System-of-Systems Acquisition Analytics Using Machine Learning Techniques

Abstract

System-of-Systems capability emerges from the collaboration of multiple systems, which are acquired from independent organizations. The systems within an SoS serve two purposes: one is to meet their own independent objectives, and the second is to contribute some capability to the SoS from which all constituents can benefit. In recent decades, the fields of machine learning and data analytics have found widespread application in system design and acquisitions. It is unanimously understood that any organization acquiring a complex system employs some form of data analytics to assess a system’s independent objectives. Even though the systems contribute to and benefit from the larger SoS, the data analytics and decision-making about the independent system is rarely shared across the SoS stakeholders. The objective of this work is to identify how the sharing of datasets and the corresponding analytics among SoS stakeholders can lead to an improved SoS capability. We propose to utilize machine learning techniques to predict the SoS capability by sharing pertinent datasets and prescribe the information links between systems to enable this sharing. This paper is an interim update on the work in progress towards the above research effort and focuses on quantifying the value of sharing information across the SoS stakeholders.