A Survey on Offloading in Federated Cloud-Edge-Fog Systems with Traditional Optimization and Machine Learning

Kar, Binayak; Yahya, Widhi; Lin, Ying-Dar; Ali, Syed Asad

doi:10.48550/arxiv.2202.10628

Cited by 5 publications

(7 citation statements)

References 118 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fog Federation is an emerging paradigm for flexibility and scalability in next-generation communication [149]. Fog computing leverages several technologies limitations such as IoTs [150], UAVs [151], Vehicular networks [152], etc.…”

Section: B Sdn Enabled Fog Federation For Interference Mitigationmentioning

confidence: 99%

Routing-Based Interference Mitigation in SDN Enabled Beyond 5G Communication Networks: A Comprehensive Survey

et al. 2023

View full text Add to dashboard Cite

The outright aim of Beyond Fifth Generation (B5G) communication is to bring a revolution in Quality of Service (QoS) through enhanced Mobile Broadband (eMBB), Ultra-Reliable Low Latency Communication (URLLC), and massive Machine Type Communication (mMTC). Thereby, due to this massive expansion in the communication paradigm, interference is bound to surface unexpected challenges in the wireless domain. Thus, interference mitigation is a foundational aim in the research paraphernalia of B5G communication. Presently, Software Defined Networking (SDN) is emerging to empower wireless communication with centralized routing-based interference mitigation. With this premise, we aim to present a focused review on SDN-based interference mitigation in wireless communication. Initially, we discuss current research horizon in the subject domain and briefly explore literature for routing-based interference mitigation. Thereby, we analyze the potential of SDN through evaluation of existing solutions for interference mitigation in B5G communication. We conclude our survey by highlighting prominent future research directions in SDN-based interference mitigation.

show abstract

Section: B Sdn Enabled Fog Federation For Interference Mitigationmentioning

confidence: 99%

Routing-Based Interference Mitigation in SDN Enabled Beyond 5G Communication Networks: A Comprehensive Survey

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Therefore, the offloading location is crucial because it determines the algorithms to be performed [60]. Such offloading is required when a service provider's assigned task exceeds its processing capacity, and must be transferred to another service provider with adequate computing power [6]. Offloading can be done in three different ways [6]: horizontally, vertically, or in a hybrid topology.…”

Section: Offloading Directionmentioning

confidence: 99%

“…To satisfy the intensive computational demands and stringent latency requirements of such applications, fog computing has been developed as a potential solution for transferring storage, networking, and processing abilities to the edge of a network [5]. The primary objective of fog computing is to bring cloud-like services to the network edge to optimize the performance of the system in terms of service latency, network bandwidth, resource utilization, and workload balancing [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Offloading Mechanisms Based on Reinforcement Learning and Deep Learning Algorithms in the Fog Computing Environment

Abdulazeez

Askar

2023

IEEE Access

View full text Add to dashboard Cite

Fog computing has emerged as a computing paradigm for resource-restricted Internet of things (IoT) devices to support time-sensitive and computationally intensive applications. Offloading can be utilized to transfer resource-intensive tasks from resource-limited end devices to a resource-rich fog or cloud layer to reduce end-to-end latency and enhance the performance of the system. However, this advantage is still challenging to achieve in systems with a high request rate because it leads to long queues of tasks in fog nodes and reveals inefficiencies in terms of delays. In this regard, reinforcement learning (RL) is a well-known method for addressing such decision-making issues. However, in large-scale wireless networks, both action and state spaces are complex and extremely extensive. Consequently, reinforcement learning techniques may not be able to identify an efficient strategy within an acceptable time frame. Hence, deep reinforcement learning (DRL) was developed to integrate RL and deep learning (DL) to address this problem. This paper presents a systematic analysis of using RL or DRL algorithms to address offloadingrelated issues in fog computing. First, the taxonomy of fog computing offloading mechanisms based on RL and DRL algorithms was divided into three major categories: value-based, policy-based, and hybridbased algorithms. These categories were then compared based on important features, including offloading problem formulation, utilized techniques, performance metrics, evaluation tools, case studies, their strengths and drawbacks, offloading directions, offloading mode, SDN-based architecture, and offloading decisions. Finally, the future research directions and open issues are discussed thoroughly.INDEX TERMS Fog computing, Internet of Things (IoT), offloading, reinforcement learning, deep reinforcement learning.

show abstract

“…The last level is most commonly referred to as the device level. The terminology may be sometimes confusing since some authors refer to it as edge level [34] (in contrast to the fog level above), or fog level [17] (in contrast to the edge level above). This level contains a large variety of end devices, from the devices running full-fledged operating systems, such as smartphones or laptops, to robots running on real-time operating systems, to network-connected home appliances, to onepurpose smart sensors, such as temperature sensors or cameras.…”

Section: Main Elements Of the Edge-cloud Continuummentioning

confidence: 99%

Towards Characterization of Edge-Cloud Continuum

Khalyeyev

Bureš

Hnětynka

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Internet of Things and cloud computing are two technological paradigms that reached widespread adoption in recent years. These paradigms are complementary: IoT applications often rely on the computational resources of the cloud to process the data generated by IoT devices. The highly distributed nature of IoT applications and the giant amounts of data involved led to significant parts of computation being moved from the centralized cloud to the edge of the network. This gave rise to new hybrid paradigms, such as edge-cloud computing and fog computing. Recent advances in IoT hardware, combined with the continued increase in complexity and variability of the edge-cloud environment, led to an emergence of a new vision of edge-cloud continuum: the next step of integration between the IoT and the cloud, where software components can seamlessly move between the levels of computational hierarchy. However, as this concept is very new, there is still no established view of what exactly it entails. Several views on the future edge-cloud continuum have been proposed, each with its own set of requirements and expected characteristics. In order to move the discussion of this concept forward, these views need to be put into a coherent picture. In this paper, we provide a review and generalization of the existing literature on edge-cloud continuum, point out its expected features, and discuss the challenges that need to be addressed in order to bring about this envisioned environment for the next generation of smart distributed applications.

show abstract

A Survey on Offloading in Federated Cloud-Edge-Fog Systems with Traditional Optimization and Machine Learning

Cited by 5 publications

References 118 publications

Routing-Based Interference Mitigation in SDN Enabled Beyond 5G Communication Networks: A Comprehensive Survey

Routing-Based Interference Mitigation in SDN Enabled Beyond 5G Communication Networks: A Comprehensive Survey

Offloading Mechanisms Based on Reinforcement Learning and Deep Learning Algorithms in the Fog Computing Environment

Towards Characterization of Edge-Cloud Continuum

Contact Info

Product

Resources

About