Multi-Objective Topology Optimization for Networked Embedded Systems

Abstract

In this paper, a new methodology is presented for topology optimization of networked embedded systems as they occur in automotive and avionic systems and partially in wireless sensor networks. By introducing a model which is (1.) suitable for heterogeneous networks with different communication bandwidths, (2.) modeling of routing restrictions and (3.) flexible binding of tasks onto processors, current design issues of networked embedded systems can be investigated. On the basis of this model, the presented methodology firstly allocates the required resources which can be communication links as well as computational nodes and secondly binds the functionality onto the nodes and the data dependencies onto the links such that no routing restrictions will be violated or capacities on communication links will be exceeded. By applying evolutionary algorithms, we are able to consider multiple objectives simultaneously during the optimization process and allow for a subsequent unbiased decision making. An experimental evaluation as well as a demonstration of a case study from the field of automotive electronics shows the applicability of the presented approach