We propose a new resource allocation scheme based on the concept of resource reservation and resource renegotiation. The new scheme is aimed at improving performance with regard to new call blocking rate, handoff dropping rate, forced call termination rate, and average bandwidth use. We compare the performance of our scheme with other schemes by using simulation.

Signaling traffic incurred in tracking mobile users and delivering enhanced services causes an additional load in the network. Efficient database and location management schemes are needed to meet the challenges from high density and mobility of users, and various service features. In this paper, the general location control and management function is treated as the combination of two parts, the global and local scope. New schemes and methods are proposed, and improvements achieved over established basic schemes are shown by using simulations.

This paper proposes a congestion control model for wireless networks. Wireless communication can cause congestion in high-speed switching networks depending on the volume of calls, their origination and the network architecture. In congested areas where wireless services are extensively used, the switching network can become congested. In addition, the quality of wireless communication can decrease because of the frequency range that allows for limited number of calls made within the cell. The congestion control model allows for evaluation of those limitations and for choosing the best possible solution.

The partition of location areas is designed to minimize the total costs of finding users' location and tracking their movement in personal communication networks (PCNs). A new scheme to partition and track mobile users and its implementation based on cellular architecture are proposed. According to the tracking strategy, the mobile station (MS) transmits only update messages at specific reporting cells, while the search for a mobile user is done at the vicinity of the cell to which the user has just reported. We use the cost analysis model to demonstrate the feasibility of updating and searching costs to reduce the amount of resources when using wireless channels. Simulations are performed to compare the performance of three schemes: always update, always search, and our new scheme.

The paper presents a new switching architecture to improve telecommunications reliability. The architecture is partitioned depending on the type of network used, reliability requirements, and expected traffic in the network. The partition size depends on the network reliability, bandwidth, and traffic. A reliability model for a telecommunication architecture is used to partition the network and to improve end-to-end reliability. The model defines critical components in the networking architecture and their connections. The component connections permit the propagation of faults from the component in which the fault originates to the other components. This propagation can cause failures in the chain (or in the tree) of components. The partitioned architecture limits the propagation of faults, simplifies fault detection, and preserves reliability of the remaining partitions. Examples of different networks are used to show the applications of the model.>

This paper presents a new algorithm for parallel compilation of files in a multiprocessor or distributed software development environment. The algorithm reduces the elapsed time of load building for software application by allowing for parallel compilation of files. The distributed load building algorithm is based on the dependency graph. Performance of the algorithm is analyzed in a multiprocessor environment. The algorithm is implemented in a distributed system and tested for different number of files in the application and various number of processors. The results show that the system performance improves significantly as the number of processors in the system increases.>

Congestion control and switch buffer allocation techniques are proposed that allow for packet admission and transfer based on the switch and network occupancy. The packets are transferred if the required bandwidth is smaller than the bandwidth currently available. Otherwise, the packets are stored in the buffer. If the buffer is full, the incoming packets are dropped and the transmission is delayed either at the sender or at the nearest node. It is proven analytically that the packets will not be dropped if the buffer size is greater than or equal to twice the size of the queue length and the traffic will not increase during propagation delay of shut-off signal between the switch and either the source or the nearest node, depending on where the transmission is delayed. The performance of different networks is evaluated to show the applications of the proposed techniques.>

The performance of the make and load building algorithms is analyzed. The average time of compilation of an application is calculated by using the make algorithm. This time depends on the number of changed files, their compilation time, and the number of files affected by the change that have to be compiled. The load building algorithm chooses the files in an application that have to be compiled and places them on the compile list. The files that are not affected by changes are not compiled. This reduces the turnaround time for compilation and load building. The average time of compilation of an application is calculated by using the load building algorithm. This time depends on the number of files in an application, the number of changed files, and the interdependencies between files. It is proven analytically how the system performance can be improved by using the load building algorithm. A relative performance analysis of the make and load building algorithms shows that the load building algorithm allows for better performance if some files in the application do not have to be compiled, and the average time of analysis by the load building algorithm is smaller than the average time of compilation of files that are unnecessarily recompiled by using the make algorithm.>

The B-ISDN (broadband integrated services digital network) is a virtual circuit-switched network that can be used for services requiring high-speed packet switching. Work is already underway to define and standardize B-ISDN in the CCITT (International Telegraph and Telephone Consultative Committee). The B-ISDN will use a flexible multiplexing format called ATM (asynchronous transfer mode). In the US proposal the B-ISDN is based on the SONET (synchronous optical network) specifications as a physical layer. An introduction is presented to the subject of computer network architecture in general, B-ISDN protocols, and interface structures, and some of the interfaces that can be used in establishing B-ISDN architecture are discussed. The authors also discuss the relationship between interfaces at reference points, the ATM header format, and SONET architecture.>

Abstract This paper describes an implementation and performance evaluation of different deadlock prevention algorithms. A deadlock prevention algorithm ensures that deadlock will never happen. The algorithms for deadlock prevention are proposed and implemented in a locally distributed system. A number of experiments were executed in a distributed system for various lengths of file operation and different numbers of files. The performance of the system and of each algorithm is evaluated and discussed. Some general results are derived for a single‐host and a distributed system.

This paper presents a practical method for evaluating file systems in which synchronization mechanisms are modeled using measurable parameters. A queueing network model of a file system is introduced. The model allows various type of locks, multiple classes of transactions, and files and sectors shared by different types of transactions to be represented. The model parameters are estimated from the values of measurable quantities. The service times of lock servers are calculated as functions of the loads on all service centers. The various lock granularities can be represented by this model. Performance measures applicable to the evaluation of computer systems are introduced and evaluated. An example involving a file system and measurement data collected in a small business installation is given to compare performance measures provided by the simulation and analytic models.

This paper presents a study of a distributed system consisting of a number of hosts connected by a local area network. The system model is based on the LOCUS distributed file system. The LOCUS file system allows replicated files, and the synchronization policy is enforced by the use of the Centralized Synchronization Sites (CSS). All requests to open a file for access must be sent to the file's CSS which checks for access conflicts. Our simulation model allows process migration. The focus of this study is on load balancing as applied to optimal process and read site placement. An algorithm is proposed that increases system performance through load balancing. This algorithm uses data collected by the system on which to base its decisions. The characteristics of the algorithm and their effects on system performance are analyzed and discussed.

This paper presents a practical and noniterative method for evaluating queueing networks in which serialization delays are represented using measurable parameters. Two types of models are introduced to describe synchronization of accesses to shared resources using simulation and numerical methods, respectively. The model parameters are estimated from the values of measurable quantities. For the analytic models, the probabilities that a shared resource is locked, thereby causing other processes to wait for the resource to be accessible, are calculated, under certain assumptions, as functions of the probabilities of access and of the number of active transactions. The service times of lock servers are calculated as functions of the loads on all service centers. Performance measures applicable to the evaluation of computer systems are introduced and evaluated. An impact of various lock granularities on system performance is presented. An example involving a distributed file system and measurement data collected in a small business installation is given to compare performance measures provided by the simulation and analytic models.

This paper presents a new approach to modeling file systems using queueing networks. The delays due to locking the files are modeled using service centers whose service times and probabilities of access are estimated from the values of measurable quantities. The model of a lock is based on the analysis of execution of transactions in the system. The lock for every file is modeled as a sequence of service centers. The decomposition method can be used to solve the model, which allows multiple classes of transactions and shared files to be represented. An example involving measurement data collected in a small business installation is given to compare performance measures provided by the simulation and analytic models.

Abstract The programming language PL/I is considered as a most useful and portable discrete event simulation tool. This paper discusses design facilities required in simulation languages, making use of a model described in PL/I. The problem of queues, parallelism and synchronization in a simulator is solved. The structure of the simulator is considered.

Abstract The programming language Pascal is considered as one of the most interesting computer system simulation tools. This paper discusses design facilities required in simulation languages, making use of a model described in Pascal. An important area is seen to be that of queues, lists or sets, and the facilities that are powerful yet simple to use are stressed. The problem of parallelism and synchronization in a simulator is solved. The structure of the simulator is considered.