Hierarchical Reinforcement Learning for the Dynamic VNE with Alternatives Problem
By: Ali Al Housseini, Cristina Rottondi, Omran Ayoub
Virtual Network Embedding (VNE) is a key enabler of network slicing, yet most formulations assume that each Virtual Network Request (VNR) has a fixed topology. Recently, VNE with Alternative topologies (VNEAP) was introduced to capture malleable VNRs, where each request can be instantiated using one of several functionally equivalent topologies that trade resources differently. While this flexibility enlarges the feasible space, it also introduces an additional decision layer, making dynamic embedding more challenging. This paper proposes HRL-VNEAP, a hierarchical reinforcement learning approach for VNEAP under dynamic arrivals. A high-level policy selects the most suitable alternative topology (or rejects the request), and a low-level policy embeds the chosen topology onto the substrate network. Experiments on realistic substrate topologies under multiple traffic loads show that naive exploitation strategies provide only modest gains, whereas HRL-VNEAP consistently achieves the best performance across all metrics. Compared to the strongest tested baselines, HRL-VNEAP improves acceptance ratio by up to \textbf{20.7\%}, total revenue by up to \textbf{36.2\%}, and revenue-over-cost by up to \textbf{22.1\%}. Finally, we benchmark against an MILP formulation on tractable instances to quantify the remaining gap to optimality and motivate future work on learning- and optimization-based VNEAP solutions.
Similar Papers
The Power of Alternatives in Network Embedding
Networking and Internet Architecture
Lets computers use network parts better.
Digital Twin-Empowered Deep Reinforcement Learning for Intelligent VNF Migration in Edge-Core Networks
Networking and Internet Architecture
Makes internet faster and uses less power.
Optimisation of Resource Allocation in Heterogeneous Wireless Networks Using Deep Reinforcement Learning
Machine Learning (CS)
Makes phone signals faster and better for everyone.