scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Application Synchronization Among Multiple MEC Servers in Connected Vehicle Scenarios

TL;DR: The problem of maintaining service continuity and synchronization of relevant data among multiple MEC servers to support vehicular applications is studied and two example applications with different requirements are studied, namely platoon management and shared world model, with promising results regarding their suitability for future implementation.
Abstract: Multi-access Edge Computing (MEC) is an emerging technology aimed to improve the communication latency and scalability e.g. of cloud-based connected vehicle applications and services. This is accomplished by bringing services closer to the end users, that is, to the network edge. In a high-mobility scenario, such as one involving vehicles, there will be a need for handovers between different MEC servers in order to maintain the required communication latency. Part of the application data may also be relevant to multiple MEC servers, covering overlapping geographical areas or being hosted by different network operators. This paper focuses on these situations and studies the problem of maintaining service continuity and synchronization of relevant data among multiple MEC servers to support vehicular applications. The analysis is conducted in the context of two example applications with different requirements, namely platoon management and shared world model, with promising results regarding their suitability for future implementation.
Citations
More filters
Journal ArticleDOI
TL;DR: A cost model is formulated as an optimization problem, the objective of which is to prompt the MEC server to judiciously allocate computing tasks to nearby MEC servers with the goal of achieving the minimal cost while the latency of tasks is guaranteed.
Abstract: Multiaccess edge computing (MEC) enables autonomous vehicles to handle time-critical and data-intensive computational tasks for emerging Internet-of-Vehicles (IoV) applications via computation offloading. However, a massive amount of data generated by colocated vehicles is typically redundant, introducing a critical issue due to limited network bandwidth. Moreover, on the edge server side, these computation-intensive tasks further impose severe pressure on the resource-finite MEC server, resulting in low-performance efficiency of applications. To solve these challenges, we model the data redundancy and collaborative task computing scheme to efficiently reduce the redundant data and utilize the idle resources in nearby MEC servers. First, the data redundancy problem is formulated as a set-covering problem according to the spatiotemporal coverage of captured images. Next, we exploit the submodular optimization technique to design an efficient algorithm to minimize the number of images transferred to the MEC servers without degrading the quality of IoV applications. To facilitate the task execution in the MEC server, we then propose a collaborative task computing scheme, where an MEC server intentionally encourages nearby resource-rich MEC servers to participate in a collaborative computing group. Accordingly, a cost model is formulated as an optimization problem, the objective of which is to prompt the MEC server to judiciously allocate computing tasks to nearby MEC servers with the goal of achieving the minimal cost while the latency of tasks is guaranteed. Experimental results show that the proposed scheme can efficiently mitigate data redundancy, conserve network bandwidth consumption, and achieve the lowest cost for processing tasks.

49 citations


Cites background from "Application Synchronization Among M..."

  • ...However, they may belong to different mobile operators [16], who are thus likely to refuse to form...

    [...]

  • ...Moreover, MEC servers may be deployed and maintained by different mobile operators [16]....

    [...]

Journal ArticleDOI
TL;DR: This work proposes a blockchain-enabled distributed NFV framework to reach consensus among multiple MANO systems where the computation tasks of the blockchain are processed with MEC.
Abstract: Distributed network function virtualization management and orchestration (NFV-MANO) offers a flexible way to manage and orchestrate diversified network services in large-scale Internet of vehicles (IoV). However, it is challenging to manage different services and resources in distributed NFV due to the difficulties of reliable message synchronization among multiple MANO systems. Recently, blockchain technology has emerged to solve the trust and security problems for the interconnections of multiple MANO systems. Moreover, multi-access edge computing (MEC) has become a prospective paradigm shift from the centralized cloud due to its advantages of completing tasks near users. In this work, we propose a blockchain-enabled distributed NFV framework to reach consensus among multiple MANO systems where the computation tasks of the blockchain are processed with MEC. The consensus procedures of MANO systems and blockchain nodes are explained in detail and the representation of the blockchain throughput is given. The blockchain throughput is the number of transactions a blockchain system can handle per second, which is an important evaluation indicator for the performance of a blockchain system. We make decisions for the primary node selection, the MANO system selection and the edge server selection for reaching consensus. Moreover, the blockchain throughput, the processing delay of computation tasks of blockchain and operational costs are jointly considered in the problem formulation. A dueling deep reinforcement learning approach is applied to solve this problem. Simulation results show the effectiveness of the proposed scheme.

27 citations


Cites methods from "Application Synchronization Among M..."

  • ...In [10], a synchronizing scheme for related data of a vehicular application among multiple MEC servers is proposed to maintain service continuity....

    [...]

Proceedings ArticleDOI
20 May 2019
TL;DR: 5G-based cellular vehicle-to-everything (C-V2X) collaborative sensing based on the results of trials conducted at test sites in China and Finland indicates that the round-trip is stable (< 60 ms) even when exchanging 1 MB/s between vehicles.
Abstract: Automated driving is expected to improve road safety and traffic efficiency. Host vehicle onboard sensing systems typically sense the environment up to 250 m ahead of the vehicle. Today's LiDARs can see approximately 120 m, and recognition of small objects, such as animals or dropped cargo, however, today reliably drop when range is more than 50m. Connected driving adds an electronic horizon to the onboard sensing system which could extend the sensing range and greatly improves the efficiency. Therefore, collaborative sensing in which the vehicle exchanges not only status messages but also real data has recently been intensively discussed. Current cellular 3G/4G networks have enhanced the downlink capacity for sharing large data blocks. However, uplink is limited and therefore vehicles are unable to share point clouds of what they see in front. This article investigates the opportunities of 5G-based cellular vehicle-to-everything (C-V2X) collaborative sensing based on the results of trials conducted at test sites in China and Finland. The results indicate that the round-trip is stable (< 60 ms) even when exchanging 1 MB/s between vehicles. Finally, the automotive industry perspective is taken into account in identifying and prioritizing potential use case scenarios for utilizing 5G based connected driving applications.

16 citations


Cites background from "Application Synchronization Among M..."

  • ...Analysis of the whole chain, from subscription to the network, communication and computing time provides valuable information for optimizing the balance between in-vehicle and mobile-edge computing (MEC) platform side data processing [1]....

    [...]

Journal ArticleDOI
TL;DR: This paper studies the optimization of communication, computation and energy resource to minimize the energy consumption in the mobile terminal, where some superior technologies are included, such as Full-Duplex (FD), Simultaneous Wireless Information and Power Transfer (SWIPT), Mobile-Edge Computing (MEC) and Multi-input Multi-output (MIMO).
Abstract: That alleviating the heavy computing task, improving spectral efficiency and prolonging battery lifetime have been the key design challenges in Internet of Things (IoT) and intelligent connected vehicles (ICV). This paper studies the optimization of communication, computation and energy resource to minimize the energy consumption in the mobile terminal, where some superior technologies are included, such as Full-Duplex (FD), Simultaneous Wireless Information and Power Transfer (SWIPT), Mobile-Edge Computing (MEC) and Multi-input Multi-output (MIMO). In this model, the MEC-assisted Base station (BS) works in FD mode, then it can transmit and receive signals in the same frequency and time. Moreover, the mobile devices offload some computation tasks to the BS and complete local computations at the same time. Besides, the mobile device harvests the energy from the BS to support its energy consumption. And, our target is to minimize the energy consumption of mobile devices. Since the problem is non-convex, we propose an iterative solving algorithm including a multi-step optimization. First, we obtain the closed-form solution of the CPU frequency. And then, we transform the remain problem into a convex one to solve it by the interior point algorithm. Finally, we obtain the approximate solution by multiple iterations. Simulation results show that the proposed algorithm is superior to the compared schemes.

9 citations


Cites background from "Application Synchronization Among M..."

  • ...INTRODUCTION With the explosion of data traffic [1], mobile devices, such as ICVs in the vehicular communication network, need to handlemore computation tasks, although their computation capability are insufficient [2], [3]....

    [...]

Proceedings ArticleDOI
01 Nov 2020
TL;DR: A high-level architecture for MEC-assisted platooning control is proposed as a virtualized application running on an edge server, and aligned with the European Telecommunications Standard Institute (ETSI) MEC reference framework.
Abstract: The Multi-access Edge Computing (MEC) paradigm allows several automotive applications to be offloaded from the vehicles to the edge. Besides a higher computation capability, compared to the on-board vehicle, and the shorter latency, compared to the remote cloud, the edge offers additional (context) information that is not directly available at the vehicle, e.g., via data fusion from multiple sources. In this paper we propose a high-level architecture for MEC-assisted platooning control. Within the architecture, the longitudinal controller is conceived as a virtualized application running on an edge server, and aligned with the European Telecommunications Standard Institute (ETSI) MEC reference framework. Performance assessment conducted through a realistic simulation framework, coupling a vehicular mobility simulator and Docker containers, showcases the feasibility and effectiveness of our proposal.

7 citations


Cites background or result from "Application Synchronization Among M..."

  • ...Notwithstanding, the literature on MEC-assisted platooning is still on its infancy, and focuses either on theoretical analysis [3] or addresses communication aspects [4], whereas less attention has been devoted to the actual deployment of the platoon controller as a virtualized application at the edge....

    [...]

  • ...The study in [3] presents a platoon management application assisting or controlling the platoons based on enhanced situational awareness available at a MEC server....

    [...]

  • ...This work is aimed to complement and extend the existing literature [3], [4]....

    [...]

References
More filters
Journal ArticleDOI
TL;DR: This paper analyzes the MEC reference architecture and main deployment scenarios, which offer multi-tenancy support for application developers, content providers, and third parties, and elaborates further on open research challenges.
Abstract: Multi-access edge computing (MEC) is an emerging ecosystem, which aims at converging telecommunication and IT services, providing a cloud computing platform at the edge of the radio access network MEC offers storage and computational resources at the edge, reducing latency for mobile end users and utilizing more efficiently the mobile backhaul and core networks This paper introduces a survey on MEC and focuses on the fundamental key enabling technologies It elaborates MEC orchestration considering both individual services and a network of MEC platforms supporting mobility, bringing light into the different orchestration deployment options In addition, this paper analyzes the MEC reference architecture and main deployment scenarios, which offer multi-tenancy support for application developers, content providers, and third parties Finally, this paper overviews the current standardization activities and elaborates further on open research challenges

1,351 citations


"Application Synchronization Among M..." refers background in this paper

  • ...The approach is different from the traditional monolith application, built as a single autonomous unit, and is thus seen as a potential approach for implementing MEC applications and other future 5G services [7]–[10]....

    [...]

Journal Article
TL;DR: The common principles behind this approach to micro-services architecture and implementation patterns are discussed, its advantages and disadvantages as well as its possible usage in M2M applications.
Abstract: This paper provides an overview of micro-services architecture and implementation patterns. It continues our series of publications about M2M systems, existing and upcoming system software platforms for M2M applications. A micro-service is a lightweight and independent service that performs single functions and collaborates with other similar services using a well-defined interface. We would like to discuss the common principles behind this approach, its advantages and disadvantages as well as its possible usage in M2M applications.

249 citations


"Application Synchronization Among M..." refers background in this paper

  • ...The approach is different from the traditional monolith application, built as a single autonomous unit, and is thus seen as a potential approach for implementing MEC applications and other future 5G services [7]–[10]....

    [...]

  • ...It is also a key enabler of the microservice architecture [6], [7], which is a means of developing software applications as a suite of independently deployable, small, modular services, in which each service runs a unique process and communicates through a well-defined, lightweight mechanism such as REST....

    [...]

Journal ArticleDOI
01 Apr 2018
TL;DR: This paper investigates a novel approach to support service provisioning in dynamic MEC environments by leveraging the potential of lightweight container‐based virtualization techniques and presents a framework where proactive service replication for stateless applications is exploited to drastically reduce the time of service migration between different cloudlets and to meet the latency requirements.
Abstract: Mobile Edge Computing (MEC) will play a key role in next-generation mobile networks to extend the range of supported delay-sensitive applications. Furthermore, an increasing attention is paid to provide user-centric services, to better address the strict requirements of novel immersive applications. In this scenario, MEC solutions need to efficiently cope with user mobility, which requires fast relocation of service instances to guarantee the desired Quality of Experience. However, service migration is still an open issue, especially for resource-constrained edge nodes interconnected by high-latency and low-bandwidth links. In this paper, by leveraging the potential of lightweight container-based virtualization techniques, we investigate a novel approach to support service provisioning in dynamic MEC environments. In particular, we present a framework where proactive service replication for stateless applications is exploited to drastically reduce the time of service migration between different cloudlets and to meet the latency requirements. The performance evaluation shows promising results of our approach with respect to classic reactive service migration.

85 citations


"Application Synchronization Among M..." refers background in this paper

  • ...That is, if the application is stateful or stateless [6]....

    [...]

  • ...It is also a key enabler of the microservice architecture [6], [7], which is a means of developing software applications as a suite of independently deployable, small, modular services, in which each service runs a unique process and communicates through a well-defined, lightweight mechanism such as REST....

    [...]

  • ...However, in the case of a storage-dependent application, the system must support data synchronization, managing the periodical propagation of data storage, in order to maintain data volume coherency and thus ensure session continuity despite migration [6]....

    [...]

  • ...Especially lightweight virtualization technologies, such as Docker, are seen as potential platforms for deploying applications in MEC [6]....

    [...]

  • ...A management architecture and replicabased approach for ultra-short latency service provisioning in mobile MEC environments is proposed in [6]....

    [...]

Proceedings ArticleDOI
19 Mar 2017
TL;DR: A time-predicted handover mechanism for vehicles is further developed by leveraging available road information and the enhanced capacity of the MEC server to satisfy the demand for high mobility and reliability.
Abstract: The evolving cellular network with centric-deployed Cloud Centers has greatly improved the mobile user experience. However, the advent of vehicular networks with a wide variety of new services and devices changes the existing cellular network landscape, and the cellular-based vehicular networks are confronted with serious challenge in terms of latency reduction and flexible service delivery. In this paper, we propose to deploy the specific server, called Mobile-Edge Computing (MEC) server, within the Radio Access Network, and allow them to connect with a set of base stations alongside roads, so as to provide flexible vehicle-related service and efficiently control the radio network. Then, the vision of MEC- assisted slicing network and a traffic scheduling policy are presented to promote network customization. As an instance of the MEC-based tailored network service, a time-predicted handover mechanism for vehicles is further developed by leveraging available road information and the enhanced capacity of the MEC server to satisfy the demand for high mobility and reliability.

72 citations

Proceedings ArticleDOI
23 May 2016
TL;DR: A 5GLow latency network slice that offers 5G low latency services from the closest network edge node is introduced that verifies that this can be achieved by re-evaluating the optimality of the mobility anchor during each handover and executing a gateway relocation procedure when needed.
Abstract: The 5G vision is to create a network that outperforms the current mobile networks in terms of flexibility, performance and use cases. This raises the requirements of the network to a totally new level. In order to achieve the latency goals the related applications and network functions need to be placed into the network edge. Full mobility support requires also enhancements to the current mobility management procedures. These include a gateway selection algorithm that is topology aware, handover procedures that are able to switch the user plane as quickly as possible and a seamless gateway relocation procedure. The low latency applications should also be able to manage the state between the application instances in different edge nodes. In this paper we introduce a 5G low latency network slice that offers 5G low latency services from the closest network edge node. Our prototype implementation verifies that this can be achieved by re-evaluating the optimality of the mobility anchor during each handover and executing a gateway relocation procedure when needed.

27 citations


"Application Synchronization Among M..." refers background in this paper

  • ...For example, the optimization of low-latency LTE/5G services within a MEC system is studied in [4]....

    [...]

  • ...The handover process should include the selection of the optimal MEC server [4] and ensure service continuity despite the server change....

    [...]