Robert Wójcik

Flow Oriented Approaches to QoS Assurance

The following flow-oriented architectures for quality of service assurance in IP networks are surveyed: Integrated Services, Connectionless Approach to QoS guarantees, Dynamic Packet State, Caspian Networks and Anagran, the Feedback and Distribution method, Flow-Based Differentiated Services, Flow-Aware Networking, the Flow-State-Aware transport, and Flow-Aggregate-Based services. The reasons why flow-awareness attracted so much attention are explained, and the current studies as well as the development history of the solutions are presented. The following features of the discussed architectures are compared: flow definition, classes of service, architecture, and signaling. Also, their pros and cons, complexity, and scalability, as well as perspectives are assessed.

Emergency Calls in Flow-Aware Networks

In this paper it is shown that flow-aware networks (FAN), although providing superior transmission quality, may force us to wait for the network resources. Such a situation is inconvenient for the realization of emergency VoIP connections. In order to overcome the presented problem, differentiated blocking along with the static router configuration approach is presented, and it is believed to be a simple, adequate, and above all, feasible solution.

QoS-Aware Net Neutrality

This paper proposes a compromise solution to the net neutrality problem, which is one of the key issues in the development process of new Internet applications and services. The solution is to use a QoS architecture, one that would provide service differentiation to support current and future demands, but one that would not require or even allow any user input. This way, ISPs (Internet Service Providers) will be refrained from introducing any explicit differentiation or prioritization, therefore, networks shall remain neutral while, still, providing necessary service differentiation. The FAN (Flow- Aware Networking) concept, presented in the paper, may be a good compromise to handle the net neutrality problem as it assures implicit service differentiation based solely on the traffic characteristics without any possibility of undesirable interference by ISPs or Internet users.

A survey on methods to provide multipath transmission in wired packet networks

IP networks were designed to provide general connectivity. At their advent, routing methods focused only on finding one optimal path between given endpoints. Although many solutions to sending traffic via multiple paths have appeared over time, the majority of current IP networks are still managed to support only single-path transmissions. This survey examines various approaches which can provide multipath transmissions in existing IP networks. Firstly, the most recognizable solutions are presented, and later, less well-known proposals are introduced. We show how it is possible to realize multipath transmission in source and hop-by-hop routing, multi-topology routing, bio-inspired routing solutions, Valiants routing, Multi-Protocol Label Switching, Software-Defined Networks, Flow-Aware Multi-Topology Adaptive Routing, Shortest-Path Bridging, Transparent Interconnection of Lots of Links, network virtualization, and Multipath TCP. Moreover, the mentioned approaches are compared, contrasted and subjectively assessed. The goal of the survey is to show that multipath transmissions can be achieved in the current IP networks and in many different ways.

Reliable Transmission in Flow-Aware Networks

A complete system which ensures reliable transmission of streaming flows in Flow-Aware Networks (FAN) is presented and analyzed in the paper. A new congestion control mechanism, called RPAEF (Remove and Prioritize in access Active Elastic Flows), is described in details. It allows for fast acceptance of new streaming flows in the admission control (AC) block of FAN routers. The mechanism of limiting the number of new flows accepted in the AC block is provided as an answer to the scalability problem of all congestion control mechanisms proposed for FAN up to now. The global list of protected flows ensures that all streaming flows redirected from the primary route in case of a network element failure are immediately accepted in the first router on a backup route. The advantages and weaknesses of the proposed solutions are described and analyzed. Moreover, it is shown that the simultaneous implementation of all of them ensures fast, scalable and reliable transmission of streaming flows in FAN.

Flow-Aware Multi-Topology Adaptive Routing

Internet routing processes currently rely on protocols that were developed more than ten years ago. Today, we have far more computational power and memory at our disposal, and it is possible to take advantage of these resources in order to greatly increase the efficiency of routing protocols. Therefore, we propose a new approach to routing packets in IP-based networks: Flow-Aware Multi-Topology Adaptive Routing, or FAMTAR. FAMTAR combines flow-aware traffic management and an adaptive routing mechanism. A standard routing protocol is used to find the optimal path between two nodes in a network. FAMTAR makes it possible to automatically create additional paths when such demand occurs. Between two endpoints, the transmission may follow n different paths, where n is limited only by the topology of the network. In this letter, we compare FAMTAR to a classic routing protocol and demonstrate FAMTARs superiority.

The Impact of Congestion Control Mechanisms on Network Performance after Failure in Flow-Aware Networks

This paper presents the impact of congestion control mechanisms proposed for Flow-Aware Networks on packet transmission in the overloaded network after a link failure. The results of simulation based analysis show how to set the values of the congestion control parameters in order to decrease the acceptance time of the interrupted streaming flows in the backup link. The research was performed for three congestion control mechanisms, the Enhanced Flushing Mechanism (EFM), the Remove Active Elastic Flows (RAEF), and Remove and Block Active Elastic Flows (RBAEF) in two different cross-protect router architectures, with the PFQ (Priority Fair Queuing) and with the PDRR (Priority Deficit Round Robin) scheduling algorithms. Moreover, the advantages and weaknesses of using the proposed solutions in FAN, considering the effects of a network element failure, are described and analyzed.

EFMP - a new congestion control mechanism for flow-aware networks

In this paper, a new congestion control mechanism for flow-aware networks, that is, enhanced flushing mechanism with priority EFMP is introduced. Proposed by J. Roberts and S. Oueslati in 2004, flow-aware networking is a concept that ensures quality of service in networks based on flows. EFMP improves the efficiency of transmission in FAN by introducing new policies in the admission control block of a cross-protect router. The mechanism is thoroughly described, analysed, and validated through simulations. The proposed mechanism inherits the advantages of previously known admission control schemes while ensuring fast acceptance times of new streaming flows and proper transmission of the remaining traffic. Moreover, the comparison with the multilayer flow-aware networks architecture shows that EFMP ensures better performance and lower cost of transmission in a network with limited resources. Copyright

Per user fairness in Flow-Aware Networks

A new fairness concept for Flow-Aware Networks (FAN) is presented and analyzed in the paper. In contrast to basic FAN, where elastic flows are treated similarly, it assumes fair access to the resources for each user independently of how many flows it generates. A new method for estimating the values of the fair rate, which is the key congestion control parameter in FAN is also provided. The new solution allows for reducing the oscillations of the periodically measured values which influences more stable transmission in the network. The new method allows for describing the traffic in a more realistic way, simultaneously simplifying its implementation in the FAN routers. Finally, the results of the simulation analysis of FAN with the new fairness algorithm and the Remove and Accept Most Active Flows (RAMAF) congestion control mechanism are presented for two versions of the TCP protocol: NewReno and NewJersey.

Fair Rate Degradation in Flow-Aware Networks

In this paper, it is shown that the admission control routine in Flow-Aware Networks (FAN) may lead to severe fair rate degradation, which negatively impacts the performance of streaming applications. In order to prevent this negative behavior, the limitation mechanism is proposed. The aim of the mechanism is to limit the maximum number of new flows that may be admitted on a link between any two consecutive networks automeasurements. The solution is efficient, viable and dramatically reduces the fair rate degradation.