6GSyn: AI-Driven Synthetic Data Generation for Next-Generation Wireless Performance Evolution
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V6I1P120Keywords:
6G, Synthetic Data Generation, AI-Driven Modeling, Wireless Networks, Network Simulation, Deep Learning, Federated Learning, 6GSyn Framework, Edge Computing, Network Optimization, Digital Twins, Reinforcement LearningAbstract
Sixth-generation (6G) wireless communication systems will require data that is more detailed, larger in scale, and more diverse than ever before in order to enable intelligent optimization, adaptive modulation, and dynamic spectrum management. However, it is expensive, time-consuming, and, in many cases, subject to privacy and environmental variations to collect real-world datasets that accurately represent the complexity of next-generation wireless environments. In order to get around these restrictions, 6GSyn unveiled an AI-driven synthetic data generation framework that was created to accurately model and simulate wireless conditions, network topologies, and user behaviors. By using sophisticated generative models like diffusion networks and graph-based neural architectures, 6GSyn is able to produce high-quality synthetic datasets that emulate multipath propagation, signal fading, interference patterns, and mobility dynamics these are the fundamental aspects that determine the 6G performance landscapes. This AI-powered method serves as a link between theoretical modeling and real-world testing; thus, it allows researchers and developers to use the algorithms for 6G network training, validation, and optimization under various scenarios that can be controlled.The experiments show that the models that have been trained on 6GSyn-generated data perform equally well or even better in different key indicators like throughput prediction, handover efficiency, and latency reduction than the models trained only on real-world data. In short, 6GSyn is the main driver in speeding up the 6G innovation process whereby developers are enabled to prototype, benchmark, and iterate at a much faster rate while the limitations of field data acquisition are minimized. Upcoming studies will broaden its abilities to cross-domain synthetic learning, which will also involve quantum-inspired computation and federated data generation to further improve the global wireless performance evolution in terms of trust, capacity, and fairness.
Downloads
References
[1] Tera, Sivarama Prasad, et al. "Towards 6g: An overview of the next generation of intelligent network connectivity." IEEE Access (2024).
[2] Sthankiya, Kishan, et al. "A Survey on AI-driven Energy Optimisation in Terrestrial Next Generation Radio Access Networks." IEEE Access (2024).
[3] PireciSejdiu, Nora, Nikola Rendevski, and Blagoj Ristevski. "AI Revolutionizing 5G and Next-Generation Networks." 2024 IEEE 17th International Scientific Conference on Informatics (Informatics). IEEE, 2024.
[4] Verma, Tulika, and Kuldeep Verma. "AI-empowered security and privacy schemes in next-generation wireless networks." Artificial Intelligence for Wireless Communication Systems. CRC Press, 2024. 126-142.
[5] Liang, Chengsi, et al. "Generative AI-driven semantic communication networks: Architecture, technologies and applications." IEEE Transactions on Cognitive Communications and Networking (2024).
[6] Tao, Zhenyu, et al. "Wireless network digital twin for 6g: Generative ai as a key enabler." IEEE Wireless Communications 31.4 (2024): 24-31.
[7] Huo, Wei, et al. "Recent Advances in Data-driven Intelligent Control for Wireless Communication: A Comprehensive Survey." arXiv preprint arXiv:2408.02943 (2024).
[8] Raghothaman, Balaji. "Training, testing and validation challenges for next generation AI/ML-based intelligent wireless networks." IEEE Wireless Communications 28.6 (2022): 5-6.
[9] Paul, Suman. "A comprehensive review on machine learning-based approaches for next generation wireless network." SN Computer Science 5.5 (2024): 468.
[10] Vu, Thai-Hoc, et al. "Applications of generative AI (GAI) for mobile and wireless networking: A survey." IEEE Internet of Things Journal (2024).
[11] Goutham, Nittu, Karan Singh, and Manisha Manjul. "Optimizing AI-Driven Efficient Communication and Pioneering 6G Network Architecture." 2024 4th International Conference on Technological Advancements in Computational Sciences (ICTACS). IEEE, 2024.
[12] Esenogho, Ebenezer, Karim Djouani, and Anish M. Kurien. "Integrating artificial intelligence Internet of Things and 5G for next-generation smartgrid: A survey of trends challenges and prospect." Ieee Access 10 (2022): 4794-4831.
[13] Guntupalli, Bhavitha. "Asynchronous Programming in Java/Python: A Developer’s Guide." International Journal of Emerging Research in Engineering and Technology 3.2 (2022): 70-78.
[14] Ponnusamy, Vijayakumar, et al. "AI‐Driven Information and Communication Technologies, Services, and Applications for Next‐Generation Healthcare System." Smart Systems for Industrial Applications (2022): 1-32.
[15] Parakala, Adityamallikarjunkumar. "Self‑Learning Bots & Cloud‑Native Platforms." International Journal of Emerging Trends in Computer Science and Information Technology 5.4 (2024): 132-141.
[16] Biti, Arjola, Olimpjon Shurdi, and Luan Ruci. "AI Driven Innovation for Boosting Performance and efficiency in Mobile and Wireless Networks." 2024 5th International Conference on Communications, Information, Electronic and Energy Systems (CIEES). IEEE, 2024.
[17] Sheelam, Goutham Kumar. "AI-Driven Spectrum Management: Using Machine Learning and Agentic Intelligence for Dynamic Wireless Optimization." European Advanced Journal for Emerging Technologies (EAJET)-p-ISSN 3050-9734 en e-ISSN 3050-9742 2.1 (2024).
[18] Padala, S. (2024). AI-Powered Intelligent IVR in Healthcare. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 5(1), 186-191.
