Pubs:2002

<bibtex> @inproceedings{273, author={Ciuhandu,O.;Murphy,J. }, title={Transaction Distribution Algorithms with user Classes for Distributed Application Performance Optimisation}, booktitle={IEEE 10th International Conference on Software,Telecommunications and Computer Networks}, year={2002}, abstract={There is a growing need for high performance enterprise distributed systems that provide the scalability and availability required by modern enterprise portals and ecommerce systems. New technologies such as Enterprise Java Beans help building these systems by providing the framework to support such increasingly complex applications. The need for different response times for transactions, according to the situation, is often not taken into account. We present a new approach for optimising the overall response time of the system, introducing transaction priorities.}, keywords={Reusablity of Software}, pdf={transaction distribution.pdf}, } </bibtex> <bibtex> @inproceedings{274, author={Mania,D.;Murphy,J.}, title={Framework for predicting the performance of Component based Systems}, booktitle={IEEE 10th International Conference on Software,Telecommunications and Computer Networks}, year={2002}, abstract={The performance of component-based systems, especially of e-commerce applications, becomes a key factor in keeping business relations active. Middleware performance offered by technologies such as EJB, .NET, CORBA does not guarantee the fulfilment of performance requirements. We propose a framework that automatically builds an analytical model and drives possible performance improvements of the system under study. We outline a methodology of discovering transactions within the system at run-time. }, keywords={E-Commerce}, pdf={framework for predicting.pdf}, } </bibtex> <bibtex> @inproceedings{275, author={Mos,A.;Murphy,J.}, title={Performance Management in Component-Oriented Systems using a Model Driven Architecture Approach}, booktitle={IEEE 6th International Enterprise Distributed Object Computing Conference}, year={2002}, abstract={Developers often lack the time or knowledge to profoundly understand the performance issues in large-scale component-oriented enterprise applications. This situation is further complicated by the fact that such applications are often built using a mix of in-house and Commercial-Off-The-Shelf (COTS) components. This paper presents a methodology for understanding and predicting the performance of component-oriented distributed systems both during development and after they have been built. The methodology is based on three conceptually separate parts: monitoring, modelling and performance prediction. Performance predictions are based on UML models created dynamically by monitoring-and-analysing a live or under-development system. The system is monitored using non-intrusive methods and run-time data is collected. In addition, static data is obtained by analysing the deployment configuration of the target application. UML models enhanced with performance indicators are created based on both static and dynamic data, showing performance hot spots. To facilitate the understanding of the system, the generated models are traversable both horizontally at the same abstraction level between transactions, and vertically between different layers of abstraction using the concepts defined by the Model Driven Architecture. The system performance is predicted and performance-related issues are identified in different scenarios by generating workloads and simulating the performance models. Work is under way to implement a framework for the presented methodology with the current focus on the Enterprise Java Beans technology.}, keywords={Component Oriented}, pdf={501.pdf}, } </bibtex> <bibtex> @inproceedings{276, author={Mos,A.;Murphy,J.}, title={A Framework for Performace Monitoring,Modelling & Prediction of Component Oriented Distributed Systems}, booktitle={ACM 3rd International Workshop on Software and Performance }, year={2002}, abstract={We present a framework that can be used to identify performance issues in component-oriented distributed systems. The framework consists of a monitoring module, a modelling module and a prediction module, that are interrelated. The monitoring block extracts real-time performance data from a live or under development system. The modelling block generates UML models of the system showing where the performance problems are located and drives the monitoring process. The performance prediction block simulates different system-loads on the generated models and pinpoints possible performance issues. The technological focus is currently on Enterprise Java Beans systems.}, keywords={Component Oriented}, pdf={framework for performance.pdf}, } </bibtex> <bibtex> @inproceedings{277, author={Todinca,D.;Perry,P. ;Murphy,J.}, title={Novel Prioritised EGPRS Medium Access Regime For Reduced File Transfer Delay During Congested Periods}, booktitle={IEE 3G 2002;Third International Conference on 3G Mobile Communications Technologies}, year={2002}, abstract={The goal of this paper is to investigate the efficiency of different algorithms used for resource allocation in data transfer over EGPRS networks. The focus is on the efficiency during congested periods in order to ensure reduced file transfer delay. A number of algorithms are presented for the resource allocation, and some generic mathematical results are presented for a two coding system. Simulation is relied on to produce results for the algorithms and it is found that Iterative Round Robin (IRR) and Oldest Queue (OQ) produce the best results. These are then proposed to be good candidates for implementing transmission control.}, keywords={GPRS }, pdf={novel proritised.pdf}, } </bibtex> <bibtex> @inproceedings{278, author={Mos,A.;Murphy,J.}, title={Understanding Performance Issues in Component-Oriented Distributed Applications:The COMPAS Framework}, booktitle={7th International Workshop on Component-Oriented Programming of the 16th European Conference on Object Oriented Programming}, year={2002}, abstract={Large enterprise applications such as financial systems are increasingly making use of Commercial-Off-The-Shelf (COTS) components in order to reduce development costs and increase productivity. Developers of such applications use productivity frameworks and component-oriented middleware such as EJB or .NET that help the development effort by providing run-time environments with support for a wide range of system-level services such as transactions and load-balancing. Due to the inherent complexity of such environments, it is often difficult to model and predict the performance of the resulting application, particularly when COTS components are used. We propose a framework that uses three interrelated modules to help developers understand and predict performance problems in component-oriented applications. The monitoring module extracts performance data in real-time from a running application. The modelling module generates UML models based on performance measurements from the monitoring module. Finally, the performance prediction module simulates the generated models for different workloads, helping developers understand the consequences of changes in user behaviour or changes in application design. Work is under way to implement the framework, with the current focus on the EJB platform.}, keywords={Component Oriented}, pdf={understanding performance issues.pdf}, } </bibtex> <bibtex> @inproceedings{279, author={Todinca,D.;Perry,P.;Murphy,J.}, title={Algorithms for Resource Allocation in Data Transfer over EGPRS Network}, booktitle={2nd European Conference on Universal Multiservice Networks}, year={2002}, abstract={Mobile telephone systems are undergoing a substantial change from voice based systems which also support data transfer to become systems which truly support packet switched data services to mobile subscribers. This evolution towards the third generation (3G) mobile system will be based on the Global System for Mobile communications (GSM) [1] and will begin with the General Packet Radio Service (GPRS) [2], [3]. Finally the additional channel capacity offered by the Enhanced Datarates for Global Evolution (EDGE) will bring 3G services to users of these systems. This final system is often regarded as part of the 3G family and is referred to as Enhanced GPRS (EGPRS). Our goal is to investigate the efficiency of different algorithms used for resource allocation in data transfer over EGPRS networks. We consider a number of users in a cell that want either to send or to receive data and a centralized controller known as the Packet Control Unit (PCU). The PCU is the part of the Base Station Sub-system (BSS) which performs the arbitration mechanism to share the radio resources between users. The users can use nine different channel coding schemes, each one allowing a certain bit rate, but for the purposes of this discussion it is assumed that users can only use coding schemes one and two (CS1 and CS2) as a higher degree of flexibility is unimportant to this investigation. }, keywords={Wireless, Mobile, GPRS, Enhanced GPRS, resource allocation algorithms}, pdf={algorithm.pdf}, } </bibtex> <bibtex> @inproceedings{411, author={G.Muntean;L.Murphy}, title={Adaptive Pre-recorded Multimedia Streaming}, booktitle={IEEE Globecom 2002}, year={2002}, abstract={Lately, multimedia-related Internet applications have become very popular, and make up an increasing percentage of network traffic. This paper presents a quality-of-transmissionorientated adaptive mechanism for streaming of pre-recorded multimedia content. It aims to maintain the continuity of both the transmission and the remote stream play-out, at the expense of varying the stream's quality. A feedback scheme, in conjunction with a quality of transmission grading scheme, allows the server to learn the current network conditions. During transmission, the server can switch between different quality versions of the same multimedia content at certain checkpoints to modify the quality of the overall streaming process, and therefore the transferred quantity of data. Preliminary statistical and user perceptual test results from our prototype system show that in increased traffic conditions, the users' satisfaction was higher than if a receiver buffering solution was used.}, keywords={Multimedia,Internet Streaming,Remote Stream Play-out}, pdf={adaptive pre.pdf}, } </bibtex> <bibtex> @inproceedings{412, author={N.Dumitrascu;L.Murphy}, title={A Framework for Optical Deployment Scheme in Component-based Systems}, booktitle={10th Conference on Software,Telecommunications & Computer Networks}, year={2002}, abstract={Lately, multimedia-related Internet applications have become very popular, and make up an increasing percentage of network traffic. This paper presents a quality-of-transmissionorientated adaptive mechanism for streaming of pre-recorded multimedia content. It aims to maintain the continuity of both the transmission and the remote stream play-out, at the expense of varying the stream's quality. A feedback scheme, in conjunction with a quality of transmission grading scheme, allows the server to learn the current network conditions. During transmission, the server can switch between different quality versions of the same multimedia content at certain checkpoints to modify the quality of the overall streaming process, and therefore the transferred quantity of data. Preliminary statistical and user perceptual test results from our prototype system show that in increased traffic conditions, the users' satisfaction was higher than if a receiver buffering solution was used.}, keywords={Internet Applications,Multimedia,Network Traffic}, pdf={framwork for.pdf}, } </bibtex> <bibtex> @inproceedings{413, author={G.Muntean;L.Murphy}, title={Adaptive Traffic-based Techniques for Live Multimedia Streaming}, booktitle={International Conference on Telecommunications}, year={2002}, abstract={The growing number of multimedia stream transmissions done through the existing "best-effort"-based networks contributes to the increased traffic conditions. The latter affect the time-sensitive applications and especially the continuity of multimedia streaming. The paper presents some adaptive techniques for transmitting live multimedia streams over the Internet, regardless the overall traffic conditions. Their goal is to maintain the continuity of both the transmission and the remote play out processes by varying the streams' quality. A feedback-controlled multimedia system was built in order to allow for the deployment and testing of the proposed adaptive mechanisms. Some experimental results show that the continuity has been maintained even in highly changing network conditions.}, keywords={Multimedia Streaming,Internet Traffic}, pdf={adaptive traffic.pdf}, } </bibtex> <bibtex> @inproceedings{414, author={M.Searles;N.Cranley;L.Murphy}, title={Adaptive Multicast Architecture for Streamed MPEG-4 over IP Networks}, booktitle={Irish Signals & Systems Conference}, year={2002}, abstract={Currently multimedia is either downloaded before viewing, or streamed over a network. However, streaming real-time or near real-time applications with a specified Quality of Service (QoS) over best-effort IP networks is not yet a solved problem. The Real-time Transport Protocol (RTP) can be used to facilitate streaming, but also has the potential to support QoS. Multicast transmissions are currently quite static and inflexible as all users receive the same treatment and it is only the network behaviour which differentiates between their perceived QoS. By gathering network statistics during the session and defining different customer groups, we propose to adapt multicast multimedia streaming to a fluctuating network load and/or client requests, thereby providing adaptive QoS.}, keywords={QoS,IP Networks,Multimedia Streaming}, pdf={adaptive multicast.pdf}, } </bibtex> <bibtex> @article{415, author={H.Melvin;L.Murphy}, title={Time Synchronization for VoIP Quality of Service}, journal={IEEE Internet Computing}, year={2002}, pages={6 Pages}, volume={25-26}, abstract={Although packet-based and unmanaged networks like the Internet are ideal for delivering timeinsensitive data such as e-mail or static Web traffic, the growing demand for Web-based multimedia data exposes the limitations of core Internet protocols. With no end-to-end delay bounds, the public Internet’s best-effort service is unsuitable for delivering time-sensitive data and for interactive applications such as voice-over-IP. Normal speech consists of talkspurts, which typically last a few hundred milliseconds, and silence periods, which occur both within a spoken word and between words. In a packet-based network, voice packets are generated periodically at the sender and transmitted across the network. To cope with the packet interarrival variance inherent in besteffort service, current VoIP implementations generally implement fixed buffer schemes. Fixed buffer schemes make no attempt to match receiver operation to current network performance. An alternative approach is to use a more complex adaptive buffer scheme. This continuously matches playout delay to network conditions, at the expense of some packet loss due to late arrivals and some distortion of intertalkspurt silence periods. Various approaches seek to optimize the quality of service of VoIP applications (see the sidebar, “Quality of Service for VoIP,” next page, for a categorization of QoS approaches). We propose a system that uses synchronized time to combine the useful characteristics of both fixed and adaptive buffer strategies, thereby improving VoIP quality of service. Using a combination of global positioning system (GPS) technologies and the network time protocol (NTP), hosts can learn the precise end-to-end delay for each packet. This information can benefit both domestic and business Internet telephony users. In this article, we outline our proposed system and discuss issues arising from the use of synchronized time.}, keywords={Web Traffic,Web-based Multimedia,VoIP}, pdf={time.pdf}, } </bibtex> <bibtex> @inproceedings{416, author={G.Muntean;L.Murphy}, title={A Novel Traffic-Based Adaptive Technique for Feedback-Controlled Transmissions of Pre-Recorded Multimedia Streams}, booktitle={11th International World Wide Web Conference}, year={2002}, abstract={The multimedia streams transmissions, done over the existing "best-effort" networks, are continuously increasing in number, making network congestion more likely to appear. The paper presents a traffic-based adaptive technique for transmitting pre-recorded multimedia streams, regardless the network condition. The adaptive mechanism is implemented by a feedback-controlled multimedia system which ensures continuous transmissions and play-out of streams even in congested network conditions. The measures taken into account vary the quantity of streamed data with the expense of modifying the streams' quality. Experimental results show improved behavior of the system in highly changing network conditions.}, keywords={Adaptive transmission, multimedia streaming, traffic-based, feedback-control}, pdf={novel.pdf}, } </bibtex> <bibtex> @inproceedings{417, author={C.Hava;J.McManis;J.Murphy;L.Murphy}, title={A Clients Perception Based Adaptive Web Server Application}, booktitle={11th International World Wide Web Conference }, year={2002}, abstract={The Web is continually increasing in size and importance and so does the interest of the Web server administrators to maximize their users' satisfaction, while efficiently using the existing resources. The paper proposes an adaptive Web server application that tries to increase the performance of the Web server that hosts a Web site, as seen from the clients' point of view. The adaptiveness is based on the customization of the Web site in a manner that emphasizes the interests of the clients. Our tests show that both the user satisfaction and the server performance are improved.}, keywords={Web server performance, customer satisfaction, adaptive Web server, and performance parameters}, pdf={clients perception.pdf}, } </bibtex> <bibtex> @inproceedings{437, author={Gabriel-Miro Muntean;L.Murphy}, title={An Adaptive Mechanism for Pre-recorded Multimedia Streaming Based on Traffic Conditions}, booktitle={11th W3C WWW Conference}, year={2002}, abstract={The multimedia streams transmissions, done over the existing "best-effort" networks, are continuously increasing in number, making network congestion more likely to appear. The paper presents a traffic-based adaptive technique for transmitting pre-recorded multimedia streams, regardless the network condition. The adaptive mechanism is implemented by a feedback-controlled multimedia system which ensures continuous transmissions and play-out of streams even in congested network conditions. The measures taken into account vary the quantity of streamed data with the expense of modifying the streams' quality. Experimental results show improved behavior of the system in highly changing network conditions.}, keywords={Adaptive transmission, multimedia streaming, traffic-based, feedback-control}, pdf={adaptive.pdf}, } </bibtex>