DATURA: A Deep Learning-Based Adaptive Traffic-Aware Unified Resource Autoscaling Framework for VNFs in 5G/B5G Networks

Abstract

This paper introduces DATURA, a Deep Learning(DL)–based Adaptive Traffic-aware Unified Resource Autoscaling framework for virtual network functions (VNFs) in 5G and beyond networks. A predictive GRU–MLP based scaling architecture is proposed and integrated with a deep reinforcement learning (DRL)-based traffic generator. The GRU–MLP scaling controller forecasts per-VNF and per-slice latencies from streaming telemetry. Temporal dependencies are captured through the GRU layer, while two multitask MLP heads estimate local (per-VNF) and global (slice-level) latency trends. Once deployed, DATURA operates fully online, executing inference-driven scaling decisions in real time. The DRL traffic generator employs Proximal Policy Optimisation (PPO) agents trained to learn transition probability matrices (TPM) that capture realistic transitions between low, medium, high, and very-high-load regimes. The underlying models are periodically retrained with updated telemetry, enabling the framework to adapt to long-term traffic evolution without service disruption. The predicted latencies are then translated by a regression layer into proactive scaling decisions and resource allocations that maintain SLA compliance while avoiding unnecessary over-provisioning. The framework is implemented in a SimPy-based 5G Core model that supports UE registration and PDU session establishment message exchanges. Detailed experiments show that DATURA consistently outperforms other existing schemes based on Long Short-Term Memory (LSTM) and GRU. The proposed framework achieves up to 73% latency reduction, 55% throughput gain, and 47% higher provisioning efficiency.