Generative AI + Competition-Driven Empowerment for Innovative Practical Teaching of SDN: A Case Study of SDN Curriculum Reform

DOI: https://doi.org/10.62517/jhet.202615212

Author(s)

Xinyu Geng*, Ruxia Wang, Xueri Li

Affiliation(s)

Computer Science Department - Network Engineering Major, Guangdong University of Science and Technology, Dongguan, Guangdong, China *Corresponding Author

Abstract

This paper addresses the pain points in traditional Software-Defined Networking (SDN) education—such as the disconnect between theory and practice, high costs associated with setting up experimental environments, and outdated content on new technologies-by proposing a deeply integrated teaching model that combines generative AI with competition-driven learning. The paper analyzes the advantages of AIGC technology in assisting lesson preparation, automatically generating lab scripts, real-time error detection, and building virtual simulation environments. By integrating the “competition-driven teaching” philosophy, it constructs a closed-loop teaching system encompassing “theory-experiment-competition.” This model utilizes large AI models to optimize teaching resources and experimental guidance, introduces virtual simulation platforms such as OpenLAB to lower the barrier to experimentation, and leverages competitions like the “Network Technology Challenge” to establish a tiered training mechanism comprising “preliminary-semi-final-final” rounds, effectively addressing the scarcity of SDN experimental resources and the lack of personalized guidance.

Keywords

Generative AI; Event-Driven; Software-Defined Networking (SDN); Curriculum Reform; Practical Teaching

References

[1] Cai J, Luo P, Zheng S, et al. Aigc-enabled Smart Instructional Design for Intercultural Communication Competence Development: A Triadic Human–AI Collaboration Model. World Journal of Educational Studies, 2026, 4(4). DOI:10.61784/WJES3155. [2] Luke B M, M. K W, Li, et al. ChatGPT for Language Teaching and Learning. RELC Journal, 2023, 54(2):537-550. DOI:10.1177/00336882231162868. [3] Sun Y C, Liao Y H, Ma X X. Trusting AI to detect AI? A systematic evaluation of the reliability and robustness of current AIGC detection tools for student academic work. Computers & Education, 2026, 249105616-105616. [4] Xiong Z, Huang Q. A mixed-methods study evaluating student acceptance of artificial intelligence-generated content for sustainable personalized learning in Chinese higher education. Scientific reports, 2026. DOI: 1.0. 1038/S41598-026-46043-6. [5] Lin L, Chen R. Research on the Reform and Innovation Strategies of College English Teaching from the Perspective of Core Competencies. Curriculum and Teaching Methodology, 2026, 9 (1). DOI:10.23977/CURTM.2026.090124. [6] Chen Y .Analysis of Teaching Reform in Vocational Mechanical Engineering Programs in the Context of Smart Manufacturing. Curriculum and Teaching Methodology, 2026, 9(1). DOI:10.23977/CURTM.2026.090123. [7] Tian L ,Wang X, Guo J, et al. Exploration of Teaching Reform of the Course "Photovoltaic Power Station Design and Operation and Control" in Applied Undergraduate Colleges: A Case Study of Shandong Institute of Petroleum and Chemical Technology. Curriculum and Teaching Methodology, 2026, 9(1). DOI:10.23977/CURTM.2026.090120. [8] Shen K, Sun T, Guo D, et al. AI Empowerment Integrated with Engineering Practice: Pathways and Practices of Teaching Reform in Emerging Engineering Education. Curriculum and Teaching Methodology, 2026, 9(1). DOI:10.23977/CURTM.2026.090119. [9] Lin X, Liang L .Teaching Reform and Practical Exploration of Robot Path Planning Programming Based on the Artificial Large Language Platform. Advances in Vocational and Technical Education, 2026, 8(1). DOI:10.23977/AVTE.2026.080110. [10]Fan Y .Construction and Research on the "Generative Inquiry" Teaching Model for Python Programming Course under the Empowerment of Artificial Intelligence Generated Content. Journal of Modern Educational Theory and Practice, 2025, 2(7). DOI:10.70767/JMETP.V2I7.75.