Decentralized vehicle-to-everything (V2X) networks (i.e., Mode-4 C-V2X and Mode 2a NR-V2X), rely on periodic Basic Safety Messages (BSMs) to disseminate time-sensitive information (e.g., vehicle position) and has the potential to improve on-road safety. For BSM scheduling, decentralized V2X networks utilize sensing-based semi-persistent scheduling (SPS), where vehicles sense radio resources and select suitable resources for BSM transmissions at prespecified periodic intervals termed as Resource Reservation Interval (RRI). In this paper, we show that such a BSM scheduling (with a fixed RRI) suffers from severe under- and over- utilization of radio resources under varying vehicle traffic scenarios; which severely compromises timely dissemination of BSMs, which in turn leads to increased collision risks. To address this, we extend SPS to accommodate an adaptive RRI, termed as SPS++. Specifically, SPS++ allows each vehicle -- (i) to dynamically adjust RRI based on the channel resource availability (by accounting for various vehicle traffic scenarios), and then, (ii) select suitable transmission opportunities for timely BSM transmissions at the chosen RRI. Our experiments based on Mode-4 C-V2X standard implemented using the ns-3 simulator show that SPS++ outperforms SPS by at least $50\%$ in terms of improved on-road safety performance, in all considered simulation scenarios.
The method of choice for parameter aggregation in Deep Neural Network (DNN) training, a network-intensive task, is shifting from the Parameter Server model to decentralized aggregation schemes (AllReduce) inspired by theoretical guarantees of better performance. However, current implementations of AllReduce overlook the interdependence of communication and computation, resulting in significant performance degradation. In this paper, we develop Caramel, a system that accelerates decentralized distributed deep learning through model-aware computation scheduling and communication optimizations fo…
Information Entropy-Based Scheduling for Communication-Efficient Decentralized Learning
Communication Systems Department, EURECOM（EURECOM通信系统部）；Department of Electrical Engineering, Linköping University（林雪平大学电子工程系）；DaSCI, Department of Computer Science and Artificial Intelligence, University of Granada（Granada大学计算机科学与人工智能系）
We consider multi-hop wireless networks serving multiple flows in which only packets that meet hard end-to-end deadline constraints are useful, i.e., if a packet is not delivered to its destination node by its deadline, it is dropped from the network. We design decentralized scheduling policies for such multi-hop networks that attain the maximum throughput of useful packets. The resulting policy is decentralized in the sense that in order to make a transmission decision, a node only needs to know the "time-till-deadline" of the packets that are currently present at that node, and not the state…
Motivated by medium access control for resource-challenged wireless Internet of Things (IoT), we consider the problem of queue scheduling with reduced queue state information. In particular, we consider a time-slotted scheduling model with $N$ sensor nodes, with pair-wise dependence, such that Nodes $i$ and $i + 1,~0 < i < N$ cannot transmit together. We develop new throughput-optimal scheduling policies requiring only the empty-nonempty state of each queue that we term Queue Nonemptiness-Based (QNB) policies. We propose a Policy Splicing technique to combine scheduling policies for small netw…
This paper investigates the resource scheduling for heterogeneous vehicular networks, where some moving vehicles are selected and scheduled as helping relays to assist information transmission between the roadside infrastructure and other moving vehicles. For such a system, we propose a mobile-service based max-min fairness resource scheduling scheme, where service amount which is more suitable for high mobility scenarios is adopted to characterize the information transmission capacity of the links and the max-min criteria is adopted to meet the fairness requirement of the moving vehicles. Sim…
Decentralized Rank Scheduling for Energy-Constrained Multi-Task Federated Fine-Tuning in Edge-Assisted IoV Networks
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Cyber Science and Technology, Sun Yat-sen University（中山大学网络安全科学与技术学院）
Recent developments in advanced sensors, wireless communications and intelligent vehicle control technologies have enabled vehicles to detect traffic anomalies on the road and then notify surrounding vehicles to improve traffic safety. However, due to the high-speed movement of vehicles and the frequent topological changes between vehicles, it is difficult for vehicles to evaluate the credibility of received messages. Quite a lot of research effort has been carried out to establish various trustworthiness platforms. These studies mostly focus on how to enhance the accuracy of credibility evalu…
Cellular Vehicle-to-Everything (C-V2X) networks can operate without cellular infrastructure support. Vehicles can autonomously select their radio resources using the sensing-based Semi-Persistent Scheduling (SPS) algorithm specified by the Third Generation Partnership Project (3GPP). The sensing nature of the SPS scheme makes C-V2X communications prone to the well-known hidden-terminal problem. To address this problem, this paper proposes a novel geo-based scheduling scheme that allows vehicles to autonomously select their radio resources based on the location and ordering of neighboring vehic…
Through connecting intelligent vehicles as well as the roadside infrastructure, the perception range of vehicles can be significantly extended, and hidden objects at blind spots can be efficiently detected and avoided. To realize this, accurate road map data must be downloaded in real time to these intelligent vehicles for navigation and localization purposes. Besides, the cloud must be updated with dynamic changes that happened in the road network. These involve the transmissions of high-definition 3D road map data for accurately representing the physical environments. In this work, we propos…
This paper proposes a Time Division Multiple Access (TDMA) MAC slot allocation protocol with efficient bandwidth usage in wireless sensor networks and Internet of Things (IoTs). The developed protocol has two primary components: a Multi-Armed Bandits (MAB)-based slot allocation mechanism for collision free transmission, and a Decentralized Defragmented Slot Backshift (DDSB) operation for improving bandwidth usage efficiency. The proposed framework is decentralized in that each node finds its transmission schedule independently without the control of any centralized arbitrator. The developed me…
Increasingly, connected cars are becoming a decentralized data platform. With greater autonomy, they have growing needs for computation and perceiving the world around them through sensors. While todays generation of vehicles carry all the necessary sensor data and computation on board, we envision a future where vehicles can cooperate to increase their perception of the world beyond their immediate view, resulting in greater safety, coordination and more comfortable experience for their human occupants. In order for vehicles to obtain data, compute and other services from other vehicles or ro…
Huawei Technologies Duesseldorf GmbH（华为技术杜塞尔多夫有限公司）；Technische Universität Berlin（柏林工业大学）
Performance of vehicle-to-vehicle (V2V) communications depends highly on the employed scheduling approach. While centralized network schedulers offer high V2V communication reliability, their operation is conventionally restricted to areas with full cellular network coverage. In contrast, in out-of-cellular-coverage areas, comparatively inefficient distributed radio resource management is used. To exploit the benefits of the centralized approach for enhancing the reliability of V2V communications on roads lacking cellular coverage, we propose VRLS (Vehicular Reinforcement Learning Scheduler), …
Emerging distributed cloud architectures, e.g., fog and mobile edge computing, are playing an increasingly important role in the efficient delivery of real-time stream-processing applications (also referred to as augmented information services), such as industrial automation and metaverse experiences (e.g., extended reality, immersive gaming). While such applications require processed streams to be shared and simultaneously consumed by multiple users/devices, existing technologies lack efficient mechanisms to deal with their inherent multicast nature, leading to unnecessary traffic redundancy …
