arXiv subjects

Chengdi Lu

Publications and source records attributed to Chengdi Lu.

4 recordsLinked to original sources

arXiv2026

MATE: Multi-Agent Traffic Engineering for Topology-Aware Distributed SRv6 Scheduling under Bursty Traffic

As network traffic becomes increasingly dynamic and bursty, conventional centralized traffic engineering (TE) suffers from long control-loop delays caused by network-state aggregation, centralized computation, and policy distribution. In this paper, we propose MATE, a multi-agent TE method for proactive distributed scheduling in hybrid networks with partial deployment of Segment Routing over IPv6 (SRv6). MATE uses historical traffic stability to characterize the burst risk of each traffic demand and path sensitivity to quantify the ability of candidate paths to accommodate additional traffic, thereby enabling differentiated proactive scheduling tailored to heterogeneous traffic characteristics. MATE adopts an offline-centralized training and online-distributed execution architecture. During training, a shared global critic evaluates joint actions under a reward combining maximum link utilization (MLU) with variability-weighted path sensitivity, while counterfactual difference rewards provide agent-specific credit for actor learning. During online execution, edge agents generate traffic-splitting policies from local observations and apply them through SRv6, avoiding centralized optimization in each scheduling interval. Experiments on the China Environment for Network Innovations (CENI) testbed and simulations on the Sanet topology show that MATE outperforms a multi-agent reinforcement learning (MARL) ablation baseline without agent-specific credit assignment, COPE, and TEAL in most evaluated scenarios and approaches centralized FIGRET on measured traffic traces. On CENI-Abilene, MATE achieves MLU within 10% of the linear-programming optimum in up to 90.1% of test instances. MATE also achieves lower median normalized MLU than FIGRET in most tested failure scenarios, with mean neural-inference times of 2.05--3.14~ms.

cs.NI↗

arXiv2025

Topology-aware Microservice Architecture in Edge Networks: Deployment Optimization and Implementation

As a ubiquitous deployment paradigm, integrating microservice architecture (MSA) into edge networks promises to enhance the flexibility and scalability of services. However, it also presents significant challenges stemming from dispersed node locations and intricate network topologies. In this paper, we have proposed a topology-aware MSA characterized by a three-tier network traffic model encompassing the service, microservices, and edge node layers. This model meticulously characterizes the complex dependencies between edge network topologies and microservices, mapping microservice deployment onto link traffic to accurately estimate communication delay. Building upon this model, we have formulated a weighted sum communication delay optimization problem considering different types of services. Then, a novel topology-aware and individual-adaptive microservices deployment (TAIA-MD) scheme is proposed to solve the problem efficiently, which accurately senses the network topology and incorporates an individual-adaptive mechanism in a genetic algorithm to accelerate the convergence and avoid local optima. Extensive simulations show that, compared to the existing deployment schemes, TAIA-MD improves the communication delay performance by approximately 30% to 60% and effectively enhances the overall network performance. Furthermore, we implement the TAIA-MD scheme on a practical microservice physical platform. The experimental results demonstrate that TAIA-MD achieves superior robustness in withstanding link failures and network fluctuations.

cs.NI↗

arXiv2025

DMSA: A Decentralized Microservice Architecture for Edge Networks

The dispersed node locations and complex topologies of edge networks, combined with intricate dynamic microservice dependencies, render traditional centralized microservice architectures (MSAs) unsuitable. In this paper, we propose a decentralized microservice architecture (DMSA), which delegates scheduling functions from the control plane to edge nodes. DMSA redesigns and implements three core modules of microservice discovery, monitoring, and scheduling for edge networks to achieve precise awareness of instance deployments, low monitoring overhead and measurement errors, and accurate dynamic scheduling, respectively. Particularly, DMSA has customized a microservice scheduling scheme that leverages multi-port listening and zero-copy forwarding to guarantee high data forwarding efficiency. Moreover, a dynamic weighted multi-level load balancing algorithm is proposed to adjust scheduling dynamically with consideration of reliability, priority, and response delay. Finally, we have implemented a physical verification platform for DMSA. Extensive empirical results demonstrate that compared to state-of-the-art and traditional scheduling schemes, DMSA effectively counteracts link failures and network fluctuations, improving the service response delay and execution success rate by approximately $60\% \sim 75\%$ and $10\%\sim15\%$, respectively.

cs.NI↗

arXiv2024

VNF Migration with Fast Defragmentation: A GAT-Based Deep Learning Method

Network function virtualization (NFV) enhances service flexibility by decoupling network functions from dedicated hardware. To handle time-varying traffic in NFV network, virtualized network function (VNF) migration has been involved to dynamically adjust resource allocation. However, as network functions diversify, different resource types may be underutilized due to bottlenecks, which can be described as multidimensional resource fragmentation. To address this issue, we firstly define a metric to quantify resource fragmentation in NFV networks. Then, we propose a multi-hop graph attention network (MHGAT) model to effectively extract resource features from tailored network layers, which captures the overall network state and produces high-quality strategies rapidly. Building on this, we develop an MHGAT method to implement fast defragmentation and optimize VNF migration. Simulations demonstrate that by fast defragmentation, the MHGAT method improves the acceptance ratio by an average of 12.8%, reduces the overload ratio by an average of 30.6%, and lowers migration loss by an average of 43.3% compared to the state-of-art benchmark.

cs.NI↗