The benefits of cooperation among devices of wireless networks are potentially so rewarding that distributed processing has become a major research topic in recent years. distributed protocols are designed to achieve ...
详细信息
The benefits of cooperation among devices of wireless networks are potentially so rewarding that distributed processing has become a major research topic in recent years. distributed protocols are designed to achieve a global task over a network of d...
The paper describes a small update and enquiry system developed on a PDP11/34 computer and the steps that are required to upgrade this system to a distributed configuration based on microcomputers. The advantages of t...
详细信息
The paper describes a small update and enquiry system developed on a PDP11/34 computer and the steps that are required to upgrade this system to a distributed configuration based on microcomputers. The advantages of the distributed approach are discussed and found to be dominant.
The first experiences of the authors in distributed processing of the finite-element method in local area networks (LANs) are described. A procedure for solving finite element problems has been implemented on five DEC...
详细信息
The first experiences of the authors in distributed processing of the finite-element method in local area networks (LANs) are described. A procedure for solving finite element problems has been implemented on five DEC computers within such a network. The principal idea is to subdivide the whole problem into substructures and to eliminate the interior nodes of those in parallel autonomous processes by frontal techniques. The aim is to keep the resulting system of equations as small as possible, so that this resulting set of equations can be solved on one processor by ICGG (incomplete choleski conjugate gradient) method in an acceptable time. As another application of distributed processing, higher evolution strategies for optimization problems in a finite-element context have been parallelized. It is concluded that substructuring as a means of performing parallel processing on a LAN is only of interest for large 2-D problems.< >
Based on the premise that flexibility is a primary objective for future data networks, it is proposed to integrate circuit switching (CS) and packet switching (PS) in a single network. This paper addresses the switchi...
详细信息
Based on the premise that flexibility is a primary objective for future data networks, it is proposed to integrate circuit switching (CS) and packet switching (PS) in a single network. This paper addresses the switching node in such a network. A novel node concept is presented, imposing PS on a CS structure. Connection management and node control functions on the one hand and packet processing/storing on the other are performed by two groups of modules. The modularity requirement leads to very small, simple processors built into storage modules for packet handling. Considering the high throughput requirement of about 1200 packets/s/node, configurations may exceed 30 packet-handling modules. The wellknown saturation effect of multiprocessor systems, i.e., decreasing incremental throughput with increasing number of processor modules, is overcome by a new concept of intermodule communications, taking advantage of the particular data-communications environment. Intermodule communications-and therefore overhead-have been significantly reduced. As a result, systems throughput for fixed processor module utilization is nearly a linear function of the number of modules, the deviation from linearity being less than 10 percent over the range considered.
The application of distributed processing, fiber optics, and hardware redundancy to collecting airstream data in the digitally controlled variable-response research aircraft (VRA) at the Flight Research Laboratory of ...
详细信息
The application of distributed processing, fiber optics, and hardware redundancy to collecting airstream data in the digitally controlled variable-response research aircraft (VRA) at the Flight Research Laboratory of Princeton University is described. Microprocessor-controlled instrumentation packages in each wingtip of the aircraft collect angle-of-attack and sideslip data in digital form; after scaling, filtering, and calibrating the data, they send it to the microprocessor digital flight control system (micro-DFCS) via digital fiber-optic data links. Each wingtip package is independent of the other; therefore, the system has dual hardware redundancy. The fiver-optic link design is presented as well as a description of the calibration and communications software. Translation of the system's dual redundancy into fault tolerance is also covered. Results of preliminary flight tests are included.
It is shown both theoretically and by simulation that a balanced amplifier has a lower VSWR withstand capability than that of the transistors used in its construction, meaning the maximum VSWR before the transistor wi...
详细信息
It is shown both theoretically and by simulation that a balanced amplifier has a lower VSWR withstand capability than that of the transistors used in its construction, meaning the maximum VSWR before the transistor will fail or its reliability degraded. A revised VSWR withstand capability should be adopted for a balanced amplifier to prevent device failure.
As the cost of central processing power falls, so the cost of peripherals become relatively more expensive. One solution is to share peripherals in a local area network (LAN). The paper describes the development of an...
详细信息
As the cost of central processing power falls, so the cost of peripherals become relatively more expensive. One solution is to share peripherals in a local area network (LAN). The paper describes the development of an advanced fileserver for LANs, the DataStore, which maintains data in a multilevel hierarchical directory structure. The Data Store will be able to handle full database transactions, administrate a distributed system and will also be used as an underlying mechanism for a more sophisticated type of operating system.
An integrated approach to implementation of computerized monitoring systems within a nuclear power plant is best achieved by distributed processing since diverse users and applications often require the same basic inp...
详细信息
An integrated approach to implementation of computerized monitoring systems within a nuclear power plant is best achieved by distributed processing since diverse users and applications often require the same basic input data. A radiation monitoring system that exemplifies application of distributed processing to a broad area of plant operation is described as a first step to integrating platn monitoring functions.
This paper addresses the problem of efficiently querying large numbers of text documents, using parallel processing methods. The optimization criteria are somewhat different from those used in querying heterogeneous d...
详细信息
ISBN:
(纸本)076951023X
This paper addresses the problem of efficiently querying large numbers of text documents, using parallel processing methods. The optimization criteria are somewhat different from those used in querying heterogeneous databases, largely because the extraction of ontological information from documents is the dominant component of query execution time. Here we assume that each document has been previously annotated using XML. In this paper we describe architecture of a system to process ontology based queries for XML annotated documents. We have introduced two basic strategies for query processing: simple strategy, and semi-join strategy, and their possible extensions using pipelining and longer lists for keyword search, Different levels of parallelism for these strategies are discussed. An evaluation model is created and used to derive optimal replication of resource agents. The theoretical and experimental results are compared.
The growth of pervasive computing, such as Internet of Things, increase the number of devices and the amount of context information being generated. Existing frameworks such as Cloud computing simply utilize these IoT...
详细信息
ISBN:
(纸本)9781538691519
The growth of pervasive computing, such as Internet of Things, increase the number of devices and the amount of context information being generated. Existing frameworks such as Cloud computing simply utilize these IoT devices as end-to-end network gateways. Paradigms such as Edge and Fog computing while able to minimize latency by bringing computing devices nearer to the data source, fail to consider the utilization of computation resource of these IoT devices. For connectivity challenged environments such as rural or disaster areas, cloud and edge/fog systems are not as accessible and devices are limited to wireless sensor networks and cheap commodity computing nodes. The goal of our research is to deliver pervasive computing to these environments by developing a middleware for heterogeneous IoT devices. Utilizing the middleware enables IoT devices to perform distributed machine information processing on available sensor nodes, without Cloud-based computing resources.
暂无评论