Experimental Assessment of the Period Calibration Method: A Case Study

Authors:
Namyun Kim;Minsoo Ryu;Seongsoo Hong;Heonshik Shin
Affiliations:
Dept. of Computer Engineering, Seoul National University, Seoul 151-742, Korea;School of Electrical Engineering and ERC-ACI, Seoul National University, Seoul 151-742, Korea;School of Electrical Engineering and ERC-ACI, Seoul National University, Seoul 151-742, Korea;Dept. of Computer Engineering, Seoul National University, Seoul 151-742, Korea
Venue:
Real-Time Systems
Year:
1999

Citing 9
Cited 2

Scheduling Processes with Release Times, Deadlines, Precedence and Exclusion Relations

IEEE Transactions on Software Engineering
Software architecture for hard real-time applications: cyclic executives vs. fixed priority executives

Real-Time Systems
An extendible approach for analyzing fixed priority hard real-time tasks

Real-Time Systems
Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment

Journal of the ACM (JACM)
Priority Inheritance Protocols: An Approach to Real-Time Synchronization

IEEE Transactions on Computers
Guaranteeing Real-Time Requirements With Resource-Based Calibration of Periodic Processes

IEEE Transactions on Software Engineering
Streamlining real-time controller design: From performance specifications to end-to-end timing constraints

RTAS '97 Proceedings of the 3rd IEEE Real-Time Technology and Applications Symposium (RTAS '97)
On task schedulability in real-time control systems

RTSS '96 Proceedings of the 17th IEEE Real-Time Systems Symposium
Toward Automatic Synthesis of Schedulable Real-Time Controllers

Integrated Computer-Aided Engineering

Performance re-engineering of embedded real-time systems

Proceedings of the ACM SIGPLAN 1999 workshop on Languages, compilers, and tools for embedded systems
Deriving hard real-time embedded systems implementations directly from SDL specifications

Proceedings of the ninth international symposium on Hardware/software codesign

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present anexperimental evaluation of the period calibration method (PCM)which was developed in Gerber et al. (1994, 1995) as a systematicdesign methodology for real-time systems. The objective of thisexperimental study is to assess design alternatives integratedinto the method and their performance implication on resultantsystems built via the PCM. Such design alternatives include schedulingjitter, sensor-to-output latency, intertask communication schemes,and system utilization. For this study, we have chosen a computerizednumerical control (CNC) machine as our target real-time system,and built a realistic controller and a plant simulator. We showthe detailed development process of the CNC controller and reportits performance. The performance results were extracted froma controlled series of more than hundred test controllers obtainedby varying four test variables. This study unveils several weaknessesof the PCM: (1) the communication scheme built into PCM incursa large latency though average sensor-to-output latency is oneof the most dominating factors in determining control quality;(2) scheduling jitter is taken seriously in PCM though its effectappears only when average sensor-to-output latency is sufficientlysmall; (3) loop processing periods are not properly optimizedfor control quality though they are another dominating factorof performance; and (4) transient overloads are not consideredat all in PCM, even though they can seriously damage the performanceof a system. Based on these results, we propose a new communicationscheme and a transient overload handling technique for the improvedperiod calibration method.