Machine learning-Based traffic offloading in fog networks

Zaharia, George-Eduard; Şoşea, Tiberiu-Alex-Irinel; Ciobanu, Radu-Ioan; Dobre, Ciprian

doi:10.1016/j.simpat.2019.102045

Cited by 12 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An optimal machine learning algorithm that maximizes resource allocation and the arrival pattern of requests is an unanswered question [30]. Another unexplored paradigm is the handling of vast amount of data in a Wi-Fi environment both in delayed and non-delayed transmissions [31]. The optimization of Genetic algorithm to best suit varied architecture for differentiated data is still to be answered [31].…”

Section: Future Researchmentioning

confidence: 99%

“…Another unexplored paradigm is the handling of vast amount of data in a Wi-Fi environment both in delayed and non-delayed transmissions [31]. The optimization of Genetic algorithm to best suit varied architecture for differentiated data is still to be answered [31]. The debate of optimal resource allocation and management for energy conservation is still open [32].…”

Section: Future Researchmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Various Machine Learning Algorithms in Fog Computing

2021

IJATCSE

View full text Add to dashboard Cite

Internet of Things is the reality of the future. It encompasses a vast prototype. The applications are limitless and the research potential is huge. Several unanswered questions still stand in the way. One of these challenging questions is the Network layer implementation of IoT. Cloud offers one perspective solution. Cloud services face the down side of connectivity and latency. Fog computing, as a complementing technology for Cloud answers the issues of latency and connectivity in the Cloud. Being novel idea in itself, Fog computing offers promising future growth. A major concept in Fog networks is its ability to learn and adopt to changing environment. This ability of the Fog devices to self-learn and improve itself is the core of machine-learning. Hence, machine-learning algorithms occupy central place in visualizing robust and effective Fog networks. This paper presents a comparative study of various machine-learning algorithms and their applications in the Fog network. The paper also projects the undiscovered research paradigms and future directions

show abstract

Section: Future Researchmentioning

confidence: 99%

Section: Future Researchmentioning

confidence: 99%

A Comparative Study of Various Machine Learning Algorithms in Fog Computing

2021

IJATCSE

View full text Add to dashboard Cite

show abstract

“…In fact, training includes utilizing an algorithm to iteratively alter the power of the connections among the perceptrons, ensuring that the network absorbs to associate a specified input (the pixels of a picture) by the right label (cat or dog). When qualified, the deep net must preferably be capable of categorizing an input, which has not been obtained previously [23].…”

Section: 1mentioning

confidence: 99%

“…e neuron, then, transmits the data downstream to several other associated neurons in a system called "forward transfer." e last secret layer is connected to the output layer at the end of this phase, which has 1 neuron with each potential desired output [23]. e fundamental structure of NN is shown in Figure 3.…”

Section: Ml-driven Networkingmentioning

confidence: 99%

Selecting the Best Routing Traffic for Packets in LAN via Machine Learning to Achieve the Best Strategy

Zhang

Liao

2021

Complexity

View full text Add to dashboard Cite

The application of machine learning touches all activities of human behavior such as computer network and routing packets in LAN. In the field of our research here, emphasis was placed on extracting weights that would affect the speed of the network's response and finding the best path, such as the number of nodes in the path and the congestion on each path, in addition to the cache used for each node. Therefore, the use of these elements in building the neural network is worthy, as is the exploitation of the feed forwarding and the backpropagation in the neural network in order to reach the best prediction for the best path. The goal of the proposed neural network is to minimize the network time delay within the optimization of the packet paths being addressed in this study. The shortest path is considered as the key issue in routing algorithm that can be carried out with real time of path computations. Exploiting the gaps in previous studies, which are represented in the lack of training of the system and the inaccurate prediction as a result of not taking into consideration the hidden layers' feedback, leads to great performance. This study aims to suggest an efficient algorithm that could help in selecting the shortest path to improve the existing methods using weights derived from packet ID and to change neural network iteration simultaneously. In this study, the design of the efficient neural network of appropriate output is discussed in detail including the principles of the network. The findings of the study revealed that exploiting the power of computational system to demonstrate computer simulation is really effective. It is also shown that the system achieved good results when training the neural network system to get 2.4% time delay with 5 nodes in local LAN. Besides, the results showed that the major features of the proposed model will be able to run in real time and are also adaptive to change with path topology.

show abstract

“…The evaluation metrics are traffic offloading rate and transmission time from the NBA‐videos provider to the user. The proposed mechanism, called IDTO is compared with two benchmarks, that is, 2,5 called CATO and MLTO respectively. In addition, the cache size is set as 128 MB, λ = 20 m , 50 m , 80 m , the hugepage size of DPDK is set as 1024 MB, and the caching time for each content is set as 3mins.…”

Section: Evaluation Performancementioning

confidence: 99%

In‐network caching based NBA‐traffic offloading mechanism: A D2D communication mode

Wang¹

2020

Internet Technology Letters

View full text Add to dashboard Cite

This letter studies the NBA (National Basketball Association)‐traffic offload mechanism based on in‐network caching and D2D (Device‐to‐Device) communication mode, where the router is enabled with the caching ability and the information exchange is based on the direct communication between two D2D groups. Meanwhile, the DPDK (Data Plane Development Kit) is used to do segmentation for the NBA‐video, which can guarantee that all segments have the same size in order to improve the caching efficiency; the clustering analysis based on maximal tree is adopted to divided into some users into several different D2D groups. Furthermore, for each D2D group, the forwarding ability is quantified based on degree centrality and available bandwidth, and it is used to select the group head. The experimental results show that the proposed novel NBA‐traffic offloading mechanism is feasible and efficient.

show abstract

Machine learning-Based traffic offloading in fog networks

Cited by 12 publications

References 13 publications

A Comparative Study of Various Machine Learning Algorithms in Fog Computing

A Comparative Study of Various Machine Learning Algorithms in Fog Computing

Selecting the Best Routing Traffic for Packets in LAN via Machine Learning to Achieve the Best Strategy

In‐network caching based NBA‐traffic offloading mechanism: A D2D communication mode

Contact Info

Product

Resources

About