Performance analysis of in-vehicle distributed control systems applying a real-time jitter monitor

Abstract

This paper presents an approach to monitor the performance degradation in CAN networks and the fault effect on time constraints of periodic control tasks. The work proposes the use of a test-based method supported by fault and error injection that helps the engineer to define how these faults degrade the system performance. In addition, a runtime jitter monitoring technique is proposed and applied to a CAN-based vehicular network. The runtime jitter analyses the performance oscillation according to a time window and with a tolerance range defined during previous performance tests. A case study was conducted monitoring a critical control system during error injection and the analysis technique was applied in order to verify the performance oscillation detection. Results show that with a typical CAN rate of 1 Mbps, the runtime jitter detect anomalies in performance during a short time period up to 30% of busload. The experiments show the degradation of 4,2 times on average jitter between 10% and 30% of busload with fault injection. The detection is also possible with higher busload 50% and 80%, but with an increase in the detection time. The present study emphasizes the importance of performance monitoring with the recent advances in automotive electronics.