Development and Evaluation of a Constructively Aligned Network Traffic Simulation (NTS) Using Generative AI

The aim of this research is to discuss the effectiveness of a Network Traffic Simulation (NTS) application, a generative AI tool that was designed to support hands-on learning in network defense at the diploma level in King Abdulaziz University (KAU). The simulation allows students to configure a testbed of a smart classroom environment by interacting with and adjusting several parameters and simulating cyberattacks. Aligned with constructive alignment principles, the NTS links learning outcomes with task-based assessments. It helps students develop practical skills in traffic scenario planning, network analysis, and evaluating defense mechanisms. To evaluate the NTS effectiveness, the researcher implemented a mixed methods approach utilizing pre-post tests, to measure learners’ performance across course learning outcomes, a task-based assessment that included several tasks related to the use of the NTS, and a questionnaire exploring learners’ perceptions of the tool. Results demonstrated significant improvements post-intervention, with positive feedback on engagement and ease of use. The paired-T test on the pre/post test results in a p-value of 0.036, which indicated that the change is statistically significant. The measured effect size of (~5) reinforces the impact of the NTS use on students’ performance. The questionnaire indicated students’ agreement and satisfaction on the three main dimensions being investigated: Learning Outcomes relatedness (mean = 4.5), Ease of Use (mean = 4.27) and Engagement (mean = 4.5). The study concludes that simulation-based learning within a constructively aligned framework significantly enhances learners’ cybersecurity education.