A Machine Learning-Based Approach to Support the Bottom-Up Design of Simple Emergent Behaviors in Systems-of-Systems
Systems-of-Systems (SoS) are composed of independent systems called constituents that, together, achieve a set of goals by means of emergent behaviors. Those behaviors can be deliberately planned as a combination of the individual functionalities (herein named as features) provided by the constituents. Currently, SoS stakeholders heavily rely on the creativity of engineers to combine the features and design the behaviors. The limitation of human perception in complex scenarios can lead to engineering sub-optimized SoS arrangements, offering global behaviors that are limited to the engineer's abilities and prior experience, potentially causing waste of the resources, sub-optimal services and reducing quality. In that sense, the main contribution of this paper is introducing a machine learning-based mechanism for inferring/suggesting emergent behaviors that could be designed over a given set of constituents. An initial dataset was elaborated from a systematic mapping to feed the mechanism and a web-application was developed as a means to permit experts evaluate this mechanism through a specific assessment. Their reporting and the statistics over the data gathered from the application usage revealed this is a promising technique towards extrapolating the human capabilities and glimpsing global behaviors, hopefully revealing behaviors non-predicted by engineers (although these behaviors were present in the dataset) that could be offered by the SoS and supporting engineers to architect SoS with (i) more diversified behaviors and (ii) enhanced SoS overall quality.