A multicore approach to model-based analysis and design of Cyber-Physical Systems

Abstract

Embedded systems took a leap as combining computational elements with physical systems led to many novel applications, further saw the rise of a new domain - Cyber-Physical Systems (CPS). Growing importance for CPS in industry threw down many challenges in a designer's perspective ranging from computational methods, modeling platforms, programming structures, relevant hardware systems, etc. Ptolemy is the platform which is tailor made for such full scale design of networked and real time systems. In an effort to explore the suitability of Ptolemy II platform for CPS design, we chose an Unmanned Aerial vehicle (UAV) application as a case study. In this paper, we model UAV in Ptolemy II in a modular and hierarchical way such that the system meets the requirements of data flows and dependencies. Key parameters of a typical CPS such as schedulability and predictability were analyzed. In the end, to better the performance of UAV, computational tasks were mapped onto a networks-on-chip based multicore system. Our experimental results show the efficiency of our high level analysis and modeling and the extracted system requirements to enhance the system predictability.