Showing papers on "Node (networking) published in 1985"

The Eden System: A Technical Review

Abstract: The Eden project is a five year experiment in designing, building, and using an "integrated distributed" computing system. We are attempting to combine the benefits of integration and distribution by supporting an object based style of programming on top of a node machine/local network hardware base. Our experimental hypothesis is that such an architecture will provide an environment conducive to building distributed applications.

Local area network

Abstract: A communications system suitable for use as a local area network (LAN) is provided wherein the network has a ring topology comprising a plurality of nodes 10 each of which is connected to adjacent nodes by links 14 and 15. Each node comprises a Link Interface Unit (LIU) 11, a Network Interforce Unit (NIU) 12 and a Terminal Interface Unit (TIU) 13. By providing forward and reverse links 14, 15 between nodes the system is capable of reconfiguring itself after link or node failure such that the failed equipment can be bypassed to minimize system disruption. Link Interface Units (LIU) 11 are also capable of bypassing their own node if a node failure is detected. System control is decentralized with each active node contributing to system control such that prime-failure sites are avoided. System protocol depends upon a token passing scheme where only the node 10 currently holding the token is entitled to transmit data and once it has finished its transmission the node 10 passes the token to the next node 10 in the ring. The system operates under a strict timing regime wherein a system cycle of substantially fixed period is established and the first rotation of the token around the ring during the system cycle is used to initiate transmission of the highest priority data with subsequent rotations of the token initiating transmission of data of progressively lower priorities. Accordingly, the timeslots available for transmission of each data type have variable-boundaries determined by the system load.

Optimal Server Location on a Network Operating as an M/G/1 Queue

Abstract: This paper extends Hakimi's one-median problem by embedding it in a general queueing context. Demands for service arise solely on the nodes of a network G and occur in time as a Poisson process. A single mobile server resides at a facility located on G. The server, when available, is dispatched immediately to any demand that occurs. When a demand finds the server busy with a previous demand, it is either rejected Model 1 or entered into a queue that is depleted in a first-come, first-served manner Model 2. Service time for each demand comprises travel time to the scene, on-scene time, travel time back to the facility and possibly additional off-scene time. One desires to locate the facility on G so as to minimize average cost of response, which is either a weighted sum of mean travel time and cost of rejection Model 1, or the sum of mean queueing delay and mean travel time. For Model 1, one finds that the optimal location reduces to Hakimi's familiar nodal result. For Model 2, nonlinearities in the objective function can yield an optimal solution that is either at a node or on a link. Properties of the objective function for Model 2 are utilized to develop efficient finite-step procedures for finding the optimal location. Certain interesting properties of the optimal location as a function of demand rate are also developed.

Data communication network

Abstract: A network for data transmission between nodes interconnected by transmission paths on which a predefined data signal is continuously transmitted to sequentially reach each node. Data traffic is controlled by apparatus responsive to receiving the predefined data signal a predetermined number of times and generating node signals each varying in time in accordance with data traffic on the network to control node access thereto. Multiple nodes are enabled to mutually write data onto the network proportional to the communication network data traffic independent of the network location of the predefined data signal.

Database partitioning in a cluster of processors

Abstract: In a distributed database system the partitioning and allocation of the database over the processor nodes of the network can be a critical aspect of the database design effort. In this paper we develop and evaluate algorithms that perform this task in a computationally feasible manner. The network we consider is characterized by a relatively high communication bandwidth, considering the processing and input output capacities in its processors. Such a balance is typical if the processors are connected via busses or local networks. The common constraint that transactions have a specific root node no longer exists, so that there are more distribution choices. However, a poor distribution leads to less efficient computation, higher costs, and higher loads in the nodes or in the communication network so that the system may not be able to handle the required set of transactions.Our approach is to first split the database into fragments which constitute appropriate units for allocation. The fragments to be allocated are selected based on maximal benefit criteria using a greedy heuristic. The assignment to processor nodes uses a first-fit algorithm. The complete algorithm, called GFF, is stated in a procedural form.The complexity of the problem and of its candidate solutions are analyzed and several interesting relationships are proven. Alternate benefit metrics are considered, since the execution cost of the allocation procedure varies by orders of magnitude with the alternatives of benefit evaluation. A mixed benefit evaluation strategy is eventually proposed.A model for evaluation is presented. Two of the strategies are experimentally evaluated, and the reported results support the discussion. The approach should be suitable for other cases where resources have to be allocated subject to resource constraints.

Analysis of Traffic Access Control Strategies in Integrated Service Networks

Abstract: A common digital transmission facility provides service to a community of heterogeneous users generating traffic with differing intensity, message length, and bit rate. In order for this type of integrated communication system to handle its traffic demands with high efficiency and flexibility, close control of access and switching at the input node is required. We propose, analyze, and compare two different strategies for managing the access of two types of traffic, a blockable wide-band (WB) type of traffic and a queueable narrow-band (NB) type of traffic, sharing the transmission resource dynamically. The first strategy assigns preemptive priority to the WB traffic over the NB traffic, whereas the second strategy employs a wide-band to narrow-band bit rate compression mechanism. Exact analytic models are developed, and solution methods are presented and implemented. It is shown that the best combined performance is obtained when the two strategies are adaptively combined according to the offered load.

Shortest paths in networks with vector weights

Abstract: For a directed network in which vector weights are assigned to arcs, the Pareto analog to the shortest path problem is analyzed. An algorithm is presented for obtaining all Pareto shortest paths from a specified node to every other node.

A Median Location Model with Nonclosest Facility Service

Abstract: This paper deals with the location of service facilities on a transportation network where the closest (in distance, time or cost) facility is known not to service some significant portion of demand. The concept of vector assignment of demand nodes to facilities is introduced to account for nonclosest facility service. A generalized formulation of the p-median problem incorporating vector assignment is presented. It is shown that an optimal solution to this vector assignment p-median problem exists which consists entirely of nodes of the graph; however, there may be more than one facility per node. Three different solution procedures are discussed for the vector assignment p-median problem. Computational experiments for three different moderately sized data sets give encouraging results. A locational example is included which gives a comparison of an optimal p-median solution and an optimal p-median solution with vector assignment.

Algorithm for Mixing Problems in Water Systems

Abstract: The “Solver” algorithm, developed as an outgrowth of work on cost allocation in water distribution systems, is a simple technique that solves a number of interesting problems in water distribution system analysis. Problems related to mixing water from different sources within the distribution network, travel time from any source to any node of the network, and development of the cost of service to any node in the network can be solved assuming steady‐state conditions, given a prior solution of the hydraulics (flow in each link) of the network. All these problems are formulated as the solution of simultaneous linear equations. The Solver algorithm has been coded in Fortran and incorporated within the structure of a multi‐purpose system of computer programs that allows for the storage, display and manipulation of data associated with node‐link networks describing water distribution systems. These programs are identified by the name Water Supply Simulation Model. The formulation of the Solver algorithm is de...

Local area networks

Abstract: A Local Area Network (LAN) is disclosed which enables a generalized data communication facility to be established over ordinary telephone wiring. The disclosed technique provides a completely general LAN architecture with any excess protocol and is well suited to CSMA/CD (carrier sense, multiple access with collision detection). The invention consists of architectural and circuit techniques which enable the construction of a local area network(s) (LAN) over ordinary wiring within a building or beween buildings within a short distance of each other (often called a campus). The LAN is implemented without disturbing the normal voice function of the telephone circuits and without the need to string additional wiring. Implementing a LAN in accordance with this invention requires only three types of hardware functional elements (in the appropriate quantities for the application): a) a Node Unit (NU), b) Repeater Unit (RU), and c) depending on the size of the network, possibly a Pulse Regenerator Unit (PRU).

Integrated voice/data network

Abstract: Circuits at a remote transmission site receive digitized voice and data samples from incoming channels. The voice samples are compressed. The samples are formatted into fixed-size data blocks with signaling and control information for transmission to a switching node. Additional bits of the voice samples are dynamically dropped, if necessary, to fit the data into the fixed-sized blocks. The signaling and control information allows receiving circuits at the switching node to determine the number of bits allocated to each sample. These receiving circuits form packets for individual channels by attaching switch routing packet headers to the individual channel data. Packet receiving circuits on the output side of the switch reformat the received packets into fixed-size nonpacket data blocks for transmission.

Name usage support through distributed processing networks linked by bridges and/or gateways

Abstract: For facilitating data communication between entities in a local area network (storage files, programs, devices, human operators, etc.), a method is disclosed for addressing such communications to logical names adopted for the entities; rather than to discrete physical locations in the network. The subject method allows for extension of name-directed communications across bridges (between separate communication media or between discrete frequency channels on one medium). Extensions of such communications across bridges are conditioned on the handling of respective communications within the channel or medium leading to respective bridges. If a named entity is reachable within a channel or medium leading to a bridge, the communication will be acknowledged by the processing facility at the node serving that entity, and the communication will not be extended. With the present method, a program running on a processor at one node of the network may call for retrieval of a data set by name, where the location of the data set need not be known or specifiable by either the program or the processor and the respective data set may be retrieved through a process of communication which is entirely transparent to the program and processor, and also not ambiguous or burdensome when the network path to the named data set contains bridges and/or gateways.

Switched point-to-point local area network control mechanism

Abstract: A local area network employs a shared control channel over which control messages between frequency agile modems for each of the user nodes of a distributed architecture-configured network are exchanged. In addition to the shared control channel, a plurality of data channel pairs is available for effecting full duplex communications between any two nodes of the network. Because all data channel assignments depend upon successful use of the control channel, a prescribed control channel contention access scheme is employed to optimize use of the control channel by all users of the network irrespective of the demand for its use. Pursuant to this scheme, each requesting node must first compare an accumulated activity measure with a traffic density threshold that is continuously optimized for the current level of control channel activity. Unless the accumulated measure is less than the threshold, the requesting user node is temporarily forbidden access to the control channel by a period of time designed to reduce traffic to the optimal level.

System and method for controlling network bus communications for input-output interlocking information among distributed programmable controllers

Abstract: A control system for controlling an industrial process includes a network of a plurality of distributed programmable controllers or nodes coupled serially to a communications bus on either a single or dual media by means of a shielded twisted wire pair cable. The programmable controllers are coupled to the bus through a communications module which uses a broadcast method to achieve peer-to-peer communications. One module of the network, designated as an active monitor, exercises exclusive supervisory control of the broadcast activity on the network. The active monitor polls each node coupled to the network and each active node responds by broadcasting unacknowledged data to all nodes in the network. The broadcast message of each node in the network is mapped directly into designated variable memory locations of each programmable controller on the network. The active monitor establishes a list of active nodes based on the responses to the poll and allocates a time slot to each active node to broadcast its data and on a cyclical basis continues to poll a different node each network scan to update the list. Fault tolerance is provided by either an active-passive monitor arrangement for the single medium embodiment or by a redundant medium connection for the dual media embodiment.

A distributed asynchronous relaxation algorithm for the assignment problem

Abstract: Relaxation methods for optimal network flow problems resemble classical coordinate descent, Jacobi, and Gauss-Seidel methods for solving unconstrained non-linear optimization problems or systems of nonlinear equations. In their pure form they modify the dual variables (node prices) one at a time using only local node information while aiming to improve the dual cost. They are particularly well suited for distributed implementation on massively parallel machine. For problems with strictly convex arc costs they can be shown to converge even if relaxation at each node is carried out asynchronously with out-of-date price information from neighboring nodes [1]. For problems with linear arc costs relaxation methods have outperformed by a substantial margin the classical primal simplex and primal-dual methods on standard benchmark problems [2], [3]. However in these particular methods it is necessary to change sometimes the prices of several nodes as a group in addition to carrying out pure relaxation steps. As a result global node price information is needed occasionally, and distributed implementation becomes somewhat complicated. In this paper we describe a distributed algorithm for solving the classical linear cost assignment problem. It employs exclusively pure relaxation steps whereby the prices of sources and sinks are changed individually on the basis of only local (neighbor) node price information. The algorithm can be implemented in an asynchronous (chaotic) manner, and seems quite efficient for problems with a small arc cost range. It has an interesting interpretation as an auction where economic agents compete for resources by making successively higher bids.

PACKET SWITCHED MULTIPORT MEMORY NxM SWITCH NODE AND PROCESSING METHOD.

Abstract: A packet switching node which processes applied data packets containing routing tag signals indicative of the output port destination to which the data packets are to be applied The invention comprises an NxM switch node that accepts data packets at any of N input ports and routes each to any of M output ports The output selected is determined by the routing tag signal in the packet The node comprises a multiport memory having a predetermined number of memory locations available for storage of data packets applied to each of a plurality of input ports Control logic coupled to the input and output ports and memory is designed so that the data packets are effectively sorted according to their desired output port destination The control logic comprises arbitration logic which randomly, in a statistical sense, chooses among any data packets that are directed to the same output port The algorithm implemented by the arbitration logic is designed so that data packets will not wait indefinitely to be routed from the switch node A method in accordance with the present invention comprises sorting and storing the data packets based upon the output port destination and then arbitrating among the data packets The final step involves routing the data packets selected during the arbitration processes to the output ports identified in the routing tag signals

A Top-Down Quadtree Traversal Algorithm

Abstract: Many standard image processing operations can be implemented using quadtrees as a simple tree traversal where, at each terminal node, a computation is performed involving some of that node's neighbors. Most of this work has involved the use of bottom-up neighbor-finding techniques which search for a nearest common ancestor. Recently, top-down techniques have been proposed which make use of a neighbor vector as the tree is traversed. A simplified version of the top-down method for a quadtree in the context of a general-purpose tree traversal algorithm is presented. It differs, in part, from prior work in its ability to compute diagonally adjacent neighbors rather than just horizontally and vertically adjacent neighbors. It builds a neighbor vector for each node using a minimal amount of information. Analysis of the algorithm shows that its execution time is directly proportional to the number of nodes in the tree. However, it does require some extra storage. Use of the algorithm leads to lower execution time bounds for some common quadtree image processing operations such as connected component labeling.

Increasing coherence in a distributed problem-solving network

Abstract: Globally coherent behavior is the holy grail of distributed problem solving network research. Obtaining coherent network activity without sacrificing node autonomy and network flexibility places severe demands on the local control component of each node. We introduce new mechanisms that allow a node to compute an abstracted, high-level description of its local state which it then uses to formulate multi-step plans. Not only do these mechanisms significantly improve local problem solving performance, but they also enable nodes to make dynamic refinements to their long-term network organisation knowledge. The coordination decisions made by nodes are thus increasingly responsive to changes in network activity as problem solving progresses. We provide experimental results indicating that these new mechanisms improve the internal control decisions of a node, reduce the communication requirements of the network, and improve network coherence. We believe that these mechanisms would also be useful for control in centralised multi-level blackboard-based problem solving systems.

A unified framework for primal-dual methods in minimum cost network flow problems

Abstract: We introduce a broad class of algorithms for finding a minimum cost flow in a capacitated network. The algorithms are of the primal-dual type. They maintain primal feasibility with respect to capacity constraints, while trying to satisfy the conservation of flow equation at each node by means of a wide variety of procedures based on flow augmentation, price adjustment, and ascent of a dual functional. The manner in which these procedures are combined is flexible thereby allowing the construction of algorithms that can be tailored to the problem at hand for maximum effectiveness. Particular attention is given to methods that incorporate features from classical relaxation procedures. Experimental codes based on these methods outperform by a substantial margin the fastest available primal-dual and primal simplex codes on standard benchmark problems.

Locating a Mobile Server Queueing Facility on a Tree Network

Abstract: This paper extends recent work on finding the stochastic queue median SQM on a network. The SQM is the optimal location of a single mobile server, when idle, who travels to customers in response to requests for service. Customer demands are limited to the nodes of the network and their requests for service arrive according to a time homogeneous Poisson process, independently from each node. When a service request finds the server busy with a previous customer, it is entered into an M/G/1 queue that is depleted in a first-in, first-out FIFO manner. The SQM is the point on the network at which the sum of mean queueing delay and mean travel time is minimized. In this paper the transportation network is restricted to be a tree. By discovering and exploiting convex properties of the objective function and related functions, an efficient finite-step algorithm is found for locating the SQM on a tree.

Three approaches to heuristic search in networks

Abstract: Three different approaches to heuristic search in networks are analyzed. In the first approach, as formulated initially by Hart, Nilsson, and Raphael, and later modified by Martelli, the basic idea is to choose for expansion that node for which the evaluation function has a minimum value. A second approach has recently been suggested by Nilsson. In this method, in contrast to the earlier one, a node that is expanded once is not expanded again; instead, a “propagation” of values takes place. The third approach is an adaptation for networks of an AND/OR graph “marking” algorithm, originally due to Martelli and Montanari.Five algorithms are presented. Algorithms A and C illustrate the first approach; PropA and PropC, the second one; and MarkA, the third one. The performances of these algorithms are compared for both admissible and inadmissible heuristics using the following two criteria: (i) cost of the solution found; (ii) time of execution in the worst case, as measured by the number of node expansions (A, C), or node “selections” (PropA, PropC), or arc “markings” (MarkA).The relative merits and demerits of the algorithms are summarized and indications are given regarding which algorithm to use in different situations.

A comparison of receiver-initiated and sender-initiated adaptive load sharing (extended abstract)

Abstract: One goal of locally distributed systems is to facilitate resource sharing. Most current locally distributed systems, however, share primarily data, data storage devices, and output devices; there is little sharing of computational resources. Load sharing is the process of sharing computational resources by transparently distributing the system workload. System performance can be improved by transferring work from nodes that are heavily loaded to nodes that are lightly loaded.Load sharing policies may be either static or adaptive. Static policies use only information about the average behavior of the system; transfer decisions are independent of the actual current system state. Static policies may be either deterministic (e.g., “transfer all compilations originating at node A to server B”) or probabilistic (e.g., “transfer half of the compilations originating at node A to server B, and process the other half locally”).

Reliable object storage to support atomic actions

Abstract: To preserve the consistency of on-line, long-lived, distributed data in the presence of concurrency and in the event of hardware failures, it is necessary to ensure atomicity and data resiliency in applications. The programming language Argus is designed to support such applications. This thesis investigates the mechanism needed to support the notion of data resiliency present in Argus. Data resiliency means that the probability is very high that the crash of a node or storage device in a distributed system does not cause the loss of vital data. Data resiliency requires the use of stable storage devices, memory devices that survive failure to a high probability. This thesis is not concerned with how to implement stable storage devices, but rather with how to organize the use of stable storage. The thesis presents a new organization of stable storage called the hybrid log that provides fast writing of information to stable storage and reasonably fast recovery of information from stable storage. In the context of this scheme, various algorithms are developed for writing objects to the log, recovering objects from the log, and housekeeping the log. {AD#A136484}

Local area network special function frames

Abstract: In a local area network having a plurality of nodes, wherein the local area network utilizes a token passing scheme for communicating between nodes, each node has an interface apparatus which operates independently of a processor associated with the node. The node can be in an on-line mode or an off-line mode, wherein the node does not participate in token passing or receive information when in the off-line mode. A method of the present invention provides for diagnosing and/or recovering a second node from a first node, the method implemented by the second node includes the steps of waiting to receive a message frame addressed to the second node. If the message frame addressed to the second node is a special function frame, and if the second node is in the off-line mode, the type of special function frame is determined to perform the command specified by the type of special function frame. The operation of the second node then returns to the step of waiting to receive a message frame addressed to it.

An architecture for control and communications in distributed artificial intelligence systems

Abstract: An architecture and implementation for a distributed artificial intelligence (DAI) system are presented, with emphasis given to the control and communication aspects. Problem solving by this system occurs as an iterative refinement of several mechanisms, including problem decomposition, kernel-subproblem solving, and result synthesis. In order for all related nodes to make optimum use of the information obtained from these problem-solving mechanisms, the system dynamically reconfigures itself, thereby improving its performance during operation. This approach offers the possibilities of increased real-time response, improved reliability and flexibility, and lower processing costs. A major component in the node architecture is a database of metaknowledge about the expertise of a node's own expert systems and those of the other processing nodes. This information is gradually accumulated during problem solving. Each node also has a dynamic-planning ability, which guides the problem-solving process in the most promising direction and a focus-control mechanism, which restricts the size of the explored solution space at the task level while reducing the communication bandwidths required. It also has a question-and-answer mechanism, which handles internode communications. Examples in the domain of digital-logic design are given to demonstrate the operation of the system.

Apparatus and method for restricting access to a communication network

Abstract: Apparatus restricts access to a communication network having at least one service node for providing services to subscribers. A subscriber terminal, coupled to the communication network, includes a secret node key. A succession of frame verifier (FV) codes, derived through the use of the secret node key, is generated and transmitted on the network. A network access controller (NAC), coupled to the network, includes a record of the secret node key and uses the key to encrypt a seed which is transmitted to the subscriber terminal for use in generating the FV codes. The NAC also independently computes the succession of FV codes which should be generated by the subscriber terminal. A distributed access controller (DAC), coupled to the communication network, includes a look-up table for storing the succession of FV codes computed by the NAC. The FV codes transmitted by the subscriber terminal are detected and compared to those stored in the look-up table. If proper correspondence between the detected and stored FV codes is not found to exist, the communication network is jammed.

A 200 Mbit/s Synchronous TDM Loop Optical LAN Suitable for Multiservice Integration

Abstract: This paper describes a 200 Mbit/s multiservice optical local area network (LAN) using a synchronous TDM loop structure. The LAN consists of a central supervisory node and multiple service nodes connected by an optical fiber loop. Each service node supports communication channels which have access to allocated time slots in TDM frames continuously circulating on the loop. Multiple independent communication paths of various speeds up to 140 Mbits/s and various modes including point-to-point, ring, and multicast, can be provided between the channels on the loop. The ring will be useful to support ring networks, such as a token ring. The structure of this LAN is quite suitable for integration of multiple services, including video, image, data, and voice, since each service can independently choose its own speed, access method, and mode. In this development, various LSI-based high-speed hardware technologies including compact E/O and O/E modules, GaAs 4 × 4 matrix switch LSI's, and high-speed TDM-processor LSI's, which are versatilely applicable to high-speed LAN's ranging from 100 Mbits/s up to 560 Mbits/s, have been successfully introduced and compact LAN equipment has been obtained. This paper deals mainly with the system and hardware structure of this LAN, together with high-speed hardware technologies. An outline of firmware and network operation, and an application example are also described.

Cutset Analysis of Networks Using Basic Minimal Paths and Network Decomposition

Abstract: The concept of basic minimal paths has been introduced, and its use in deducing the node cutsets of a network was described. This 3 paper deals with two important aspects of basic minimal paths: 1) the deduction of link cutsets from node cutsets, and 2) reduction of computational requirements in deducing the basic minimal paths using network decomposition.