Modern war relies heavily on various combat units, such as command and control units, surveillance units, and reconnaissance units. These units are usually combined organically as a combat SoS (System of Systems) to conduct given missions. To ensure that the combat SoS executes correctly, the communication systems (e.g., communication vehicles, communication UAVs) must be planned carefully to connect all constituent systems or units. However, the c ommunication a rchitecture d esign problem for combat SoS (SoS-CAD) is very challenging as the combat SoS usually resides in a dynamic and confrontational environment. In this paper, we formally formulate the SoS-CAD problem with integer programming and prove its NP-hardness. The SoS-CAD problem has high requirements for the solving speed as well as the solution quality, but traditional meta-heuristic algorithms cannot satisfy them. Thus, we propose a deep reinforcement learning-based method called CADer to solve it. Specifically, we introduce the attention mechanism and dynamic embedding mechanism into CADer with considering the characteristics of the SoS-CAD problem itself. The massive experiment results show that CADer performs well in the generalization ability and can achieve the best tradeoff between the solving speed and the solution quality against the meta-heuristic algorithm.

As one of the products in the US Department of Defense Architecture Framework version 2.0 (DoDAF 2.0), the Operational Activity to Services Traceability Matrix product (SvcV-5) links the operational viewpoint (OV) and service viewpoint (SvcV). SvcV-5 is an essential product for optimizing the design of other service view products; thus, it is necessary to study how to optimize the design of SvcV-5. This paper studies the semi-automatic design method of SvcV-5 based on the service identification method. The main idea of this paper is to extract relevant information from previous architecture design products, such as OV-6b, CV-4 and CV-6, and then to study the method of taking service identification and designing the SvcV-5 product. First, a message-based service initial identification method is used to generate the initial service set. Second, considering the measure of the cohesion and the coupling degree of the service, a service improving algorithm is used to update the initial service set. In this process, a dependency matrix between operational activities is established; this matrix includes data dependencies and capability requirement dependencies. Then, according to the mapping result of the service identification method, service-related information can be determined manually by designers. Finally, SvcV-5 can be generated through an automatic algorithm based on the service identification result and the OV-6b product. This article verifies the proposed method using the motivation example of the earthquake rescue information system (ERIS) architecture product design. Through conducting experimental analysis and comparing our method with other service identification methods, we illustrate the effectiveness of the proposed SvcV-5 optimization design method.