Dealing with Uncertainty in Software Architecture on the Internet-of-Things with Digital Twins

When architecting Software-intensive Systems-of-Systems (SoS) on the Internet-of-Things (IoT), architects face two sorts of uncertainties. First, they have only limited knowledge about the operational environment where the SoS will actually be deployed. Second, the constituent systems which will compose the SoS might not be known a priori (at design-time) or their availability (at run-time) is affected by dynamic factors, due to the openness of the IoT. The consequent research question is thereby how to deal with uncertainty in the design of an SoS architecture on the IoT. To tackle this challenging issue, this paper addresses the notion of uncertainty due to partial information in SoS and proposes an enhanced SoS Architecture Description language (SosADL) for expressing SoS architectures on the IoT under uncertainty. The core SosADL is extended with concurrent constraints and the concept of digital twins coupling the physical and virtual worlds. This novel approach is supported by an integrated toolset, the SosADL Studio. Validation results demonstrate its effectiveness in an SoS architecture for platooning of self-driving vehicles.