DRL-APNS: A Deep Reinforcement Learning-Powered Framework for Accurate Predictive Network Slicing Allocation

Wireless networks have undergone significant advancements with the rapid progress in Software Defined Networks (SDN), Open RAN (O-RAN) and 5G technology. Among the most notable developments is the emergence of network slicing, which leverages the concept of virtual networks to separate the end-to-end network and computational resources into individual network slices per one or more services/tenants. However, determining the appropriate allocation of computational and network resources for each network slice to meet the specific requirements of each service remains a challenge, especially with continuously changing demands and varying Key Performance Indicators (KPIs) per service and the risk of insufficient or excessive resource allocation. To address these issues, this paper proposes an intelligent predictive framework based on Deep Reinforcement Learning (DRL). Our framework utilizes historical demand and KPI requirements to predict and reserve optimized network slices for multiple services in the future, considering unique constraints, dynamic pricing and under-provisioning. Using different datasets, we validated our system's effectiveness, scalability, and adaptiveness by comparing it with different baselines and state-of-the-art approaches. Our results affirm the efficiency of the proposed solution, showcasing a minimum cost reduction of 15% compared to different baselines and state-of-the-art solutions while incurring less than 2% additional resource consumption. Furthermore, our system demonstrates excellent scalability and adaptability across varying network conditions.