Adaptive Differentiated Edge Caching with Machine Learning for V2X Communication

Varanasi, Vinayaka Shashank; Chilukuri, Shanti

doi:10.1109/comsnets.2019.8711328

Cited by 19 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the successor of node 159 can be node 200 (there are no nodes with IDs between 159 and 200), which means that node 200 has a predecessor the node 159 [ 19 , 20 ].…”

Section: The Proposed Systemmentioning

confidence: 99%

See 1 more Smart Citation

A Blockchain-Based Verifiable User Data Access Control Policy for Secured Cloud Data Storage

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Adding the adequate level of security of information systems dealing with sensitive data, privacy, or defense systems involves some form of access control. The audits performed are dealing with the determination of the allowed activities of the legal users, when attempting to access resources of the system. Usually, full access is provided after the user has been successfully authenticated through an authentication mechanism (e.g., password), while the corresponding authorization control is based on the confidentiality level of the respective resources and the authorization level assigned to each user. A very important diversification occurring in modern digital technologies is related to the identification based on blockchain technology, which is presented as a public, distributed data series, unable to modify its history and grouped in time-numbered blocks. In this work, a blockchain-based verifiable user data access control policy for secured cloud data storage is suggested for a version associated with big data in health care. It is an innovative system of applying classified access policies to secure resources in the cloud, which operates based on blockchain technology. System evaluation is carried out by studying a case in its resilience to Eclipse attack under different malicious user capabilities for routing table poisoning.

show abstract

“…For example, the successor of node 159 can be node 200 (there are no nodes with IDs between 159 and 200), which means that node 200 has a predecessor the node 159 [ 19 , 20 ].…”

Section: The Proposed Systemmentioning

confidence: 99%

“…We alter a variable called nonce every time we want to change the hash result, usually by incrementing it by one. The likelihood of finding a nonce n for a given message (msg) such that H = SHA2562(msg|| n ) is less than or equal to the target T is [ 16 , 20 ]

…”

Section: The Proposed Systemmentioning

confidence: 99%

A Blockchain-Based Verifiable User Data Access Control Policy for Secured Cloud Data Storage

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Edge computation offloading can provide a significant boost to the overall QoE by optimizing all the KPIs due to much lower network load. A few works considered machine learning based content caching schemes using K-nearest neighbours [98], kernel ridge regression [99], bayesian learning [100], Collaborative filtering [101], but these traditional machine learning approaches fail to capture the real-time dynamics of content popularity at different locations and preferences among different users. However, in a study [102], it was shown that a neural network outperforms traditional machine learning approaches for edge caching whenever the number of input features is high and communication range and file sizes are large.…”

Section: E Computation Offloading At the Edgementioning

confidence: 99%

Federated learning and next generation wireless communications: A survey on bidirectional relationship

Shome¹,

Waqar²,

Khan³

2021

Preprint

View full text Add to dashboard Cite

In order to meet the extremely heterogeneous requirements of the next generation wireless communication networks, research community is increasingly dependent on using machine learning solutions for real-time decision-making and radio resource management. Traditional machine learning employs fully centralized architecture in which the entire training data is collected at one node e.g., cloud server, that significantly increases the communication overheads and also raises severe privacy concerns. Towards this end, a distributed machine learning paradigm termed as Federated learning (FL) has been proposed recently. In FL, each participating edge device trains its local model by using its own training data. Then, via the wireless channels the weights or parameters of the locally trained models are sent to the central PS, that aggregates them and updates the global model. On one hand, FL plays an important role for optimizing the resources of wireless communication networks, on the other hand, wireless communications is crucial for FL. Thus, a 'bidirectional' relationship exists between FL and wireless communications. Although FL is an emerging concept, many publications have already been published in the domain of FL and its applications for next generation wireless networks. Nevertheless, we noticed that none of the works have highlighted the bidirectional relationship between FL and wireless communications. Therefore, the purpose of this survey paper is to bridge this gap in literature by providing a timely and comprehensive discussion on the interdependency between FL and wireless communications.

show abstract

“…Follow-up research utilized this technology in the context of connected vehicles as well, namely Cellular Vehicle-to-Everything (C-V2X) communications [5]- [10]. In C-V2X technology, vehicles with the assistance of cellular infrastructure, collaborate to offload Vehicleto-Infrastructure (V2I) traffic using direct Vehicle-to-Vehicle (V2V) links [5], reduce retrieve time [6], [7], improve bandwidth efficiency and enhance data service performance [8], and improve overall service quality and delivery rate by proactively placing relevant data in vehicles' storage [9], [10]. Another technology for 5G evolution is Full-Duplex (FD) radios, which allows simultaneous transmission and reception on the same time/frequency resources [11].…”

Section: Introduction Fmentioning

confidence: 99%

Probabilistic Analysis of Operating Modes in Cache-Enabled Full-Duplex D2D Networks

Naslcheraghi¹,

Wette²,

Sansò³

2021

Preprint

View full text Add to dashboard Cite

With the extensive acquisition of various mobile applications, cellular networks are facing challenges due to exponentially growing demand for high data rate, which causes a great burden on mobile core networks and backhaul links. Cache-enabled Device-to-Device (D2D) communication, which is recognized as one of the key enablers of the fifth generation (5G) cellular network, is a promising solution to alleviate this problem. However, conventional half-duplex (HD) communication may not be sufficient to provide fast enough content delivery over D2D links in order to meet strict latency targets of emerging D2D applications. In-band full-duplex (FD), with its capability of allowing simultaneous transmission and reception, can provide more content delivery opportunities, thus resulting improved spectral efficiency and latency reduction. However, given the random nature of the cached contents in user devices and users' random requests, it is unlikely to consider all involving nodes in content exchange collaborations as a pure HD or FD network. In this paper, we aim to analyze the caching perspective of a finite network of D2D nodes in which each node is endowed with FD capability and utilize a more realistic caching policy. We model and analyze all possible operating modes for an arbitrary device, which we compute the probability of occurrence of each mode along with the Probability Mass Functions (PMFs) of nodes that are operating in all possible modes. Our analysis concretely quantize all possible outcomes that strongly depend on the random nature of the caching parameters, yielding to have an accurate insight on the caching performance and all possible outcomes of the cache-enabled FD-D2D network.

show abstract

Adaptive Differentiated Edge Caching with Machine Learning for V2X Communication

Cited by 19 publications

References 12 publications

A Blockchain-Based Verifiable User Data Access Control Policy for Secured Cloud Data Storage

A Blockchain-Based Verifiable User Data Access Control Policy for Secured Cloud Data Storage

Federated learning and next generation wireless communications: A survey on bidirectional relationship

Probabilistic Analysis of Operating Modes in Cache-Enabled Full-Duplex D2D Networks

Contact Info

Product

Resources

About