Resilient Edge-to-Cloud AI Architectures for Distributed Real-Time Decision Making
TL;DR
A research-driven conceptual framework for resilient edge-to-cloud AI architectures supporting distributed real-time decision making and identifies limitations associated with heterogeneous devices, uncertain ground truth, model drift, communication failures, and the absence of uniform evaluation criteria are identified.
Abstract
The increasing deployment of artificial intelligence (AI) in distributed environments has created a need for architectures capable of combining low-latency inference, computational scalability, data protection, and operational resilience. Conventional cloud-centric AI pipelines can provide substantial computational resources but may introduce latency, network dependency, privacy concerns, and vulnerability to service interruptions. Edge-to-cloud architectures address these limitations by distributing data processing and inference across edge devices, intermediate computing nodes, and centralized cloud infrastructure. This paper develops a research-driven conceptual framework for resilient edge-to-cloud AI architectures supporting distributed real-time decision making. The study synthesizes the supplied literature concerning AI-assisted medical image classification, radiological decision processes, ground-truth uncertainty, workload-related behavior, fatigue, information protection, and automated image segmentation. Particular emphasis is placed on how inference placement, data integrity, uncertainty management, workload awareness, and adaptive orchestration can collectively improve system resilience. The methodology develops a layered architectural model consisting of sensing and acquisition, edge inference, adaptive orchestration, cloud intelligence, resilience management, and decision feedback. The analysis indicates that resilience should not be treated exclusively as infrastructure availability; rather, it must encompass model reliability, data quality, human interaction, computational continuity, and decision confidence. The proposed framework provides a conceptual basis for designing distributed AI systems in which latency-sensitive decisions are executed near data sources while computationally intensive and globally coordinated processes remain cloud-enabled. The study also identifies limitations associated with heterogeneous devices, uncertain ground truth, model drift, communication failures, and the absence of uniform evaluation criteria.