| Popis: |
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-how's 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 |
