Schahram Dustdar

Adaptive Score-based Routing Balancer is introduced, a dynamic, score-based request routing mechanism for Kubernetes-based service deployments over the computing continuum that jointly considers infrastructure-level information, response time measurements, and application-level quality indicators, with a particular focus on serving Machine Learning workloads.

This article categorizes existing UAV inspection architectures, identifies their key system challenges and architectural requirements, and experimentally assesses the feasibility of semantic edge intelligence on NVIDIA Jetson UAV-class hardware using the COCO-Bridge dataset.

DRLM achieves up to 51% faster inference and 67% reduced queuing delays in edge environments, all while maintaining accuracy.

Certified caching can boost edge image classification speed by 1.65x without compromising reliability.

A structured taxonomy reveals that traditional performance metrics fail to capture the complexities of modern distributed computing environments, potentially hindering system optimization.

LMEdge slashes latency while ensuring accuracy and resource efficiency in LLM inference across diverse edge devices.

The shift from static software components to adaptive, goal-directed agents demands a new engineering framework to ensure reliability and trust in AI systems.

Most reinforcement learning orchestration systems fail to demonstrate the robustness expected under real-world conditions, challenging the validity of existing benchmarks.

Controller performance in edge clusters can swing dramatically based on workload intensity, with a deep reinforcement-learning approach losing to a simple heuristic by 29 percentage points under heavy load.

Forget incentive compatibility, can you even trust the marketplace operator?

AIF-Router achieves stable online learning for adaptive AI service orchestration, even in unpredictable edge environments, showcasing the potential of Active Inference in real-world applications.

Pricings, inspired by SaaS subscription models, offer a surprisingly effective and generalizable way to represent and optimize resource allocation in complex computing environments.

Watch an agent learn to juggle the knobs of multiple stream processing services to meet latency goals in a resource-constrained edge environment.

Current service orchestration solutions fall short of achieving autonomous, resilient, and scalable performance in the Computing Continuum, highlighting the urgent need for standardized evaluation environments.