Adaptive 5G Network Slicing With Real-Time Traffic Classification and Experimental Validation

The growth of 5G applications makes it difficult to meet diverse performance requirements while using network resources efficiently. Fixed network slicing methods cannot adapt to changing traffic, leading to higher latency, lower throughput, and increased packet loss. This paper presents an experimental validation of adaptive slicing on a 3GPP Release 16-compliant 5G Standalone testbed combining Open5GS, srsRAN, software-defined radios, and commercial devices. The framework classifies traffic demand into low, medium, or high levels and adjusts slice resources in real time. Measurements show approximately 15% lower latency, higher throughput, and significantly reduced packet loss compared with static slicing. Unlike simulation-based studies or deep learning approaches requiring specialized hardware, the proposed setup achieves real-time adaptation on only CPU resources, demonstrating that practical adaptive slicing can be realized with open-source platforms and standard 5G equipment.