AI-Driven Dynamic Network Slicing for Resource Optimization in 5G Networks: Implementation and Performance Evaluation
Ayushi Jain, Prateek Vijay Jain, Aditya Verma, Lisa Gopal, Preeti Madhukar Chaudhary · 2024
We introduce in this paper an AI-based dynamic network slicing model for resource allocation targeting 5G networks. It does this by using machine learning algorithms that help the model learn and adapt to live traffic conditions so as to intelligently manage different service types, including eMBB (enhanced Mobile Broadband), URLLC (Ultra-Reliable Low Latency Communication) and mMTC (massive Machine Type Communication). This leads to substantial improvements in three of the four core performance metrics, latency, throughput and energy efficiency (at a low sacrifice of when it comes to QoS adherence). Their work also demonstrates that AI technologies hold the promise for revolutionary network management, offering a scalable solution that can address ever-increasing requirements of next-generation telecommunications, by surpassing the capabilities of well-established static slicing techniques.