Data-Driven Online Slice Admission Control and Resource Allocation in NextG Mobile Networks
2026-08-04 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors propose a method called OPA to help network providers decide in real time whether to accept requests for virtual networks, called slices, by pricing resources based on their scarcity and future value. This method uses dynamic pricing to guide decisions, aiming to maximize revenue while managing limited infrastructure. They also develop a data-driven approach that learns from past data to improve decisions. Tests on a real network showed that their method earns significantly more revenue and runs much faster than current advanced techniques.
5Gnetwork slicingresource allocationonline pricingslice admission controlopportunity costdynamic pricingdata-driven learningrevenue maximizationdeep reinforcement learning
Authors
Muhammad Sulaiman, Bo Sun, Mohammad Ali Salahuddin, Xiaoqi Tan, Raouf Boutaba
Abstract
Virtualization in 5G and beyond networks enables the creation of virtual networks (i.e., network slices) tailored to the needs of different applications. To maximize revenue under limited infrastructure resources, InPs must decide in real time whether to admit incoming slice requests (SRs) based on their resource demands and offered values, while accounting for the opportunity cost of consuming scarce resources. To address this challenge, we introduce Online Pricing-based Slice Admission Control and Resource Allocation (OPA) framework. This framework dynamically assigns pseudo-prices to resources that capture long-term scarcity and anticipated inter-temporal opportunity costs. The short-term admission and resource allocation decisions for each SR are then guided by these prices. Additionally, we design an exponential pricing strategy that guarantees bounded worst-case performance. To improve practical performance, we further develop a data-driven exponential pricing approach that learns from historical data. Evaluations on a real-world network topology show that it improves mean revenue by 32.2% and 26.7% over state-of-the-art DRL and optimization-based approaches, respectively, while reducing computational cost by an order of magnitude relative to the latter.