Mixed-criticality systems (MCS) aim at boosting the integration density in safety-critical systems, resulting into efficient systems, while simultaneously providing increased performance. The DREAMS project provides a cross-domain architectural style for MCS based on networked, virtualized multi-cores controlled by hierarchical resource managers. However, the availability of a platform is only one side of the coin: deploying mixed-critical applications to shared resources typically requires design-time configurations (e.g., to ensure real-time constraints or separation constraints mandated by safety regulations). These configurations are the outcome of complex optimization problems which are intractable in a manual process that also hardly can guarantee the consistency of all deployable artefacts nor their traceability to the requirements. However, existing toolchains lack support for MCS integration, and particularly DREAMS' advanced platform capabilities. We present an integrated model-driven toolchain and the underlying metamodels covering all relevant aspects of MCS including applications, timing, platforms, deployments, configurations and annotations for extra-functional properties such as safety. The approach focuses on the left branch of the V-cycle, and ranges from product-line and design space exploration to resource allocation and configuration generation. We report on the integration of exploration tools and a reconfiguration graph synthesizer, and evaluate the resulting toolchains in two use cases consisting of a product-line of wind power control applications and an avionic subsystem respectively.

Mixed-Criticality Systems (MCS) reconcile safety-critical requirements with multi-core architectures, by offering spatial and temporal isolation while preserving other extrafunctional properties such as optimised energy consumption or minimised latencies. MCS designers struggle to manually balance the offered functionalities with pertinent implementation choices in order to ensure that the system eventually meets all constraints. Existing attempts to further automate this process focus on specific concerns, and fail to account for variation in system functionalities. Our contribution is to integrate product-lines that capture functional variations with evolutionary optimisation to explore possible implementations and their impact on extra functional properties. Our solution is a model-driven process (and a tool prototype) to automatically select functionally different products that balance well the various concerns of interest. We illustrate how this process applies to the construction of wind turbines. Moving toward product-lines eventually contributes to reduce high development costs and the long time to market associated with MCS.

The solution of many engineering and scientific problems requires the exploration of a huge n-dimensional design space. Typical approaches rely on an abstract problem model consisting of a system model (description of the problem's variable couplings) and an optimization specification defining the objectives as well as the constraints bounding the design space. Advances in solver technologies enabled to efficiently search the solution space, however the diversity of the approaches led to problem descriptions that are difficult to reuse, as well as to solutions that are hard to compare. Our Exploration Meta-Model (EMM) addresses this issue by providing a unified language for optimization specifications that is a well-defined basis for model-based implementations of solver-independent design-space exploration (DSE) tool-chains. The EMM is a light-weight framework that allows to a) describe optimization specifications independent of particular optimization methods and solvers, b) relate solutions and optimization specifications, and c) define domain profiles that provide high-level optimization specifications that ease the adoption of automated DSE by domain experts. The applicability of our framework to different optimization methods is demonstrated by applying it to the generic vector optimization problem and to single-objective linear programs. The EMM's support to relate optimization results to input specifications is exercised for the Opt4J framework. Finally, a profile for real-time embedded systems demonstrates how the EMM can be tailored to specific domains.