We propose a simple and intuitive cost mechanism which assigns costs for the competitive usage of m resources by n selfish agents. Each agent has an individual demand;demands are drawn according to some probability di...
详细信息
As microarchitectural and system complexity grows, comprehending system behavior becomes increasingly difficult, and often requires obtaining and sifting through voluminous event traces or coordinating results from mu...
详细信息
ISBN:
(纸本)1595930183
As microarchitectural and system complexity grows, comprehending system behavior becomes increasingly difficult, and often requires obtaining and sifting through voluminous event traces or coordinating results from multiple, non-localized sources. Owl is a proposed framework that overcomes limitations faced by traditional performance counters and monitoring facilities in dealing with such complexity by pervasively deploying programmable monitoring elements throughout a system. The design exploits reconfigurable or programmable logic to realize hardware monitors located at event sources, such as memory buses. These monitors run and writeback results autonomously with respect to the CPU, mitigating the system impact of interrupt-driven monitoring or the need to communicate irrelevant events to higher levels of the system. The monitors are designed to snoop any kind of system transaction, e.g., within the core, on a bus, across the wire, or within I/O devices. Copyright 2005 ACM.
We propose, implement and evaluate new energy conservation schemes for efficient data propagation in wireless sensor networks. Our protocols are adaptive, i.e. locally monitor the network conditions and accordingly ad...
详细信息
We propose, implement and evaluate new energy conservation schemes for efficient data propagation in wireless sensor networks. Our protocols are adaptive, i.e. locally monitor the network conditions and accordingly adjust towards optimal operation choices. This dynamic feature is particularly beneficial in heterogeneous settings and in cases of redeployment of sensor devices in the network area. We implement our protocols and evaluate their performance through a detailed simulation study using our extended version of ns-2. In particular we combine our schemes with known communication paradigms. The simulation findings demonstrate significant gains and good trade-offs in terms of delivery success, delay and energy dissipation.
We present an improved upper bound on the competitiveness of the online coloring algorithm First-Fit in disk graphs which are graphs representing overlaps of disks on the plane. We also show that this bound is best po...
详细信息
DiffServ is the basis of contemporary QoS-enabled networks. Setting up DiffServ QoS requires extensive engineering effort in dimensioning and provisioning, especially for adjacent networks under different administrati...
详细信息
ISBN:
(纸本)0780395654
DiffServ is the basis of contemporary QoS-enabled networks. Setting up DiffServ QoS requires extensive engineering effort in dimensioning and provisioning, especially for adjacent networks under different administrations linked in a "federated" hierarchy. In this paper we present a case study for QoS techniques employed in the GRNET MAN networks of Athens and Crete. After introducing the supported QoS mechanisms and service types, we discuss our dimensioning methodology and present two algorithms for worst-case dimensioning. We explain the provisioning mechanisms of GRNET and we present in brief our new automated provisioning ANS tool. Finally, we deal with the extension of our mechanisms and tools in hierarchically federated networks and give some future directions of our work.
In this paper, we present the design principles for virtual spaces and two different tools as solutions for supporting e-collaboration and multi-user communication in Web-based learning communities. The first solution...
详细信息
In this paper, we present the design principles for virtual spaces and two different tools as solutions for supporting e-collaboration and multi-user communication in Web-based learning communities. The first solution, called Virtual Conference, is designed and implemented in the framework of the VirRAD European project. It is a two-dimensional space where participants represented by their photos can use various e-collaboration tools. The second solution, called EVE Training Area, is a three-dimensional space where participants, represented by 3D humanoid avatars, can use a variety of e-collaboration tools. This paper describes the functionality provided by both tools, compares them, and proposes cases for exploiting each solution.
UMTS is evolving toward a future wireless all-IP network. In this paper we present how it supports realtime IP multimedia services, as these services are expected to drive the adoption of wireless all-IP networks. The...
详细信息
UMTS is evolving toward a future wireless all-IP network. In this paper we present how it supports realtime IP multimedia services, as these services are expected to drive the adoption of wireless all-IP networks. The scheme of real time streaming video is one of the newcomers in wireless data communication and in particular in UMTS, raising a number of novel requirements in both telecommunication and data communication systems. This scheme applies when the mobile user is experiencing real time video content. In this work we focus on the design and implementation of a rate and loss control mechanism for monitoring the UMTS network state and estimating the appropriate rate of the streaming video data.
Numerous architectures have been recently proposed for residue arithmetic components, each with its own speed, area and power consumption characteristics. In this paper, we present KoVer, a novel software tool that gi...
详细信息
Numerous architectures have been recently proposed for residue arithmetic components, each with its own speed, area and power consumption characteristics. In this paper, we present KoVer, a novel software tool that gives a designer the opportunity to explore several architectures for implementing his residue arithmetic blocks, select the one that best suits his goals and instantly get the HDL level description of the selected architecture.
Structural computing consists of both theory and practices to support all hypertext domains in a native way. Component-Based Open Hypermedia Systems (CB-OHS) constitute the incarnation of this discipline. Nevertheless...
详细信息
This paper presents a new technique to determine the dynamic and frequency response of capnographs using a custom built 'EtCO2 simulator system'. Capnographs are devices that use CO2 from a patients' expir...
详细信息
This paper presents a new technique to determine the dynamic and frequency response of capnographs using a custom built 'EtCO2 simulator system'. Capnographs are devices that use CO2 from a patients' expired breath to monitor the cardiopulmonary status during anaesthesia and mechanical ventilation. Capnographs at present are routinely calibrated via a static calibration method only. The dynamic response of the capnographs is not accounted for. The frequency and time response are important as they determine if capnographs can be used in high frequency and pediatric ventilation schemes. Experiments performed using the method described in this paper proved that old capnographs usually do not satisfy the manufacturer quoted specifications for time and frequency response. Therefore, a routine check for capnographs is recommended. The method can also be used to verify manufacturer quoted specifications. The EtCO2 simulator system, designed and constructed simulates human respiration cycle. The gas sources used are 5% CO2 and room air that can be switched alternatively. Both supplies are pressure regulated and connected through non-return valves to electric valves. The valves are microprocessor controlled and the on/off time is user defined allowing a wide range of waveforms to be simulated. The output from the simulator is delivered to capnograph. Capnograms are captured by digital video recording. The captured video in 'avi' file format is then converted into individual frames. These frames are converted into digital data through image processing in Matlab. The data obtained is subjected to extensive analysis to determine the frequency and time response of the respective capnograph. Copyright 2005 ISA. All Rights Reserved.
暂无评论