System-of-Systems Architecture Selection: A Survey of Issues, Methods, and Opportunities

Fang, Zhemei

doi:10.1109/jsyst.2021.3119294

Cited by 19 publications

(3 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is challenging to readjust the connection between surviving combat entities in real time based on the current state of the UCSoS. In addition, the UCSoS reconstruction problem is essentially a variant of the portfolio decision problem [14,15], which means that the UCSoS reconstruction problem is a combinatorial optimization problem and also an NP-hard problem. Traditional algorithms, such as approximation algorithms and metaheuristic algorithms, are usually used to solve the portfolio decision problem, but it is difficult to achieve a satisfactory balance between solution time and solution quality in large-scale cases.…”

Section: Introductionmentioning

confidence: 99%

Optimal Unmanned Combat System-of-Systems Reconstruction Strategy with Heterogeneous Cost via Deep Reinforcement Learning

Li,

Yuan,

Ren

et al. 2024

Mathematics

View full text Add to dashboard Cite

The unmanned combat system-of-systems (UCSoS) in modern warfare is comprised of various interconnected entities that work together to support mission accomplishment. The soaring number of entities makes the UCSoS fragile and susceptible to triggering cascading effects when exposed to uncertain disturbances such as attacks or failures. Reconfiguring the UCSoS to restore its effectiveness in a self-coordinated and adaptive manner based on the battlefield situation and operational requirements has attracted increasing attention. In this paper, we focus on the UCSoS reconstruction with heterogeneous costs, where the collaboration nodes may have different reconstruction costs. Specifically, we adopt the heterogeneous network to capture the interdependencies among combat entities and propose a more representative metric to evaluate the UCSoS reconstruction effectiveness. Next, we model the combat network reconstruction problem with heterogeneous costs as a nonlinear optimization problem and prove its NP-hardness. Then, we propose an approach called SoS-Restorer, which is based on deep reinforcement learning (DRL), to address the UCSoS reconstruction problem. The results show that SoS-Restorer can quickly generate reconstruction strategies and improve the operational capabilities of the UCSoS by about 20∼60% compared to the baseline algorithm. Furthermore, even when the size of the UCSoS exceeds that of the training data, SoS-Restorer exhibits robust generalization capability and can efficiently produce satisfactory results in real time.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimal Unmanned Combat System-of-Systems Reconstruction Strategy with Heterogeneous Cost via Deep Reinforcement Learning

Li,

Yuan,

Ren

et al. 2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…As a result, system of systems (SoS) [1,2] and SoS engineering (SoSE) [1,2] have emerged as new areas of research in various fields such as military [3], aerospace [4], and health care [5], among others. The concept of architectural design in civil engineering has inspired the integration of architecture into SoSE to manage complexity and aid in system development and integration [6]. Architecture is the conceptual model that describes the fundamental properties of a system in its environment, including its components, relationships, and principles for design and evolution [7,8].…”

Section: Introductionmentioning

confidence: 99%

Ontology-Based Architecture Process of System-of-Systems: From Capability Development to Operational Modeling

Feng

Zou

Zhou³

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

System-of-systems (SoS) architecture is crucial in managing complex and interconnected systems. However, the description and modeling of SoS architecture pose significant challenges and require a structured and organized approach. In this study, a metamodel for SoS architecture that considers both structural and behavioral perspectives is defined. The metamodel is then mapped to ontologies that are enhanced with a flow-based extension to characterize architecture views. On this basis, an SoS capability ontology (SoSCO) and an SoS operational ontology (SoSOO) are built with factors, relationships, and flows. A four-step architecture process for developing capabilities and a five-step architecture process for operational modeling are provided based on the ontologies. The proposed approach is applied in a search and rescue case study, demonstrating its ability to improve operability in the early design stage. The process is implemented using the Unified Architecture Framework (UAF) so that various stakeholders and engineers can better understand and develop an SoS.

show abstract

“…However, the previous study does not focus on behavior for invisible SoS. The previous study [5] reviews the current status of SoS architecture selection studies from seven perspectives, including conceptual framework, evaluation criteria, interdependency, uncertainty, autonomy, dynamic evolution, and computational methods. However, the previous study does not focus difference between the assumable range depending on virtual SoS and the assumable range depending on invisible SoS.…”

Section: Introductionmentioning

confidence: 99%

Deriving the difference between the assumable ranges depending on virtual System-of-Systems (SoS) and invisible SoS

Kobayashi¹

2022

Int J Jpn Assoc Mgt Sys

View full text Add to dashboard Cite

The previous study states needing to confirm whether systems designers and systems engineers can applicate in other fields the architecture description method that clarifies the objects to reduce misunderstanding of the scopes of virtual system-of-systems (SoS). In order to confirm applicate in other fields, we concretely applicate the previous architecture description method to the case both including virtual SoS and invisible SoS. Especially, we try to clarify the difference between the assumable range depending on virtual SoS and the assumable range depending on invisible SoS. We consider that the systems engineers and systems designers can expand the two assumable ranges using the previous architecture description method. In the evaluation method, we show the assumable range depending on virtual SoS and the assumable range depending on invisible SoS. Next, we show the difference depending on virtual SoS and invisible SoS. Finally, to verify the difference, the three writers that understood the previous architecture description method confirmed the results. As results, we suggest to depend on the position and contractual relationship with the visible one, in order to hear the relation of virtual SoS. However, we consider hearing the relation of invisible SoS more difficult than hearing the relation of virtual SoS. The reason why we consider it difficult is that the relation of virtual SoS is direct, and the relation of invisible SoS is indirect. From the above, we showed the difference between the assumable range depending on virtual SoS and the assumable range depending on invisible SoS. Finally, this study concludes with future research topics.

show abstract

System-of-Systems Architecture Selection: A Survey of Issues, Methods, and Opportunities

Cited by 19 publications

References 108 publications

Optimal Unmanned Combat System-of-Systems Reconstruction Strategy with Heterogeneous Cost via Deep Reinforcement Learning

Optimal Unmanned Combat System-of-Systems Reconstruction Strategy with Heterogeneous Cost via Deep Reinforcement Learning

Ontology-Based Architecture Process of System-of-Systems: From Capability Development to Operational Modeling

Deriving the difference between the assumable ranges depending on virtual System-of-Systems (SoS) and invisible SoS

Contact Info

Product

Resources

About