Michael Jarschel

An Evaluation of QoE in Cloud Gaming Based on Subjective Tests

Cloud Gaming is a new kind of service, which combines the successful concepts of Cloud Computing and Online Gaming. It provides the entire game experience to the users remotely from a data center. The player is no longer dependent on a specific type or quality of gaming hardware, but is able to use common devices. The end device only needs a broadband internet connection and the ability to display High Definition (HD) video. While this may reduce hardware costs for users and increase the revenue for developers by leaving out the retail chain, it also raises new challenges for service quality in terms of bandwidth and latency for the underlying network. In this paper we present the results of a subjective user study we conducted into the user-perceived quality of experience (QoE)in Cloud Gaming. We design a measurement environment, that emulates this new type of service, define tests for users to assess the QoE, derive Key Influence Factors (KFI) and influences of content and perception from our results.

Heuristic Approaches to the Controller Placement Problem in Large Scale SDN Networks

Software Defined Networking (SDN) marks a paradigm shift towards an externalized and logically centralized network control plane. A particularly important task in SDN architectures is that of controller placement, i.e., the positioning of a limited number of resources within a network to meet various requirements. These requirements range from latency constraints to failure tolerance and load balancing. In most scenarios, at least some of these objectives are competing, thus no single best placement is available and decision makers need to find a balanced trade-off. This work presents POCO, a framework for Pareto-based Optimal COntroller placement that provides operators with Pareto optimal placements with respect to different performance metrics. In its default configuration, POCO performs an exhaustive evaluation of all possible placements. While this is practically feasible for small and medium sized networks, realistic time and resource constraints call for an alternative in the context of large scale networks or dynamic networks whose properties change over time. For these scenarios, the POCO toolset is extended by a heuristic approach that is less accurate, but yields faster computation times. An evaluation of this heuristic is performed on a collection of real world network topologies from the Internet Topology Zoo. Utilizing a measure for quantifying the error introduced by the heuristic approach allows an analysis of the resulting trade-off between time and accuracy. Additionally, the proposed methods can be extended to solve similar virtual functions placement problems which appear in the context of Network Functions Virtualization (NFV).

Interfaces, attributes, and use cases: A compass for SDN

The term Software Defined Networking (SDN) is prevalent in todays discussion about future communication networks. As with any new term or paradigm, however, no consistent definition regarding this technology has formed. The fragmented view on SDN results in legacy products being passed off by equipment vendors as SDN, academics mixing up the attributes of SDN with those of network virtualization, and users not fully understanding the benefits. Therefore, establishing SDN as a widely adopted technology beyond laboratories and insular deployments requires a compass to navigate the multitude of ideas and concepts that make up SDN today. The contribution of this article represents an important step toward such an instrument. It gives a thorough definition of SDN and its interfaces as well as a list of its key attributes. Furthermore, a mapping of interfaces and attributes to SDN use cases is provided, highlighting the relevance of the interfaces and attributes for each scenario. This compass gives guidance to a potential adopter of SDN on whether SDN is in fact the right technology for a specific use case.

SDN-Based Application-Aware Networking on the Example of YouTube Video Streaming

Application-Aware Networking is a promising approach to provide good application quality to users in scenarios with limited network resources, like todays access networks. With SDN, a particularly interesting method to enable flowbased traffic management in networks has become available. In this work we take a look at how a specific application, i.e., YouTube Streaming, can benefit from such an SDN-based Application-Aware Network. We implement and investigate an approach based on Deep Packet Inspection (DPI) and one based on direct information input from the application in an OpenFlow testbed in order to show, how these different types of application information can be exploited to enhance the Quality of Experience (QoE). Furthermore, we determine the overhead caused by each of the presented approaches.

Pareto-optimal resilient controller placement in SDN-based core networks

Recently, Software Defined Networking (SDN) has gained a lot of attention, even for the use in core communication networks. When deploying SDN in large core networks, the number and location of controllers must be carefully planned. A first study on this topic by Heller et al. [3] was followed by more detailed publications that included resilience or dynamic controller provisioning. In our previous work [2], we provide an overview over related work and include different resilience issues in the controller placement process. We argued that it is not sufficient to look only at node-to-controller latencies but a controller placement should also fulfill certain resilience constraints especially for the control plane.

Gaming in the clouds: QoE and the users’ perspective

Abstract Cloud Gaming is a new kind of service, which combines the successful concepts of Cloud Computing and Online Gaming. It provides the entire game experience to the users remotely from a data center. The player is no longer dependent on a specific type or quality of gaming hardware, but is able to use common devices. The end device only needs a broadband internet connection and the ability to display High Definition (HD) video. While this may reduce hardware costs for users and increase the revenue for developers by leaving out the retail chain, it also raises new challenges for service quality in terms of bandwidth and latency for the underlying network. In this paper we present the results of a subjective user study we conducted into the user-perceived quality of experience (QoE) in Cloud Gaming. We design a measurement environment, that emulates this new type of service, define tests for users to assess the QoE, derive Key Influence Factors (KIF) and influences of content and perception from our results.

Modelling of OpenFlow-based software-defined networks: the multiple node case

OpenFlow (OF) is one of the most widely used protocols for controller-to-switch communication in a software defined network (SDN). Performance analysis of OF-based SDN using analytical models is both highly desirable and challenging. There already exists a very elegant analytical model based on M/M/1 queues to estimate the packet sojourn time and probability of lost packets for the case in which a controller is responsible for only a single node in the data plane. However the literature falls short when it comes to the multiple node case, i.e. when there is more than one node in the data plane. In this work we propose a model to address this challenge by approximating the data plane as an open Jackson network with the controller also modeled as an M/M/1 queue. The model is then used to evaluate the system in the light of some of the metrics, such as; how much time a packet spends on average in an OF-based network and how much data we can pump into the network given the average delay requirements. Finally the PDF and the CDF of the time spent by the packet in an OF-based SDN for a given path is derived.

Dynamic application-aware resource management using Software-Defined Networking: Implementation prospects and challenges

Todays Internet does not provide an exchange of information between applications and networks, which may result in poor application performance. Concepts such as application-aware networking or network-aware application programming try to overcome these limitations. The introduction of Software-Defined Networking (SDN) opens a path towards the realization of an enhanced interaction between networks and applications. Hence, a more dynamic and demand-based allocation of network resources to heterogeneous applications can be realized. The implementation of the resource management action, however, may have an impact on the data transport and application quality. This paper summarizes resource management mechanisms provided by current SDN approaches based on OpenFlow and exemplary evaluates implementation prospects and challenges.

On the usability of OpenFlow in data center environments

Since its introduction OpenFlow has been used as an enabler for network experiments in a variety of fields. Although OpenFlow was initially only used in the research domain, the concept is now finding its way into data centers due to the relatively cheap hardware and high flexibility. In this paper, we take a look at the scalability and usability of OpenFlow in data centers. Based on data center traffic models and OpenFlow measurements, we evaluate whether OpenFlow is able to cope with the short flow inter-arrival times of the traffic models by means of simulation.

On The Modeling of OpenFlow-based SDNs: The Single Node Case.

OpenFlow is one of the most commonly used protocols for communication between the controller and the forwarding element in a software defined network (SDN). A model based on M/M/1 queues is proposed in [1] to capture the communication between the forwarding element and the controller. Albeit the model provides useful insight, it is accurate only for the case when the probability of expecting a new flow is small. Secondly, it is not straight forward to extend the model in [1] to more than one forwarding element in the data plane. In this work we propose a model which addresses both these challenges. The model is based on Jackson assumption but with corrections tailored to the OpenFlow based SDN network. Performance analysis using the proposed model indicates that the model is accurate even for the case when the probability of new flow is quite large. Further we show by a toy example that the model can be extended to more than one node in the data plane.