Seinosuke Narita

Parallel processing of robot-arm control computation on a multimicroprocessor system

A parallel-processing scheme is described for robot-arm control computation on any number of parallel processors. The scheme employs two multiprocessor scheduling algorithms called, respectively, depth first/implicit heuristic search (DF/IHS) and critical path/most immediate successors first (CP/MISF); these were recently developed by the authors. The scheme is applied to the parallel processing of dynamic control computation for the Stanford manipulator. In particular, the proposed algorithms are applied to the computation of the Newton-Euler equations of motion for the Stanford manipulator and implemented on a multimicroprocessor system. The test result was so successful that the use of six processor pairs in parallel could attain the processing time of 5.37 ms. It is also shown that the proposed parallel-processing scheme is applicable to an arbitrary number of processors.

Real Time Control of System Voltage and Reactive Power

This paper presents a centralized optimizing computational algorithm for the on-line control of voltage and reactive power. The body of the paper is divided into two parts.

A Multi-Grain Parallelizing Compilation Scheme for OSCAR (Optimally Scheduled Advanced Multiprocessor)

This paper proposes a multi-grain parallelizing compilation scheme for Fortran programs. The scheme hierarchically exploits parallelism among coarse grain tasks, such as, loops, subroutines or basic blocks, among medium grain tasks like loop iterations and among near fine grain tasks like statements. Parallelism among the coarse grain tasks called the macrotasks is exploited by carefully analyzing control dependences and data dependences. The macrotasks are dynamically assigned to processor clusters to cope with run-time uncertainties, such as, conditional branches among the macrotasks and variation of execution time of each macrotask. The parallel processing of macrotasks is called the macro-dataflow computation. A macrotask composed of a Do-all loop, which is assigned onto a processor cluster, is processed in the medium grain in parallel by processors inside the processor cluster. A macrotask composed of a sequential loop or a basic block is processed on a processor cluster in the near fine grain by using static scheduling. A macrotask composed of subroutine or a large sequential loop is processed by hierarchically applying macro-dataflow computation inside a processor cluster. Performance of the proposed scheme is evaluated on a multiprocessor system named OSCAR. The evaluation shows that the multi-grain parallel processing effectively exploits parallelism from Fortran programs.

Job Scheduling Scheme for Pure Space Sharing Among Rigid Jobs

This paper evaluates the performance of job scheduling schemes for pure space sharing among rigid jobs. Conventional job scheduling schemes for the pure space sharing among rigid jobs have been achieved by First Come First Served (FCFS). However, FCFS has a drawback such that it can not utilize processors efficiently. This paper evaluates the performance of job scheduling schemes that are proposed to alleviate the drawback of FCFS by simulation, performance analysis and experiments on a real multiprocessor system. The results showed that Fit Processors First Served (FPFS), which searches the job queue and positively dispatches jobs that fit idle processors, was more effective and more practical than others.

Logical structure analysis of book document images using contents information

Numerous studies have so far been carried out extensively for the analysis of document image structure, with particular emphasis placed on media conversion and layout analysis. For the conversion of a collection of books in a library into the form of hypertext documents, a logical structure extraction technology is indispensable, in addition to document layout analysis. The table of contents of a book generally involves very concise and faithful information to represent the logical structure of the entire book. That is to say, we can efficiently analyze the logical structure of a book by making full use of its contents pages. This paper proposes a new approach for document logical structure analysis to convert document images and contents information into an electronic document. First, the contents pages of a book are analyzed to acquire the overall document logical structure. Thereafter, we are able to use this information to acquire the logical structure of all the pages of the book by analyzing consecutive pages of a portion of the book. Test results demonstrate very high discrimination rates: up to 97.6% for the headline structure, 99.4% for the text structure, 97.8% for the page-number structure and almost 100% for the head-foot structure.

Parallel processing of near fine grain tasks using static scheduling on OSCAR (optimally scheduled advanced multiprocessor)

The authors propose a compilation scheme for parallel processing near fine-grain tasks, each of which consists of several instructions or a statement, on a multiprocessor system called OSCAR. The scheme allows one to minimize synchronization and data transfer overheads and to optimally use registers of each processor by employing a static scheduling algorithm considering data transfer. This scheme can effectively be combined with macro-dataflow computation and with making the loop concurrent. A compiler using the proposed scheme has been implemented on OSCAR, which has been designed to take full advantage of the static scheduling. A performance evaluation of the scheme on OSCAR is also described.<<ETX>>

Model Coordination Method Applied to Power System Control and Estimation Problems

This paper presents an application of the Model Coordination Method to the multi-area power system operation and control. The heirarchical structure of the Power Pool composed of member areas is analyzed. The data required for the coordination of each area are defined for the two examples of power system operation, viz., the state estimation and the voltage and reactive power control problems. The memory requirements and computation time are also discussed.

Load Distribution Among Real-Time Control Computers Connected Via Communication Media

Abstract This paper presents an efficient method to distribute a real-time computing load among a plurality of control computers interconnected via communication media. Along with the increasing demand for enhanced control of complicated systems, the computing load on control computers has Increased in both quantity and complexity. This tendency is observed in every spectrum of control computer applications ranging from small systems such as robot control to large-scale applications such as steel-mill control. The load distribution or parallel processing scheme employing multiple processors has recently attracted much attention to meet ever-increasing computing load. However, the design of multicomputer systems has so far been made mainly on the basis of the empirical know-hows of the system designer because of the lack of an efficient load distribution method by which to partition the total computing load into tasks, to assign them to the member processors, and to determine the sequence of task processing on each processor. The purpose of this paper is to present a theoretical yet practical method of task control and synchronization by employing the multiprocessor scheduling theory. The real-time control of industrial robots, which has recently attracted widespread attention, Is adopted as a concrete example of application of the proposed load distribution method for illustrative purpose

A Computational Algorithm for Real-Time Control of System Voltage and Reactive Power Part II - Algorithm of Optimization

An efficient computational algorithm is presented for the real-time control of system voltage and reactive power on the basis of a simplified linear model. A modified version of the complex method of Box is used for the minimization of bus voltage deviation in the first phase of optimization and a numerical search technique for the reduction of transmission losses due to reactive power flows in the second phase. The numerical example for a sample practical system is also given.

The Roles of Information Technology in Systems Control

Abstract This report is intended to provide a perspective on the roles of recent information technology in systems control. In the first place, a brief historical sketch is presented on the use of computers from its infant stage to recent highly integrated total systems. It is pointed out that the areas of computer application have been spreading out from continuous processes to discrete systems where a wide variety of novel computer aided technologies are incorporated not only in the execution stage but also in the plan, design, evaluation and test stages of systems control. Various functions of information technology in systems control such as information acquisition, information transmission, information processing and information storage are then reviewed, together with their recent developments and foreseeable future prospects. Finally, image processing, machine diagnosis and knowledge engineering approaches are discussed as salient examples of the intensive use of information technology in systems control.