Jul 2026· International Scientific Conference on Information, Communication and Energy Systems and Technologies· pp. 139-152· 0 citations· 45 references
Abstract
The fast development of Edge AI has moved the intelligence towards distributed Edge-Cloud computing infrastructure moving away from centralized cloud in terms of low-latency, privacy-preserving, and context-aware applications. However, the deployment and management of the AI-based workloads in heterogeneous and resourceconstrained environments faces mounting complexity with the need for continuous and autonomous orchestration mechanisms. This paper provides a survey on Edge AI orchestration along the Edge-Cloud continuum based on a closed-loop lifecycle encompassing monitoring, decision making, placement, scaling, migration, and adaptation. We examine the ways in which modern systems sense dynamic environments, reason over multi-objective constraints, and perform runtime control actions to adapt and optimize performance, efficiency, and quality of service. Additionally, we systematically review state-of-the-art approaches starting from classic optimization, to emerging federated intelligence, autonomous agents, and foundation model-driven paradigms. Lastly, we identify key open challenges, including cross-layer monitors, explainable decision making, and continual adaptation under concept drift, outlining future research directions oriented towards fully autonomous and selfoptimizing Edge AI systems.
Cloud Continuum applications require experimental environments capable of combining heterogeneous Edge, Fog, Cloud, and high-performance computing resources while preserving reproducibility, observability, and control over distributed deployments. This paper presents a two-level reference architecture for Cloud Continuum experimentation built on top of the SLICES Cloud Continuum Blueprint. The proposed approach separates the research-infrastructure layer, which exposes and manages distributed resources, from the application layer, where Cyber-Physical workflows are organized according to an Edge-Fog-Cloud pattern in which placement, timing, and data provenance are treated as first-class experimental concerns. The architecture is designed to support multiple continuum applications rather than a single domain-specific prototype. At the Edge, applications interact with physical devices and perform low-latency sensing or safety actions; at the Fog, they execute near-source coordination, mediation, and stream-processing logic; at the Cloud, they consolidate global knowledge through analytics, optimization, and visualization. This partitioning enables researchers to deploy, customize, and compare alternative control and monitoring strategies over the same programmable infrastructure substrate. The approach is validated through two representative use cases: Renewable Energy Community management, where distributed Digital Twin coordination and time-window-based energy control are requested, and AirWatch, a monitoring pipeline focused on anomaly detection, low-latency alerting, and cloud-side aggregation. Both workloads are evaluated through a systematic campaign of 40 runs comparing virtualized and physical edge deployments over a geographically distributed infrastructure.
Fabio Orazio Mirto, Giuseppe Tricomi, L. D’Agati et al.· 0 citations
Cloud-edge computing environments are evolving rapidly, requiring orchestration mechanisms that may automatically construct and manage complex multi-step workflows with little human intervention. We introduce a framework for the agentic AI and how it should be able to orchestrate an autonomous end-to-end workload of cloud-edge enterprise infrastructures in general. The proposed framework relies on large language model (LLM)-driven agents capable of dynamic task decomposition, real-time decision-making, and self-correcting execution pipelines to manage heterogeneous workloads. Through the incorporation of multi-agent coordination protocols, context-aware scheduling algorithms, and feedback-driven optimization loops, the system facilitates seamless task delegation throughout edge nodes and cloud backend systems while managing latency, resource allocation, and compliance constraints. Experimental evaluations show up to percentage improvements in workflow completion rates, resource utilization, and fault tolerance over traditional static-command Rule-based orchestration approaches. Additionally, the framework features explainability modules and audit trails to promote transparency and accountability in autonomous operations. The results provide evidence that agentic AI architectures can serve as a scalable, resilient and intelligent control mechanism for next generation enterprise workflow management across hybrid cloud-edge settings. This has laid a foundation and is to our best of knowledge, the first systematic pioneers work that lays down a roadmap for production-grade autonomous orchestration deployed in analytics and enterprise domains.
Shiza Arshad, Anusha Joodala, A. Agade et al.· 2026 International Conferenc...· 0 citations
Industrial Internet of Things (IIoT) ecosystems are increasingly reliant on artificial intelligence (AI) to enable predictive analytics, real-time control, and intelligent automation. However, the centralized nature of traditional cloud computing introduces latency, bandwidth, and privacy constraints that limit the real-time applicability of AI models in industrial settings. This paper explores hybrid cloud-edge infrastructures as a scalable solution for deploying AI in IIoT environments. We present an architectural framework that balances compute-intensive model training in the cloud with low-latency inference at the edge. Key challenges including model orchestration, data management, and security in distributed environments are analyzed. Through case studies and performance evaluations, we demonstrate how hybrid architectures can effectively support scalable and resilient AI deployments for a range of industrial applications. Our findings highlight open research challenges and provide recommendations for building robust hybrid IIoT systems.
Jennifer Clark· International Journal of Mac...· 0 citations
Industrial automation systems are undergoing a rapid transformation driven by the convergence of edge and cloud computing under the umbrella of Industry 4.0. These systems demand scalable, resilient, and low-latency computational infrastructures to support data-intensive and time-critical tasks. Traditional centralized cloud architectures often fall short in addressing the latency and bandwidth requirements of modern industrial environments, while edge-only solutions may lack the scalability and global coordination needed for complex workloads. This paper presents a comprehensive study of edge-cloud orchestration strategies tailored for scalable industrial automation systems. We explore dynamic workload allocation methods, latency-aware orchestration, and resource optimization techniques that enable seamless integration between edge and cloud resources. Through an in-depth analysis of architectural models, real-world use cases, and orchestration frameworks, we identify key design patterns and challenges. Our findings reveal that intelligent orchestration can significantly enhance operational efficiency, system scalability, and responsiveness in industrial settings. We also outline the open research areas and future directions toward fully autonomous and self-optimizing industrial infrastructures.
A. Reza· International Journal of Mac...· 0 citations
CloudSkin aims to create a cognitive cloud-edge continuum platform that optimally exploits heterogeneous resources. Using AI, the platform automatically adapts to system and application behavior, and enables secure and seamless service deployment. Barcelona Supercomputing Center has led the design and development of an AI-based “Learning Plane” to automatically and continuously manage services in the cloudedge continuum to adapt to the dynamic environment. In the project, we enabled basic system models and workload characterization including regressions and time-series models, different levels of smart policies including heuristics and reinforcement learning, and we developed a data-connector agent to leverage those mechanisms towards real-world use cases. In this paper, we report on the technical results and insights we have explored within the project, explain how they are integrated as a learning plane to support CloudSkin use cases, and finally outline new open research lines.
Peini Liu, Joan Oliveras Torra, Marc Palacín et al.· Annual International Compute...· 0 citations
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.
Dr. Chinedu Eze, Dr. Fatima Bello· International Journal of Adv...· 0 citations