End-to-end QoS Provisioning through Resource Adaptation

Proceedings of IEEE International Conference on Multimedia Computing and Systems, 1997

Quality of Service (QoS) management becomes more and more important, especially in networks where many applications are competing for a limited number of resources. As these applications become more complex (consider e.g. multiparty multimedia applications), the number of options for QoS management increases, leading to more complex decision processes. In this paper, we propose an approach for cooperative QoS management, where application-oriented QoS agents are distributed throughout the network and the end systems, communicating with each other. This distributed management system tries to guarantee the QoS level negotiated with the users, at the same time optimizing resource usage. The advantages of distributing the management process are (i) an easier and more precise localization of the cause of QoS problems, (ii) better knowledge of local situations, (iii) a lower complexity for a single QoS agent and (iv) an increase in possible actions. We describe management procedures for QoS negotiation, adaptation and renegotiation.

Lecture Notes in Computer Science, 2001

This paper presents a policy-based software architecture and implementation for application Quality of Service (QoS) management. The approach is dynamic in that the application is started with an initial resource allocation, and if it does not meet its QoS requirement, a resource manager attempts to allocate more resources to it until its QoS requirement is met. One key problem is that of determining the corrective action(s) to be taken when an application's QoS requirements are not being satisfied. For example, one possible action is to adjust the application's CPU priority when its QoS requirement is not being met. However, if there are several applications on the same host with QoS requirements, this may not be feasible. In other words, there may be constraints on the corrective actions depending on other factors. This paper explores the use of administrative policies to guide decisions on actions to take to meet QoS requirements and presents a prototype and initial experimentation.

Proceedings Eighth IEEE Workshop on Future Trends of Distributed Computing Systems. FTDCS 2001

The provision of novel Internet services has both to specify and to maintain differentiated Quality-of-Service (QoS) levels. Services should tailor to different user QoS preferences together with the differentiated quality properties deriving from servers and access points and devices, from workstations connected with high-capacity networks to wearable devices exploiting limited-capacity wireless links. The paper claims that service provision with negotiated and controlled QoS over best-effort networks calls for a support infrastructure that activates intermediate nodes along the path between clients and servers. In fact, the paper proposes MASQ, an active middleware solution for the QoS management of Video-on-Demand (VoD) streaming. At negotiation time, MASQ exploits code mobility to establish an active path between the requesting client and the VoD server chosen to tailor VoD flows based on user profiles and device properties. At provision time, MASQ dynamically controls the offered QoS level to adapt locally when and where network resource availability changes. MASQ significantly benefits from dynamic and flexible programmability stemming from the employment of high-level policies.

Due to the increasing growth of Web Services, Quality of Service (QoS) is becoming a key issue in web services community. Providers and clients need to use QoS-aware architectures to get/ensure end-to-end QoS. The QoS delivery to clients is highly affected by the web service performance itself, by the hosting platform (e.g., Application Server) and by the underlying network (e.g., Internet). Thus, even if web services together with hosting platform provide acceptable QoS, they also require sufficient available network resources to deliver end-to-end QoS. In this paper, we propose a solution approach to the problem of end-to-end QoS support for web services. Our approach rely on the utilization of a web service, called Network Resources Manager (NRM), to take care of the QoS support in the network connecting the client host and the matching web service location. NRM either relies on the network QoS capabilities (e.g., Integrated Services, Differentiated Services, Multiprotocol Label Switching), if any, or uses a measurement-based scheme to estimate the quality that can be delivered between the two locations. One of the key differentiator of our solution is that it does not require any changes to the currently used infrastructure by the users and web services providers.

Future Trends of Distributed Computer Systems, 2001

The provision of novel Internet services has both to specify and to maintain differentiated Quality-of-Service (QoS) levels. Services should tailor to different user QoS preferences together with the differentiated quality prop- erties deriving from servers and access points and de- vices, from workstations connected with high-capacity networks to wearable devices exploiting limited-capacity wireless links. The paper claims that service provision

2000

In order to achieve the best application-level Quality-of-Service (QoS), multimedia applications need to be dynamically tuned and reconfigured to adapt to fluctuating computing and communication environments. QoS-sensitive adaptations are critical when applications run in general-purpose systems, with no mechanisms provided for supporting resource reservations and real-time guarantees.

2001

The Internet is a dynamic network of heterogeneous transmission media with widely varying bandwidth capacities and latency characteristics. Given the tremendous popularity of the Internet, Internet traffic has not only increased but also changed in character. New classes of streaming multimedia applications, such as Video on Demand and IP Telephony, are being increasingly deployed. Such media rich applications require time bounded processing and communication. This imposes a need for temporal & spatial guarantees, such as high data throughput and low latency, from the underlying network. These applications can suffer severe performance degradation under conditions of unpredictable delays and losses in the network, as is the case in the Internet today. Consequently runtime Quality of Service (QoS) adaptation is necessary to enable operation of these applications with acceptable performance in spite of potentially insufficient network and end-system resources. This thesis presents the design, implementation and evaluation of an adaptive QoS mechanism that enables multimedia applications to perform satisfactorily under constrained system and network resource availability. We identify packet loss suffered by the application due to network congestion and processor overload as the crucial parameter affecting application performance. The adaptive mechanism aims to improve the QoS perceived by the end user, by optimizing this packet loss through control of the application data transport characteristics. It performs runtime adaptations using a policy based algorithm. Adaptations investigated include

Lecture Notes in Computer Science, 2007

Currently, several multimedia devices support the UPnP protocol allowing automatic detection of devices, connection of devices and agreement on a certain quality of the communication established between a server of content (Media Server) and a player of content (Media Renderer). The focus of this paper is to add to the UPnP standard quality of service (QoS) some elements to incorporate better performance in the local networks. All these additions are compatible with the current standard.

Recently, the Internet has become a popular platform for the delivery of multimedia content. Currently, multimedia services are either offered by Over-the-top (OTT) providers or by access ISPs over a managed IP network. As OTT providers offer their content across the best-effort Internet, they cannot offer any Quality of Service (QoS) guarantees to their users. On the other hand, users of managed multimedia services are limited to the relatively small selection of content offered by their own ISP. This article presents a framework that combines the advantages of both existing approaches, by dynamically setting up federations between the stakeholders involved in the content delivery process. Specifically, the framework provides an automated mechanism to set up end-to-end federations for QoSaware delivery of multimedia content across the Internet. QoS contracts are automatically negotiated between the content provider, its customers, and the intermediary network domains. Additionally, a federated resource reservation algorithm is presented, which allows the framework to identify the optimal set of stakeholders and resources to include within a federation. Its goal is to minimize delivery costs for the content provider, while satisfying customer QoS requirements. Moreover, the presented framework allows intermediary storage sites to be included in these federations, supporting on-the-fly deployment of content caches along the delivery paths. The algorithm was thoroughly evaluated in order to validate our approach and assess the merits of including intermediary storage sites. The results clearly show the benefits of our method, with delivery cost reductions of up to 80% in the evaluated scenario.

2000 Eighth International …, 2000