H. de Meer

Utility curves: mean opinion scores considered biased

In the Coqos project task performance measures and a corresponding framework are suggested and pursued as a novel and more suitable means for determining utility curves. TPM are intended to avoid limits inherent in traditional measures like mean opinion scores. MOS rely merely on subjective ratings rather than on more objective performance in relation to a particular task or application of interest. Informational relevance and its impact on subjects can be measured more effectively by TPM. Inhibiting psychological and cognitive effects like consciousness or nonconsciousness of degradations or individual focusing and perspectives of subjects can be more appropriately evaluated and dealt with by means of TPM. The increasing importance of adaptation, in particular with the advance of MPEG4, as a means for QoS provisioning, both in wireless and wired environments, requires sensible techniques to effectively determine utility curves.

Cooperative QoS management for multimedia applications

Quality of service (QoS) management is becoming 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. The authors 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. They describe management procedures for QoS negotiation, adaptation and renegotiation.

Controlled stochastic Petri nets

A new framework for the extension of stochastic Petri nets (SPNs) is introduced. SPNs are extended by elements providing means for a dynamic optimization of performability measures. A new type of transition is defined, offering a feature for specification of controlled switching, called reconfiguration, from one marking of a SPN to another marking. Optional reconfiguration transitions are evaluated in order to optimize a specified reward or cost function. The result of an analysis is provided in the output of a numerical computation, in the form of a graphical presentation of an optimal, marking dependent control strategy and the resulting performability measure when applying the optimal strategy. The extended SPNs are called COSTPNs (Controlled Stochastic Petri Nets). COSTPNs are mapped on EMRMs (Extended Markov Reward Models) for a numerical analysis. Computational analysis is possible with algorithms adopted from Markov decision theory, including transient and stationary optimization. The scope of the paper is to introduce the new control structure for SPNs and to present an algorithm for the mapping of COSTPNs on EMRMs.A new framework for the extension of stochastic Petri nets (SPNs) is introduced. SPNs are extended by elements providing means for a dynamic optimization of performability measures. A new type of transition is defined, offering a feature for specification of controlled switching, called reconfiguration, from one marking of a SPN to another marking. Optional reconfiguration transitions are evaluated in order to optimize a specified reward or cost function. The result of an analysis is provided in the output of a numerical computation, in the form of a graphical presentation of an optimal, marking dependent control strategy and the resulting performability measure when applying the optimal strategy. The extended SPNs are called COSTPNs (Controlled Stochastic Petri Nets). COSTPNs are mapped on EMRMs (Extended Markov Reward Models) for a numerical analysis. Computational analysis is possible with algorithms adopted from Markov decision theory, including transient and stationary optimization. The scope of the paper is to introduce the new control structure for SPNs and to present an algorithm for the mapping of COSTPNs on EMRMs.

Towards formal semantics for QoS support

The introduction of the concept of QoS has led to an extension of the traditional concepts of service and service specification. However, the design of QoS support is usually done without a systematic approach, leading to concepts of QoS support ranging from basic QoS monitoring capabilities to hard real-time guarantees. In more advanced QoS support, intermediate layers should be designed in a way that enables the masking or controlled handling of sporadic QoS violations. To implement this degradation path support across multiple layers, a negotiation of preferred and supportable failure semantics is a requirement. To realize these advanced QoS support features, not only new QoS control mechanisms within the layers have to be developed but the semantics of QoS negotiation protocols between layers must be better understood and subsequently extended. A framework formally based on set theory and relations is presented that allows the specification of QoS hierarchies including a well-defined failure type model. The framework supports the development of QoS negotiation protocols and can be used as a formal base for a structured system analysis.

QoS-adaptation by software agents in the presence of defective reservation mechanisms in the Internet

Originally, the Internet delivered best-effort service quality with respect to end-to-end delay. Recently, extensions such as RSVP have been proposed to provide guaranteed real-time services as well. Unfortunately, network resources, such as routers, do not yet fully, support RSVP reservation protocols so that guarantees cannot truly be given. We suggest to follow the paradigm of open programmable networks for a more complete QoS provisioning. Reservation gaps or tunnels are dynamically closed by means of a software agent approach that is flexibly deployed for an application oriented QoS support. Agents are dynamically located to such tunnels in order to monitor the tunnels, to provide feedback information in case of QoS violations, and to decide on possible compensating measures to be taken.

QoS management: a model-based approach

Quality of service (QoS) management is an important issue in todays high-speed distributed systems supporting multimedia applications. Most existing QoS management schemes usually just cope with technical issues of resource reservations and QoS guarantees, often completely neglecting revenue issues which are especially important for service providers in order to maximize their profit. The revenue to be expected does not only depend on the stream itself but also very much on stochastic events such as network failures or QoS violations. A QoS management system taking revenue issues and the possibly stochastic behavior of the environment into account thus seems to be superior to the existing ones. We show how controller programs for such enhanced QoS management systems can be developed based on a new kind of Petri nets, so-called controlled stochastic Petri nets. We show how to numerically analyze such models using a tool environment in order to obtain strategies for the QoS management system.