Computational Intelligence based Complex Adaptive System-of-system Architecture Evolution Strategy

Abstract

There is a constant challenge to incorporate new systems and upgrade existing systems under threats, constrained budget and uncertainty into systems of systems (SoS). It is necessary for program managers to be able to assess the impacts of future technology and stakeholder changes. This research helps analyze sequential decisions in an evolving SoS architecture through three key features: SoS architecture generation, assessment and implementation through negotiation. Architectures are generated using evolutionary algorithms and assessed using type II fuzzy nets. The approach accommodates diverse stakeholder views, converting them to key performance parameters (KPPs) for architecture assessment. It is not possible to implement an acknowledged SoS architecture without persuading the systems to participate. A negotiation model is proposed to help the SoS manger adapt his strategy based on system owners' behavior. Viewpoints of multiple stakeholders are aggregated to assess the overall mission effectiveness of an architecture against the overarching objectives. A search and rescue (SAR) example illustrates application of the method. Future research might include group decision making for evaluating architectures.

Department(s)

Engineering Management and Systems Engineering

Comments

U.S. Department of Defense, Grant H98230-08-D-0171

Keywords and Phrases

Acquisition; Architecture; Evolutionary algorithms; Machine learning; Meta-Architectures; Systems of systems

International Standard Book Number (ISBN)

978-331926107-2

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 Springer, All rights reserved.

Publication Date

01 Jan 2016

Share

 
COinS