Kazumi Kumazoe

Forward error correction in ATM networks: an analysis of cell loss distribution in a block

In almost all conventional transport protocols, ARQs (automatic repeat request) have been used to recover lost packets, in which receivers would request sources to retransmit lost packets. In these retransmission based error recovery schemes, the transmission delay can reach an unacceptable level for traffic with stringent delay constraints in high speed networks because their propagation delay is very large relative to packet transmission times. On the other hand, FEC (forward error correction) adds redundant packets to data ones, all of which are organized into a group called a block, and hence allows the receivers to correct some of the lost packets without retransmissions. This capability is desirable for high speed networks. The authors exactly analyze the distribution of the number of cells lost within a block in ATM networks with correlated cell arrivals, and examine the benefits due to FEC by means of the analysis.<<ETX>>

CapStart: An Adaptive TCP Slow Start for High Speed Networks

In this document, we introduce Cap Start TCP, an adaptive Slow Start scheme that consistently achieves fast TCP file transfer times regardless of high speed network scenario. Once the TCP session is established, we estimate TCP session path capacity scenario, and tune the transport protocol to deliver fast transfer times. We demonstrate significant transaction performance improvements, of as much as three times faster completion times in transcontinental high speed network experiments for various capacity scenarios.

Transport protocols for fast long-distance networks: comparison of their performances in JGN

Various new transport protocols have been proposed with the aim of the efficient use of abundant resources in fast long-distance networks, and a number of experiments to investigate the performances of those protocols have already been reported. However, they have mainly focused on the throughput characteristics of a single connection or under a stable condition, and thus, more variety of throughput characteristics in actual network environments should be investigated aiming at practical use. Therefore, in this paper, the throughput characteristics of some practical high-speed transport protocols, high-speed TCP (HSTCP), scalable TCP, and simple available bandwidth utilization library (SABUL) with multiple connections or with changes of competitive traffic are investigated through experiments on the Japan gigabit network (JGN), an open testbed in Japan, using implementations available to the public. For TCP-based protocols, the influence of the receiver-side OS (TCP implementation) on throughput performance is also investigated, which is of practical importance from the deployment viewpoint. On the basis of the results of these experiments, some considerations on transport protocols for fast long-distance networks are given.

Multiple Station Aggregation Procedure for Radio-On-Demand WLANs

With the rapid growth in Internet network infrastructure, there is an urgent need to deploy energy-efficient networking technology. In particular, there is a need for energy-efficient wireless local area networks (WLANs), which are widely used due to their ease of deployment and low installation costs. To realize this, radio-on-demand (ROD) have been proposed. Access points (APs) in ROD are equipped with wake-up receivers that change their status to sleep or active mode based on the network traffic distribution. This study proposes a station aggregation scheme targeting multiple stations (STAs) in ROD. In this scheme, APs cooperate with each other and aggregate their STAs based on their utilization. Simulation results demonstrate the effectiveness of the scheme in terms of power saving and load balancing in ROD networks.

Quality of assured service through multiple DiffServ domains

Differentiated service (DiffServ) is a technology which is proposed to provide quality of service (QoS) in the Internet, and it is superior to integrated service (IntServ) technology in respect to the simplicity of its architectures and the scalability of networks. Although various simulation studies and estimations over testbeds have investigated the QoS which is offered via the DiffServ framework, almost all of them were focused on the characteristics in a single DiffServ domain. However, the Internet is actually composed of a large number of AS (assured service) domains, and thus packets are very likely to arrive at their destinations through many different domains. From this viewpoint, we focus on the QoS performance in the model consisting of multiple DiffServ domains, especially we investigate quality of assured service to achieve statistical bandwidth allocation with AF-PHB (assured forwarding per hop behavior). Our simulation results show some throughput characteristics of flows over multiple DiffServ domains, and we also make it clear whether the network configurations and traffic properties have impacts on QoS over multiple DiffServ domains or not.

Performance Evaluation of Power Saving Scheme for Wireless LAN with Station Aggregation

The widespread deployment of wireless LANs (WLANs) has increased the importance of developing power-saving technologies. We have been involved in the research and development of Radio-On-Demand Networks (ROD) that reduce energy consumption in the operation of WLANs. In this paper, we evaluate the effectiveness of a power-saving scheme with that uses station aggregation for ROD WLANs by simulations. The simulation results show that our proposed scheme can contribute in reducing the power consumption of access points (APs).

Improving delay characteristics of real-time flows by adaptive early packet discarding

The quality of real-time applications is significantly affected by the delay of packets traversing a network Some real-time applications set limits for acceptable network delay, and thus, a packet delayed longer than this limit before arriving at its destination is not only worthless but also harmful to the quality of the application because it may increase the queuing delay of other packets Therefore, we propose an adaptive scheme for real-time applications in which such packets are discarded early In this scheme, packets experiencing too much delay are discarded at intermediate nodes based on the delay limit for the application and the delay experienced by each packet Such early discarding of packets is expected to improve the overall delay characteristics of real-time flows competing for network resources shared only by those flows Simulation results showed that our scheme is effective.

Masking lossy networks by TCP tunnel with Network Coding

Transmission Control Protocol (TCP) with Network Coding (TCP/NC) was designed to recover the lost packets without TCP retransmission to improve the goodput performance in lossy networks. However, TCP/NC is too costly to be implemented in some types of end devices, e.g., with less memory and power. In addition, TCP/NC across loss-free but thin networks may waste scarce link bandwidth due to the redundant combination packets sacrificed for the lossy network. In this paper, we propose the TCP/NC tunnel to convey end-to-end TCP sessions on a single TCP/NC flow traversing a lossy network between two special gateways without per-flow management. We implemented and validated our proposal in Network Simulator 3, in which each gateway runs a reinforced version of TCP/NC that we previously developed. The results show that the proposed TCP/NC tunnel can mitigate the goodput degradation of end-to-end TCP sessions traversing a lossy network without any change in TCP on each end host.

Making TCP/NC Adjustable to Time Varying Loss Rates

Applying network coding (NC) into the protocol stack has been studied with much attention in order to improve Transmission Control Protocol (TCP) goodput in inherently lossy networks (e.g., wireless networks in unstable environments). TCP with network coding (TCP/NC) is expected to recover the lost packets without retransmission at the sink by sending the redundant combination packets which are encoded at the source. While TCP/NC can work in theory, two problems have not been well solved especially in time-varying packet loss conditions. One is how to decide the good parameters (e.g., redundancy factor R) based on a recent network condition estimated from continuous observation. The other one is how to dynamically adapt an ongoing NC-layer process based on the decided parameters. Therefore, in this paper, we propose a functionally improved TCP/NC variant called the TCP/NC with loss rate estimation (TCP/NCwLRE) which can automatically adjust the NC-layer behaviors to adapt to time-varying channels. We implemented and validated our proposal in Network Simulator 3. The results show that the TCP/NCwLRE improves the TCP goodputs in time-varying non-correlated random loss channels.

Station aggregation scheme considering channel interference for radio on demand networks

With the rapid growth of the Internet, deploying energy-efficient networking technology is an urgent matter. In particular, wireless LAN (WLAN), which is widely used due to its ease of deployment and low cost of installation, is also required to be energy efficient. For this purpose, R & D activities for Radio-On-Demand-Networks (ROD) have been proposed. In ROD networks, access points (APs) have been equipped with wake-up receivers, switching their status to sleep mode, depending on the traffic distribution in the network. In the present paper, a station (STA) aggregation scheme in ROD networks considering channel interference is proposed. In this scheme, APs cooperate with each other and aggregate their STAs depending on the channel utilization information rather than the AP utilization. The simulation results reveal the scheme effectiveness in terms of power savings without throughput degradation in WLANs even in the presence of interference.