Kent Felske

Rate-based proportional-integral control scheme for active queue management

Most high-speed links do not have adequate buffering and as a result Active Queue Management (AQM) schemes that utilize queue size information for congestion control cannot be effectively applied on these links. A high-speed link will, typically, have small buffers in relation to the bandwidth-delay product of the link. In this paper we argue that rate-based AQM schemes be used for such links. The goal here is to match the aggregate rate of the active TCP connections to the available capacity while maintaining minimal queue size and high link utilization. The AQM scheme described here employs a Proportional-Integral (PI) control strategy and explicitly takes into account the time delay in the control process.

Clock recovery based on packet inter-arrival time averaging

Accurate source clock recovery is an important element of circuit emulation services (CES) over packet networks. A well-known and widely implemented technique for clock recovery in CES is the one that is based on packet inter-arrival time (sometimes called time difference of arrival (TDOA)) averaging. The technique is very simple to implement but provides good performance only when packet losses and packet delay variation (PDV) are very low and well controlled. This technique has not been fully characterized analytically in the literature. In this paper, we provide a full analytical examination of this well-known clock recovery technique. We analyze the effects of correlation of the PDV experienced by the constant bit rate (CBR) traffic stream on the quality of the clock recovered by a receiver. We prove analytically that, for a general input process, high correlation of the PDV produces a large variance of the recovered clock. The paper also describes simple all-digital implementations of the clock recovery scheme using standard digitally controlled oscillators (DCOs).

Design of rate-based controllers for active queue management in TCP/IP networks

In our previous work [J. Aweya, M. Ouellette, D. Montuno, K. Felske, Rate-based proportional-integral control scheme for active queue management, International Journal of Network Management, John Wiley & Sons, Ltd., vol. 16, issue 3, May-June 2006, pp. 203-231] we argued that rate-based active queue management (AQM) schemes are most appropriate for high speed links which, typically, have small buffers in relation to the bandwidth-delay product of the link. We continue our discussion in this paper to study the performance of other rate-based AQM controllers. We consider integral (I) and proportional (P) rate-based controllers for the AQM problem, we then characterize all stabilizing feedback gains for the closed-loop TCP/AQM system. Using a network topology with short- and long-lived TCP flows, we present simulation results for the rate-based AQM controllers. We observe that the I-controller is able to control properly the system compared to the P-controller. The P-controller in most cases produces offsets from the target values. To further support our observations, we use a closed-loop control model and control theory to explain why the P-controller has major limitations in the control of a first-order plant like our TCP/AQM first-order plant.

Enhanced EPON auto-discovery for fast network and service recovery

The Ethernet passive optical network (EPON) is an emerging broadband access networking technology that offers flexible bandwidth with simplicity, reliability and cost effectiveness. The automated discovery of optical network units (ONU) and the coordination of the operation between ONU and the optical line termination (OLT) is the mandate of the multi-point control protocol (MPCP). The auto-discovery mechanism is for finding newly attached ONU as well as reconnecting active (or recovered) ONU in case of service interruptions. On the basis of the IEEE 802.3ah MPCP, this paper introduces a set of enhancements to the auto-discovery mechanism. With these improvements, the EPON MPCP is able to support carrier-grade telecommunications services by recovering quickly from failures with minimum service impact. Moreover, it leads to a scalable and efficient scheme for balancing system response and bandwidth efficiency.

Clock synchronization for packet networks using a weighted least-squares error filtering technique and enabling circuit emulation service

Circuit emulation service (CES) allows time-division multiplexing (TDM) services (T1/E1 and T3/E3 circuits) to be transparently extended across a packet network. With circuit emulation over IP, for instance, TDM data received from an external device at the edge of an IP network is converted to IP packets, sent through the IP network, passed out of the IP network to its destination, and reassembled into TDM bit stream. Clock synchronization is very important for CES. This paper presents a clock synchronization scheme based on a double exponential filtering technique and a linear process model. The linear process model is used to describe the behaviour of clock synchronization errors between a transmitter and a receiver. In the clock synchronization scheme, the transmitter periodically sends explicit time indications or timestamps to a receiver to enable the receiver to synchronize its local clock to the transmitters clock. A phase-locked loop (PLL) at the receiver processes the transmitted timestamps to generate timing signal for the receiver. The PLL has a simple implementation and provides both fast responsiveness (i.e. fast acquisition of transmitter frequency at a receiver) and significant jitter reduction in the locked state. Copyright

Clock synchronization using a linear process model

In this paper, we present a clock synchronization scheme based on a simple linear process model which describes the behaviors of clocks at a transmitter and a receiver. In the clock synchronization scheme, a transmitter sends explicit time indications or timestamps to a receiver, which uses them to synchronize its local clock to that of the transmitter. Here, it is assumed that there is no common network clock available to the transmitter and the receiver and, instead, the receiver relies on locking its clock to the arrival of the timestamps sent by the transmitter. The clock synchronization algorithm used by the receiver is based on a weighted least-squares criterion. Using this algorithm, the receiver observes and processes several consecutive clock samples (timestamps) to generate accurate timing signals. This algorithm is very efficient computationally, and requires the storage of only a small number of clock samples in order to generate accurate timing signals.

Fast-Unreserved Failure Restoration for Meshed Intelligent Photonic Networks

In this article, an unreserved restoration solution for fast failure restoration in intelligent photonic networks is proposed. The unreserved restoration scheme is a real-time restoration technique that allows for utilizing network capacity dynamically and with full flexibility. However, it has the disadvantage of having a long restoration time as real-time redials are required after a failure is detected. The restoration time is crucial because long restoration times can result in data loss that is not expected, especially in high-speed networks. The proposed method targets reducing the aggregated optical cross-connect switching time to minimize real-time failure restoration time. With the proposed solution, in an event of failure, the restoration time can be reduced to times that are similar to those achieved in the reserved schemes. Common unreserved schemes have an inherent need for retries because the first try after failure detection and notification cannot always be guaranteed due to lack of network resource. In this paper, an enhanced implementation for the proposed solution is designed and described, which allows the features of the proposed solution to be fully realized and overcomes the inherent drawback of redundant OXC switching events for retries in common unreserved schemes. Through simulation experiments, it is shown that under a given network condition, the real-time path setup time for failure restoration required in the proposed solution can be improved by ∼68% compared with the common unreserved schemes.