Efficient QoS Provisioning for Adaptive Multimedia in Mobile Communication Networks by Reinforcement Learning

Yu, F. Richard; Wong, Vincent W. S.; Leung, Victor C. M.

doi:10.1007/s11036-005-4464-2

Cited by 51 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Where our self-learning HAS approach is focused on the client side, existing RLbased adaptive streaming techniques target server or network side solutions to Quality of Service (QoS) provisioning for adaptive streaming systems. Fei, Wong, and Leung (2006) formulate call admission control and bandwidth adaptation for adaptive multimedia delivery in mobile communication networks as a Markov Decision Problem (MDP), which they solve using Q-Learning. RL is applied by Charvillat and Grigoras (2007) to create a dynamic adaptation agent, considering both user behaviour and context information.…”

Section: Learning In Adaptive Streamingmentioning

confidence: 99%

Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client

et al. 2014

View full text Add to dashboard Cite

In recent years, HTTP Adaptive Streaming (HAS) is becoming the de-facto standard for adaptive video streaming services. A HAS video consists of multiple segments, encoded at multiple quality levels. State-of-the-art HAS clients employ deterministic heuristics to dynamically adapt the requested quality level based on the perceived network conditions. Current HAS client heuristics are however hardwired to fit specific network configurations, making them less flexible to fit a vast range of settings. In this article, a (Frequency Adjusted)Q-Learning HAS client is proposed. In contrast to existing heuristics, the proposed HAS client dynamically learns the optimal behaviour corresponding to the current network environment in order to optimize the Quality of Experience (QoE). Furthermore, the client has been optimized both in terms of global performance and convergence speed. Thorough evaluations show that the proposed client can outperform deterministic algorithms by 11% to 18% in terms of Mean Opinion Score (MOS) in a wide range of network configurations.

show abstract

Section: Learning In Adaptive Streamingmentioning

confidence: 99%

Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Moreover, in [15] is presented effective QoS provisioning for wireless adaptive multimedia based on using a form of discounted reward reinforcement learning known as Q-learning. The proposed scheme in [15] considered the handoff dropping probability and average allocated bandwidth constraints simultaneously, in order to achieve optimal CAC (Call Admission Control) and bandwidth allocation policies that can maximize network revenue and guarantee QoS constraints.…”

Section: Related Workmentioning

confidence: 99%

“…The proposed scheme in [15] considered the handoff dropping probability and average allocated bandwidth constraints simultaneously, in order to achieve optimal CAC (Call Admission Control) and bandwidth allocation policies that can maximize network revenue and guarantee QoS constraints. A step forward is made in [16], where is proposed a generic adaptive reservation-based QoS model for the integrated cellular and WLAN networks.…”

Section: Related Workmentioning

confidence: 99%

Advanced Mobile Terminal for Heterogeneous Wireless Networks

Shuminoski

Janevski

2014

IJGDC

View full text Add to dashboard Cite

show abstract

“…With this method, the optimal modulation level and transmit power can be obtained depending on the incoming traffic rate, buffer condition, and channel condition. In [13], a reinforcement learning has been used in order to provide QoS for adaptive multimedia in mobile communication networks. The optimal strategy has been derived with Qlearning because the explicit state transition is not required.…”

Section: Network Management Based On Reinforcement Learningmentioning

confidence: 99%

A Reinforcement Learning-Based Lightpath Establishment for Service Differentiation in All-Optical WDM Networks

Koyanagi

Tachibana

Sugimoto

2009

GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference

View full text Add to dashboard Cite

In this paper, we propose a lightpath establishment method based on reinforcement learning for providing the service differentiation in all-optical WDM networks. In our proposed method, the optimal policy for the lightpath establishment is derived with Q-learning. With the derived policy, each node decides whether a lightpath establishment request of each class should be accepted or not. This method can be available even if the number of wavelengths is large and there is no assumption about the lightpath establishment. We also discuss how the proposed method is utilized with Generalized Multi-Protocol Label Switching (GMPLS). In numerical examples, we investigate the impacts of learning parameters on the performance of the proposed method. Then, we show that our proposed method can provide the service differentiation for the lightpath blocking probability, while utilizing wavelengths effectively.

show abstract

Efficient QoS Provisioning for Adaptive Multimedia in Mobile Communication Networks by Reinforcement Learning

Abstract: Abstract

Cited by 51 publications

References 17 publications

Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client

Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client

Advanced Mobile Terminal for Heterogeneous Wireless Networks

A Reinforcement Learning-Based Lightpath Establishment for Service Differentiation in All-Optical WDM Networks

Contact Info

Product

Resources

About