CaR-PLive: Cloud-assisted reinforcement learning based P2P live video streaming: a hybrid approach

Sina, Majid; Dehghan, Mehdi; Rahmani, Amir Masoud

doi:10.1007/s11042-019-08102-1

Cited by 8 publications

(3 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The predicted QoS can be used to choose a neighbor peer. Reference [26] uses reinforcement learning in a cloud-assisted P2P streaming system. The goal of using machine learning is to restrict the cloud rental cost according to a desired QoS level.…”

Section: Related Workmentioning

confidence: 99%

Behavior Dissection of NGWN Live Audio and Video Streaming Users with Enhanced and Efficient Modelling

Ali

Ullah

Ahmed

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Peer-to-peer (P2P) live video streaming is an application-level approach providing ease of deployment with low cost as compared to the IP multicast and client/server (C/S) architecture. These systems solely rely on end-hosts to disseminate the content; therefore, their performance largely banks on end-hosts, called peers. Since peers themselves are controlled by users, users’ activities become activities of peers. In such a network, the highly dynamic behavior of users impacts the network performance. Therefore, for performance improvement, a thorough understanding of user behavior is crucial. To explore and understand user behavior, numerous studies have been carried out. However, user behavior is complex, having several elements with dependency relationships, which make it difficult for a single measurement study to represent it comprehensively. Therefore, this work takes a two-step approach. Firstly, it collects existing measurement studies and analyzes, compares, and contrasts them to extract user behavior metrics and their relationships from them. Secondly, in light of the observations gained, this research analyzes traces of user behavior collected from an operational system. Such an outcome is useful, on one hand, for user behavior modelling towards performance improvement in NGWN, and on the other hand, it provides insights for further measurements and analysis.

show abstract

Section: Related Workmentioning

confidence: 99%

Behavior Dissection of NGWN Live Audio and Video Streaming Users with Enhanced and Efficient Modelling

Ali

Ullah

Ahmed

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…The work proposed in the CaR-PLive network [22] combines the advantages of P2P networks cloud computing to design an effective cloud-based P2P live video streaming algorithm. The algorithm cloud-assisted reenforcement learning with P2P networks for live video streaming (CaR-PLive) uses cloud storage services (CSSs) to store the P2P data and then broadcasts this data with the help of the content delivery network (CDN).…”

Section: 7mentioning

confidence: 99%

Live Streaming Architectures for Video Data: A Review

Ginimav¹,

Prasad²,

Gowrishankar³

2020

JISMAC

View full text Add to dashboard Cite

Video communication has become a crucial part of our everyday lives due to its ease of use and applicability. Also, the demand for video streaming services has grown exponentially due to the recent Covid19 situation. Over the years, researchers have formulated different algorithms and architectures for effective video streaming. Due to the presence of a large variety of algorithms, system designers are often unable to decide the most optimum video streaming architectures for effective system design. In this work, some of the most recent and effective streaming architectures and algorithms are discussed along with their performance metrics. This will assist readers in deciding the most optimum algorithms and architectures for their application. Along with the algorithmic comparisons, this text also recommends certain improvements in the reviewed algorithms for further improving their performance.

show abstract

“…The agent takes actions and observes the outcome of these actions. RL has been applied successfully in a variety of resource management settings [15,57,53]. Here we develop an RL approach for the Hybrid [24] architecture and apply it to cloud resource management.…”

Section: Introductionmentioning

confidence: 99%

Scalable Virtual Machine Migration using Reinforcement Learning

2022

View full text Add to dashboard Cite

Solutions based on Reinforcement Learning (RL) have been presented to manage cloud infrastructure, however, these tend to be centralised and suffer in their ability to maintain Quality of Service (QoS) for data centres with thousands of nodes. To address this, we propose a reinforcement learning management policy, which is able to run decentralized, and achieve fast convergence towards efficient resource allocation, resulting in lower SLA violations compared to centralised architectures. To address some of the common challenges in applying RL to cloud resource management, such as slow learning and state/action management, we use parallel learning and reduction of the state/action space. We have also demonstrate unique, multi-level reinforcement learning cooperation, that further reduces SLA violations. We use simulation to evaluate and demonstrate our proposal in practice, and compared the results obtained with an established heuristic, demonstrating significant improvement to SLA violations and higher scalability.

show abstract

CaR-PLive: Cloud-assisted reinforcement learning based P2P live video streaming: a hybrid approach

Cited by 8 publications

References 63 publications

Behavior Dissection of NGWN Live Audio and Video Streaming Users with Enhanced and Efficient Modelling

Behavior Dissection of NGWN Live Audio and Video Streaming Users with Enhanced and Efficient Modelling

Live Streaming Architectures for Video Data: A Review

Scalable Virtual Machine Migration using Reinforcement Learning

Contact Info

Product

Resources

About