Formal description of an approach for power consumption estimation of embedded systems

Abstract

This paper presents a formal description of an approach for model-based engineering of energy-efficient automation systems. Energy consumption is an important decision criterion, which has to be included in the search for good architectural and design alternatives already on the early system design stages. In the method, we describe an embedded system with an operational model for the processor hardware and an application model for the software. UML extended with MARTE profile elements is used for this part. Both models are transformed into a stochastic Petri net using transformation rules. The procedure steps are described with formal mathematical language and graphical illustrations.

High-level power estimation techniques in embedded systems hardware: an overview

“…On another hand, a formal description of a power consumption estimation approach of embedded systems is presented in [39]. An embedded system consisting of a hardware and a software is denoted as a System Model (SM).…”

MARTE/pCCSL: Modeling and Refining Stochastic Behaviors of CPSs with Probabilistic Logical Clocks

“…Other works, either based on MARTE [35] or just on UML [9] also use stochastic models to analyze the energy consumption. In this case, the authors rely on Stochastic Petri Nets while in our work we use Stochastic Hybrid Automata.…”