Showing papers in "Journal of High Speed Networks in 1999"

Optical burst switching (OBS) - a new paradigm for an optical Internet

Abstract: To support bursty traffic on the Internet (and especially WWW) efficiently, optical burst switching (OBS) is proposed as a way to streamline both protocols and hardware in building the future generation Optical Internet. By leveraging the attractive properties of optical communications and at the same time, taking into account its limitations, OBS combines the best of optical circuit-switching and packet/cell switching. In this paper, the general concept of OBS protocols and in particular, those based on Just-Enough-Time (JET), is described, along with the applicability of OBS protocols to IP over WDM. Specific issues such as the use of fiber delay-lines (FDLs) for accommodating processing delay and/or resolving conflicts are also discussed. In addition, the performance of JET-based OBS protocols which use an offset time along with delayed reservation to achieve efficient utilization of both bandwidth and FDLs as well as to support priority-based routing is evaluated.

Terabit burst switching

Abstract: Demand for network bandwidth is growing at unprecedented rates, placing growing demands on switching and transmission technologies. Wavelength division multiplexing will soon make it possible to combine hundreds of gigabit channels on a single fiber. This paper presents an architecture for Burst Switching Systems designed to switch data among WDM links, treating each link as a shared resource rather than just a collection of independent channels. The proposed network architecture separates burst level data and control, allowing major simplifications in the data path in order to facilitate all-optical implementations. To handle short data bursts efficiently, the burst level control mechanisms in burst switching systems must keep track of future resource availability when assigning arriving data bursts to channels or storage locations. The resulting Lookahead Resource Management problems raise new issues and require the invention of completely new types of high speed control mechanisms. This paper introduces these problems and describes approaches to burst level resource management that attempt to strike an appropriate balance between high speed operation and efficiency of resource usage.

Optical burst switching (OBS) - a new paradigm for an optical Internet

Abstract: To support bursty traffic on the Internet (and especially WWW) efficiently, optical burst switching (OBS) is proposed as a way to streamline both protocols and hardware in building the future gener...

Optical crossconnects for high-capacity lightwave networks

Abstract: Optical crossconnects are rapidly emerging as critical elements for provisioning and restoration in high-capacity wavelength-division-multiplexed optical networks High port count appears to be emerging as particularly important in this core-network application, with 500-port optical crossconnects (OXCs) widely expected to be needed within about five years This requirement severely strains current optical-switching technologies The emergence of this new application is, however, beginning to stimulate new device technologies One of these is the free-space micromachined optical switch (FS-MOS) This approach combines the advantages of free-space interconnection and monolithic integrated optics, thus offering the possibility of achieving high port-count in a small, low-cost system with excellent optical quality In this paper, we review the fundamental principles, fabrication, and performance of the FS-MOS, and discuss both its port-count scalability and its ability to incorporate advanced optical-networking functionality within the switch fabric itself

A terabit IP switch router using optoelectronic technology

Abstract: Terabit IP switch router is a key to the success of next generation Internet (NGI) with its backbone capacity supporting exponentially increasing traffic. The challenges in designing a terabit IP switch router include (1) a large capacity switch fabric providing high speed interconnection for a number of smaller capacity router modules, and (2) a fast arbitration scheme resolving output contention within stringent time constraint while achieving high throughput and low delay. In this paper, an input-output buffered switch architecture with a speedup of two is employed; our simulation results show that it can nearly achieve the theoretic bound in average delay/throughput performance of an output buffered switch. We propose a 256\times 256 multicast optical interconnection network (OIN) based on advanced wavelength division multiplexing (WDM) technology as the switch fabric for terabit IP switch routers. Its component and interconnection complexity, and power budget are evaluated. A novel ping-pong arbitration (PPA) scheme is used to solve the output contention in the OIN. The arbitration time of an N-input switch can be achieved in the order of \log_4\lceil N/2\rceil. For instance, with N=256 the arbitration can be completed in 11 gates delay, less than 5 ns using the current CMOS technology, showing that the PPA scheme can support multiple terabit/s switch capacity.

Optical IP routers: design and performance issues under self-similar traffic

Abstract: The increased data traffic experienced today and the projected increase in the data traffic in the future demand exploration of novel approaches to IP transport such as transport of IP traffic over optics. The bimodal nature of the IP trafficc short packets which are typical of transactional-style flows and large packets or bursts which are encountered in the transport of large data blocks requires, design of routers that are capable of routing packets with variable lengths efficiently. In this paper, we discuss the design aspects of such all-optical IP-routers. The broadcast and select architecture is a prime candidate for implementing optical IP routers. Construction of optical routers with buffering, wavelength conversion and multipath routing are considered. The merits and demerits of all these cases and the effect of buffer size, wavelength conversion and multiple-path routing on the blocking probability and probability of packet loss are discussed.

Congestion control policies for wireless multimedia CDMA networks

Abstract: The issues of integrating multimedia traffic in the reverse (mobile to base station) link of wireless CDMA networks are studied. Due to their delay constraint, realtime (voice/video) services are subject to connection-level admission control. In order to maintain the quality of realtime voice/video traffic while fully utilizing the unused channel capacity, non-realtime data traffic follows burst-level congestion control. Two congestion control policies are introduced and their performance under 3 types of feedback information is compared. The impact of various system parameters, such as the traffic parameters (especially video) and the processing gain of the CDMA system are also quantified.

Reducing clean cell loss rate in wireless ATM networks

Abstract: In wireless asynchronous transfer mode (ATM) networks, the bit error rate is high and burst errors may occur in transmission due to jamming and fading. When single-bit error occurs in cell header, it can be easily corrected by the CRC-8 code in the HEC (Header Error Correction) field. However, HEC can not recover the cells with burst errors, and they will be lost or mis-routed accordingly. A strategy to spread each bit of a header field over the entire data field has been proposed to reduce the cell loss probability in wireless ATM networks. In such method, most burst errors are transformed into single-bit errors in header and the HEC is able to recover it. Intuitively, each corrected cell has a higher probability to contain incorrect payload due to burst errors. When network becomes congested, these dirty cells should be dropped first to reduce the number of error cells received by receiver. Meanwhile, the number of retransmitted cells is also reduced. In this paper, the cell payload error probability of a corrected cell is analyzed. A simple cell priority swapping mechanism and the cell discarding strategy are also introduced to reduce the clean cell loss rate on wireless ATM networks. To precisely recognize dirty cells, an efficient hybrid data/header interleaving strategy is proposed. The performance of proposed strategies are investigated by simulation. The simulation results show that the proposed strategies substantially reducing the clean cell loss rate.

Distributed and dynamic resource allocation in wireless ATM access networks

Abstract: Wireless ATM access networks are currently discussed intensely. In this article, the dynamic resource allocation within the MAC layer of WATM systems is discussed. Emphasizing ease of implementation, the protocols of WATMnet, MEDIAN, MBS and Magic WAND are compared. Based upon this, a novel MAC protocol is outlined that attempts to combine the benefits while avoiding some of the drawbacks of these projects. Central to this new scheme called Distributed and Dynamic Resource Allocation (DADRA) is the move of uplink traffic prediction and computation into the mobile terminals (MT), leaving the base station to collect precise demand requests and to coordinate media access. The reduced processing demand on the base station may lower equipment costs and increase the number of supported connections while the load on the individual MT is increased marginally.

Error protection for ATM-based wireless networking systems

Abstract: Variable rate error protection is required to support the broad range of quality of service (QoS) requirements for multimedia services in future Asynchronous Transfer Mode (ATM)-based wireless networking systems known as wireless ATM (WATM). In this paper, the performance of a rate-compatible punctured convolution (RCPC) coding scheme is examined. It provides adaptive forward error correction (FEC) at the physical (PHY) layer of the (non-ATM) wireless access segment, that interworks with the fixed ATM transport network. Bit error rate (BER) performance of the RCPC codes is evaluated for a range of wireless protocol data unit (PDU) formats. The throughput is also compared with well known Bose-Chaudhuri-Hocquenghem (BCH) and Reed-Solomon (RS) block codes. An hybrid automatic repeat request (ARQ)/FEC protocol that uses RCPC coding to distribute error protection between the wireless PHY and data link control (DLC) layers is also presented. Issues relating to complexity/cost trade-off, and effects of multipath fading, require further study.