Genetic Algorithm Optimization of SoS Meta-Architecture Attributes for Fuzzy Rule Based Assessments

The analysis of an acknowledged systems of systems (SoS) meta-architecture requires a preliminary method for potential trade space exploration to ensure compliance to evolving capability requirements. It is important to assess the SoS meta-architecture concept to ensure that it satisfies all stakeholder needs and requirements in the early stages of development. There are numerous linguistic terms called key performance attributes (KPAs) that could be used to assess the different aspects of the architectures capabilities, however, too many KPAs could complicate the assessment. The initial population of suitable KPAs is reduced through non-derivative based optimization employed by a genetic algorithm (GA) that generates the ideal KPA candidates though optimal rank selection. A Mamdani-type rule based fuzzy inference system (MRBFIS) is then used to make a fuzzy assessment of the SoS meta-architecture concept using GA optimized and assessed KPAs as MRBFIS inputs. The MRBFIS is a beneficial addition to an architecture assessment because it enables a nonlinear output that allows a more dynamic and adjustable assessment. The integrated assessment method detailed in this paper utilizes the GA optimized KPAs and the MRBFIS to provide a valuable fuzzy assessment of SoS meta-architecture concepts to determine if the architecture is feasible and acceptable.