AI-Based Resource Management in Beyond 5G Cloud Native Environment

Bagaa, Miloud; Pöyhönen, Petteri; Taleb, Tarik; Flinck, Hannu

doi:10.1109/mnet.011.2000392

Cited by 41 publications

(26 citation statements)

References 13 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML plays a vital role in creating self-managed IoT devices, including heterogeneous and distributed components of different environments [ 65 , 66 ]. Moreover, automated ML is used to solve real-world applications' massive IoT data problems [ 67 ].…”

Section: Machine Learning For Iotmentioning

confidence: 99%

Machine Learning for Smart Environments in B5G Networks: Connectivity and QoS

Alsamhi

Almalki

Al-Dois

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The number of Internet of Things (IoT) devices to be connected via the Internet is overgrowing. The heterogeneity and complexity of the IoT in terms of dynamism and uncertainty complicate this landscape dramatically and introduce vulnerabilities. Intelligent management of IoT is required to maintain connectivity, improve Quality of Service (QoS), and reduce energy consumption in real time within dynamic environments. Machine Learning (ML) plays a pivotal role in QoS enhancement, connectivity, and provisioning of smart applications. Therefore, this survey focuses on the use of ML for enhancing IoT applications. We also provide an in-depth overview of the variety of IoT applications that can be enhanced using ML, such as smart cities, smart homes, and smart healthcare. For each application, we introduce the advantages of using ML. Finally, we shed light on ML challenges for future IoT research, and we review the current literature based on existing works.

show abstract

Section: Machine Learning For Iotmentioning

confidence: 99%

Machine Learning for Smart Environments in B5G Networks: Connectivity and QoS

Alsamhi

Almalki

Al-Dois

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…In order to offer the desired connectivity, the platform should be able to appropriately control underlying communication resources to satisfy different services, often requiring expert knowledge to do so. Even with expert knowledge to control the communication resources, to satisfy the computation demanding nature of AI applications, how to collaborate such platform to work with edge computing is still unsolved in literature [5]- [7]. In this paper, we propose zero-touch network to serve smart factory scenarios as illustrated in Fig.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, to realize next-generation networking system design, serverless framework [8] and open radio access network (O-RAN) structure are both considered in the platform implementations. As a result, promising technologies, such as AL-enabled networking and edge computing [6], [7], [9], can be deployed in the proposed platform effortlessly to enjoy network automation and reduced latency to further facilitate AI applications in both training and inferring stage.…”

Section: Introductionmentioning

confidence: 99%

Zero-Touch Network on Industrial IoT: An End-to-End Machine Learning Approach

Lin¹,

Lin²,

Chen³

2022

Preprint

View full text Add to dashboard Cite

Industry 4.0-enabled smart factory is expected to realize the next revolution for manufacturers. Although artificial intelligence (AI) technologies have improved productivity, current use cases belong to small-scale and single-task operations. To unbound the potential of smart factory, this paper develops zero-touch network systems for intelligent manufacturing and facilitates distributed AI applications in both training and inferring stages in a large-scale manner. The open radio access network (O-RAN) architecture is first introduced for the zerotouch platform to enable globally controlling communications and computation infrastructure capability in the field. The designed serverless framework allows intelligent and efficient learning assignments and resource allocations. Hence, requested learning tasks can be assigned to appropriate robots, and the underlying infrastructure can be used to support the learning tasks without expert knowledge. Moreover, due to the proposed network system's flexibility, powerful AI-enabled networking algorithms can be utilized to ensure service-level agreements and superior performances for factory workloads. Finally, three open research directions of backward compatibility, end-to-end enhancements, and cybersecurity are discussed for zero-touch smart factory.

show abstract

“…T HE onset of the Artificial Intelligence (AI) and Deep Learning (DL) era has led to a recent shift in computation from hand-encoded algorithms to data-driven solutions [1]. One such impact of DL is on resource management in distributed computational paradigms [2], [3]. The most popular such paradigm, cloud computing, harnesses the data processing capacities of multiple devices and provides services at scale with high Quality of Service (QoS).…”

Section: Introductionmentioning

confidence: 99%

MetaNet: Automated Dynamic Selection of Scheduling Policies in Cloud Environments

Tuli¹,

Casale²,

Jennings³

2022

Preprint

View full text Add to dashboard Cite

Task scheduling is a well-studied problem in the context of optimizing the Quality of Service (QoS) of cloud computing environments. In order to sustain the rapid growth of computational demands, one of the most important QoS metrics for cloud schedulers is the execution cost. In this regard, several data-driven deep neural networks (DNNs) based schedulers have been proposed in recent years to allow scalable and efficient resource management in dynamic workload settings. However, optimal scheduling frequently relies on sophisticated DNNs with high computational needs implying higher execution costs. Further, even in non-stationary environments, sophisticated schedulers might not always be required and we could briefly rely on low-cost schedulers in the interest of cost-efficiency. Therefore, this work aims to solve the non-trivial meta problem of online dynamic selection of a scheduling policy using a surrogate model called MetaNet. Unlike traditional solutions with a fixed scheduling policy, MetaNet on-the-fly chooses a scheduler from a large set of DNN based methods to optimize task scheduling and execution costs in tandem. Compared to state-of-the-art DNN schedulers, this allows for improvement in execution costs, energy consumption, response time and service level agreement violations by up to 11, 43, 8 and 13 percent, respectively.

show abstract

AI-Based Resource Management in Beyond 5G Cloud Native Environment

Cited by 41 publications

References 13 publications

Machine Learning for Smart Environments in B5G Networks: Connectivity and QoS

Machine Learning for Smart Environments in B5G Networks: Connectivity and QoS

Zero-Touch Network on Industrial IoT: An End-to-End Machine Learning Approach

MetaNet: Automated Dynamic Selection of Scheduling Policies in Cloud Environments

Contact Info

Product

Resources

About