An integrated edge and Fog system for future communication networks

Kuo, Ping-Heng; Mourad, Alain; Lu, Chenguang; Berg, Miguel; Duquennoy, Simon; Chen, Yingyu; Hsu, Yi-Huai; Zabala, Aitor; Ferrari, Riccardo; González, Sergio; Li, Chi‐Yu; Chien, Hsu-Tung

doi:10.1109/wcncw.2018.8369023

Cited by 12 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal of the project is to deliver a convergent 5G multi-RAT access through an integrated virtualized edge and fog solution that is flexible, scalable, and interoperable with other domains including transport (fronthaul, backhaul), core and clouds. Some of the most recent literature provided by this project is: [142]…”

Section: ) Ran Coming From Several Vendorsmentioning

confidence: 99%

A Survey of the Functional Splits Proposed for 5G Mobile Crosshaul Networks

Larsen

Checko²,

Christiansen

2019

IEEE Commun. Surv. Tutorials

337

211

View full text Add to dashboard Cite

Pacing the way towards 5G has lead researchers and industry in the direction of centralized processing known from Cloud-Radio Access Networks (C-RAN). In C-RAN research, a variety of different functional splits is presented by different names and focusing on different directions. The functional split determines how many Base Station (BS) functions to leave locally, close to the user, with the benefit of relaxing fronthaul network bitrate and delay requirements, and how many functions to centralize with the possibility of achieving greater processing benefits. This work presents for the first time a comprehensive overview systematizing the different work directions for both research and industry, while providing a detailed description of each functional split option and an assessment of the advantages and disadvantages. This work gives an overview of where the most effort has been directed in terms of functional splits, and where there is room for further studies. The standardization currently taking place is also considered and mapped into the research directions. It is investigated how the fronthaul network will be affected by the choice of functional split, both in terms of bitrates and latency, and as the different functional splits provide different advantages and disadvantages, the option of flexible functional splits is also looked into.

show abstract

Section: ) Ran Coming From Several Vendorsmentioning

confidence: 99%

A Survey of the Functional Splits Proposed for 5G Mobile Crosshaul Networks

Larsen

Checko²,

Christiansen

2019

IEEE Commun. Surv. Tutorials

337

211

View full text Add to dashboard Cite

show abstract

“…For example, task assignment 1 which utilizes only fog to process three tasks, traffic is transmitted from UE to a fog link with flow length 1/𝜇 𝐿 1 , arrival rate 𝜆 in 𝐻 [1, 1], and 𝐶 𝑈𝐹 capacity in 𝑌 [1]. Traffic is then handled at fog node to process those tasks with 𝑉 [1,4] flow workload, 𝐻 [1,4] arrival rate, and 𝑌 [4] fog node capacity. Finally, we can determine the delay associated with task assignment 1 by adding the communication delay from UE to fog and the computation delay at that fog node.…”

Section: Delay Modelmentioning

confidence: 99%

“…While cloud computing provides rapid availability, good reliability, and nearly limitless capacity, fog and edge computing contribute mobility and performance enhancement. By combining these three systems and establishing a multi-tier architecture based on a cloud-edge-fog hierarchy as defined in [4], enables the effective handling of a variety of services with different characteristics while preserving availability and reliability [5].…”

Section: Introductionmentioning

confidence: 99%

Task Assignment and Capacity Allocation for ML-Based Intrusion Detection as a Service in a Multi-Tier Architecture

Lai

Sudyana

Lin

et al. 2023

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

Intrusion Detection Systems (IDS) play an important role in detecting network intrusions. Because intrusions have many variants and zero-day attacks, traditional signature-and anomaly-based IDS often fail to detect them. On the other hand, solutions based on Machine Learning (ML), have better capabilities for detecting variants. In this work 1 , we adopt an ML-based IDS which uses three in-sequence tasks, pre-processing, binary detection, and multi-class detection, with a multi-tier architecture with one-, two-, and three-tier architectural configurations. We then mapped three in-sequence tasks into these architectures, resulting in ten task assignments. We evaluated these with queueing theory to determine which tasks assignments were more appropriate for particular service providers. With simulated annealing, we obtained the computation capacity by allocating the total cost appropriate to each tier, based on the fixed parameter set with the objective of minimizing overall delay. These investigations showed that using only the edge and allocating all tasks to it gave the best performance. Furthermore, a two-tier architecture with edge and cloud components was also sufficient for IDS as a Service with the delay that was three times better than for other task assignments. Our results also indicate that more than 85% of the total capacity was allocated and spread across nodes in the lowest tier for pre-processing to reduce delays.

show abstract

“…Related research and investigation results are discussed below. In [ 29 ], MEC is regarded as one type of edge computing, while architectures such as Edge/Fog Computing are proposed. While there is a concept-based discussion, it does not refer to the players.…”

Section: Related Workmentioning

confidence: 99%

MEC/Cloud Orchestrator to Facilitate Private/Local Beyond 5G with MEC and Proof-of-Concept Implementation

Nakazato

Maruta

et al. 2022

Sensors

View full text Add to dashboard Cite

The emergence of 5G-IoT opens up unprecedented connectivity possibilities for new service use cases and players. Multi-access edge computing (MEC) is a crucial technology and enabler for Beyond 5G, supporting next-generation communications with service guarantees (e.g., ultra-low latency, high security) from an end-to-end (E2E) perspective. On the other hand, one notable advance is the platform that supports virtualization from RAN to applications. Deploying Radio Access Networks (RAN) and MEC, including third-party applications on virtualization platforms, and renting other equipment from legacy telecom operators will make it easier for new telecom operators, called Private/Local Telecom Operators, to join the ecosystem. Our preliminary studies have discussed the ecosystem for private and local telecom operators regarding business potential and revenue and provided numerical results. What remains is how Private/Local Telecom Operators can manage and deploy their MEC applications. In this paper, we designed the architecture for fully virtualized MEC 5G cellular networks with local use cases (e.g., stadiums, campuses). We propose an MEC/Cloud Orchestrator implementation for intelligent deployment selection. In addition, we provide implementation schemes in several cases held by either existing cloud owners or private and local operators. In order to verify the proposal’s feasibility, we designed the system level in E2E and constructed a Beyond 5G testbed at the Ōokayama Campus of the Tokyo Institute of Technology. Through proof-of-concept in the outdoor field, the proposed system’s feasibility is verified by E2E performance evaluation. The verification results prove that the proposed approach can reduce latency and provide a more stable throughput than conventional cloud services.

show abstract

An integrated edge and Fog system for future communication networks

Cited by 12 publications

References 4 publications

A Survey of the Functional Splits Proposed for 5G Mobile Crosshaul Networks

A Survey of the Functional Splits Proposed for 5G Mobile Crosshaul Networks

Task Assignment and Capacity Allocation for ML-Based Intrusion Detection as a Service in a Multi-Tier Architecture

MEC/Cloud Orchestrator to Facilitate Private/Local Beyond 5G with MEC and Proof-of-Concept Implementation

Contact Info

Product

Resources

About