Showing papers on "Heterogeneous network published in 1995"
TL;DR: This article attempts to identify different issues and to put many of the activities in wireless into a framework that can provide perspective on what is driving them, and perhaps even yield some indication of where they appear to be going in the future.
Abstract: This article attempts to identify different issues and to put many of the activities in wireless into a framework that can provide perspective on what is driving them, and perhaps even yield some indication of where they appear to be going in the future The technologies and systems that are currently providing, or are proposed to provide, wireless communications services can be grouped into about seven relatively distinct groups All of the technologies and systems are evolving as technology advances and perceived needs change Some trends are becoming evident in the evolutions The different groups and evolutionary trends are explored along with factors that influence the characteristics of members of the groups The grouping is generally with respect to scale of mobility and communications applications or modes Different design compromises are evident in the different technologies and systems The evidence suggests that the evolutionary trajectories are aimed toward at least three large groups of applications or services, namely, high-tier PCS (current cellular radio), high-speed wireless local-area networks (WLANS), and low-tier PCS (an evolution from several of the current groups) It is not clear to what extent several groups, eg, cordless telephones, paging, and wide area data, will remain after some merging with the three large groups >
355 citations
Patent•
06 Jun 1995TL;DR: In this paper, the authors propose a network printing system for enhancing two-way communication between host computers and printers connected to a network, which provides an imaging device protocol (DP) which enables various network service protocol/ports for host computers to communicate with the printer by seamless plug-and-play connectivity.
Abstract: A network printing system for enhancing two-way communication between host computers and printers connected to a network. More particularly, the network printing system provides an imaging device protocol (DP) which enables various network service protocol/ports for host computers to communicate with the printer by "seamless plug and play" connectivity. IDP operates independently of the network layers below and only requires that the transport protocol/port be bidirectional. IDP allows all of the incoming print job information to be placed in the print queue regardless of the protocol for a wide variety of heterogenous network protocols. As a result, the network printing system enables print jobs from host computers connected to the network by a wide variety of heterogenous network protocols to be fairly arbitrated at the printer.
140 citations
TL;DR: The theory, design and ongoing prototyping of a wireless ATM LAN/PBX capable of supporting mobile users with multi-Mb/s access rates and multi-Gb/s aggregate capacities and a new wireless VP/VC concept and a Homing Algorithm are described to provide ATM cell routing and connections in the network.
Abstract: We describe the theory, design and ongoing prototyping of a wireless ATM LAN/PBX capable of supporting mobile users with multi-Mb/s access rates and multi-Gb/s aggregate capacities. Our proposed LAN consists of network nodes called Portable Base Stations (PBS) providing microcell coverage. The PBSs are designed to be low-cost, compact and high-speed and can be relocated conveniently. We employ a concept of ad-hoc networking in the layout of the PBS-to-PBS interconnection. That is, the PBSs can be distributed in an arbitrary topology to form a backbone network and can be reconfigured with relative ease. The PBS-to-PBS backbone links are high-speed (Gb/s) for supporting high system capacity. Although they can either be wired or wireless, our emphasis is on wireless implementations. The user-to-PBS links, on the other hand, are primarily for mobile access (e.g., 2-20 Mb/s) and therefore are wireless. Wired connections from stationary users to PBSs are also possible. Typical mobile users are assumed to be laptops or notebook computers. Services supported include conventional data applications (e.g., over TCP/IP or SPX/IPX) as well as multimedia (video, voice and data) applications with QoS (Quality-of-Service) guarantees. A “wireless ATM” concept is proposed so as to provide seamless internetworking with other wired ATM local and wide-area networks. Algorithms and control in our network are highly distributed for simple implementations and ease of mobility management. A new wireless VP/VC concept and a Homing Algorithm are described to provide ATM cell routing and connections in the network. PBS hardware and software architectures are discussed. Call management, network management and signaling are designed for simplicity, high performance and modular implementations. A fast network restoration scheme is proposed to cope with the potential link or node failures in the ad-hoc network. Error control is addressed taking the unreliable wireless links into consideration. Finally, a prototyping project called BAHAMA (Broadband Ad Hoc ATM Anywhere) for demonstrating this network concept is briefly outlined.
122 citations
TL;DR: The present paper provides an overview of the past and present of the wireless LAN industry, as well as a perspective of the future directions that encompass a vision for a ubiquitous local wireless computing environment that leads to a fusion of communications and computation.
Abstract: Pahlavan (1985) published an article entitled "Wireless office information networks". That article examined spread spectrum, standard radio and infrared (IR) technologies for intra-office wireless networking. In May of that year the FCC released the ISM (industrial, scientific, and medical) bands for spread spectrum local communications. Although ISM bands are not restricted to any specific application, wireless local area networks (LANs) were one of the most prominent applications that were envisioned by the rule makers in the FCC. Since 1985, many small start-up companies, as well as small groups in larger companies, have started to develop wireless LANs. The present paper provides a sequel to Pahlavan by providing an overview of the past and present of the wireless LAN industry, as well as a perspective of the future directions that encompass a vision for a ubiquitous local wireless computing environment that leads to a fusion of communications and computation. >
102 citations
01 Jan 1995
TL;DR: In this article, the authors describe a range of issues related to the design and analysis of networks which are subject to the random failure of their components, including data communications networks, voice communication networks, transportation networks, computer architectures, electrical power networks and command and control systems.
Abstract: Publisher Summary Network reliability encompasses a range of issues related to the design and analysis of networks which are subject to the random failure of their components. Relatively simple, and yet quite general, network models can represent a variety of applied problem environments. Network classes for which the models are discussed are particularly appropriate include data communications networks, voice communications networks, transportation networks, computer architectures, electrical power networks and command and control systems. The ultimate objective of research in the area of network reliability is to give design engineers procedures to enhance their ability to design networks for which reliability is an important consideration. Ideally, one would like to generate network design models and algorithms which take as input the characteristics of network components as well as network design criteria, and produce as output an "optimal" network design.
94 citations
25 Oct 1995
TL;DR: These models are general enough to cover performance evaluation of both homogeneous and heterogeneous computations in dedicated and nondedicated NOW systems and quantify the heterogeneity of networks and characterize the performance effects.
Abstract: A heterogeneous network of workstations (NOW) introduces a new performance factor into distributed computing: a large variation of the computing power of the different workstations. This unique factor makes traditional performance models/metrics for homogeneous computing measurement and evaluation not suitable for heterogeneous computing. We present models which quantify the heterogeneity of networks and characterize the performance effects. The models consider effects of both the heterogeneity and time-sharing in a nondedicated environment. Speedup, efficiency and scalability are defined. These models are general enough to cover performance evaluation of both homogeneous and heterogeneous computations in dedicated and nondedicated NOW systems. To validate and support performance modeling results, we conducted a collection of experimental measurements for evaluating computing performance and scalability of a group of application programs on a heterogeneous NOW.
88 citations
01 Apr 1995
TL;DR: The motivation for and an overview of Dome are provided, including a preliminary performance evaluation of dynamic load balancing for distributed vectors, and it is shown that a parallel program can be made failure resilient through Dome''s architecture independent checkpoint and restart mechanisms.
Abstract: Writing parallel programs for distributed multi-user computing environments is a difficult task. The Distributed object migration environment (Dome) addresses three major issues of parallel computing in an architecture independent manner: ease of programming, dynamic load balancing, and fault tolerance. Dome programmers, with modest effort, can write parallel programs that are automatically distributed over a heterogeneous network, dynamically load balanced as the program runs, and able to survive compute node and network failures. This paper provides the motivation for and an overview of Dome, including a preliminary performance evaluation of dynamic load balancing for distributed vectors. Dome programs are shorter and easier to write than the equivalent programs written with message passing primitives. The performance overhead of Dome is characterized, and it is shown that this overhead can be recouped by dynamic load balancing in imbalanced systems. Finally, we show that a parallel program can be made failure resilient through Dome''s architecture independent checkpoint and restart mechanisms.
84 citations
01 Dec 1995
TL;DR: An advanced simulation environment is described which is able to accurately predict the performance bottlenecks of a multimedia wireless network system being developed at UCLA, determine the trade-off point between the various bottlenECks, and provide performance measurements and validation of algorithms which are not possible through experimentation and too complex for analysis.
Abstract: This paper describes an advanced simulation environment which is used to examine, validate, and predict the performance of mobile wireless network systems. This simulation environment overcomes many of the limitations found with analytical models, experimentation, and other commercial network simulators available on the market today. We identify a set of components which make up mobile wireless systems and describe a set of flexible modules which can be used to model the various components and their integration. These models are developed using the Maisie simulation language. By modeling the various components and their integration, this simulation environment is able to accurately predict the performance bottlenecks of a multimedia wireless network system being developed at UCLA, determine the trade-off point between the various bottlenecks, and provide performance measurements and validation of algorithms which are not possible through experimentation and too complex for analysis.
72 citations
02 Aug 1995
TL;DR: A simple yet comprehensive model for use in compiling for a network of processors, and compiler algorithms for generating optimal and sub-optimal schedules of loops for load balancing, communication optimizations and network contention are proposed.
Abstract: In this paper we study the problem of scheduling parallel loops at compile-time for a heterogeneous network of machines. We consider heterogeneity in three aspects of parallel programming: program, processor and network. A heterogeneous program has parallel loops with different amount of work in each iteration; heterogeneous processors have different speeds; and a heterogeneous network has different cost of communication between processors. We propose a simple yet comprehensive model for use in compiling for a network of processors, and develop compiler algorithms for generating optimal and sub-optimal schedules of loops for load balancing, communication optimizations and network contention. Experiments show that a significant improvement of performance is achieved using our techniques.
40 citations
23 Oct 1995
TL;DR: This paper describes an end-to-end system combining a scalable video compression algorithm, video delivery software, a software video decoder, and a market-based mechanism for the resolution of conflicts in providing video to the user.
Abstract: Precompressed video delivery systems commonly operate at fixed data rates. However, variations in the availability of network bandwidth and processor cycles are common in dynamic general purpose computing environments. Variability arises from the outright lack of resources (e.g. network bandwidth and cpu cycles), contention for available resources due to congestion, or a user's unwillingness to allocate needed resources to the task. Users of a scalable video delivery system have greater flexibility and therefore, the system can more effectively deliver video in the presence of system resource scarcity. This paper describes an end-to-end system combining a scalable video compression algorithm, video delivery software, a software video decoder, and a market-based mechanism for the resolution of conflicts in providing video to the user.
32 citations
TL;DR: An advanced simulation environment is described which is able to accurately predict the performance bottlenecks of a multimedia wireless network system being developed at UCLA, determine the trade-off point between the various bottlenECks, and provide performance measurements and validation of algorithms which are not possible through experimentation and too complex for analysis.
Abstract: This paper describes an advanced simulation environment which is used to examine, validate, and predict the performance of mobile wireless network systems. This simulation environment overcomes many of the limitations found with analytical models, experimentation, and other commercial network simulators available on the market today. We identify a set of components which make up mobile wireless systems and describe a set of flexible modules which can be used to model the various components and their integration. These models are developed using the Maisie simulation language. By modeling the various components and their integration, this simulation environment is able to accurately predict the performance bottlenecks of a multimedia wireless network system being developed at UCLA, determine the trade-off point between the various bottlenecks, and provide performance measurements and validation of algorithms which are not possible through experimentation and too complex for analysis.
Patent•
06 Jun 1995TL;DR: In this article, a network printing system is provided for allowing a single channel connection to support multiple channel connections when implemented over a direct connect, non-network device, and a socket simulation protocol (SSP) is incorporated into the printing system for providing multiple data paths for allowing serial based host drivers to interact with the network printer in the same synchronous model as in multiple connection based drivers.
Abstract: A network printing system is provided for allowing a single channel connection to support multiple channel connections when implemented over a direct connect, non-network device. More particularly, a socket simulation protocol (SSP) is incorporated into the printing system for providing multiple data paths for allowing serial based host drivers to interact with the network printer in the same synchronous model as in multiple connection based drivers. SSP enables a normalized interface to the printing system so that various heterogeneous network services protocol/ports may interact in the same way and for also enabling new protocol/ports to be easily extended and integrated into the network printing system.
27 Sep 1995
TL;DR: Design considerations for future-generation personal communication networks (PCN) that integrate wireless access with the broadband wireline asynchronous transfer mode (ATM) network are presented.
Abstract: This paper presents design considerations for future-generation personal communication networks (PCN) that integrate wireless access with the broadband wireline asynchronous transfer mode (ATM) network. Apart from the wireless ATM network architecture, some of the other issues that we report on include the design of the wireless-to-wireline network interfaces, and the specification of a wireless protocol reference model. Two examples are given of ways to accomplish diversity and related handoffs in the wireless ATM network.
01 Jan 1995
TL;DR: A novel strategy for video transport is proposed using a layered source coder in conjunction with a variable QOS, multiple-substream abstraction for the transport, which addresses specifically the need to obtain simultaneously high spectral efficiency, good subjective quality, and low perceptual delay on a wireless channel.
Abstract: Wireless access to continuous-media services such as video, voice, and audio is becoming increasingly prevalent. Interactive video services such as video conferencing and multimedia editing are two such services of particular interest. We discuss some of the problems with using the MPEG standard (which was designed for wired, circuit-switched services) for wireless packet-video transport in a mobile environment. We propose a novel strategy for video transport using a layered source coder in conjunction with a variable QOS, multiple-substream abstraction for the transport. This abstraction addresses specifically the need to obtain simultaneously high spectral efficiency, good subjective quality, and low perceptual delay on a wireless channel. It also addresses the heterogeneous transport resulting from the concatenation of a wireless access link with a broad-band backbone network.
01 Jan 1995
TL;DR: Metricom provides one of the best combinations of bandwidth, coverage area and cost for a wireless data network, and early users of the datagram mode confirm two well-known but sometimes forgotten principles.
Abstract: As the trend towards smaller, lighter and more powerful computers continues, mobility and wireless connectivity become increasingly important. The MosquitoNet project is studying issues in wireless and mobile computing, and this paper presents our performance analysis and observations of one of the emerging wireless technologies: the Metricom Microcellular Digital Network (MCDN). Metricom provides one of the best combinations of bandwidth, coverage area and cost for a wireless data network. We find that the throughput of their radio devices is comparable to a modern modem, but the latency, or round-trip delay, is much higher. The maximum throughput we measured was 30-40 Kbits/second, but the minimum latency for even the smallest IP packet is at least 60ms. We have experimented with both the datagram and Hayes modem emulation modes of Metricom’s wireless radios. We are early users of the datagram mode, and our comparisons of these modes confirm two well-known but sometimes forgotten principles. First, packet switching allows more efficient sharing of resources than does circuit switching. Second, interfaces that are satisfactory for use by human beings often show their flaws, ambiguities and omissions when used as programming interfaces for software control of devices.
01 Mar 1995
TL;DR: The results indicate that processor speeds are application dependent and it is shown how to use this information along with memory constraints for efficient scheduling.
Abstract: In this paper we present a summary of the issues that need to be dealt with to effectively use a heterogeneous network of machines. We specifically point out the impact of processor and memory heterogeneity on the performance of parallel programs. Our results indicate that processor speeds are application dependent and we show how to use this information along with memory constraints for efficient scheduling.
TL;DR: This paper describes a flexible, tree-structured virtual machine made up of arbitrary and heterogeneous computing nodes dispersed across the country, and presents results on performance, price-performance, and toolkit-based parallelization, and compares these against equivalent computations on a Cray/Y-MP.
02 Apr 1995
TL;DR: Several techniques for locating faults in a network which is modeled as an undirected graph are presented, which are completely different from the existing techniques in which fault location begins after all the status information has been collected.
Abstract: Presents several techniques for locating faults in a network which is modeled as an undirected graph. The novelty of these techniques lies in combining the process of collecting status information (from each network element) with the process of locating a fault, which is completely different from the existing techniques in which fault location begins after all the status information has been collected. The techniques presented in the paper have different characteristics and hence they are applicable in different networking environments. However, an intelligent combination of the techniques can be used in a large scale heterogeneous network in an efficient manner for locating faults.
01 Jan 1995
TL;DR: In this article, the multi-installment load distribution strategy is applied to a linear network of processors without front-ends, where the communication links in the network are assumed to have non-zero delays.
Abstract: In this paper the multi-installment load distribution strategy is applied to a linear network of processors without front-ends. The communication links in the network are assumed to have non-zero delays. The load is distributed in more than one installment in order to minimize the processing time. Recursive equations are developed for heterogeneous networks and a closed-form solution is derived for homogeneous networks. To obtain the ultimate performance limits of the network, a computational study is conducted and some significant results are inferred
04 Oct 1995
TL;DR: Two network architectures are considered, one based on semi-permanent circuit switching, the other one using the fast connect capability of the DECT subsystem.
Abstract: This paper explores the applicability of DECT wireless systems in MAP local industrial networks. Two network architectures are considered, one based on semi-permanent circuit switching, the other one using the fast connect capability of the DECT subsystem. Performances and application domains are discussed.
TL;DR: This paper presents a MAC (medium access control) layer protocol GRAPO (optimized group randomly addressed polling) for wireless (local area) data network that statistically optimizes the original version of GRAP proposed earlier.
Abstract: This paper presents a MAC (medium access control) layer protocol GRAPO (optimized group randomly addressed polling) for wireless (local area) data network. GRAPO statistically optimizes the original version of GRAP proposed earlier [6, 7, 9] to deliver smooth converging and better throughput/delay performance. It is a good candidate of MAC protocol for wireless LANs and other wireless network applications to serve time bounded services.
16 Oct 1995
TL;DR: This paper compares the access control mechanisms of SNMP version 2 against those proposed for CMIP, using the Typed Access Matrix model as a framework to study the two approaches in detail.
Abstract: In this paper, we discuss access control for objects distributed over heterogeneous network management systems. In particular, we compare the access control mechanisms of SNMP version 2 against those proposed for CMIP. We employ the Typed Access Matrix model as a framework to study the two approaches in detail. Apart from the differences due to their management model, both schemes use an identitybased ACL scheme on object groups defined as collections of subtrees. We present an access control scheme integrating both systems.
01 Sep 1995
TL;DR: An implementation called TRACS for retrieval and assembly of satellite image data is presented and the idea of an implicit commitment is presented as providing a way to enable automated coordination of resources localized among heterogeneous agents.
Abstract: This paper describes a multiple agent system for distributed planning, specifically for intelligent network information retrieval. The system consists of a set of reactive agents located at each information- or capability-provider site plus an agent to track each information request. The agents negotiate with each other to assemble a distributed plan for satisfaction of each information need and each agent also interfaces with local retrieval and data processing functions. The idea of an implicit commitment is presented as providing a way to enable automated coordination of resources (information and capabilities) localized among heterogeneous agents. The advantages of a “shared machine” implemented by such a commitment protocol are discussed and an implementation called TRACS for retrieval and assembly of satellite image data is presented.
Patent•
20 Apr 1995
TL;DR: In this article, the authors propose a switching network which uses coupled power switching modules and corresponding software to perform the service of user-dependent switching of the supply voltage of individual network components.
Abstract: Computers are increasingly operated in local area networks (LAN). These presuppose that all the required components of the network are in operation in each case, with the result that, in order to ensure reliable network operation, all the network components are often switched on at the beginning of work, although it is rare that all the devices are needed in the course of the working day. The invention is based on the problem of switching on all the components of a network interconnection (personal computers, monitors, printers, etc.), as a function of the user behaviour, only when this is necessary. There is constructed in parallel with the existing local data network a switching network which uses coupled power switching modules and corresponding software to perform the service of user-dependent switching of the supply voltage of the individual network components. The installation of this system in personal computers means that it may be ensured that the number of components of the network which is switched on is always the minimum number required for reliable network operation.
Book•
01 Jan 1995
TL;DR: A computational and engineering view on open distributed real-time multimedia exchange and system-level resource management for network-based multimedia applications are presented.
Abstract: Advance reservations for predictive service.- Distributed advance reservation of real-time connections.- Issues of reserving resources in advance.- A computational and engineering view on open distributed real-time multimedia exchange.- Support for user-centric modular real-time resource management in the Rialto operating system.- A rate-based execution abstraction for multimedia computing.- VuSystem performance measurements.- Design of universal continuous media I/O.- A new OS architecture for high performance communication over ATM Networks.- Meeting arbitrary QoS constraints using Dynamic Rate Shaping of coded digital video.- Dynamic QoS management for scalable video flows.- Dynamic service aggregation for efficient use of resources in interactive video delivery.- Evaluation of QOS-Control Servers on Real-Time Mach.- System-level resource management for network-based multimedia applications.- Session IV: A NOSSDAV retrospective.- An end to end software only scalable video delivery system.- A distributed real-time MPEG video audio player.- Analysis of audio packet loss in the internet.- Digital audio and video in industrial systems.- Workstation video playback performance with competitive process load.- When can we unplug the radio and telephone?.- An Adaptive Stream Synchronization Protocol.- A Method and apparatus for measuring media synchronization.- Integrated processor scheduling for multimedia.- Scheduling and admission testing for jitter constrained periodic threads.- A CPU scheduling algorithm for continuous media applications.- Dynamic configuration of conferencing applications using pattern-matching multicast.- WAVE: A new multicast routing algorithm for static and dynamic multicast groups.- Connection establishment for multi-party real-time communication.- The role of multicast communication in the provision of scalable and interactive Video-On-Demand service.- RED-VBR: A new approach to support delay-sensitive VBR video in packet-switched networks.- Determining end-to-end delay bounds in heterogeneous networks.- Adaptive QoS-based API for ATM networking.- Burst scheduling networks: Flow specification and performance guarantees.- A novel video-on-demand storage architecture for supporting constant frame rate with variable bit rate retrieval.- The design and implementation of a RAID-3 multimedia file server.- Efficient data layout, scheduling and playout control in MARS.- Storage replication and layout in Video-On-Demand servers.- Scalable MPEG2 video servers with heterogeneous QoS on parallel disk arrays.- The design of a variable bit rate continuous media server.
TL;DR: This article examines the place of analytical models in realtime performance management applications and proposes a system based on a composite model that provides the optimal software environment for performance analysis and tuning of heterogeneous networks.
Abstract: This article examines the place of analytical models in realtime performance management applications. The main objectives are to define, specify and implement a system based on a composite model that provides the optimal software environment for performance analysis and tuning of heterogeneous networks.
TL;DR: Two different programming paradigms for heterogeneous computing, Cluster-M and Heterogeneous Associative Computing are evaluated, which can efficiently support heterogeneous networks by preserving a level of abstraction without containing any architectural details.
01 Dec 1995
TL;DR: This work has studied the performance of TCP and NFS over a wireless network to understand the effects of wireless communication on these protocols and improve performance without requiring changes to the current network Infrastructure.
Abstract: Technological trends suggest that soon communication networks will consist of a high speed wired backbone with numerous wireless Local Area Networks. Mobile computing and wireless subnetworks are increasingly in demand. Mobile routing solutions provide wireless LANs with seamless connectivity to backbone wired systems. However, these solutions do not provide acceptable performance. Wireless networks have distinct transmission characteristics which present challenges to achieving eecient performance. Performance over wireless links is limited by high error rates, mobility, and low bandwidth. We have studied the performance of TCP and NFS over a wireless network. The prevalence of these protocols means that mobile hosts will frequently use them when communicating with stationary hosts. Measurements have been collected to determine the response of these protocols in the presence of various error patterns. These measurements show that NFS and TCP performance suuer extreme degradation due to these wireless link characteristics. Unexpectedly, NFS performance is not better than an TCP FTP le transfer. NFS performance over wireless links is limited by large packet sizes, long retransmission timeouts, and slow response to losses. Our goal is to understand the eeects of wireless communication on these protocols and improve performance without requiring changes to the current network Infrastructure.