Hai Anh Tran

User to user adaptive routing based on QoE

Service quality can be defined as “the collective effect of service performances which determine the degree of satisfaction of a user of the service” [1]. In other words, quality is the customers perception of a delivered service. As larger varieties of services are offered to customers, the impact of network performance on the quality of service will be more complex. It is vital that service engineers identify network-performance issues that impact customer service. They also must quantify revenue lost due to service degradation. The Quality of Experience (QoE) becomes recently the most important tendency to guarantee the quality of network services. QoE represents the subjective perception of end-users using network services with network functions such as admission control, resource management, routing, traffic control, etc. In this paper, our main focus is routing mechanism driven by QoE end-users. With the purpose of avoiding the NP-complete problem and reducing the complexity problem for the future Internet, we propose two protocols based on user QoE measurement in routing paradigm to construct an adaptive and evolutionary system. Our first approach is a routing driven by terminal QoE basing on a least squares reinforcement learning technique called Least Squares Policy Iteration. The second approach, namely QQAR (QoE Q-learning based Adaptive Routing), is a improvement of the first one. QQAR basing on Q-Learning, a Reinforcement Learning algorithm, uses Pseudo Subjective Quality Assessment (PSQA), a real-time QoE assessment tool based on Random Neural Network, to evaluate QoE. Experimental results showed a significant performance against over other traditional routing protocols.

QoE-Based Server Selection for Content Distribution Networks

As current server capacity and network bandwidth become increasingly overloaded by the rapid growth of high quality emerging multimedia services such as mobile online gaming, social networking or IPTV, a critical factor of success of these multimedia services becomes the end-user perception of quality while them using the service. As a result, user-centered approaches that consider quality of experience (QoE) constitute the current design trend for network systems of content providers and network operators. A content distribution network (CDN) that replicates the content from original servers to the replicated servers close to end users is actually an effective solution to improve network quality. We propose a QoE-based server selection algorithm in the context of a CDN architecture. Using realistic characteristics of the server selection process, we formalize our selection model as a sequential decision problem solved by the multi-armed bandit (MAB) paradigm. By using realistic experiments, we demonstrate that our approach yields significant improvements in term of user perception compared to traditional methods (such as Fastest, Closest and Round Robin).

QoE model driven for network services

Actually, wealthy network services such as Internet protocol television (IPTV) and Voice over IP (VoIP) are expected to become more pervasive over the Next Generation Network (NGN). In order to serve this purpose, the quality of these services should be evaluated subjectively by users. This is referred to as the quality of experience (QoE). However, there are many issues that may impact user’s perception in many different ways. This paper surveys the QoE models and systems for existing and future network services.

QoE Content Distribution Network for Cloud Architecture

Cloud Service has become now a real trend in the development of network services. It is a concept of deporting resources and services on remote servers as opposed to traditional hosting on the user workstation. In fact, cloud services require more bandwidth due to high quality media. Content Distribution Network (CDN) with a mechanism of replication of information among multiple servers is a solution to support high request volume and ameliorate network quality. Integrating Cloud concept into Content Distribution Network (CDN) is an effective approach to improve network quality. In this paper, we propose a Content Distribution Network Cloud Architecture (CDNCA). Our approach is based not only on Quality of Service criteria (QoS) (e.g. round trip time, network hops, loss rate, etc.) but also on the Quality of Experience that represents end-users perception and satisfaction. Experimental results show that CDNCA yields significant improvements over traditional approaches.

Global state-dependent QoE based routing

For years, wireless network systems have been trying to satisfy end-users and support high quality multimedia applications such as Mobile TV, VoIP, etc. Combining wireless networks with multimedia content distribution needs efficient routing protocols. We develop in this paper a new routing protocol, namely DOQAR (Dynamic Optimized QoE Adaptive Routing), to improve the user perception and optimize the usage of network resources. In our end-to-end model, smartphone users connect to content servers in a wired network across a wireless access network. In order to evaluate the QoE, we use a Multi-Layer Perception-based (MLP) method. Experimental results show a significant performance against other traditional routing protocols.

Real-Time state-dependent routing based on user perception

In order to successfully resolve the network infrastructures problems the network provider has to improve the service quality. However in traditional ways, maintaining and improving of the service quality are generally determined in terms of quality of service criteria, not in terms of satisfaction and perception to the end-user. The latter is represented by Quality of Experience (QoE) that becomes recently the most important tendency to guarantee the quality of network services. QoE represents the subjective perception of end-users using network services with network functions such as admission control, resource management, routing, traffic control, etc. In this paper, we focus on routing mechanism driven by QoE end-users. Today, NP-complete is one of the most routing algorithm problems when trying to satisfy multi QoS constraints criteria simultaneously. In order to avoid the classification problem of these multiple criteria reducing the complexity problem for the future Internet, we propose two protocols based on user QoE measurement in routing paradigm to construct an adaptive and evolutionary system. Our first approach is a routing driven by terminal QoE basing on a least squares reinforcement learning technique called Least Squares Policy Iteration. The second approach, namely QQAR (QoE Q-learning based Adaptive Routing), is a improvement of the first one. QQAR basing on Q-Learning, a Reinforcement Learning algorithm, uses Pseudo Subjective Quality Assessment (PSQA), a real-time QoE assessment tool based on Random Neural Network, to evaluate QoE. Experimental results showed a significant performance against over other traditional routing protocols.

A Dynamic QoE Routing System for User-Centric Applications

Today, maintaining the best quality of experience (QoE) as the subjective perception of end-users is one of the most important requirements of both wireless and wired networks. To achieve this goal, we frequently use network functions such as admission control, resource management, routing and traffic control. We focus on the design and evaluation of a QoE-aware routing mechanism. We present an end-to-end model where Smartphone users connect to content servers through a wired network across a wireless access network. We propose an adaptive and evolutionary system with a QoE-aware routing protocol, namely QoE Q-learning-based adaptive routing. Our experimental results demonstrate significant performance improvements in mean opinion score for various network loads, convergence time during the initialisation phase and control overheads over other traditional approaches.Copyright

Quality of experience vs. quality of service : Application for a CDN Architecture

We are witnessing in recent years a rapid development of interconnecting applications. In addition to those that contributed to the popularity of the early Internet (email, file transfer, etc.), there are now applications that rely on network data more sensitive. They include sound applications (voice, music programs, etc.), image applications (television programs, videoconferencing, video on demand, etc.) and urgent information applications (market orders). However, it is important for the operators and providers not to forget sight of the reason for this new infrastructure: to provide network service that user wants to use. Accomplishing this idea means assuring positive experience of end users. Therefore, service providers are switching the focus from traditional Quality-of-Service (QoS) to user satisfaction, which is the overall success of a network from the user perspective. The perceived end-to-end quality becomes one of the main goals required by users that must be guaranteed by the network operators and the Internet service providers, through manufacturer equipment. This is referred to as the quality of experience (QoE) notion that becomes commonly used to represent user perception. This paper will focus on a vision of a new paradigm which make interactions first-class objects from the perspective of the user, the application and the network components. This is achieved by analyzing the interaction between the user and the application with quality perception metrics which are used to fix the control/command chain in network components. The idea here is how to integrate these metrics into a control/command chain in order to construct a network system? In this paper, we focus on one main mechanism for a Content Delivery Network Architecture: the server selection function.

User-centric Content Distribution Network architecture

Nowadays, the end-users have multitude of offers that make service prices decrease in using a network environment with multiple-operators and multiple-network. Consequently, the competition between network providers increases. The customer is today in a strong position with ability to select the best one among different competing providers. Besides similar pricing schemes, which are a useful decision aid for users, their choices are also influenced by expected and experience quality. So, the interest of service providers in how users perceive usability, reliability, quality and price-worthiness has increased. As a consequence, the QoE notion has been introduced to help service providers to take into account the user perception and satisfaction. In this paper, we propose an end-to-end QoE model applied to a Content Distribution Network architecture.

User to user QoE routing system

Recently, wealthy network services such as Internet protocol television (IPTV) and Voice over IP (VoIP) are expected to become more pervasive over the Next Generation Network (NGN). In order to serve this purpose, the quality of these services should be evaluated subjectively by users. This is referred to as the quality of experience (QoE). The most important tendency of actual network services is maintaining the best QoE with network functions such as admission control, resource management, routing, traffic control, etc. Among of them, we focus here on routing mechanism. We propose in this paper a protocol integrating QoE measurement in routing paradigm to construct an adaptive and evolutionary system. Our approach is based on Reinforcement Learning concept. More concretely, we have used a least squares reinforcement learning technique called Least Squares Policy Iteration. Experimental results showed a significant performance gain over traditional routing protocols.