Adaptive Multi-Constraint Workload Partitioning for Distributed Edge–Cloud Systems under Dynamic Network and Energy Conditions
Journal of Intelligent Decision Making and Information Science · 03.10.2026 · 3 (16s) · 2398-2411
DOI: 10.17762/jidmis.v3.5177 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Intelligent Decision Making and Information Science, online erschienen am 03.10.2026. Verfasst von K. Vivekananda Reddy. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Distributed edge-cloud architecture for critical IoT applications should be resilient to changes in network dynamics, fluctuations in energy supply, and different computational settings. Current methods for task allocation have been designed either statically or only to optimize one goal and therefore cannot maintain stability when faced with uncertainties in all three dimensions. In this paper, we propose an adaptive multi-constraint task allocation method that combines the sensing of changing conditions in the network, energy and computing domains together with predictive decision-making for the reallocation of workload between the edge-cloud system components. Our approach views task allocation as a constrained decision problem that takes into consideration deadline satisfaction, energy efficiency, and overall system stability. Experimental results on various IoT workloads show considerable improvements in performance in terms of fewer deadline misses (up to 48%), increased throughput (up to 32%), and better edge energy consumption stabilization at a high level of variability when compared against state-of-the-art static and single-constraint approaches. We demonstrate that using multiple constraints within a decision framework for the adaptive management of distributed edge-cloud systems can provide a substantial benefit in terms of stable and efficient functioning of emerging IoT infrastructures.
Zitieren
APA
Reddy, K. V. (2026). Adaptive Multi-Constraint Workload Partitioning for Distributed Edge–Cloud Systems under Dynamic Network and Energy Conditions. Journal of Intelligent Decision Making and Information Science, 3(16s), 2398-2411. https://doi.org/10.17762/jidmis.v3.5177
Vancouver
Reddy KV. Adaptive Multi-Constraint Workload Partitioning for Distributed Edge–Cloud Systems under Dynamic Network and Energy Conditions. Journal of Intelligent Decision Making and Information Science. 2026;3(16s):2398-2411. doi:10.17762/jidmis.v3.5177
BibTeX
@article{Reddy2026,
author = {Reddy, K. Vivekananda},
title = {Adaptive Multi-Constraint Workload Partitioning for Distributed Edge–Cloud Systems under Dynamic Network and Energy Conditions},
journal = {Journal of Intelligent Decision Making and Information Science},
year = {2026},
volume = {3},
number = {16s},
pages = {2398--2411},
doi = {10.17762/jidmis.v3.5177}
}
EUVIMED