Dynamic Buffer Allocation Research Articles

Packrat Parsing with Dynamic Buffer Allocation

Packrat parsing is a type of recursive decent parsing with guaranteed liner time parsing. For this,memoization technique is implemented in which all parsing results are memorized to avoid repetitive scanningof inputs in case of backtracking. The issue with this technique is large heap consumption for memoization whichout weigh the benefits. In many situations the developers need to make a tough decision of not implementingpackrat parsing despite the possibility of exponential time parsing. In this paper we present our developedtechnique to avoid such a tough choice. The heap consumption is upper bounded since memorized results arestored in buffer, capacity of which is decided at runtime depending on memory available in the machine. Thisdynamic buffer allocation is implemented by us in Mouse parser. This implementation achieves stableperformance against a variety of inputs with backtracking activities while utilizing appropriate size of memoryfor heap.

Implementation of Dynamic and Efficient Virtual Channel Router for Network on Chip with Virtual Channel Arbitration Reduction and Parallel Switch Allocation Unit

— Network on chip (NoC) is a new method of interconnecting modules in system on chip (SoC). Now a day, it is believed that this new communication subsystem will replace the bus-based architecture and will become dominant in SoC design technology. The performance of NoC mainly depends on the router so it is considered as the crucial part in the NoC design. This paper describes the different factors which affect the NoC performance and provides solution to solve these problems. The proposed router has three architectural modifications which makes it dynamic and efficient as compare to generic virtual channel router. This paper introduced the dynamic buffer allocation scheme in which virtual channels and buffer slots are selected and allocated dynamically depending on the network traffic conditions in real time which in turn increases the throughput. In this paper, we have focused on optimizing the virtual channel arbitration (VA) unit design and switch allocation (SA) unit design as well as focusing the maximum utilization of buffer so that it will result in minimizing the latency, area and power. The source code of the router is written in VHDL hardware description language and the simulation and synthesizing the router is done in Xilinx ISE Design Suite 13.1. The parameters like area, frequency, delay, power, latency and throughput are calculated. The results of this modified virtual channel router are compared with the generic virtual channel router. Keywords—Intellectual Property (IP), Network on Chip (NoC), Network Interface (NI), Switch allocation (SA), System-on-Chip (SoC), Virtual channel (VC), Virtual channel arbitration (VA)

On Optimal Buffer Allocation for Guaranteeing Quality of Service in Multimedia Internet Broadcasting for Mobile Networks

In this paper the problem of guaranteeing Quality of Service via optimal buffer allocation is considered: namely, we compute the optimal buffer with respect to a real-world dataset accounting for the expected data traffic volume for a predefined set of business users belonging to a mobile network scenario. Two distinct approaches are followed to tackle this issue, in a static and dynamic fashion, respectively: the former relies on nonlinear programming, while the latter relies on model predictive control. The proposed formulation in terms of optimal static buffer allocation enables the minimization of the wasted amount of data traffic in order to prevent users from paying the assignment of extra resources in addition to the available traffic bundle. Instead, optimal dynamic buffer allocation pushes resource optimization forward by enabling personalization: indeed, tracking the prediction of data traffic consumption for each user allows to satisfy personalized Quality of Service guarantees. Numerical simulations show the effectiveness of the proposed approaches in terms of buffer saving and decrease in Quality of Service mismatch.

Runtime buffer management to improve the performance in irregular Network-on-Chip architecture

This paper presents a heterogeneous adaptable router to reduce latency in irregular mesh Network-on-Chip (NoC) architectures. Regular mesh-based NoC architecture may become irregular due to variable sized IPs and needs new routing algorithms to ensure throughput. Therefore, an irregular NoC mesh is considered and an adaptive algorithm is used for routing. The performance measures such as throughput, latency, and bandwidth are defined at design time to guarantee the performance of NoC. However, if the application has to change its communication pattern, parameters set at design time (say buffer size) may result in large area and power consumption or increased latency. Routers with large input buffers improve the efficiency of NoC communication, but they incur excessive power dissipation and hardware overheads. Routers with small buffers reduce power consumption, but result in high latency. In the proposed NoC router, input buffers can be dynamically allocated, thereby, latency can be reduced. In a 4 × 4 irregular mesh NoC with a buffer depth of 4 slots, 20% reduction in latency and 9% increase in throughput are attained using dynamic buffer allocation. An 8 × 8 irregular mesh NoC with the proposed router is exposed to the synthetic traffics like uniform, bit complement, tornado and hotspot traffics and it offered a 30.42% reduction in overall average latency and 18.33% increase in overall saturation throughput. The proposed router outperformed the static router by 22.63% less average latency for E3S benchmark applications. For the same performance, maximum of 55% reduction in buffer requirement and 53% less power consumption is achieved.

Improving mobile network performance with two queueing buffer allocations of priority-based queueing scheme

As current mobile core network systems are expected to evolve into all-IP networks, packet switching will be a prerequisite for all mobile applications. Next-generation mobile networks, as envisioned by ITU-T, are packet-based networks capable of providing consistent and ubiquitous service to end users, independent of the network, access technology, and device used. This study discusses the differentiated packet forwarding performance of four major types of mobile network traffic under the proposed mobile network priority-based queueing (MPQ) scheme with two queueing buffer allocations, namely dynamic queueing buffer (DQB) allocation and overflow queueing buffer (OQB) allocation. As different queueing buffer allocations are adopted to store arriving packets in DQB and OQB, the MPQ scheme shows different packet forwarding performance under these two methods. In this study, we use ns2 (Network Simulator version 2) as the simulation platform to simulate several scenarios. The simulation results show that the MPQ scheme is able to support differentiated packet forwarding behavior for mobile traffic with both DQB and OQB allocations in a mobile core network. Some issues were identified in the MPQ scheme with both DQB and OQB allocation, which will need to be addressed.

Cooperative relaying in Wi-Fi networks with network coding

Recently, network coding has emerged as a new cooperative technique for improving network throughputs over traditional routing techniques. Network coding allows intermediate nodes to combine packets using an algebraic function before forwarding. Selfless cooperation by the intermediate nodes is thus implicitly assumed in the network employing network coding. Such cooperation in principle should not happen for free but for mutual benefits shared by source-destination pairs and the cooperating intermediate nodes. Effective resource allocation techniques are thus required to efficiently utilize the limited network resources at the intermediate nodes. In this article, we propose one such effective buffer allocation algorithm, called buffer equalized opportunistic network coding (BE-ONC), to dynamically exploit buffer spaces at a relay node of a relay-based IEEE 802.11 network. The BE-ONC technique combines packets opportunistically based on dynamic buffer allocation at the relay. Through simulations, we illustrate that the proposed scheme improves over the classical packet scheduling schemes in terms of delay and successful packet delivery ratio in a cooperative relay-based Wi-Fi network. Our experimental results further confirm the potential benefits of BE-ONC in terms of packet delivery ratio, when compared with first-in first-out scheduling at the relay node. The guidelines for extending our proposed scheme to a more general scenario, where more than two users are involved, and the relay is allowed to transmit its own packet, are also provided.

A Cross-Layer Resource Allocation Algorithm with Dynamic Buffer Allocation Mechanism

A novel cross-layer wireless resource allocation algorithm called DBMQT is proposed which distributes the resource based on dynamic buffer allocation mechanism for orthogonal frequency division multiplex access (OFDMA) system. The aim of allocation algorithm is to maximize system throughput while satisfying the QoS requirement for multi-user and multi-service. The algorithm consists of two steps. Firstly, with the assumption of a finite queue model for arrival packets, the scheme adjusts users’ buffer according to dynamic buffer allocation mechanism. In the second step, a distinct scheduling priority is defined for each user integrates MAC QoS requirements, queue status and PHY Channel State Information (CSI), assuming that the power is uniformly allocated on each subcarrier. Using these scheduling priorities, a scheduling rule for mixed traffics is proposed. Simulation results indicate that the proposed algorithm can achieve better performance in terms of system throughput, packet loss rate and efficiency of the buffer than tradition algorithm under enhancing QoS guarantees for different services.

A Study on Differentiated Service Queuing Scheme with an Overflow Buffer Allocation Within a UMTS Core Network

According to the QoS features of the four types of UMTS traffic, this study proposes a priority-based queuing scheme to support differentiated services among all UMTS traffic; it bases on packet transmission priorities of four types of UMTS traffic to handle packets forwarding in a gateway within a UMTS core network. In the proposed queuing scheme, a static dedicated logical queuing buffer allocation and a dynamic overflow buffer allocation are used to support packet enqueuing/dequeuing jobs. In this study, the ns2 network simulator is used as a simulation platform and different categories of simulation scenarios are executed. Moreover, the IETF DiffServ scheme is used as a comparison to understand the packet forwarding performance of the proposed scheme. By analyzing simulation data, two important points can be drawn. The proposed queuing scheme supports a differentiated packet forwarding behavior among four types of UMTS traffic. And, the differentiated packet forwarding behaviors with the proposed queuing scheme are similar to the packet forwarding behavior with the IETF DiffServ scheme.

이동망에서 IPTV 서비스 제공 시 핸드오버 시간과 지터를 고려한 동적 버퍼 할당 기법

이동망에서 멀티캐스트 기반으로 IPTV 제공 시 품질저하 없이 서비스를 제공하기 위해서는 핸드오버에 따른 패킷 손실과 영상 단절을 최소화하는 기법이 지원되어야 한다. 특히 버퍼링 기반의 기법들은 단말의 버퍼 크기에 따라 영상 단절이나 패킷 손실을 방지할 수 있으므로 높은 QoS를 요구하는 IPTV에 적합하다. 본 논문에서는 이동망 마다 패킷 손실과 영상 단절을 막기 위한 필요 버퍼량이 변화하는 것을 고려하여 이동 단말과 멀티캐스트 중계 노드의 버퍼 크기를 동적으로 변경하여 할당하는 DBAHAJ(Dynamic Buffer Allocation with Handover and Jitter) 기법을 제안한다. 본 기법은 핸드오버동안 영상 단절이 발생하지 않도록 단말의 핸드오버 시간을 고려하여 버퍼 크기를 할당한다. 이와 더불어 이동망에서 멀티캐스트 중계 노드의 종단 지연 차이에 따른 이동망에서 단말의 버퍼 보충량을 고려하여 이동 단말과 중계 노드의 버퍼크기를 동적으로 조절한다. 이와 같은 핸드오버 시간과 중계 노드의 지연 차이를 고려한 버퍼크기 조절을 통해 본 기법은 핸드오버 동안 영상 재생과 패킷 손실을 방지한다. 제안된 기법의 성능 검증을 위하여 NS-2 기반의 시뮬레이터를 설계하고 성능을 검증한 결과 IP 멀티캐스트와 오버레이 멀티캐스트 기반의 이동 환경에서 영상 단절과 패킷 손실을 100% 방지함을 확인하였다. To provide IPTV service over mobile networks, the mechanism that reduce packet loss and interrupt of multimedia service during the handover should be supported. Especially, buffering based mechanism is preferable for supporting IPTV services in the way of preserving streaming service using stored data and recovering non-received data after handover. But previous research doesn't consider the buffer allocation for applying various environments which can change handover time or end to end delay of relay node. This paper propose DBAHAJ mechanism that optimize buffer size of mobile nodes and relay node for supporting seamless IPTV service over mobile environments. Mobile node determines buffer size by checking handover time and maximum difference of sequence to keep playing video data. And multicast agent recovers packet loss during the handover by sending buffered data. By these two procedure, node supports seamless IPTV service on mobile networks. We confirm performance of this mechanism on NS-2 simulator.

Adaptive Channel Buffers in On-Chip Interconnection Networks— A Power and Performance Analysis

On-chip interconnection networks (OCINs) have emerged as a modular and scalable solution for wire delay constraints in deep submicron VLSI design. OCIN research has shown that the design of buffers in the router influences the energy consumption, area overhead, and overall performance of the network. In this paper, we propose a low-power low-area OCIN architecture by reducing the number of buffers within the router. To minimize the performance degradation due to the reduced buffer size, we use the already existing repeaters along the inter-router channels to double as buffers along the channel when required. At low network loads, the proposed adaptive channel buffers function as conventional repeaters, propagating the signals. At high network loads, the adaptive channel buffers function as storage elements in addition to the router buffers. The router buffers can be assigned either statically or dynamically to the incoming packets. Static allocation reserves equal buffer space partitioned among all of the incoming packets, whereas dynamic allocation reserves buffer space on a per-flit basis, enabling higher buffer occupancy. We evaluate the proposed adaptive channel buffers with both static and dynamic buffer allocation policies in the 90-nm technology node, using 8 times 8 mesh and folded torus network topologies. Simulation results using the SPLASH-2 suite benchmarks and synthetic traffic patterns show that, by reducing the router buffer size, our proposed architecture achieves nearly 40 percent savings in router buffer power, 30 percent savings in overall network power, and 41 percent savings in area, with only a marginal 1-5 percent drop in throughput under dynamic buffer allocation and about 10-20 percent drop in throughput for statically assigned buffers.

Dynamic Line Balancing and Buffer Allocation for Reacting to Unstable Changes in Demand

Dynamic Line Balancing and Buffer Allocation for Reacting to Unstable Changes in Demand

Optimal chaining scheme for video-on-demand applications on collaborative networks

By forwarding the server stream client by client, a chaining-based scheme is a good way to reduce the server streams for streaming applications in well-connected networks. In this paper, we prove that the minimum number of required server streams in such schemes is n-k+1, where n is the number of client requests and k is a value determined by client buffer sizes and the distribution of requests. In addition, we present an optimal chaining algorithm using a dynamic buffer allocation strategy. Compared to existing chaining schemes, our scheme not only utilizes the backward (basic chaining) and/or forward (adaptive chaining) buffer, but also exploits the buffers of other clients in order to extend the chain as much as possible. In this way, more clients can be chained together and served by the same server stream. Our simulation results show that the requirements of the server streams in the presented scheme are much lower those of existing chaining schemes. We also introduce mechanisms for handling VCR functions and fault exceptions in practical applications.

Performance improvement of dynamic buffered ATM switch

Performance of ATM networks depends on switch performance and architecture. This paper presents a simulation study of a new dynamic allocation of input buffer space in ATM switching elements. The switching elements are composed of input and output buffers which are used to store received and forwarded cells, respectively. Efficient and fair use of buffer space in an ATM switch is essential to gain high throughput and low cell loss performance from the network. In this paper, input buffer space of each switching element is allocated dynamically as a function of traffic load. A shared buffer pool is provided with threshold-based virtual partition among input ports, which supplies the necessary input buffer space as required by each input port. The system behaviour under varying traffic loads has investigated using a simulation program. Also, a comparison with a static allocation scheme shows that the threshold based dynamic buffer allocation scheme ensures an increased network throughput and a fair share of the buffer space even under bursty loading conditions.

Queueing systems for multiple FBM-based traffic models

AbstractA multiple fractional Brownian motion (FBM)-based traffic model is considered. Various lower bounds for the overflow probability of the associated queueing system are obtained. Based on a probabilistic bound for the busy period of an ATM queueing system associated with a multiple FBM-based input traffic, a minimal dynamic buffer allocation function (DBAF) is obtained and a DBAF-allocation algorithm is designed. The purpose is to create an upper bound for the queueing system associated with the traffic. This upper bound, called a DBAF, is a function of time, dynamically bouncing with the traffic. An envelope process associated with the multiple FBM-based traffic model is introduced and used to estimate the queue size of the queueing system associated with that traffic model.

Dynamic buffer allocation in video-on-demand systems

In video-on-demand (VOD) systems, as the size of the buffer allocated to user requests increases, initial latency and memory requirements increase. Hence, the buffer size must be minimized. The existing static buffer allocation scheme, however, determines the buffer size based on the assumption that the system is in the fully loaded state. Thus, when the system is in a partially loaded state, the scheme allocates a buffer larger than necessary to a user request. This paper proposes a dynamic buffer allocation scheme that allocates to user requests buffers of the minimum size in a partially loaded state, as well as in the fully loaded state. The inherent difficulty in determining the buffer size in the dynamic buffer allocation scheme is that the size of the buffer currently being allocated is dependent on the number of and the sizes of the buffers to be allocated in the next service period. We solve this problem by the predict-and-enforce strategy, where we predict the number and the sizes of future buffers based on inertia assumptions and enforce these assumptions at runtime. Any violation of these assumptions is resolved by deferring service to the violating new user request until the assumptions are satisfied. Since the size of the current buffer is dependent on the sizes of the future buffers, it is represented by a recurrence equation. We provide a solution to this equation, which can be computed at the system initialization time for runtime efficiency. We have performed extensive analysis and simulation. The results show that the dynamic buffer allocation scheme reduces initial latency (averaged over the number of user requests in service from one to the maximum capacity) to 1/29.4 /spl sim/ 1/11.0 of that for the static one and, by reducing the memory requirement, increases the number of concurrent user requests to 2.36 /spl sim/ 3.25 times that of the static one when averaged over the amount of system memory available. These results demonstrate that the dynamic buffer allocation scheme significantly improves the performance and capacity of VOD systems.

A multi-queue TCP window control scheme with dynamic buffer allocation

Abstract Explicit transmission control protocol (TCP) window control through the modification of the receiver’s advertised window in ACK packets is one of the ways intermediate network elements can contribute to the end-to-end TCP control. The TCP receiver’s advertised window, which indicates the level of the receive buffer of a TCP connection, limits the maximum window and consequently the throughput that can be achieved by the TCP sender. Thus, appropriate reduction of the advertised window by intermediate network elements can control the number of packets sent from a TCP sender. This paper describes a TCP window control scheme for a shared memory system with multiple queues. A dynamic buffer threshold, computed using a simple recursive algorithm, is used to dynamically allocate buffer space to the queues.

An accurate and practical buffer allocation model for the buffer cache based on marginal gains

A new dynamic buffer allocation strategy based on the notion of marginal gains is presented for the buffer cache that is used by the operating system to store frequently accessed disk blocks in main memory, and the performance of the proposed strategy is compared with those of previous allocation strategies. In the proposed strategy, marginal gain values are predicted by exploiting functions that approximate the expected number of buffer hits per unit time. Experimental results from both trace-driven simulation and an actual implementation in the FreeBSD operating system show that the proposed strategy accurately predicts the marginal gain values for various workloads resulting in significantly improved buffer hit ratios.

Dynamic buffer allocation in video-on-demand systems

In video-on-demand (VOD) systems, as the size of the buffer allocated to user requests increases, initial latency and memory requirements increase. Hence, the buffer size must be minimized. The existing static buffer allocation scheme, however, determines the buffer size based on the assumption that the system is in the fully loaded state. Thus, when the system is in a partially loaded state, the scheme allocates a buffer larger than necessary to a user request. This paper proposes a dynamic buffer allocation scheme that allocates to user requests buffers of the minimum size in a partially loaded state as well as in the fully loaded state. The inherent difficulty in determining the buffer size in the dynamic buffer allocation scheme is that the size of the buffer currently being allocated is dependent on the number of and the sizes of the buffers to be allocated in the next service period. We solve this problem by the predict-and-enforce strategy , where we predict the number and the sizes of future buffers based on inertia assumptions and enforce these assumptions at runtime. Any violation of these assumptions is resolved by deferring service to the violating new user request until the assumptions are satisfied. Since the size of the current buffer is dependent on the sizes of the future buffers, the size is represented by a recurrence equation. We provide a solution to this equation, which can be computed at the system initialization time for runtime efficiency. We have performed extensive analysis and simulation. The results show that the dynamic buffer allocation scheme reduces initial latency (averaged over the number of user requests in service from one to the maximum capacity) to 1 ÷ 29.4 ≁ 1 ÷ 11.0 of that for the static one and, by reducing the memory requirement, increases the number of concurrent user requests to 2.36 ∼ 3.25 times that of the static one when averaged over the amount of system memory available. These results demonstrate that the dynamic buffer allocation scheme significantly improves the performance and capacity of VOD systems.

Buffer Management Simulation in Atm Networks

Computer networking communications are now in the era of dedicated, high-speed switched networks. Asynchronous Transfer Mode (ATM) networks are increasing in importance because ATM technology has the ability to deliver a high quality of service, while simultaneously supporting multiple classes of traffic on the same transmission pathway. Traffic management is increasingly becoming an important focus of study in ATM networks. In this context, congestion control through adequate buffering is becoming particularly significant to minimize the probability of cell loss and cell delay when multiple large traffic bursts are received concurrently at a switch [1,2]. This paper presents a simulation of a new dynamic buffer allocation management scheme in ATM networks. To achieve this objective, an algorithm that detects congestion and updates the dynamic buffer allocation scheme was developed for the OPNET simulation package via the creation of a new ATM module. This dynamic buffer allocation scheme utilizes four identified attributes: in-use bandwidth, in-use bandwidth of distinct Quality of Service (QoS) of an incoming traffic, available number of buffers on the corresponding logical queue, and the latest short-term cell arrival rate destined to the corresponding output port. The behavior of the network under bursty traffic conditions was examined.

Traffic control through in-service monitoring for QoS improvement in ATM networks

Asynchronous transfer mode (ATM) networks are expected to support multimedia communications with diverse traffic characteristics, these traffic are statistically multiplexed to efficiently utilize the network bandwidth. However, the high bandwidth utilization may deteriorate traffic-dependent quality of service (QoS). To accommodate QoS requirements while still maintaining high bandwidth utilization, it is necessary to prioritize user's service requirements through effective resource management. This article presents a traffic control approach through in-service monitoring, which employs dynamic buffer allocation to allow complete buffer sharing by all service classes as well as improves QoS of delay-sensitive traffic using the so-called Earliest Expected Due-time First scheduling. The simulation results demonstrate that diverse multimedia traffic achieves satisfactory performance using our scheme. A feasible implementation architecture is also addressed.