新一代IP QoS的实现

文章介绍了新一代IP骨干网上的IP QoS实现技术，论述了集成业务(IntServ)与差分业务(DiffServ)解决方案的特点，详细介绍了相关的队列管理与排队机制。并结合多协议标签交换（MPLS)技术的最新发展，阐述了综合多协议标签交换流量工程与DiffServ技术体系端到端IP QoS的实现。     

嵌入式RTOS中任务优先级反转问题研究

针对嵌入式实时系统任务调度策略的特点，任务在运行的时候可能被更高优先级的任务中断。分析了嵌入式RTOS中的最高就绪任务的查找算法，指出该调度算法存在的不同优先级的反转问题，并且针对这一问题进行研究，给出了相应的优先级继承方案。较好地解决了RTOS中任务调度中的优先级的反转问题。     

Uplink Scheduling in CDMA Packet-Data Systems

Uplink scheduling in wireless systems is gaining importance due to arising uplink intensive data services (ftp, image uploads etc.), which could be hampered by the currently in-built asymmetry in favor of the downlink. In this work, we propose and study algorithms for efficient uplink packet-data scheduling in a CDMA cell. The algorithms attempt to maximize system throughput under transmit power limitations on the mobiles assuming instantaneous knowledge of user queues and channels. However no channel statistics or traffic characterization is necessary. Apart from increasing throughput, the algorithms also improve fairness of service among users, hence reducing chances of buffer overflows for poorly located users. The major observation arising from our analysis is that it is advantageous on the uplink to schedule “strong” users one-at-a-time, and “weak” users in larger groups. This contrasts with the downlink where one-at-a-time transmission for all users has shown to be the preferred mode in much previous work. Based on the optimal schedules, we propose less complex and more practical approximate methods, both of which offer significant performance improvement compared to one-at-a-time transmission, and the widely acclaimed Proportional Fair (PF) algorithm, in simulations. When queue content cannot be fed back, we propose a simple modification of PF, Uplink PF (UPF), that offers similar improvement. Hereafter, we refer to users with low recieved power at the base even when transmitting at peak transmit power as “weak” users, and the strongly recieved users at the base as “strong” users. Krishnan Kumaran is currently a member of the Complex Systems Modeling section in the Corporate Strategic Research of ExxonMobil Corp., Clinton, NJ. Formerly, he was a Member of Technical Staff in the Mathematics of Networks and Systems Research Department at Bell Labs in Murray Hill, NJ, where his research interests were in modeling, analysis and simulation of design, resource management and scheduling issues in telecommunication networks. Lijun Qian is an assistant professor in the Department of Electrical Engineering at Prairie View A&M University. He received his B.S. from Tsinghua University in Beijing, M.S. from Technion-Israel Institute of Technology, and Ph.D. from WINLAB, Rutgers University, all in electrical engineering. Before joining PVAMU, he was a researcher at Networks and Systems Research Department of Bell Labs in Murray Hill, NJ. His major research interests are in wireless communications and networking technologies, especially in radio resource management, protocol design, TCP/RLP optimization and MPLS traffic engineering.     

A Bluetooth Based Sensor Network for Civil Infrastructure Health Monitoring

Communicating with sensors has long been limited either to wired connections or to proprietary wireless communication protocols. Using a ubiquitous and inexpensive wireless communication technology to create Sensor Area Networks (SANs) will accelerate the extensive deployment of sensor technology. Bluetooth, an emerging, worldwide standard for inexpensive, local wireless communication is a viable choice for SANs because of its inherent support for some of the important requirements – low power, small form factor, low cost and sufficient communication range. In this paper we outline an approach, centered on the Bluetooth technology, to support a sensor network composed of fixed wireless sensors for health monitoring of highways, bridges and other civil infrastructures. We present a topology formation scheme that not only takes into account the traffic generated by different sensors but also the associated link strengths, buffer capacities and energy availability. The algorithm makes no particular assumptions as to the placement of nodes, and not all nodes need to be in radio proximity of each other. The output is a tree shaped scatternet rooted at the sensor hub (data logger) that is balanced in terms of traffic carried on each of the links. We also analyze the scheduling, routing and healing aspects of the resulting sensor-net topology.     

网格资源管理系统模型研究

网格资源管理系统是网格计算系统的重要组成部分。文章分析了网格资源管理系统的功能需求，具体论述了该模型的原型系统，最后介绍了相关研究工作。     

基于水印的图像认证和完整性保护技术

数字水印技术的发展为解决图像认证和完整性保护问题提供了新的思路。对用于篡改检测和图像认证的水印技术做了综述。数字水印技术根据其识别差错的能力分为四种类型:易损水印、半易损水印、混合水印和自嵌入水印。最后还对水印认证技术的安全性问题进行了讨论。     

Scheduling Algorithms for Packet-Oriented MAC Protocols in Wireless Multimedia Systems

Future generation wireless multimediacommunications will require efficient Medium AccessControl (MAC) protocols able to guarantee suitable Qualityof Service (QoS) levels for different traffic classes whileachieving a high utilization of radio resources. This paperproposes a new scheduling technique to be adopted at the MAClevel in wireless access systems, named Dynamic Scheduling-Time DivisionDuplexing (DS-TDD), that efficiently managesvideo, voice, Web and background traffics. A theoretical approachis proposed in this paper to evaluate the DS-TDD performance withvoice and Web traffics. Simulation results have permitted tohighlight the following promising characteristics of the DS-TDDscheme: (i) a high capacity of real-time traffics isattained with a QoS insensitive to Web and background trafficloads; (ii) a high throughput can be guaranteed whilepreserving the QoS levels of the different traffic classes;(iii) heavier downlink traffic loads do not modify the QoSof uplink traffics. Finally, extensive comparisons with differentscheduling schemes proposed in the literature have permitted tohighlight the better performanceof DS-TDD.     

Evaluation of performance enhancing proxies in internet over satellite

Performance enhancing proxies (PEPs) are widely used to improve the performance of TCP over high delay‐bandwidth product links and links with high error probability. In this paper we analyse the performance of using TCP connection splitting in combination with web caching via traces obtained from a commercial satellite system. We examine the resulting performance gain under different scenarios, including the effect of caching, congestion, random loss and file sizes. We show, via analysing our measurements, that the performance gain from using splitting is highly sensitive to random losses and the number of simultaneous connections, and that such sensitivity is alleviated by caching. On the other hand, the use of a splitting proxy enhances the value of web caching in that cache hits result in much more significant performance improvement over cache misses when TCP splitting is used. We also compare the performance of using different versions of HTTP in such a system. Copyright © 2003 John Wiley & Sons, Ltd.     

The Role of Test Protocols in Automated Test Generation for Embedded-Core-Based System ICs

Modular testing is an attractive approach to testing large system ICs, especially if they are built from pre-designed reusable embedded cores. This paper describes an automated modular test development approach. The basis of this approach is that a core or module test is dissected into a test protocol and a test pattern list. A test protocol describes in detail how to apply one test pattern to the core, while abstracting from the specific test pattern stimulus and response values. Subsequent automation tasks, such as the expansion from core-level tests to system-chip-level tests and test scheduling, all work on test protocols, thereby greatly reducing the amount of compute time and data involved. Finally, an SOC-level test is assembled from the expanded and scheduled test protocols and the (so far untouched) test patterns. This paper describes and formalizes the notion of test protocols and the algorithms for test protocol expansion and scheduling. A running example is featured throughout the paper. We also elaborate on the industrial usage of the concepts described.     

IMPACCT: Methodology and Tools for Power-Aware Embedded Systems

Power-aware systems are those that must exploit a widerange of power/performance trade-offs in order to adapt to the power availabilityand application requirements. They require the integration of many novel powermanagement techniques, ranging from voltage scaling to subsystem shutdown.However, those techniques do not always compose synergistically with eachother; in fact, they can combine subtractively and often yield counterintuitive,and sometimes incorrect, results in the context of a complete system. Thiscan become a serious problem as more of these power aware systems are beingdeployed in mission critical applications.To address the problem of technique integration for power-aware embedded systems, we propose a new design tool framework called IMPACCT and the associated design methodology. The system modeling methodology includes application model for capturing timing/powerconstraints and mode dependencies at the system level. The tool performs power-awarescheduling and mode selection to ensure that all timing/power constraintsare satisfied and that all overhead is taken into account. IMPACCT then synthesizesthe implementation targeting a symmetric multiprocessor platform. Experimentalresults show that the increased dynamic range of power/performance settingsenabled a Mars rover to achieve significant acceleration while using lessenergy. More importantly, our tool correctly combines the state-of-the-arttechniques at the system level, thereby saving even experienced designersfrom many pitfalls of system-level power management.