Decreasing Utilization of Systems with Multi-Rate Cause-Effect Chains While Reducing End-to-End Latencies

TL;DR

This paper introduces a method that optimizes communication interval configurations in multi-rate cause-effect chains under the LET model, reducing system resource waste and end-to-end latencies.

Contribution

It presents a search-based approach to configure communication intervals, controlling data propagation and task instance relevance to improve system efficiency.

Findings

Significant reduction in system utilization achieved.

End-to-end latencies decreased through optimized configurations.

Method effectively manages sporadic task instances.

Abstract

The Logical Execution Time (LET) model has deterministic properties which dramatically reduce the complexity of analyzing temporal requirements of multi-rate cause-effect chains. The configuration (length and position) of task's communication intervals directly define which task instances propagate data through the chain and affect end-to-end latencies. Since not all task instances propagate data through the chain, the execution of these instances wastes processing resources. By manipulating the configuration of communication intervals, it is possible to control which task instances are relevant for data propagation and end-to-end latencies. However, since tasks can belong to more than one cause-effect chain, the problem of configuring communication intervals becomes non-trivial given the large number of possible configurations. In this paper, we present a method to decrease the waste of processing resources while reducing end-to-end latencies. We use a search algorithm to analyze different communication interval configurations and find the combination that best decrease system utilization while reducing end-to-end latencies. By controlling data propagation by means of precedence constraints, our method modifies communication intervals and controls which task instances affect end-to-end latencies. Despite the sporadic release time of some task instances during the analysis, our method transforms those instances into periodic tasks. We evaluate our work using synthetic task sets and the automotive benchmark proposed by BOSCH for the WATERS industrial challenge.