Buffer Management Scheme Research Articles

An adaptive and efficient buffer management scheme for resource-constrained delay tolerant networks

Provisioning buffer management mechanism is especially crucial in resource-constrained delay tolerant networks (DTNs) as maximum data delivery ratio with minimum overhead is expected in highly congested environments. However, most DTN protocols do not consider resource limitations (e.g., buffer, bandwidth) and hence, results in performance degradation. To strangle and mitigate the impact of frequent buffer overflows, this paper presents an adaptive and efficient buffer management scheme called size-aware drop (SAD) that strives to improve buffer utilization and avoid unnecessary message drops. To improve data delivery ratio, SAD exactly determines the requirement based on differential of newly arrived message(s) and available space. To vacate inevitable space from a congested buffer, SAD strives to avoid redundant message drops and deliberate to pick and discard most appropriate message(s) to minimize overhead. The performance of SAD is validated through extensive simulations in realistic environments (i.e., resource-constrained and congested) with different mobility models (i.e., Random Waypoint and disaster). Simulation results demonstrate the performance supremacy of SAD in terms of delivery probability and overhead ratio besides other metrics when compared to contemporary schemes based on Epidemic (DOA and DLA) and PRoPHET (SHLI and MOFO).

Contact expectation based routing for delay tolerant networks

In conventional networks, routing problem can be modeled as the design of an efficient source-to-destination route based on persistent end-to-end paths. However, in a delay tolerant network (DTN), nodes are intermittently connected and thus, the end-to-end paths will not always exist, in which routing is a challenging issue. Previous DTN routing protocols tend to make routing decision based on the nodes’ contact information. In this paper, we observe that considering both the nodes’ contact information and message property such as the time-to-live (TTL) would help to improve the performance. Embedded this idea, we first propose an expected encounter based routing protocol (EER) which distributes multiple replicas of a message proportionally between two encounters according to their expected encounter values. In case of a single replica of a message, EER makes the routing decision by comparing two encountering nodes’ minimum expected meeting delays to destination. We further propose a community aware routing protocol (CAR) which takes advantages of the high contact frequency property of the nodes within the same community. We also propose the buffer management strategies corresponding for the two protocols. We conduct simulations to evaluate our proposed protocols and some existing ones on three metrics: delivery ratio, latency and goodput. The simulation results illustrate that our proposed EER and CAR protocols outperform other existing ones.

A Knapsack-based buffer management strategy for delay-tolerant networks

In delay-tolerant networks, the dramatic change of topology and the frequent interruption of connections make it difficult to forward the message to destination. Routing protocols in DTNs seek to improve the delivery ratio through increasing the number of message copies. However, the redundant message copies easily cause the occurrence of buffer’s overflowing. In this paper, in order to maximize the utilization of network resources, especially when the bandwidth is limited and the message sizes are different, we present a theoretical framework called the Knapsack-based Message Scheduling and Drop strategy in Theory (KMSDT) based on Epidemic routing protocol. KMSDT sorts the messages in the buffer according to the per-unit utility and, if buffer overflows, decides which message to drop based on the solution to the knapsack problem. Furthermore, a practical framework called the Knapsack-based Message Scheduling and Drop strategy in Practice (KMSDP) is also developed. Rather than collecting the global statistics as done in KMSDT, KMSDP estimates all the parameters through the locally-collected statistics. Simulations based on both synthetic and real mobility traces are done in ONE. Results show that, without affecting the average delay and overhead ratio, KMSDP and KMSDT achieve better delivery ratio than other congestion control strategies.

선박 내 WiMedia WLP 기반 Mobile IP 네트워크에서 성능향상을 위한 버퍼관리

In this paper, we use WiMedia WLP-based networks to meet the demand for IT services of a ship. If a mobile node moves to a congested base station of a new subnetwork, we will propose a scheme for improving performance of radio link of existing communicating mobile nodes. An old base station denotes packets stored during a handover. And, a proposed buffer management determines to discard the buffered packets in accordance with congestion degree at the congested new base station. Simulation results show that the proposed buffer management scheme improves link utilization in congested wireless links.

Mobility Similarity-Based Routing in Buffer-Limited Delay Tolerant Networks

In delay tolerant networks (DTNs), multiple-copy routing is often adopted to improve the probability of successful message delivery but causes more traffic loads. The excessive increase in multiple messages copies often exhausts the network resources and deteriorates its performance significantly. To solve this problem, a mobility similarity-based routing (SBR) algorithm is proposed in this paper. On one hand, destination similarity is used to help the message carrier node find the appropriate relay nodes with the higher opportunity to meet the destination node in order to improve the delivery ratio. On the other hand, carrier similarity is adopted to avoid sending the same copy to the nodes with mobility similarity so as to reduce the number of message copies. Furthermore, inspired by the law of diminishing marginal utility in economics, a buffer management scheme based on the message transmission status is proposed. Experimental results show that the proposed SBR routing algorithm combined with the buffer management scheme can improve the delivery ratio and has the lower overhead ratio compared to other routing algorithms.

Reliable Packet Flow Control for Preventing Buffer Overflow in Wi-Fi Serial Bus

This letter proposes a novel buffer management scheme for improving the packet delivery of Universal Serial Bus (USB) services in wireless networks. In the future, USB may be used with various wireless services, most notably Wi-Fi, thus realizing Wi-Fi USB (WSB). However, data transmission of Wi-Fi and USB is asynchronous due to differences in their Medium Access Control (MAC), resulting in buffer overflow. To alleviate this problem, we propose an overflow prevention scheme where rates of USB transmission are varied depending on status of Wi-Fi. The proposed scheme is evaluated via the NS-3 simulator, showing that the packet delivery ratio of USB data can reach near 100% even in wireless transmission.

Congestion control in social-based sensor networks: A social network perspective

Social-based sensor networks are prone to congestion due to the limited storage space on each node and the unpredictable end-to-end delay. In this paper, we aim to develop an efficient congestion control approach from the social network perspective. For this purpose, we first identify the role of social ties in the process of congestion and specify a list of major congestion factors. Based on these factors, we then model the congestion control as a multiple attribute decision making problem (MADM), in which the weight of congestion factors is measured by an entropy method. We present a MADM-based congestion control approach that determines a set of forwarding messages and its transmission order on each encounter event. Moreover, we design a buffer management scheme that deletes messages whose removal would incur the least impact upon the network performance when the buffer overflows. Extensive real-trace driven simulation is conducted and the experimental results finally validate the efficiency of our proposed congestion control approach.

RFFE: A Buffer Cache Management Algorithm for Flash-Memory-Based SSD to Improve Write Performance

Flash-memory-based solid-state drives use multiple NAND flash memory chips as storage media and deploy a large-sized random access memory (RAM) inside it. This RAM buffer absorbs the read and write requests by file systems, and thus the resulting write requests to NAND flash memory are determined by the buffer replacement scheme. Many of the previously proposed algorithms concentrate on improving the random write performance by reordering the writes, addressing the temporal locality, or evicting the clean pages beforehand. However, the sequential write patterns in the incoming write stream are not completely utilized by the flash translation layer; this increases garbage collection overhead. To overcome this limitation, we propose a novel algorithm, called random first flash enlargement (RFFE), to improve the performance of the write operation. The algorithm identifies the interleaved sequential writes and builds various policy decisions, and the write sequence is constructed by contemplating the flash memory characteristics. In particular, the write stream is written into an appropriate log block area. Trace driven simulation is compared with the previously proposed least recently used fully-associative sector translation (FAST), block padding least recently used (BPLRU), and recently-evicted-first (REF) buffer management schemes. The result shows that the RFFE outperforms the previously proposed schemes with respect to merge, erase, and write count.

Sociality-based comprehensive buffer management for multicast in DTNs

In delay tolerant networks DTNs, multicast is widely adopted for emergency notification in crisis environments, or data scattering under military rescue situations, due to its robustness and high resource utilisation. Although the topology of DTNs is highly dynamic, they also demonstrate relatively stable social characteristics, e.g., the social centrality. In this paper, we propose a sociality-based comprehensive buffer management for multicast routing SCBMR, where nodes with high social centrality are selected in priority as relay nodes. However, choosing nodes with high centrality may result in great transmission workload on these nodes, and consequently they have to drop messages frequently when the buffer space is limited. We thus design a corresponding buffer management strategy that drops the buffered messages with more replicas and shorter TTL in the network. This will save the buffer space for the messages that has not been well-distributed in the network. Through extensive simulation, we verify that SCBMR can increase the data delivery ratio significantly without compromising the transmission cost and delay.

Efficient Buffer Management for Tree Indexes on Solid State Drives

Recently, with the widely use of flash memory based solid state drives (SSDs), a lot of studies have been conducted on SSD-based data management, such as index structures, query processing, and buffer management schemes. This paper focuses on buffer schemes for SSD-based database systems. However, differing from previous studies, we concentrate on buffer schemes for tree indexes on SSDs. This work is motivated by the observation that access patterns on index pages are much different from those on data pages. Generally, in a typical tree index, e.g., B+-tree, the root and internal nodes have higher read frequencies than leaf nodes have. However, traditional SSD-oriented buffering methods do not consider this special feature of indexes, and thus is not efficient when used as index buffer management schemes. In this paper, we present a new buffering scheme for tree indexes on SSDs that is named Clean-First and Dirty-Redundant-Write (CFDRW) scheme. The contributions of CFDRW are manifold. First, it assigns priorities to index pages to reflect the differences of access patterns of the nodes in a tree index. Second, it uses priority and recency to detect the hotness of index pages and proposes a new replacement algorithm based on priority and recency of the buffered index pages. Third, it exploits the internal parallelism of SSDs and proposes to write out buffer pages in a coarse granularity, i.e., to write out several pages using one physical I/O operation. We compare our proposal on two commodity SSDs with many previous methods including LRU, LIRS, and six flash-memory-based buffering schemes, by using synthetic and real workloads. The results show that our proposal outperforms the competitors under all workloads and SSDs in terms of various metrics including hit ratio, read count, write count, and elapsed time.

Geographic routing based on predictive locations in vehicular ad hoc networks

Many geographic routing algorithms have been proposed for vehicular ad hoc networks (VANETs), which have the strength of not maintaining any routing structures. However, most of which rely on the availability of accurate real-time location information. It is well known that vehicles can be intermittently connected with other vehicles. Thus, in such networks, it is difficult or may incur considerable cost to retrieve accurate locations of moving vehicles. Furthermore, the location information of a moving vehicle available to other vehicles is usually time-lagged since it is constantly moving over time. Fortunately, we observe that the short-term future locations of vehicles can be predicted. Based on the important observation, we propose a novel approach for geographic routing which exploits the predictive locations of vehicles. Thus, we have developed a prediction technique based on the current speed and heading direction of a vehicle. As a result, the request frequency of location updates can be reduced. In addition, we propose two forwarding strategies and three buffer management strategies. We have performed extensive simulations based on real vehicular GPS traces collected from around 4,000 taxis in Shanghai, China. Simulation results clearly show that geographic routing based on predictive locations is viable and can significantly reduce the cost of location updates.

Rethinking buffer management in data center networks

Data center operators face extreme challenges in simultaneously providing low latency for short flows, high throughput for long flows, and high burst tolerance. We propose a buffer management strategy that addresses these challenges by isolating short and long flows into separate buffers, sizing these buffers based on flow requirements, and scheduling packets to meet different flow-level objectives. Our design provides new opportunities for performance improvements that complement transport layer optimisations.

Enhanced fuzzy logic‐based spray and wait routing protocol for delay tolerant networks

SummaryDelay tolerant networks are a class of ad hoc networks that enable data delivery even in the absence of end‐to‐end connectivity between nodes, which is the basic assumption for routing in ad hoc networks. Nodes in these networks work on store‐carry and forward paradigm. In addition, such networks make use of message replication as a strategy to increase the possibility of messages reaching their destination. As contact opportunities are usually of short duration, it is important to prioritize scheduling of messages. Message replication may also lead to buffer congestion. Hence, buffer management is an important issue that greatly affects the performance of routing protocols in delay tolerant networks. In this paper, Spray and Wait routing protocol, which is a popular controlled replication‐based protocol for delay tolerant networks, has been enhanced using a new fuzzy‐based buffer management strategy Enhanced Fuzzy Spray and Wait Routing, with the aim to achieve increased delivery ratio and reduced overhead ratio. It aggregates three important message properties namely number of replicas of a message, its size, and remaining time‐to‐live, using fuzzy logic to determine the message priority, which denotes its importance with respect to other messages stored in a node's buffer. It then intelligently selects messages to schedule when a contact opportunity occurs. Because determination of number of replicas of a message in the network is a difficult task, a new method for estimation of the same has been proposed. Simulation results show improved performance of enhanced fuzzy spray and wait routing in terms of delivery ratio and resource consumption. Copyright © 2014 John Wiley & Sons, Ltd.

New Strategy to Optimize the Performance of Epidemic Routing Protocol

delay tolerant networks (DTN, Delay Tolerant Networks) are networks where connectivity is intermittent because of the difficulties encountered in the environment such as climate, mobility, the breakdowns of energy, etc. To achieve a good delivery of data despite all these challenges, new network architecture was developed. This one consists on the addition of a supplementary layer in the OSI protocol stack, above the transport layer. This new policy is called: the bundle protocol. Its main role is to store data until an opportunity of transmission appears by using the Store and Forward technique and the concept of custody transfer. Routing protocols in this type of network do not try to find the shortest path as it is the case in the conventional protocols, but they focus on the increase in data delivery. The techniques used for this purpose can be divided into two large families. Some protocols adopt the approach of replication, which involves the duplication of messages in the network by providing multiple copies in order to increase the likelihood of transmission. Others, are based on knowledge, that is to gather information about the network status and manage shipments efficiently. In DTN routing protocol forwarding decision and buffer management strategy are important to improve the chance of message delivery. In this paper, the new strategy proposed optimizes Epidemic routing protocol; it consists on using the path of ACKs messages and the path of all messages that have reached their destination to resolve the disadvantages of Epidemic routing protocol with the FIFO method. According to the simulation, the proposed method shows better delivery rate, better delivery probability and lower communication overhead compared to FIFO strategy and it is suitable for Epidemic.

GAR: Group aware cooperative routing protocol for resource-constraint opportunistic networks

Opportunistic networks are a new evolution of mobile ad hoc networks composed of intermittently connected nodes, in which the routing based on the dynamic topology is a challenging issue. In opportunistic networks, the mobile nodes with common interest or close relationship may form into groups and move together, which brings us a good feature to employ when designing the routing protocol for the resource-constraint opportunistic networks. Our main idea in this paper is to maximize the message delivery probability with the consideration of the group feature in the opportunistic network under the constraints of bandwidth and buffer space. Embedded this idea, we propose a cooperative routing protocol called GAR, which includes a cooperative message transfer scheme and a buffer management strategy. In the cooperative message transfer scheme, the limited bandwidth is considered and the message transfer priorities are designed to maximize the improved delivery probability. In the buffer management strategy, by considering the constraint of buffer space, we propose a cooperative message caching scheme and the dropping order of the messages is designed to minimize the reduced delivery probability. We also propose an improved strategy to utilize the extra contact duration between each pair of encountering nodes to further improve the performance. Finally, we conduct the simulations to demonstrate the effectiveness of our proposed GAR protocol under different network parameters.

Opportunistic And Playback-Sensitive Scheduling For Video Streaming

Given the strict Quality of Service (QoS) requirements of video streaming, this paper proposes a novel solution for simultaneous streaming of multiple video sessions over a mobile cellular system. The proposed solution combines a buffer management strategy with a packet scheduling algorithm. The buffer management strategy selectively discards packets of a user from base station buffer whereas the packet scheduling algorithm schedules packets of a user according to its instantaneous channel quality, average throughput and playback buffer information. Simulation results demonstrate that the proposed solution is effective in providing a continuous video playback with good perceptual quality for more users. If at least a good perceptual quality is to be satisfied for all users (QoS constraint of video streaming), then the proposed solution improves the system capacity by 40% over a conventional packet scheduling algorithm.

Application-aware virtual paths insertion for NOCs

Network-on-chip (NoC) has rapidly become a promising alternative for complex system-on-chip architectures including recent multicore architectures. Additionally, optimizing NoC architectures with respect to different design objectives that are suitable for a particular application domain is crucial for achieving high-performance and energy-efficient customized solutions. Despite the fact that many researches have provided various solutions for different aspects of NoCs design, a comprehensive NoCs system solution has not emerged yet. This paper presents a novel methodology to provide a solution for complex on-chip communication problems to reduce power, latency and area overhead. Our proposed NoC communication architecture is based on setting up virtual source–destination paths between selected pairs of NoCs cores so that the packets belonging to distance nodes in the network can bypass intermediate routers while traveling through these virtual paths. In this scheme, the paths are constructed for an application based on its task-graph at the design time. After that, the run time scheduling mechanism is applied to improve the buffer management, virtual channel and switch allocation schemes and hence, the constructed paths are optimized dynamically. Moreover, in our design the router complexity and its overheads are reduced. Additionally, the suggested router has been implemented on Xilinx Virtex-5 FPGA family. The evaluation results captured by SPLASH-2 benchmark suite reveal that in comparison with the conventional NoC router, the proposed router takes 25% and 53% reduction in latency and energy, respectively besides 3.5% area overhead. Indeed, our experimental results demonstrate a significant reduction in the average packet latency and total power consumption with negligible area overhead.

Integrated write buffer management for solid state drives

NAND flash memory-based Solid State Drives (SSD) have many merits, in comparison to the traditional hard disk drives (HDD). However, random write within SSD is still far slower than sequential read/write and random read. There are two independent approaches for resolving this problem as follows: (1) using overprovisioning so that reserved portion of the physical memory space can be used as, for example, log blocks, for performance enhancement, and (2) using internal write buffer (DRAM or Non-Volatile RAM) within SSD. While log blocks are managed by the Flash Translation Layer (FTL), write buffer management has been treated separately from the FTL. Write buffer management schemes did not use the exact status of log blocks, and log block management schemes in FTL did not consider the behavior of the write buffer management scheme. This paper first demonstrates that log blocks and write buffers maintain a tight relationship, which necessitates integrated management to both of them. Since log blocks can also be viewed as another type of write buffer, we can manage both of them as an integrated write buffer. Then we propose an Integrated Write buffer Management scheme (IWM), which collectively manages both the write buffer and log blocks. The proposed scheme greatly outperforms previous schemes in terms of write amplification, block erase count, and execution time.

Buffer Management in the Sliding-Window (SW) Packet Switch for Priority Switching

Switch and router architectures employing a shared buffer are known to provide high throughput, low delay, and high memory utilization. Superior performance of a shared-memory switch compared to switches employing other buffer strategies can be achieved by carefully implementing a buffer-management scheme. A buffer-sharing policy should allow all of the output interfaces to have fair and robust access to buffer resources. The sliding-window (SW) packet switch is a novel architecture that uses an array of parallel memory modules that are logically shared by all input and output lines to store and process data packets. The innovative aspects of the SW architecture are the approach to accomplishing parallel operation and the simplicity of the control functions. The implementation of a buffer-management scheme in a SW packet switch is dependent on how the buffer space is organized into output queues. This paper presents an efficient SW buffer-management scheme that regulates the sharing of the buffer space. We compare the proposed scheme with previous work under bursty traffic conditions. Also, we explain how the proposed buffer-management scheme can provide quality-of-service (QoS) to different traffic classes.

A FAST AND FAIR SHARED BUFFER FOR HIGH-RADIX ROUTER

High-radix router based on the tile structure requires large amount of buffer resources. To reduce the buffer space requirement without degrading the throughput of the router, shared buffer management schemes like dynamically allocated multi-queue (DAMQ) can be used by improving the buffer utilization. Unfortunately, it is commonly regarded that DAMQ is slow in write and read. To address this issue, we propose a fast and fair DAMQ structure called F2DAMQ for high-radix routers in this paper. It uses a fast FIFO structure in the implementation of idle address list as well as data buffer and achieves some critical performance improvement such as continuous and concurrent write and read with zero-delay. Besides, F2DAMQ also uses a novel credit management mechanism which is efficient in avoiding one virtual channel (VC) monopolizing the shared part of the buffer and achieving fairness among competing VCs sharing the buffer. The analyses and simulations show that F2DAMQ performs well in achieving low latency, high throughput and good fairness under different traffic patterns.