In the field of System-of-Systems (SoS) engineering, the study of interactions between complex systems froma holistic point of view is important for finding emerging behaviours. To observe as many behaviours aspossible, especially when field testing is not a viable option, simulations play an important role in design spaceexploration and formulation for the Firefighting SoS framework. The presented work describes an AgentBased Model (ABM) approach for simulation of wildfire spread and its detection using collaborating vehicles:Unmanned Aerial Vehicles (UAVs), or partly autonomous air- and land-based vehicles. Implemented in theopen-source software NetLogo, the usage of its Geographic Information System (GIS) extension allows tosimulate scenarios at specific locations. This ABM will be used in the future for Agent-Based Simulations(ABS) for the study of an SoS framework oriented to firefighting, including design and optimization of the SoS,constituent systems and their subsystems.

The conceptual design of mission-tailored aircraft is increasingly shifting towards system of systems (SoS) perspectives that account for system interactions using a holistic view. Agent-based modelling and simulation (ABMS) is a common approach for analysing an SoS, but the behaviour of its agents tends to be defined by rigid behaviour trees. The present work aims to evaluate the suitability of a prompt-engineered large language model (LLM) acting as the Incident Commander (IC), replacing the fixed behaviour trees that govern the agents' decisions. The research contributes by developing a prompting framework for operational guidelines, constraints, and priorities to obtain an LLM commander within a wildfire suppression, SoS capable of replicating human decisions. By enabling agents in a simulation model with decision-making capabilities closer to those expected from humans, the commander's decisions and potential emergent patterns can be translated into more defined requirements for aircraft conceptual design (ACD) (e.g., endurance, payload, sensors, communications, or turnaround requirements). Results showed that an LLM commander facilitated adaptive and context-aware decisions that can be analysed via decision logs. The results allow designers to derive aircraft requirements for their specific roles from operational outcomes rather than a priori assumptions, linking SoS mission needs and ACD parameters.

The increasing interest in System-of-Systems (SoS) for engineering applications are introducing new challenges that must be overcome at an early design stage. One of these is the integration of different tools that can be used to make predictions about a system under development and how these together can be used to predict SoS performances by comparison of parameter spaces.The purpose of this paper is therefore to illustrate how different SoS architectures can be modeled, simulated, and evaluated throughout different scenarios by different teams of researchers following a common workflow.An ontology is used as an overarching knowledge base where information about entities, such as scenario details, can be extracted and used for the setup of Agentbased Simulations(ABS) through a tool integration software acting as master that controls the correct execution of the defined workflow.The tool integration software also enables additional modelling capabilities, such as a Design of Experiments (DOE) definition for design space explorations, an Optimizer with different algorithms, user-defined Python scripts, etc.