Rapid prototyping and performance evaluation of ETSI MEC-based applications

Noferi, Alessandro; Nardini, Giovanni; Stea, Giovanni; Virdis, Antonio

doi:10.1016/j.simpat.2022.102700

Cited by 11 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simu5G allows one to simulate arbitrary 5G network layouts, including all the protocols from the application to the physical layer. Moreover, it includes a model of the ETSI MEC architecture, described in [27], allowing users to simulate MEC-based applications. Simu5G's MEC model includes the RNIS and LS, the latter being useful to support PlaaS.…”

Section: Validation and Performance Evaluationmentioning

confidence: 99%

“…Our simulator runs computations instantly -in simulated timebut allows one to insert computation delays at the end of such computations, to delay the response of a MEC App. These delays are computed based on the number of machine instructions of the computation, the MEC host CPU speed and the fraction of CPU allocated to the MEC App [27].…”

Section: ) Impact Of Computation Times Of the Controller Logicmentioning

confidence: 99%

“…In other words, we devise a service providing mechanisms for discovery, subscription, dynamic join/leave, etc., to run in an ETSI MEC framework. We describe an architecture, comprising placement, behavior and interaction of the various functions, that allows this service to be used by vehicles, and we provide a reference open-source implementation for the popular Simu5G simulator [1], [27], that researchers and practitioners can use, e.g., to test their own control logic in a lifelike environment, comprising both 3GPP-compliant 5G network access and an ETSI-compliant MEC architecture. We explicitly design our PlaaS framework so that it can run across different MEC systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Platooning-as-a-Service in a Multi-Operator ETSI MEC Environment

2023

Self Cite

View full text Add to dashboard Cite

Multi-access Edge Computing (MEC) is expected to support platooning of vehicles, by running the control logic that computes the acceleration values of the vehicles based on their position and speed. Connectivity between vehicles and the MEC system is likely to be realized through the mobile network. However, platoons will be composed of vehicles that are customers of different co-located mobile operators, hence -in all likelihood -will also be customers of different MEC systems. In this paper, we devise and evaluate an architectural framework that realizes Platooning-as-a-Service (PlaaS) in a multi-operator MEC environment, compliant with the ETSI MEC standard: we describe the entities involved and their interactions, we release an open-source proof-of-concept implementation for the popular Simu5G simulator, and we evaluate the effect of our framework -and especially its latencies -on platoon stability.

show abstract

Section: Validation and Performance Evaluationmentioning

confidence: 99%

Section: ) Impact Of Computation Times Of the Controller Logicmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Platooning-as-a-Service in a Multi-Operator ETSI MEC Environment

2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the network architecture and the traffic generation set, we could start testing the behavior of the MEC server by altering some of the simulation parameters. We experimented with some of the options mentioned by the authors in their thorough description of the MEC capabilities of Simu5G in [ 57 ]. Our experiments covered different cases of physical resources available on the server and the resources required by the app instances.…”

Section: Modeling and Simulationmentioning

confidence: 99%

“…We collected the response times for each sent CPM in each vehicle, our primary focus. Still, we also recorded the end-to-end network latency from the cars to the MEC app instances, a significant portion of the response time [ 57 ]. Results about the average end-to-end latency, which are also seen in Figure 9 , show that the network latency (calculated between source vehicles and corresponding processing MEC entities) experienced by the majority of the nodes in this particular scenario is around 12–15 ms with even the most extraordinary outlier below 50 ms.…”

Section: Modeling and Simulationmentioning

confidence: 99%

Implementation of MEC-Assisted Collective Perception in an Integrated Artery/Simu5G Simulation Framework

Kovács,

Bokor

2023

Sensors

View full text Add to dashboard Cite

Advanced vehicle-to-everything (V2X) safety applications must operate with ultra-low latency and be highly reliable. Therefore, they require sophisticated supporting technologies. This is especially true for cooperative applications, such as Collective Perception (CP), where a large amount of data constantly flows among vehicles and between vehicles and a network intelligence server. Both low and high-level support is needed for such an operation, meaning that various access technologies and other architectural elements also need to incorporate features enabling the effective use of V2X applications with strict requirements. The new 5G core architecture promises even more supporting technologies, like Multi-access Edge Computing (MEC). To test the performance of these technologies, an integrated framework for V2X simulations with 5G network elements is proposed in the form of combining Simu5G, a standalone 5G implementation, with the go-to V2X-simulator, Artery. As a first step toward a fully functional MEC-assisted CP Service, an extension to Simu5G’s edge implementation is introduced. The edge application is responsible for dispatching the Collective Perception Messages generated by the vehicles via the 5G connectivity so that a MEC server provided by the network can process incoming data. Simulation results prove the operability of the proposed integrated system and edge computing’s potential in assisting V2X scenarios.

show abstract

Edge computing in the loop simulation framework for automotive use cases evaluation

2023

View full text Add to dashboard Cite

Edge architectures provide local, decentralized services, enabling balancing network traffic and distributing hardware resources. Later, many new use cases can be implemented by combining the advantages of the edge computing concept with the services of 5G systems. One of the biggest beneficiaries of this could be the Vehicle-to-Cloud (V2C) technology, where it is necessary to efficiently process large amounts of data resulting from Vehicle-to-Everything communication (V2X) services. In specific use cases, this makes it possible to process sensor data collectively, enhanced by fusion, which promotes a more effective virtual representation of the real world. The effective implementation of these technologies is a complex task. One of the most important steps before tests on actual infrastructures with real vehicles is evaluating and validating edge cloud systems. We present a solution for this problem, the Cloud-in-the-Loop (CiL) simulation framework. It can orchestrate a real-size, telco-grade level, Kubernetes-based edge cloud infrastructure based on information gathered from a traffic simulator and performing fine-grained benchmarking and data collection. In addition to the performance analysis of the edge system, it also enables an in-depth examination of cloud-native applications serving complex automotive use cases. In this paper, we focus on presenting the developed framework and its capabilities by utilizing the system with implemented test applications, and give an example of testing QoS and QoE aspects of the edge cloud-based V2C concept.

show abstract

Rapid prototyping and performance evaluation of ETSI MEC-based applications

Cited by 11 publications

References 23 publications

Platooning-as-a-Service in a Multi-Operator ETSI MEC Environment

Platooning-as-a-Service in a Multi-Operator ETSI MEC Environment

Implementation of MEC-Assisted Collective Perception in an Integrated Artery/Simu5G Simulation Framework

Edge computing in the loop simulation framework for automotive use cases evaluation

Contact Info

Product

Resources

About