ARCHIVES
VOL. 13, ISSUE 3 (2026)
Adaptive AI scheduling across edge-cloud continuum
Authors
Dr. G Sripriya, Darun M K, Nandana K
Abstract
The Edge–Cloud Continuum
integrates edge nodes, fog layers, and cloud infrastructures to support
intelligent, low-latency AI workloads, yet existing scheduling approaches
suffer from static policies and single-objective optimisation. To address this,
an Adaptive AI-driven Task Scheduling (AATS) framework is proposed, combining
Deep Q-Network reinforcement learning with deadline-safety heuristics and
federated model updates across continuum tiers. Results demonstrate a 65.4%
latency reduction, 54.8% lower energy consumption, and 89.5% higher throughput
over static baselines, confirming the hybrid Edge–Cloud Continuum as the
optimal paradigm for next-generation AI systems.
Download
Pages:46-49
How to cite this article:
Dr. G Sripriya, Darun M K, Nandana K "Adaptive AI scheduling across edge-cloud continuum". International Journal of Multidisciplinary Research and Development, Vol 13, Issue 3, 2026, Pages 46-49
Download Author Certificate
Please enter the email address corresponding to this article submission to download your certificate.