancement of V2X, primary AIC, namely, vehicle speed guidance, has been tested in many places.…”

“…To enhance V2X communications, Ref. [7], [8] provide "vehicle as an edge" solutions. With the intelligence with fuzzy logic and reinforcement learning, vehicles are classified as hierarchical nodes.…”

Edge-facilitated Augmented Vision in Vehicle-to-Everything Networks

“…7The edge server updates the collected sensor data. (8) The edge server loads the received camera images (step 2) to the object detector. (9) The edge server sends the detection result to the sender.…”

“…Vehicular communication systems play a key role in sharing information between vehicles 2 1 and roadside units (RSU). Current solutions focus on four types of communication: vehicle-to-vehicle (V2V), vehicleto-infrastructure (V2I), vehicle-to-cloud (V2C) and vehicleto-everything (V2X) [3]- [8]. Although these solutions fulfill basic demands, efficiently sharing complex and large volumes of data among vehicles at scale remains a challenge.…”