This paper proposes a novel ultra high-speed file server based on a personal computer (PC) to provide the instantaneous delivery of huge files, like movie files, graphic images and computer programs, over high-speed networks. In order to improve the sustained sequential read speed from arrays of hard drives to host memory in the server, two key techniques are proposed: "multi-stage striping (MSS)" and the "sequential file system (SFS)." An experimental file server based on a general-purpose PC is constructed and its performance is measured. The results show that the server offers ultra high read speeds, up to 105Mbytes/s, with just 8 hard drives.
Satoshi UEHARA Tsutomu MORIUCHI Kyoki IMAMURA
The maximum order complexity (MOC) of a sequence is a very natural generalization of the well-known linear complexity (LC) by allowing nonlinear feedback functions for the feedback shift register which generates a given sequence. It is expected that MOC is effective to reduce such an instability of LC as an extreme increase caused by the minimum changes of a periodic sequence, i. e. , one-symbol substitution, one-symbol insertion or one-symbol deletion per each period. In this paper we will give the bounds (lower and upper bounds) of MOC for the minimum changes of an m-sequence over GF(q) with period qn-1, which shows that MOC is much more natural than LC as a measure for the randomness of sequences in this case.
Yoshiaki SHIKATA Yoshitaka TAKAHASHI
We consider a finite-capacity single-server queue with constant service and vacation times, which is seen in the time division multiple access (TDMA) scheme. First we derive the probability that j customers remain in the queue when a test customer arrives. Using this probability we then evaluate the probability that the test customer who arrives during the vacation or service time has to wait in the queue for longer than a given time. From these results, we obtain the waiting time distribution for the customer arriving at an arbitrary time. We also show a practical application to wireless TDMA communications systems.
Onur ALTINTA Yukio ATSUMI Teruaki YOSHIDA
Packet scheduling is one of the key mechanisms that will be employed in the network nodes (routers and switches) for supporting multiple quality of services. In this paper we propose a new packet scheduling algorithm called Urgency-based Round Robin (URR) which computes an index for flows in order to keep track of instantaneous bursts. Basically the index is employed as a measure of the time-dependent service necessity for each flow thus making it possible to detect those flows which might be in need of momentary service. Also, we propose a novel weight allocation scheme to be used together with the scheduler with the aim of preventing network underutilization. Our algorithm can be considered as a version of Weighted Round Robin (WRR) with improved delay characteristics. We show analytically that URR has the desired capability of upper-bounding unfairness. We also show, by simulation, that URR can improve delay performance even under extremely bursty traffic conditions without bandwidth overprovisioning. We also give simulation results for network traffic which exhibits long range dependency (self-similarity) and show that URR is again more effective than a plain round robin multiplexer.
Siriporn PISANPATTANAKUL Miki YAMAMOTO Hiromasa IKEDA
One of the objectives of ABR traffic control is a fair allocation of transmission rate to every connection. Algorithms which have been proposed can achieve the fair allocation of transmission rate in persistent traffic, even though the connections have different number of hops. In bursty traffic, however, the transmission rate during the burst period, called average burst throughput, may become degraded when the number of hops increases. In this paper, we evaluate the average burst throughput characteristics of ERICA switch algorithm and investigate the effect of the number of hops. We propose a new bandwidth allocation method which can improve the performance degradation by taking the number of hops into account. The effectiveness of our method is evaluated by computer simulation.
An enhanced priority reservation algorithm for ATM multicast switches with a one-shot scheduling scheme is proposed. This algorithm is an input reservation method in which priority is selected among input ports considering the number of rejected copy requests and the blocked age of head-of-line (HOL) cells. The operation procedure of the proposed algorithm is described, and the average cell-delay and throughput performance is evaluated by simulation. The simulation results show that the proposed algorithm yields better performance than the conventional algorithms.
When wireless multi-media information such as voice, video, data and so on are transmitted, the difference required quality of Service (QoS) including required Bit Error Rate (BER), required information bit rate, message's delay constraints as well as traffic performance should be taken into account. A wireless multi-media system should achieve a flexible balance of these differences. In this letter, an Adaptive Chip/Bit Control Method is proposed for Wireless Multi-media CDMA System. The proposed method controls both chip and bit rate of each medium according to the offered traffic condition and the quality measurement of each medium. In the proposed method, measurement are carried out in the base station. Simulation results show that the proposed method not only maintain the required BER of each medium, but achieve a higher total throughput even in high traffic condition. Thus we see that the proposed method possesses higher flexible ability than conventional methods.
Toshiharu HIGUCHI Katsuhisa HOMMA Takahiro KAWAHARADA
Differences in the behavior of dispenser cathodes and oxide cathodes in laminar-flow type and crossover type electron guns were investigated by experiments and simulations under high-current-density conditions. When an oxide cathode is operated under such conditions, the heating effect due to Joule heat in the oxide layer exceeds the cooling effect, depending on the product of the work function and the cathode current, resulting in a rise in the cathode temperature. This rise in cathode temperature aggravates deterioration of emission characteristics during the life of an oxide cathode. In the case of the dispenser cathode, however, the cathode temperature decreases under high-current-density conditions. When an oxide cathode in a crossover type electron gun is operated, equipotential surfaces are formed in the curved surface in the oxide layer. The formation of an equipotential surface leads to relaxation of the loading. It is considered that this is the reason for the longer life of an oxide cathode in a crossover type electron gun than that of an oxide cathode in a laminar-flow type electron gun.
A convenient signaling scheme, termed orthogonal on-off BPSK (O3BPSK), along with a simple one-shot linear decorrelating detector (LDD) has been proposed by Zheng and Barton as a technique for near-far resistant detection in the asynchronous DS/CDMA systems. The temporally adjacent bits from different users in the received signals are decoupled by using the on-off signaling, and the data rate is maintained with no increase in transmission rate by adopting an orthogonal structure. The system performance of this signaling scheme in terms of bit error rate (BER) has been analyzed over an AWGN channel by Zheng and Barton. In this paper, we further study the system performance over Nakagami-m fading channel. A closed form for the BER of such a scheme is successfully derived. Numerical results show that the O3BPSK signal scheme along with the LDD receiver still offers a good near-far resistant property over Nakagami-m channel.
In this paper, a novel pass-transistor logic with an efficient level restoration circuit, named Power Saved Pass-transistor Logic (PSPL), is proposed. It is shown how, through the use of regenerative feedback with pMOS switches, we reduce the power consumption and propagation delay compared to conventional pass-transistor logic. To demonstrate the performance of PSPL, a 5454-bit multiplier is designed. For speed and power optimization, the multiplier uses high compression-rate compressors without Booth Encoding, and a 108-bit conditional sum adder with separated carry generation block. The measured multiplication time was 13. 5 ns in a 0. 6 µm single-poly triple-metal 3. 3 V CMOS process. Furthermore, a sequential circuit of a low power 7-bit serial counter is designed and fabricated in a 0. 6 µm single-poly triple-metal 3. 3 V CMOS process. The measured operating speed was 250 MHz.
Akira NAGAMI Hirofumi INADA Takaya MIYANO
A generalized radial basis function network consisting of (1 + cosh x)-1 as the basis function of the same class as Gaussian functions is investigated in terms of the feasibility of analog-hardware implementation. A simple way of hardware-implementing (1 + cosh x)-1 is proposed to generate the exact input-output response curve on an analog circuit constructed with bipolar transistors. To demonstrate that networks consisting of the basis function proposed actually work, the networks are applied to numerical experiments of forecasting chaotic time series contaminated with observational random noise. Stochastic gradient descent is used as learning rule. The networks are capable of learning and making short-term forecasts about the dynamic behavior of the time series with comparable performance to Gaussian radial basis function networks.
Akimasa HIRATA Yoshio YUSE Toshiyuki SHIOZAWA
In order to enhance the energy transfer efficiency in a Cherenkov laser, we propose to use a tapered waveguide with a dielectric thickness properly varied stepwise in the longitudinal direction. With the aid of particle simulation, we investigate the nonlinear characteristics of the Cherenkov laser with the tapered waveguide, demonstrating the effectiveness of our proposal for efficiency enhancement.
Yeali S. SUN Fu-Ming TSOU Meng Chang CHEN
As the current Internet becomes popular in information access, demands for real-time display and playback of continuous media are ever increasing. The applications include real-time audio/video clips embedded in WWW, electronic commerce, and video-on-demand. In this paper, we present a new control protocol R3CP for real-time applications that transmit stored MPEG video stream over a lossy and best-effort based network environment like the Internet. Several control mechanisms are used: a) packet framing based on the meta data; b) adaptive queue-length based rate control scheme; c) data preloading; and d) look-ahead pre-retransmission for lost packet recovery. Different from many adaptive rate control schemes proposed in the past, the proposed flow control is to ensure continuous, periodic playback of video frames by keeping the receiver buffer queue length at a target value to minimize the probability that player finds an empty buffer. Contrary to the widespread belief that "Retransmission of lost packets is unnecessary for real-time applications," we show the effective use of combining look-ahead pre-retransmission control with proper data preloading and adaptive rate control scheme to improve the real-time playback performance. The performance of the proposed protocol is studied via simulation using actual video traces and actual delay traces collected from the Internet. The simulation results show that R3CP can significantly improve frame playback performance especially for transmission paths with poor packet delivery condition.
Takuya KURAKAKE Mikio MAEDA Yasuhiro ITO Naoyoshi NAKAMURA Kimiyuki OYAMADA
We propose a method of reducing laser-clipping-induced distortion in a subcarrier multiplexed (SCM) optical-cable TV system. This scheme reduces amplitude peaks of the SCM signal by controlling the phases of video carriers to prevent the clipping which occurs when these peaks fall below the threshold of a laser-diode. It is experimentally shown that using this method reduces the bit error rate in an AM-VSB / QAM hybrid optical-transmission system.
Exception handling is not only useful for increasing program readability, but also provides an effective means to check and locate errors, so it increases productivity in large-scale program development. Some typical and frequent program errors, such as out-of-range indexing, null dereferencing, and narrowing violations, cause exceptions that are otherwise unlikely to be caught. Moreover, the absence of a catcher for exceptions thrown by API procedures also causes uncaught exceptions. This paper discusses how the exception handling mechanism should be supported by the compiler together with the operating system and debugging facilities. This mechanism is implemented in the compiler by inserting inline check code and accompanying propagation code. One drawback to this approach is the runtime overhead imposed by the inline check code, which should therefore be optimized. However, there has been little discussion of appropriate optimization techniques and efficiency in the literature. Therefore, a new solution is proposed that formulates the optimization problem as a common assertion elimination (CAE). Assertions consist of check code and useful branch conditions. The latter are effective to remove redundant check code. The redundancy can be checked and removed precisely with a forward iterative data flow analysis. Even in performance-sensitive applications such as telecommunications software, figures obtained by a CHILL optimizing compiler indicate that CAE optimizes the code well enough to be competitive with check suppressed code.
This paper describes a real-time connection admission control scheme for supporting multiple service categories. The scheme is based on a real-time cell-loss ratio evaluation algorithm for VBR based on peak/sustainable cell rates and maximum burst size. The algorithm is based on a notion of Allan variance of VP utilization. The most remarkable characteristics of the admission control scheme are that it terminates within constant time, a few milliseconds, and that its time is independent of both the number of VCs and the capacity of a cell buffer.
Disk arrays are widely accepted as a disk subsystem for video servers due to its high throughput as well as high concurrency. RAID-like disk arrays are usually managed in either RAID level 3 (a request is handled by all the disks in the system) or RAID level 5 (a request is handled by some number of disks subject to the request size) when they are used in video servers, i. e. , either only one video stream is handled at a time in RAID level 3 or a certain number of video streams are handled independently at the same time in RAID level 5. Note that RAID level 3 is inappropriate to handle large number of video streams and RAID level 5 is inefficient to handle multiple video streams since handling continuous video streams is inherently synchronous operation. In this paper, we propose a new video data layout scheme called region-based layout and synchronous management of RAID5 called synchronous RAID5 for disk array used in video servers. It is shown that we can reduce the amount of buffers required to support a given number of video requests by integrating our region-based layout with synchronous RAID5 scheme. Group Sweeping Scheduling (GSS) is used as a basic disk scheduling. We have shown through analysis that our proposed scheme is superior to the existing schemes in the respect of the buffer requirements.
The Multiwavelength Optical Networking (MONET) program consists of a consortium of industrial partners, working together with the intent to demonstrate the key capabilities needed for configurable WDM networks. This involves integrating WDM technologies with optical switching technologies to provide a managed, high capacity, national scale WDM server layer to transport optical signals transparently across multiple interworking subnetworks.
Hiroaki SANJOH Hiroyuki ISHII Hiroshi YASAKA Kunishige OE
Input-wavelength-insensitive tunable wavelength conversion was achieved in the range of 1530 to 1560 nm using cascaded semiconductor laser wavelength converters (a DFB laser and an SSG-DBR laser). The power penalty in the wavelength conversion of input signal between 1530 and 1555 nm, where the wavelength ranged between 1537 and 1557 nm, is less than 1 dB for 5 Gbit/s signals.
Yoshiharu MUROYA Kenji SATO Tetsuro OKUDA Takahiro NAKAMURA Hirohito YAMADA Toshitaka TORIKAI
Well-defined wavelength distributed feedback laser diodes (DFB-LDs) are required in WDM network systems. Since the EDFA gain bands have been expanded, even more wavelengths are needed for large-capacity dense-WDM transmission systems. A precisely pitch-controlled Bragg grating fabricated by electron beam (EB) lithography is very attractive for realizing these DFB-LDs. This paper describes this precise pitch- and phase-controlled grating delineated by a novel method called weighted-dose allocation variable-pitch EB-lithography (WAVE). In this method, an EB-dose profile for the grating is precisely controlled by a combination of the allocation and weighting of multiple exposures. This enables us to fabricate a precise fixed-pitch grating as well as a flexible grating with a continuously chirped structure. The stitching error at the exposure field boundary, the grating pitch, and the phase shift were evaluated by using a moire pattern generated by superimposing the microscope raster scan and the grating on a wafer. We also estimated amounts of the stitching errors from fabricated and calculated lasing characteristics, and clarified that the affect of the errors on the single-mode stability of LDs is negligible. Precise wavelength controlled λ/4 phase shifted DFB-LDs were successfully demonstrated as a result of both the WAVE method and the highly uniform MOVPE crystal growth.