Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2506.10570

6G Infrastructures for Edge AI: An Analytical Perspective

Kurt Horvath·Shpresa Tuda·Blerta Idrizi·Stojan Kitanov·Fisnik Doko·Dragi Kimovski
View original source ↗Read source document ↗Export metadata ↓

Abstract

The convergence of Artificial Intelligence (AI) and the Internet of Things has accelerated the development of distributed, network-sensitive applications, necessitating ultra-low latency, high throughput, and real-time processing capabilities. While 5G networks represent a significant technological milestone, their ability to support AI-driven edge applications remains constrained by performance gaps observed in real-world deployments. This paper addresses these limitations and highlights critical advancements needed to realize a robust and scalable 6G ecosystem optimized for AI applications. Furthermore, we conduct an empirical evaluation of 5G network infrastructure in central Europe, with latency measurements ranging from 61 ms to 110 ms across different close geographical areas. These values exceed the requirements of latency-critical AI applications by approximately 270%, revealing significant shortcomings in current deployments. Building on these findings, we propose a set of recommendations to bridge the gap between existing 5G performance and the requirements of next-generation AI applications.

Explore related subjects

cs.DC

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Kurt Horvath, Shpresa Tuda, Blerta Idrizi, Stojan Kitanov, Fisnik Doko, Dragi Kimovski. 2025-06-12. 6G Infrastructures for Edge AI: An Analytical Perspective. https://doi.org/10.1109/ipdpsw66978.2025.00167

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Learning to Remember: Attentive Reinforcement Learning for Edge Serverless Autoscaling

In edge computing, the stochastic and bursty nature of serverless workloads challenges autonomous resource orchestration. Traditional reactive controllers, such as the Kubernetes Horizontal Pod Autoscaler (HPA), suffer from reaction latency, leading to Service Level Objective (SLO) violations during traffic spikes and resource flapping during ramp-downs. While Deep Reinforcement Learning (DRL) offers a pathway toward proactive management, standard agents suffer from \textit{temporal blindness}, an inability to exploit the recent temporal context in non-Markovian edge environments. To bridge this gap, we propose a stability-aware autoscaling framework unifying short-horizon temporal context and control via an Attention-Enhanced Double-Stacked LSTM architecture integrated within a Proximal Policy Optimization (PPO) agent. Unlike shallow recurrent models, our approach employs a learned attention mechanism that weights recent historical states non-uniformly, suppressing high-frequency jitter while preserving the trend that precedes demand shifts. We validate the framework on two independent Kubernetes clusters using real-world Azure Functions traces. Against the single-layer LSTM ablation and the static HPA baseline, our approach reduces P90 latency by $\approx$67\%, and holds average latency within the 50ms hard SLO for 98.8\% of the run against 49.6\% and 43.5\% respectively. Against Kubernetes Event-Driven Autoscaling (KEDA), it matches latency performance at 75\% fewer replica-steps and 59\% less churn, with P90 hard-SLO violation bursts of at most 5 consecutive intervals against up to 24 for KEDA. These results indicate that mitigating temporal blindness through deep attentive memory improves the reliability and stability of Kubernetes autoscaling under bursty edge workloads.

cs.DC↗
arXiv2026

Scheduling Coflows in Multi-Core OCS Networks with Performance Guarantee

The coflow abstraction captures application-level communication patterns and enables coordinated scheduling of parallel flows to reduce job completion times in distributed systems. Modern data center networks (DCNs) are employing multiple independent optical circuit switching (OCS) cores operating concurrently to meet the massive bandwidth demands of application jobs. However, existing coflow scheduling research primarily focuses on the single-core setting, while studies of multi-core fabrics have largely considered electrical packet switching (EPS) networks. To address this gap, this paper studies the coflow scheduling problem in multi-core OCS networks under the not-all-stop reconfiguration model, in which the reconfiguration of one circuit does not interrupt other circuits. The challenges stem from two aspects: (i) cross-core coupling induced by traffic assignment across heterogeneous cores; and (ii) per-core OCS scheduling constraints, namely \textit{port exclusivity} and \textit{reconfiguration delay}. We propose an approximation algorithm that jointly integrates cross-core flow assignment and per-core circuit scheduling to minimize the total weighted coflow completion time (CCT) and establish a provable worst-case performance guarantee. Furthermore, our algorithm framework can be applied to the multi-core EPS scenario with a corresponding approximation guarantee for packet-switched fabrics. Trace-driven simulations using real Facebook workloads demonstrate that our algorithm can reduce the total weighted CCT and tail CCT.

cs.DC↗
arXiv2026

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving

Pipeline parallelism (PP) is widely used to partition layers of large language models (LLMs) across GPUs, enabling scalable inference for large models. However, existing systems rely on static PP configurations that fail to adapt to dynamic settings, such as serverless platforms and heterogeneous GPU environments. Reconfiguring PP by stopping and redeploying service incurs prohibitive downtime, so reconfiguration must instead proceed live and in place, without interrupting inference. However, live in-place PP reconfiguration is fundamentally challenging. GPUs are already saturated with model weights and KV cache, leaving little room for new layer placements and necessitating KV cache resizing, at odds with systems like vLLM that preallocate for throughput. Moreover, maintaining KV consistency during execution is difficult: stop-and-copy introduces large pauses, while background synchronization risks inconsistency as states evolve. We present PipeLive, which enables live in-place PP reconfiguration with minimal disruption. PipeLive introduces a redesigned KV cache layout together with a co-designed extension to PageAttention, forming a unified mechanism for live KV resizing. It further adopts an incremental KV patching mechanism, inspired by live virtual machine migration, to synchronize KV states between source and target configurations and identify a safe switch point. PipeLive achieves a 2.5X reduction in time-to-first-token (TTFT) without KV cache overflow compared to disabling KV resizing. Furthermore, compared to a variant without KV patching, it reduces reconfiguration overhead from seconds to under 10ms, and improves TTFT and time-per-output-token (TPOT) by up to 54.7% and 14.7%, respectively.

cs.DC↗