Game-Theoretic Validation and Analysis of Air Combat Simulation Models

The paper presents a new game theoretic approach towards the validation of discrete event air combat simulation models. In the approach, statistical techniques are applied for estimating game models based on simulation data. The estimation procedure is presented in cases involving games with both discrete and continuous decision variables. The validity of the simulation model is assessed by comparing the properties of the estimated games to actual practices in air combat. The approach enhances existing methods for the validation of discrete event simulation models by incorporating the inherent game setting of air combat into the analysis. The estimated games also provide a novel game theoretic perspective to simulation metamodeling which is used to facilitate simulation analysis. The utilization of the game theoretic approach is illustrated by analyzing simulation data produced with an existing air combat simulation model.

In this paper, air combat simulation data is reconstructed into a dynamic Bayesian network. It gives a compact probabilistic model that describes the progress of air combat and allows efficient computing for study of different courses of the combat. This capability is used in what-if type analysis that investigates the effect of different air combat situations on the air combat evolution and outcome. The utilization of the dynamic Bayesian network is illustrated by analyzing simulation results produced with a discrete event air combat simulation model called X-Brawler.

Statistical method, and in particular, simulation is the most widely used operations research modelling approach now employed by industry and government. Validation of a simulation model is the procedure designed to determine whether the model is an accurate representation of the portion of reality under consideration. It is a process distinct from model building or debugging (although interrelated). In this work, strategies and practical numerical techniques for validating large-scale production simulation models (or any other large system) are detailed. An evolution of the central concepts of large-scale model validation is represented first. The distinction between model user's risk and model builder's risk is highlighted as an important development which alters the problem into a consideration of the basis a decision-maker should use in determining whether to rely on the outputs of such models. Two quantitative techniques which are applications of the Turing test and of mathematical programming are de...

A new method for determining the causes of discrepancies between dynamic simulation models and measured data is described. Whilst principally aimed at the validation of building thermal simulation codes, the method may rind application in the validation of simulation models from other disciplines. The new method relies on generating a model of the discrepancies in terms of the variables driving the physical reality which produced the experimental data and the corresponding simulation. Inspection of the resulting error model allows the principal contributors to simulation error to be identified, its dynamic nature to be characterised, and the likely cause of the error to be identified. The method is tested by generating a 'quasi-truth' dataset using the building thermal simulation code SERI-RES. A series of simulations is then prepared with perturbations to selected input parameters. The new tool is found to be capable of recovering details of the perturbations. Finally, the power of the new technique is demonstrated in a series of comparisons between the predictions of the model SERI-RES and data collected in outdoor test rooms. These comparisons reveal that the principal source of error in the predictions is the treatment of the interactions between the heater and the air and fabric of the room. The new technique proves sufficiently sensitive to detect the changing structure of the prediction errors as the position of the heater within the room is changed.

This paper gives the history of verification and validation of discrete-event simulation models as seen through the eyes of its authors and their experiences. The history is divided into three time periods: the early era covering years up to 1970, the awareness era covering the years of the 1970s and 1980s, and the modern era covering the years of 1990 to the present.

In a typical game scenario, the attention in unmanned aerial vehicle (UAV) air combat should be focused on both sides' maneuvering decision strategies. However, most existing studies focus only on improving their own maneuvering decisions, ignoring the importance of the opponent's strategy in the two-player game. This paper proposes a reinforcement learning (RL)-based air combat decision method considering the opponent's maneuvering strategy. Through the proposed limited imitation offline RL (LIORL) method, the opponent's air combat decision method is refined using existing air combat data. Based on the enemy's superior strategy, an air combat simulation environment is created, and the RL method is applied to train the agent for UAV air combat maneuvering decision strategies. No current research utilizes static datasets for the acquisition of adversary strategies. This study, in contrast, offers a more reliable approach in comparison to methodologies predicated on assuming adversary strategies. Ablation experiments have been meticulously executed to showcase the capability of the LIORL algorithm in identifying the optimal enemy strategy while exerting a lesser impact on the dataset than incumbent algorithms. The employment of the LIORL algorithm enables the agent to refine the adversary's strategy, resulting in an augmented win rate against our UAV. Through air combat simulations, we empirically validate the agent's decision-making process based on the adversary's strategy, thereby affirming the efficacy of the proposed methodology.

Reinforcement learning (RL) has recently proven itself as a powerful instrument for solving complex problems and even surpassed human performance in several challenging applications. This signifies that RL algorithms can be used in the autonomous air combat problem, which has been studied for many years. The complexity of air combat arises from aggressive close-range maneuvers and agile enemy behaviors. In addition to these complexities, there may be uncertainties in real-life scenarios due to sensor errors, which prevent estimation of the actual position of the enemy. In this case, autonomous aircraft should be successful even in the noisy environments. In this study, we developed an air combat simulation, which provides noisy observations to the agents, therefore, make the air combat problem even more challenging. Thus, we present a state stacking method for noisy RL environments as a noise reduction technique. In our extensive set of experiments, the proposed method significantly outperforms the baseline algorithms in terms of the winning ratio, where the performance improvement is even more pronounced in the high noise levels. In addition, we incorporate a self-play scheme to our training process by periodically updating the enemy with a frozen copy of the training agent. By this way, the training agent performs air combat simulations to an enemy with smarter strategies, which improves the performance and robustness of the agents. In our simulations, we demonstrate that the self-play scheme provides important performance gains compared to the classical RL training.

Test-driven simulation modelling: A case study using agent-based maritime search-operation simulation

The air combat process is regarded as the discrete event dynamic system which is composed of a series of discrete-states, and its discrete state sub-model is established. In order to choose the tactical maneuver, the evaluation function is constructed by the air combat situation index and the air combat capability index. Combining with the 3 degree-of-freedom (3DOF) aircraft model, the maneuver command generator is designed, controlling the moving state of aircraft. Finally, the simulation of the combat-turning is carried out using Matlab.

The evaluation and validation of simulation models are important stages of model development. The aim of this work was to validate the Buttercup model (BCM) with experimental data from on-farm trials. Two on-farm experiments (Experiment 1 E1 and Experiment 2 E2) were carried out to evaluate the effect of supplementing dairy cattle with different sources of protein in Small Scale Dairy Farming Systems. Three concentrates (C1= maize grain 610, soybean meal 310, urea 30, and cane molasses 50g kg−1 DM; C2= maize grain 630, soybean meal 320 and cane molasses 50g kg−1 DM; and C3= maize grain 900, urea 50 and cane molasses 50g kg−1 DM) were developed using the BCM. The effect of the concentrates on milk yield, body condition score and live weight was evaluated using a double Latin Square experimental design. In E1 there were no significant differences (P> 0.05) for the variables evaluated. In E2, significant differences (P<0.05) were observed in milk fat content, for C2 (33.8g kg−1) was higher than C1 and C3 (26.2 and 26.0g kg−1). The results suggest that it was possible to fulfil the metabolisable protein requirements of the cows in these systems with low cost sources of non-protein nitrogen like the urea used in C3; and that the synthesis of microbial protein (from non-protein nitrogen and fermentable metabolisable energy of the concentrates) was enough to fulfil the cows’ requirements of MP for the milk yield levels observed in both experiments. The results also indicate that when specific input data set from the experiments was used the model predictions are acceptable, when comparing predicted vs. observed data as a very significant correlation was observed (P<0.01).

For many biological systems, a variety of simulation models exist. A new simulation model is rarely developed from scratch, but rather revises and extends an existing one. A key challenge, however, is to decide which model might be an appropriate starting point for a particular problem and why. To answer this question, we need to identify entities and activities that contributed to the development of a simulation model. Therefore, we exploit the provenance data model, PROV-DM, of the World Wide Web Consortium and, building on previous work, continue developing a PROV ontology for simulation studies. Based on a case study of 19 Wnt/β-catenin signaling models, we identify crucial entities and activities as well as useful metadata to both capture the provenance information from individual simulation studies and relate these forming a family of models. The approach is implemented in WebProv, a web application for inserting and querying provenance information. Our specialization of PROV-DM contains the entities Research Question, Assumption, Requirement, Qualitative Model, Simulation Model, Simulation Experiment, Simulation Data, and Wet-lab Data as well as activities referring to building, calibrating, validating, and analyzing a simulation model. We show that most Wnt simulation models are connected to other Wnt models by using (parts of) these models. However, the overlap, especially regarding the Wet-lab Data used for calibration or validation of the models is small. Making these aspects of developing a model explicit and queryable is an important step for assessing and reusing simulation models more effectively. Exposing this information helps to integrate a new simulation model within a family of existing ones and may lead to the development of more robust and valid simulation models. We hope that our approach becomes part of a standardization effort and that modelers adopt the benefits of provenance when considering or creating simulation models.

In this tutorial we present techniques for building valid and credible simulation models. Ideas to be discussed include the importance of a definitive problem formulation, discussions with subject-matter experts, interacting with the decision-maker on a regular basis, development of a written assumptions document, structured walk-through of the assumptions document, use of sensitivity analysis to determine important model factors, and comparison of model and system output data for an existing system (if any). Each idea will be illustrated by one or more real-world examples. We will also discuss the difficulty in using formal statistical techniques (e.g., confidence intervals) to validate simulation models.

An approximate dynamic programming approach was developed to generate intelligence maneuvering decisions for CGF (Computer Generated Forces) during one-on-one air combat simulation. Simplified kinematic equations of aircraft were built up in flight-path coordinate system, the 3 DOF (degree of freedom) control command was improved, and the common basic flight maneuvering set was described quantitatively. Then, a new method of air combat maneuvering decision was designed according to actual battlefield situation, using trajectory sampling, feature extraction, policy learning. With this method, CGF can learn an approximately optimal policy of air-combat maneuvering during real-time simulation. Result of simulation confirms that proposed method can improve the intelligent decision ability of CGF during simulated air combat training.

This paper presents an evaluation on passenger vehicle's ride and handling performance when converted into an electric vehicle (EV). The evaluations were done using a validated 14 degrees of freedom ride and handling model. The mathematical modelling of vehicle's ride and handling model as well as its validations are described. Two types of experiments were performed to validate the developed simulation model; the ride test and the handling test. The validated simulation model was used to evaluate the vehicle's ride and handling performance of the vehicle when converted into an electric vehicle. The evaluation involves two weight distribution ratios which are 60:40, for normal vehicle and 40:60 for EV conversion. The validated simulation model used active suspension system in order to improve the EV conversion's ride and handling performance. It is found that modification into EV affects vehicle's handling performance quite significant but not ride performance. The EV conversion's weight, which is distributed towards the rear of the vehicle, causes the vehicle to travel off from its original travelling path. The application of active suspension system is proposed to improve EV conversion's handling performance as well as its ride comfort performance.

Microscopic traffic simulation models have been playing an important role in the evaluation of transportation engineering and planning practices for the past few decades, particularly in cases in which field implementation is difficult or expensive to conduct. To achieve high fidelity and credibility for a traffic simulation model, model calibration and validation are of utmost importance. Most calibration efforts reported in the literature have focused on the informal practice, and they have seldom proposed a systematic procedure or guideline for the calibration and validation of simulation models. This paper proposes a procedure for microscopic simulation model calibration. The validity of the proposed procedure was demonstrated by use of a case study of an actuated signalized intersection by using a widely used microscopic traffic simulation model, Verkehr in Staedten Simulation (VISSIM). The simulation results were compared with multiple days of field data to determine the performance of the calibrate...