Small Buffer Size Research Articles

Improving Wireless TCP Throughput by a Novel TCM-Based Hybrid ARQ

A novel hybrid ARQ (HARQ) scheme using a concatenated two-state trellis-coded modulation (CT-TCM) code is proposed for improving wireless TCP throughput. A distinguished feature of the proposed scheme is that the heavily punctured TCM codes are used for retransmissions of the corrupted data block, which are combined at the receiver with the previously received sequences of the same data block for decoding. By this method, significantly improved coding gain and efficient spectrum utilization can be achieved with very low complexity. A Markov model is developed to evaluate TCP throughput over the proposed HARQ in wireless link. By both analysis and simulation, we demonstrate that compared with other existing TCM-based ARQ schemes, significant improvement of TCP throughput over wireless links is achieved by the proposed CT-TCM HARQ while smaller buffer size is required at the access point.

Simulation Perspectives on Link Buffer Sizing

The problem of determining the optimal buffer size for an Internet link has recently attracted the strong revived attention of networking scientists. While consonant in dissenting from the conventional wisdom to set the buffer size to the product of the link bitrate and round-trip propagation delay of served connections, the new studies often propose alternative guidelines that starkly contradict each other. In this paper, we review the problem of link buffer sizing from two simulation perspectives. First, we use the packet-level simulator ns-2, which is currently the predominant tool for evaluation of network designs, to explore the contradictions between the buffer sizing guidelines. We attribute the contradictions to differences in assumptions and goals of the earlier studies and present our own argument for using small constant buffer sizes. Second, we reflect on the suitability of ns-2 itself for studying the problem of link buffer sizing. We the identify ns-2 deficiencies that undermine the trustworthiness of results provided by this prevailing simulation tool. We also suggest directions and discuss challenges for designing a simulation methodology capable of providing undisputed answers on link buffer sizing.

Low-delay rate control for real-time H.264/AVC video coding

This paper presents an efficient rate control scheme for the H.264/AVC video coding in low-delay environments. In our scheme, we propose an enhancement to the buffer-status based H.264/AVC bit allocation method. The enhancement is by using a PSNR-based frame complexity estimation to improve the existing mean absolute difference based (MAD-based) complexity measure. Bit allocation to each frame is not just computed by encoder buffer status but also adjusted by a combined frame complexity measure. To prevent the buffer from undesirable overflow or underflow under small buffer size constraint in low delay environment,the computed quantization parameter (QP) for the current MB is adjusted based on actual encoding results at that point. We also propose to compare the bits produced by each mode with the average target bits per MB to dynamically modify Lagrange multiplier (/spl lambda//sub MODE/) for mode decision. The objective of QP and /spl lambda//sub MODE/ adjustment is to produce bits as close to the frame target as possible, which is especially important for low delay applications. Simulation results show that the H.264 coder, using our proposed scheme, obtains significant improvement for the mismatch ratio of target bits and actual bits in all testing cases, achieves a visual quality improvement of about 0.6 dB on the average, performs better for buffer overflow and underflow,and achieves a similar or smaller PSNR deviation.

패킷 손실률에 기반한 효율적인 TCP Buffer Tuning 알고리즘

기존 TCP 기술은 송<TEX>${\cdot}$</TEX>수신측에 각각 고정된 크기의 버퍼를 할당하기 때문에 높은 대역폭(High-Bandwidth) 및 큰 전송지연(High Delay)을 가진 통신에는 적합하지 못하다. 따라서 종단간의 TCP 처리량을 개선하기 위해 통신망 상황에 따라 자동으로 TCP 버퍼를 조절하려는 시도가 있어왔다. ATBT(Automatic TCP Buffer Tuning)에서 송신측은 현재의 혼잡 제어 윈도우(CWND)의 값에 따라 송신 버퍼 크기를 조절하고 수신측은 운영체제가 정해ens 최대 크기의 TCP 버퍼 값으로 수신 버퍼 크기를 고정한다. DRS(Dynamic Right Sizing) 에서는 이전에 수신한 TCP 데이터의 두 배를 현재 송신할 TCP 데이터라고 예측함으써, TCP 수신측은 단순히 이에 따라 수신 버퍼 크기를 동적으로 변화시킨다. 그렇지만 TCP 세그먼트의 손실 가능성으로 인해 정확히 두 배로 버퍼 크기를 변화시킬 필요는 없다. 따라서 우리가 제안한 패킷 손실률에 기반한 효율적인 TCP 버퍼 조절 알고리즘(TBT-PLR:TCP Buffer Tuning Algorithm based on Packet Loss Ratio)은 TCP 송신측에는 ATBT 방법을 TCP 수신측에는 TBT-PLR 방법을 적용하였다. 실제 TCP 성능을 테스트하기 위해서 리눅스 커널 2.4.18을 수정하여 구현하였으며 기존의 고정된 크기의 TCP 버퍼를 가진 경우와 버퍼 크기가 동적으로 변하는 TBT-PLR을 적용한 경우를 비교하였다. 결과적으로, TCP 연결들간의 균형있는 메모리 사용으로 인해 성능 향상을 얻을 수 있었다. Tho existing TCP(Transmission Control Protocol) is known to be unsuitable for a network with the characteristics of high RDP(Bandwidth-Delay Product) because of the fixed small or large buffer size at the TCP sender and receiver. Thus, some trial cases of adjusting the buffer sizes automatically with respect to network condition have been proposed to improve the end-to-end TCP throughput. ATBT(Automatic TCP fluffer Tuning) attempts to assure the buffer size of TCP sender according to its current congestion window size but the ATBT assumes that the buffer size of TCP receiver is maximum value that operating system defines. In DRS(Dynamic Right Sizing), by estimating the TCP arrival data of two times the amount TCP data received previously, the TCP receiver simply reserves the buffer size for the next arrival, accordingly. However, we do not need to reserve exactly two times of buffer size because of the possibility of TCP segment loss. We propose an efficient TCP buffer tuning technique(called TBT-PLR: TCP buffer tuning algorithm based on packet loss ratio) since we adopt the ATBT mechanism and the TBT-PLR mechanism for the TCP sender and the TCP receiver, respectively. For the purpose of testing the actual TCP performance, we implemented our TBT-PLR by modifying the linux kernel version 2.4.18 and evaluated the TCP performance by comparing TBT-PLR with the TCP schemes of the fixed buffer size. As a result, more balanced usage among TCP connections was obtained.

Routing and Time-Slot Assignment in Optical TDM Networks

Optical time-division multiplexing (O-TDM) networks can provide a finer bandwidth granularity than wavelength-division multiplexing networks, and will play an important role in future all-optical networks. Since optical buffers are expensive, a small buffer size will be the characteristic of O-TDM systems. This paper analyzes the problem of routing and time-slot assignment in O-TDM networks. The results lead to the proposal of a Dijkstra-like shortest-path routing scheme that intends to maximize the performance of an optical network with a small number of optical buffers. Performance evaluation of the proposed scheme is also presented.

Numerical accuracy of multipole expansion for 2-D MLFMA

A numerical study of the multipole expansion for the multilevel fast multipole algorithm (MLFMA) is presented. In the numerical implementation of MLFMA, the error comes from three sources: the truncation of the addition theorem; the approximation of the integration; the aggregation and disaggregation process. These errors are due to the factorization of the Green's function which is the mathematical core of the algorithm. Among the three error sources, we focus on the truncation error and a new approach of selecting truncation numbers for the addition theorem is proposed. Using this approach, the error prediction and control can be improved for the small buffer sizes and high accuracy requirements.

Design of an interactive video-on-demand system

We design an interactive video-on-demand (VOD) system using both the client-server paradigm and broadcast delivery paradigm. Between the VOD warehouse and customers, we adopt a client-server paradigm to provide an interactive service. Within the VOD warehouse, we adopt a broadcast delivery paradigm to support many concurrent customers. In particular, we exploit the enormous bandwidth of optical fibers for broadcast delivery, so that the system can provide many video programs and maintain a small access delay. In addition, we design and adopt an interleaved broadcast delivery scheme, so that every video stream only requires a small buffer size for temporary storage. A simple proxy is allocated to each ongoing customer, and it retrieves video from optical channels and delivers video to the customer through an information network. The proposed VOD system is suitable for large scale applications with many customers, and has several desirable features: 1) it can be scaled up to serve more concurrent customers and provide more video programs, 2) it provides interactive operations, 3) it only requires point-to-point communication between the VOD warehouse and the customer and involves no network control, 4) it has a small access delay, and 5) it requires a small buffer size for each video stream.

A novel scheme for streaming multimedia to personal wireless handheld devices

Delivering streaming video over wireless is an important component of many interactive multimedia applications running on personal wireless handheld devices. Such personal devices have to be inexpensive, compact, and lightweight. Wireless channels have a high channel bit error rate and limited bandwidth. Delay variation of packets due to network congestion and the high bit error rate degrades the quality of video at the handheld device. Multimedia application use a buffer at the handheld device smooth out the delay variation and improve the quality of streaming video. However, the buffer size has to be kept small in order to reduce the size, weight and power consumption of handheld devices. We propose a novel selective retransmission scheme for multimedia transmission over wireless networks. Our scheme is based on retransmission of only the most important information in a video in order to achieve a high quality of video. Our objective is to develop a simple cost effective scheme which offers an acceptable video quality over a noisy wireless channel using a small buffer size at the handheld device. We have developed an analytical model to determine the networking requirements, video quality as a function of video compression parameters and network error conditions, and optimally dimension the buffer at the handheld device.

Efficient buffer sharing in shared memory ATM systems with space priority traffic

In this letter we study the problem of the optimal design of buffer management policies within the class of pushout and expelling policies for a shared memory asynchronous transfer mode (ATM) switch or demultiplexer fed by traffic containing two different space priorities. A numerical study of the optimal policies for small buffer sizes is used to help design heuristics applicable to large buffer sizes. Simulation studies for large buffer systems are then presented.

A Dynamic Granularity Control Algorithm for Avoiding TCP Deadlocks over Congested ATM Networks

Conventional TCP suffers throughput deadlocks over congested ATM (Asynchronous Transfer Mode) networks due to retransmission timeouts caused by cell loss at ATM level under heavy congestion. A modified congestion control algorithm for TCP is proposed to improve the effective throughput of IP over ATM UBR even in a situation such that an external CBR pressure exist at the same port of the ATM switch. When TCP faces congestion then TCP will reset its retransmission timer. In the proposed algorithm, the MSS (maximum segment size) is reduced from 9140 bytes, the recomended value in RFC 1612, at the same time. When TCP is in fast retransmit machine phase, the MSS is reduced to 512 bytes. A considerable improvement in the effective throughput of TCP has been achieved by these two modifications under relatively small switch buffer size and high CBR stream pressure. The idea, called “Dynamic Granularity Control (DGC)”, have been implemented and evaluated on the Linux kernel.

PCRTT Enhancement for Off-Line Video Smoothing

An enhancement of the Piecewise Constant Rate Transmission and Transport (PCRTT) algorithm for reducing the burstiness of a video stream, based on smoothing constant interval is proposed. The new algorithm, called e-PCRTT, relies on geometrical consideration rather than traditional rate-control analysis. E-PCRTT is shown to construct transmission rate-plans with smaller buffer sizes, as compared to the original PCRTT. Alternatively, for the same buffer size, e-PCRTT reduces the number of bandwidth changes as compared to PCRTT. In addition, e-PCRTT produces a rate-plan that requires a smaller initial playback delay.

An accurate bit-rate control for real-time MPEG video encoder

In this paper, we present a novel framework for the forward bit-rate control method for a real-time MPEG video encoder. First, we propose bit-rate estimation and control algorithms based on the linear relationship between the actually generated bit count and the codeword count. Then, we also propose an encoder architecture for real-time MPEG video. Simulation results show that the proposed algorithm provides more accurate controllability and better picture quality than those of the MPEG TM5. Since the proposed buffer control algorithm can be managed efficiently even for small buffer sizes, it can be used for low-cost communication terminals or consumer-oriented products.

The UniMIN switch architecture for large-scale ATM switches

A general expansion architecture is proposed that can be used in building large-scale switches using any type of asynchronous transfer mode (ATM) switch. The proposed universal multistage interconnection network (UniMIN) switch is composed of a buffered distribution network (DN) and a column of output switch modules (OSMs), which can be any type of ATM switch. ATM cells are routed to their destination using a two-level routing strategy. The DN provides each incoming cell with a self-routing path to the destined OSM, which is the switch module containing the destination output port. Further routing to the destined output port is performed by the destination OSM. Use of the channel grouping technique yields excellent delay/throughput performance in the DN, and the virtual FIFO concept is used for implementing the output buffers of the distribution module without internal speedup. We also propose a "fair virtual FIFO" to provide fairness between input links while preserving cell sequence. The distribution network is composed of one kind of distribution module which has the same size as the OSM, regardless of the overall switch size N. This gives good modular scalability in the UniMIN switch. Performance analysis for uniform traffic and hot-spot traffic shows that a negligible delay and cell loss ratio in the DN can be achieved with a small buffer size, and that DN yields robust performance even with hot-spot traffic. In addition, a fairness property of the proposed fair virtual FIFO is shown by a simulation study.

Fast simulation of queues with long-range dependent traffic

Self-similar stochastic processes have been proposed as more accurate models of certain categories of traffic (e.g., Ethernet traffic, variable-bit-rate video). Analytical and simulation approaches applicable to traditional traffic models may not be applicable to these categories of traffic due to their long range dependence Existing analytical results for the tail distribution of the waiting time in a single server queue based on Fractional Gaussian Noise and large deviation theory, are valid under a steady-state regime and for asymptotically large buffer sizes. Predicted performance based on steady-state regimes may be overly pessimistic for practical applications. Analytical approaches to obtain transient queueing behavior and queueing distributions for small buffer sizes become quickly intractable In this paper, we develop a fast simulation approach based on importance sampling that we use to simulate the queueing behavior of self-similar processes in a multiplexer, including the estimation of very low cell-loss probabilities. We describe two heuristic approaches, a simpler one, as well as a second heuristic approach, inspired by asymptotically efficient simulation of general Gaussian processes. Our simulation experiments provide insight on transient behavior that is not possible to predict using current analytical results. Finally, our simulations show good agreement with existing results when approaching steady-state

Scalable shared-buffering ATM switch with a versatile searchable queue

The shared-buffering architecture is promising to make a large-scale ATM switch with small buffer size. However, there are two important problems, namely, memory-access speed and complex-control implementation. Advanced 0.5 /spl mu/m CMOS technology now makes it possible to integrate a huge amount of memory, and enables us to apply more sophisticated architecture than ever before. We propose the funnel-structured expandable architecture with shared multibuffering and the advanced searchable-address queueing scheme for these two problems. The funnel structure gives a flexible capability to build various sizes of ATM switches which are proportional to the number of LSI chips. The searchable-address queue, in which all the addresses of the stored cells for different output ports are queued in a single-FIFO hardware and the earliest address is found by the search function provided inside the queue, can reduce the total memory capacity drastically, and enables the address queue to be contained inside the LSI chip. This technique also has a great advantage for implementing the multicast and multilevel priority-control functions. A 622 Mbit/s 32/spl times/8 ATM switch LSI chip set, which consists of a BX-LSI and a CX-LSI, is developed using 0.5 /spl mu/m pure CMOS technology. By using four chip sets, a 622 Mbit/s 32/spl times/32 switch can be installed on one board.

A continuous-flow model for production networks with finite buffers, unreliable machines, and multiple products

This paper presents a flow approximation of production networks with finite buffers and unreliable machines. Parts of various types compete for service before a machine, or they may be assembled before service to yield a composite part. Up times and down times of machines have arbitrary but known distributions and service times have gamma distributions, or may be constant quantities. Random service times are approximated by piece wise deterministic variables. Acyclic networks are considered first. The model is a combination of discrete-event simulation and analysis. The simulator keeps track of the buffer and machine states. Between two consecutive state transitions, flow rates remain constant and the model calculates the cumulative flow of each part type. Compared to a conventional simulator, the model is superior in speed and very accurate. An alternative model is developed for nonacyclic production networks where each machine provides service to different parts repetitively. The model is employed to simulate a re-entrant production line under a class of heuristic scheduling policies. The optimal policy is the one that meets demand while maintaining small buffer sizes and short delays of parts.

Optical input buffers for the HiPower photonic ATM switch-analysis and experiments

We describe an optical input buffer for the HiPower photonic ATM switch. This buffer can control the cell throughput in accordance with back pressure signals and incoming optical cells. We analyze the cell loss probability of the optical input buffer. Only a small buffer size of five is needed to obtain a cell loss probability of less than 10/sup -15/ with 1024 ports. Experimental 10 Gb/s operation using optical fiber delay lines with gate control circuits shows that the bit error rate of the buffer is less than 10/sup -12/.

Access control of bursty voice traffic in ATM networks

Asynchronous Transfer Mode (ATM) Broadband Networks are expected to provide a large number of services and applications. A predominant service will be the support of multimedia traffic applications that integrate different types of traffic (e.g., video, voice and data) over the same connection. The heterogeneous traffic-types differ, widely, not only in their individual bit-rates but also in their corresponding correlations and burstiness parameters. Access flow control algorithms are required to enforce and maintain a specific QOS for each type of traffic. In this paper, we present an effective access flow control algorithm that can be applied at the user to network interface (UNI). The scheme is based upon a preventive control principle and uses a control signal, that is function of the buffer occupancy level, to control the source coder sampling rate. The scheme avoids congestion and enhances the statistical multiplexing gain, consequently providing a higher bandwidth utilization for each QOS. We provide a performance analysis study, supported by simulations, of the access node multiplexer. We studied the resulting Quasi Birth Death queueing process, with state dependant arrivals, using matrix-geometric techniques, and found that both MMPP/Er/1/ K and the Poisson Process approximations provided very close results for an ATM multiplexer with small buffer size and access control.

Route discovery for multistage fabrics in ATM switching nodes

This paper presents an intra-node Route Discovery Protocol (RDP) applicable to multistage switch fabrics in nodes of ATM Local Area Networks (LANs), as well as in transit nodes of future high-speed Metropolitan or Wide Area Networks (MANs or WANs). The proposed RDP automatically builds and periodically updates routing tables in each network adapter. These routing tables contain the mapping between the logical adapter addresses and the currently available physical routes through the multistage switch fabric to all other adapters attached to the node. In addition, functional entities located at specific adapters are detected and associated with physical routes in the routing tables. Detecting all routes during system startup is the basis for fast connection setup with low latency. By periodically monitoring all possible table entries, our protocol provides continuous supervision of the node's internal link status and can support possible higher-layer extensions to perform load balancing over alternative routes. Small control buffers in network adapters, which are typical for practical implementations, may lead to overflow conditions and, thus, to incompletely updated routing tables. An effective stochastic solution to this problem is presented and it will be shown through probabilistic analysis that reasonably small buffer sizes suffice for executing RDP with sufficient robustness.

Buffer dimensioning for delay- and loss-sensitive traffic

Multiplexing of delay- and loss-sensitive traffic requires a common analytical framework for buffer dimensioning, buffer sharing schemes, as well as buffer entry and exit priorities. This paper performs a relevant study by employing discrete-time queueing techniques, appropriate for the small buffer sizes envisaged in ATM technology. The model, solution method and relevant metrics are presented. The numerical results are critically reviewed. These give rise to a buffer dimensioning algorithm. Loss requirements are primarily satisfied. However, an acceptable upper bound for the delay of the delay-sensitive traffic can also be accommodated.