Probabilistic Scheduling Guarantees under Error Bursts in Controller Area Network (CAN)

Dependable communication is becoming a critical factor due to the pervasive usage of networked embedded systems that increasingly interact with human lives in many real-time applications. However, these systems are often subject to faults that manifest as error bursts and affect the timing properties of the messages used in the communication. Controller Area Network (CAN) has gained wider acceptance as a standard in a large number of distributed industrial and control applications, mostly due to its cost effectiveness, efficient bandwidth utilization, ability to provide real-time guarantees, as well as its fault-tolerant capability. Research so far has focussed on rather simplistic error models which assume only singleton errors separated by a minimum interarrival time. However, error bursts of various lengths during message transmissions have an adverse effect on the message response times that needs to be accounted for. In this paper we propose a methodology which enables the provision of appropriate probabilistic real-time guarantees in distributed real-time systems under error bursts. The proposed approach introduces a comprehensive probabilistic error model together with appropriate schedulability analysis for the particular case of real-time message scheduling on CAN.