Aug 2026· ACM Transactions on Modeling and Performance Evaluation of Computing Systems· 0 citations· 22 references
TL;DR
This work proposes an enhanced Proximal Policy Optimization (PPO) framework for resource-aware and latency-sensitive SFC placement in edge-enabled networks, and demonstrates the applicability of the proposed framework in mission-critical and latency-sensitive service environments.
Abstract
Modern networked systems are progressively adopting network virtualization and Service Function Chaining (SFC) to deliver scalable, flexible and low-latency services. A central challenge in this context is the Service Function Chain Placement Problem (SFC-PP), which involves efficiently placing Virtualized Network Functions (VNFs) under stringent resource constraints and Quality of Service (QoS) requirements in dynamic network environments. To address this, we propose an enhanced Proximal Policy Optimization (PPO) framework for resource-aware and latency-sensitive SFC placement in edge-enabled networks. Our approach incorporates network performance metrics into the PPO learning pipeline through delay-aware reward design, resource-aware state representation and feasibility-aware action masking, thereby improving policy stability and infrastructure utilization. Extensive evaluations on multiple topologies including RNET, NSFNET, GBN and GEANT2 demonstrate that the proposed PPO significantly outperforms the Random Selection (RS), Q-Learning (QL) and Deep Q-Network (DQN) baselines, achieving up to 31% higher service acceptance, with reduced service latency and improved resource efficiency. A healthcare-oriented case study demonstrates the applicability of the proposed framework in mission-critical and latency-sensitive service environments. These results highlight PPO as a robust and scalable solution for intelligent service orchestration in dynamic network environments.
A constrained optimization model that supports different management goals through alternative objective functions (latency-aware or power-aware) while enforcing operational constraints, including node capacities, slice-specific latency bounds, and explicit limits on VNF migrations/relocations between scheduling periods is proposed.
R. Moreno-Vozmediano, E. Huedo, R. Montero et al.· Journal of Network and Syste...· 0 citations
A QoE-aware framework for Multi-Access Edge Computing-enabled Open Radio Access Network (O-RAN) architectures, combining a graph attention network (GAT) encoder, distributed multi-agent DRL, and privacy-preserving FL, while transitioning control from Quality of Service (QoS) to QoE metrics is proposed.
Manoj Prasad Kunasegran, Wai Leong Pang, S. K. Phang· IEEE Access· 0 citations
Meta's rapid expansion in users, business operations, and AI workloads is straining our backbone network, while physical constraints—such as fiber, space, and power—limit the speed of capacity growth. To address these challenges, we present a service-aware network capacity planning suite that systematically improves network efficiency with a service collaboration approach. We propose the "safe capacity" abstraction which enables services to incorporate current and projected network conditions into their compute and storage allocation decisions. We introduce a hose-carving method that efficiently translates service-level traffic demands into detailed traffic matrices, allowing for more precise bandwidth allocation. To promote responsible network usage, we design a network rate card which attributes network consumption to individual services, incentivizing optimization and resource trade-offs. Additionally, new enforcement features at the end-host layer dynamically adjust resource allocations and traffic flows at runtime to maximize utilization. This paper is the first to detail a collaborative, service-aware approach to backbone network efficiency at Meta scale. Based on years of operational experience, we share practical insights and highlight new directions for research in network efficiency.
V. Dangui, A. Razmjoo, Guanqing Yan et al.· Proceedings of the ACM SIGCO...· 0 citations
The rapid evolution of beyond-5G and emerging 6G networks is driving the need for flexible, reliable, and cost-efficient virtualized Radio Access Network (vRAN) architectures capable of supporting heterogeneous services such as enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communication (URLLC), and Massive Machine-Type Communication (mMTC). Future disaggregated RAN systems are expected to rely heavily on network slicing, functional split flexibility, and optical x-haul infrastructures to support stringent performance, scalability, and availability requirements. In this paper, we present an integrated framework for reliable, slice-aware, and functional split-aware Virtual Network Function (VNF) placement with lightpath provisioning in disaggregated vRAN environments. The proposed approach maximizes mobile network operators'profit by jointly optimizing function placement and optical resource allocation under latency, processing, bandwidth, and availability constraints. We formulate the problem as an Integer Linear Programming (ILP) model with two variants: one that employs unshared backups and another that uses a more cost-efficient shared backup scheme. To address ILP complexity, we develop a heuristic algorithm and a Genetic Algorithm (GA)-based metaheuristic that yields near-optimal solutions in real time. Extensive evaluations on topologies up to 128 nodes show that shared backup variants yield up to 18% higher profit, while maintaining up to 5-10% lower normalized CPU usage than unshared counterparts.
Mayank Ramnani, Shasank Dixit, Sushil K. Yadav et al.· 0 citations
This paper proposes a Service Level Agreement (SLA)-aware resource allocation framework for 6G V2X slicing, realized as a Soft Actor-Critic (SAC) based xApp within the Open-Radio Access Network (O-RAN) near-realtime-RAN Intelligent Controller (near-RT-RIC). The xApp dynamically distributes radio resources across heterogeneous slices, minimizing SLA violations while considering fairness and throughput efficiency. Unlike heuristic or single-metric Deep Reinforcement Learning (DRL) methods, our design incorporates deadline awareness and service reliability directly into the reward formulation. Simulation results show that the proposed scheme consistently outperforms fixed, random, proportional, and Exponential moving Average (EMA)-based baselines, improving average packet delivery ratio (PDR), reducing mean SLA violations, and achieving a Pareto-optimal trade-off between throughput and compliance. These findings demonstrate the potential of O-RAN-native intelligent control for future 6G networks.
M. Tariq, Deepak Singh, M. Saad et al.· International Conference on...· 0 citations
Mobile edge networks delivers low-latency, high-quality services by deploying Virtual Network Functions (VNFs) on resource-constrained edge nodes. However, sequential VNF processing incurs significant latency, while reusing existing VNFs under heavy demand may force requests onto longer paths, increasing bandwidth consumption. Parallelization combined with efficient VNF placement is therefore essential, yet these decisions are inherently coupled and may lead to suboptimal deployments if optimized separately. To address this challenge, this paper proposes a unified framework that jointly optimizes VNF parallelization and placement to minimize latency and resource consumption. The framework constructs a Dependency-Deployment Graph (DPG) that integrates VNF functional dependencies with Mobile Edge Networks topology. By assigning latency and resource weights to DPG nodes and edges, the framework captures the interplay between transmission delay, resource usage, parallelization, and deployment decisions. To efficiently explore the solution space, iterative algorithms progressively refine candidate configurations by pruning inferior solutions and focusing on promising regions of the search space. Experimental evaluations across diverse network configurations demonstrate that the proposed framework achieves promising improvements in reducing service latency and resource consumption compared with representative baseline methods. The results further indicate the effectiveness and robustness of the proposed joint parallelization and placement strategy under the tested heterogeneous edge computing scenarios.
Yuhao Xie, Zhen Zhang, Yuhui Deng et al.· IEEE Transactions on Network...· 0 citations