Intel4EC 2025

Overview

The emergence of Computing Continuum with ever-expanding Cloud boundaries and its evolution into the proverbial Fog, Edge, and IoT paradigms has paved the way for realizing transformational and innovative digital solutions. Emerging application areas such as smart transportation logistics, smart cities, healthcare, and industry 4.0 sectors encompassing highly distributed services that use many devices involving large-scale data generation, gathering, storage, and analysis in real-time further encourage its adoption. While the geo-distributed and federated nature of the continuum continues to improve the agility, responsiveness, and effectiveness of such distributed applications. This paradigmatic shift in the post-digital transformation era has also triggered drastically changing expectations of dynamic service deployment and infrastructure usage patterns, further introducing significant complexities to the Edge-Cloud layers. These include challenges related to performance sustainability, resilience, and scalability of massive digital operations and services. These issues break down to reconciling many and typically allude to dynamically changing demand, requirements, and constraints of digital applications, which require the Edge-Cloud infrastructures to be deployed in sites that are in large numbers and are sometimes located in remote areas. 

To manage such fault-prone Edge-Cloud systems, infrastructure and service providers rely on human-intensive means to meet the increasing capacity demand and high availability of digital services. However, due to the continuously changing landscape, utilizing manual interventions to manage such large-scale systems is implausible. Hence, mitigating such issues requires digital applications and Edge-Cloud infrastructure to reposition their focus from adopting more efficient, effective, quick, and cheap compute capabilities to embracing more autonomous and self-driven technologies. Recently, Intelligent Cloud Operations and Services (a.k.a AIOps) gained traction that advocates using AI/ML techniques to embed intelligence at the Edge-Cloud management layers and automate digital operations and services by only requiring human intervention for critical issues beyond automation capabilities. Moreover, the recent emergence of Generative AI and Large Language Models (LLMs) have given a great boost to the vision of realizing autonomous Cloud-Edge systems. While AIOps/LLMs usage is still in early phases, academia and industry foresee many possible advancements ranging from root-cause analysis, early anomaly detection, and mitigation to predictive and prescriptive maintenance and management in Edge-Cloud systems. Additionally, such intelligence powered transformation can ensure that the continuum supply chain meets the heightened user demands in terms of openness, security, privacy and resilience, energy and resource efficiency and provide Cloud-Edge technologies with an ability to scale, accelerate innovation and enable industry-specific needs.

Following the successful first and second edition, the third edition of Intel4EC workshop aims to bring together researchers, developers and practitioners from academia and industry to present their experiences, results and research progress covering architectural designs, methods and applications of AI/ML/LLM-enabled Edge-Cloud operations and services. By bringing together these research topics, Intel4EC looks forward to helping the community define open standards, AI/ML benchmarks that contribute to experiment reproducibility and systematize the complete management pipeline for a myriad of Cloud-Edge operations.

Topics

Intel4EC 2025 workshop aims to attract the Cloud, Fog, Edge, AI/ML/LLM, Big Data and distributed computing community for novel research contributions to intelligent, adaptive, manageable and observable Edge-Cloud systems that include topics of interest, but are not limited to:

• Performance instrumentation, monitoring and observability

• Causal attribution and root-cause analysis

• Performance diagnosis and prognosis

• Failure prediction and fault localisation

• Anomaly detection and prediction

• Chaos engineering and analytics

• Capacity planning, scalability and workload management

• Edge-Cloud sprawl management and multi-tenancy issues

• AI/ML techniques for cost and energy-efficient operations

• Adaptive resource provisioning, scheduling and run-time optimisation

• Trust, security and privacy-preserving AI/ML

• SLA breach, violation and vulnerability detection

• Service discovery and microservice composition

• Intelligent programming models

• Distributed data (e.g. logs, traces) integration, management and analysis

• Self-adaptive and self-healing systems

• Experiment reproducibility, benchmarks, and application case-studies

Click to Check more on Call for papers: Submission Guidelines , Important Deadlines and Special Issue,  Keynotes and Program for 2025 Edition.

CONTACT

• For any queries and questions regarding the workshop and submissions, please contact the organisers.