Tricha Anjali

A new scheme for traffic estimation and resource allocation for bandwidth brokers

This paper is motivated by the concern of a multi-service network provider who plans to offer quality of service guarantees to users. A bandwidth broker acts as the resource manager for each network provider. Neighboring bandwidth brokers communicate with each other to establish inter-domain resource reservation agreements. Conventional approaches for resource allocation rely on pre-determined traffic characteristics. If allocation follows the traffic demand very tightly, the resource usage is efficient but leads to frequent modifications of the reservations. This would lead to increased inter-bandwidth-broker signaling in order to propagate the changes to all the concerned networks. Contrarily, if large cushions are allowed in the reservations, the modifications are far spaced in time but the resource usage becomes highly inefficient. In this paper, a new scheme for estimating the traffic on an inter-domain link and forecasting its capacity requirement, based on a measurement of the current usage, is proposed. The method allows an efficient resource utilization while keeping the number of reservation modifications to low values.

Optimal policy for label switched path setup in MPLS networks

An important aspect in designing a multiprotocol label switching (MPLS) network is to determine an initial topology and to adapt it to the traffic load. A topology change in an MPLS network occurs when a new label switched path (LSP) is created between two nodes. The LSP creation involves determining the route of the LSP and the according resource allocation to the path. A fully connected MPLS network can be used to minimize the signaling. The objective of this paper is to determine when an LSP should be created and how often it should be re-dimensioned. An optimal policy to determine and adapt the MPLS network topology based on the traffic load is presented. The problem is formulated as a continuous time Markov decision process with the objective to minimize the costs involving bandwidth, switching, and signaling. These costs represent the trade-off between utilization of network resources and signaling/processing load incurred on the network. The policy performs a filtering control to avoid oscillations which may occur due to highly variable traffic. The new policy has been evaluated by simulation and numerical results show its effectiveness and the according performance improvement. A sub-optimal policy is also presented which is less computationally intensive and complicated.

TEAM: A traffic engineering automated manager for DiffServ-based MPLS networks

In this article an automated manager called traffic engineering automated manager (TEAM) for DiffServ/MPLS networks is introduced, and its design and implementation details are discussed. TEAM is designed for complete automated management of an Internet domain. TEAM is an adaptive manager that provides the required quality of service to the users and reduces the congestion in the network. The former is achieved by reserving bandwidth resources for the requests and the latter by distributing the load efficiently. These goals are achieved by online measurements of the network state. TEAM is composed of a traffic engineering tool (TET), which adaptively manages the bandwidth and routes in the network, a measurement and performance evaluation tool (MPET), which measures important parameters in the network and inputs them to the TET, and a simulation tool (ST), which may be used by TET to consolidate its decisions. These three tools work in synergy to achieve the desired network operation objectives. The experimental results demonstrate the efficiency of TEAM as a network manager in different and unpredictable traffic conditions at the expense of a limited increase in the computational complexity and costs.

A new path selection algorithm for MPLS networks based on available bandwidth estimation

A network should deploy QoS-aware path selection algorithms for efficient routing. To this end, measurements of the various characteristics of the network can provide insight into the state and performance of the network. In this paper, we present a new QoS-aware path selection algorithm for flows requiring bandwidth guarantees based on an estimation algorithm for the available bandwidth on the links of the network. The estimation algorithm for the available bandwidth predicts the available bandwidth and also tells the duration for which the estimate is valid with a high degree of confidence. Thus, the path selection algorithm is adaptive and not very computationally intensive.

Invited A new traffic engineering manager for DiffServ/MPLS networks: design and implementation on an IP QoS Testbed

In a multi-service network, different applications have varying QoS requirements. The IETF has proposed the DiffServ architecture as a scalable solution to provide Quality of Service (QoS) in IP Networks. In order to provide quantitative guarantees and optimization of transmission resources, DiffServ mechanisms should be complemented with efficient traffic engineering (TE) mechanisms, which operate on an aggregate basis across all classes of service. The MultiProtocol Label Switching (MPLS) technology is a suitable method to provide TE, independent of the underlying layer2 technology. Currently, the combined use of Differentiated Services (DiffServ) and MPLS is a promising technique to provide Quality of Service (QoS), while efficiently exploiting network resources. In this paper, TEAM, an automated manager for DiffServ/MPLS networks is introduced and its design. The design and implementation details are discussed.

ABEst: an available bandwidth estimator within an autonomous system

The explosive growth of the Internet has induced a need for developing tools to understand the composition and dynamics of the Internet traffic. Measurements of the various characteristics of a network provide insight into the state and performance of the network whether it is behaving as expected and whether changes in the network have improved or degraded its performance. Available bandwidth on the links of a network is an important metric which can predict the performance of the network. In this paper, an estimation algorithm for the available bandwidth on a link is presented. The algorithm estimates the available bandwidth and tells the duration for which the estimate is valid with a high degree of confidence. The algorithm dynamically changes the number of past samples that an used for prediction and also the duration for which the prediction holds.

LSP and /spl lambda/SP Setup in GMPLS Networks

In this paper, a new optimal policy is introduced to determine and adapt the generalized multiprotocol label switching (GMPLS) network topology based on the current traffic load. The integrated traffic engineering paradigm provides mechanisms for dynamic addition of physical capacity to optical networks. In the absence of such mechanisms, the rejection of incoming requests will be higher. The objective of the proposed policy is to minimize the costs involving bandwidth, switching and signaling. The policy is derived by utilizing the Markov decision process theory. The new policy is split into two levels: the MPLS network level and the optical network level. In addition to the optimal policy, a sub-optimal policy and a threshold-based policy are also proposed which are less computationally intensive but have comparable performance to the optimal policy. The proposed policies have been evaluated by simulation and compared to some heuristics. Numerical results, which show their effectiveness and the achieved performance improvement, are presented.

A new threshold-based policy for label switched path (LSP) set-up in MPLS networks

In this paper, a new policy is introduced to determine and adapt the MPLS network topology based on the current traffic load. The objective of the new policy is to minimize the costs involving bandwidth, switching and signaling. The new policy is based on a threshold criterion and requires only the knowledge of some parameters locally stored in the source router. The value of the threshold depends on the cost coefficients and on the length (number of intermediate hops) of the LSP. The new policy also performs a filtering control to avoid oscillations which occur due to highly variable traffic. The new policy has been evaluated by simulation and numerical results show its effectiveness and the according performance improvement.

Optimal filtering in traffic estimation for bandwidth brokers

We present a method for an on-line traffic optimal estimation on a communication link. The proposed filtering procedure is based on a traffic model consisting of a birth-and-death process, elaborates the current noisy measurements from the link and minimizes the estimation error conditional variance. Performance of the method is tested by considering both simulated and real data. This result is of interest with reference to a possible procedure for bandwidth allocation in the framework of bandwidth brokers. The bandwidth allocation is necessary to provide quality of service guarantees to users and requires, as a preliminary step, on-line traffic estimation.

Threshold-based policy for LSP and lightpath setup in GMPLS networks

In this paper, a new policy is introduced to determine and adapt the generalized multiprotocol label switching (GMPLS) network topology based on the current traffic load. The objective of the new policy is to minimize the costs involving bandwidth, switching and signaling. The new policy is based on a threshold criterion. The policy is split into two levels, the first deals with the MPLS network and the second with the lightpath level. The two thresholds depends on the cost coefficients and the number of the intermediate hops. Our policy also performs a filtering control to avoid oscillations which occur due to highly variable traffic. The proposed policy has been evaluated by simulation and numerical results, which show its effectiveness and the achieved performance improvement.