Umeå University's logo

As microservice-based systems scale across thecloud-edge continuum, traditional centralized scheduling mecha-nisms increasingly struggle with latency, coordination overhead,and fault tolerance. This paper presents a new architectural di-rection: leveraging service mesh sidecar proxies as decentralized,in-situ schedulers to enable scalable, low-latency coordination inlarge-scale, cloud-native environments. We propose embeddinglightweight, autonomous scheduling logic into each sidecar, allow-ing scheduling decisions to be made locally without centralizedcontrol. This approach leverages the growing maturity of servicemesh infrastructures, which support programmable distributedtraffic management. We describe the design of such an archi-tecture and present initial results demonstrating its scalabilitypotential in terms of response time and latency under varyingrequest rates. Rather than delivering a finalized scheduling algo-rithm, this paper presents a system-level architectural directionand preliminary evidence to support its scalability potential.

The Edge-Cloud Continuum is a large-scale, loosely coupled system consisting of multiple stakeholders, regions, dynamic infrastructures, and conflicting objectives. With surging growth and demand, the Continuum’s energy and carbon footprint have massively increased, resulting in great operational expense, environmental impact, and strain on power grids. Methods to mitigate this face significant challenges: Quality of Service (QoS) guarantees must be balanced against not only carbon emissions, but the loadings, capacities, and QoS of the (smart) grids that power the underlying infrastructure. Integrated models to enable reasoning across both a Continuum and its associated SmartGrids are therefore required.

This work presents a formal model to reason across the integration of Smart Grids and the Edge-Cloud Continuum. Firstly, we identify the components, interactions, and properties crucial to mitigating cross-Continuum energy and carbon footprint while maintaining user, provider, and power grid QoS. We then present associated mathematical models to enable a model-based simulation to be developed based on our work. We present this simulation (all code is available for download) and use a simple scheduling algorithm to demonstrate the feasibility of utilizing knowledge from both the Smart Grid and EdgeCloud Continuum for carbon and energy management, showing that significant savings are possible

Accurate workload prediction is essential for proactive resource allocation in large-scale Content Delivery Networks (CDNs), where traffic patterns are highly dynamic and geographically distributed. This paper introduces a CDN-tailored prediction and autoscaling framework that integrates statistical and deep learning models within an adaptive feedback loop. The framework is evaluated using 18 months of real traffic traces from a production multi-tier CDN, capturing realistic workload seasonality, cache–tier interactions, and propagation delays. Unlike generic cloud-edge predictors, our design incorporates CDN-specific features and model-switching mechanisms to balance prediction accuracy with computational cost. Seasonal ARIMA (S-ARIMA), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Online Sequential Extreme Learning Machine (OS-ELM) are combined to support both short-horizon scaling and longer-term capacity planning. The predictions drive a queue-based resource-estimation model, enabling proactive cache–server scaling with low rejection rates. Experimental results demonstrate that the framework maintains high accuracy while reducing computational overhead through adaptive model selection. The proposed approach offers a practical, production-tested solution for predictive autoscaling in CDNs and can be extended to other latency-sensitive edge-cloud services with hierarchical architectures.

The energy consumption of Cloud–Edge systems is becoming a critical concern economically, environmentally, and societally; some studies suggest data centers and networks will collectively consume 18% of global electrical power by 2030. New methods are needed to mitigate this consumption, e.g. energy-aware workload scheduling, improved usage of renewable energy sources, etc. These schemes need to understand the interaction between energy considerations and Cloud–Edge components. Model-based approaches are an effective way to do this; however, current theoretical Cloud–Edge models are limited, and few consider energy factors. This paper analyses all relevant models proposed between 2016 and 2023, discovers key omissions, and identifies the major energy considerations that need to be addressed for Green Cloud–Edge systems (including interaction with energy providers). We investigate how these can be integrated into existing and aggregated models, and conclude with the high-level architecture of our proposed solution to integrate energy and Cloud–Edge models together.

Use of the serverless paradigm in cloud application development is growing rapidly, primarily driven by its promise to free developers from the responsibility of provisioning, operating, and scaling the underlying infrastructure. However, modern cloud-edge infrastructures are characterized by large numbers of disparate providers, constrained resource devices, platform heterogeneity, infrastructural dynamicity, and the need to orchestrate geographically distributed nodes and devices over public networks. This presents significant management complexity that must be addressed if serverless technologies are to be used in production systems. This position paper introduces COGNIT, a major new European initiative aiming to integrate AI technology into cloud-edge management systems to create a Cognitive Cloud reference framework and associated tools for serverless computing at the edge. COGNIT aims to: 1) support an innovative new serverless paradigm for edge application management and enhanced digital sovereignty for users and developers; 2) enable on-demand deployment of large-scale, highly distributed and self-adaptive serverless environments using existing cloud resources; 3) optimize data placement according to changes in energy efficiency heuristics and application demands and behavior; 4) enable secure and trusted execution of serverless runtimes. We identify and discuss seven research challenges related to the integration of serverless technologies with multi-provider Edge infrastructures and present our vision for how these challenges can be solved. We introduce a high-level view of our reference architecture for serverless cloud-edge continuum systems, and detail four motivating real-world use cases that will be used for validation, drawing from domains within Smart Cities, Agriculture and Environment, Energy, and Cybersecurity.

Cloud infrastructures are rapidly evolving from centralised systems to geographically distributed federations of edge devices, fog nodes, and clouds. These federations (often referred to as the Cloud-Edge Continuum) are the foundation upon which most modern digital systems depend, and consume enormous amounts of energy. This consumption is becoming a critical issue as society's energy challenges grow, and is a great concern for power grids which must balance the needs of clouds against other users. The Continuum is highly dynamic, mobile, and complex; new methods to improve energy efficiency must be based on formal scientific models that identify and take into account a huge range of heterogeneous components, interactions, stochastic properties, and (potentially contradictory) service-level agreements and stakeholder objectives. Currently, few formal models of federated Cloud-Edge systems exist - and none adequately represent and integrate energy considerations (e.g. multiple providers, renewable energy sources, pricing, and the need to balance consumption over large-areas with other non-Cloud consumers, etc.). This paper conducts a systematic analysis of current approaches to modelling Cloud, Cloud-Edge, and federated Continuum systems with an emphasis on the integration of energy considerations. We identify key omissions in the literature, and propose an initial high-level architecture and approach to begin addressing these - with the ultimate goal to develop a set of integrated models that include data centres, edge devices, fog nodes, energy providers, software workloads, end users, and stakeholder requirements and objectives. We conclude by highlighting the key research challenges that must be addressed to enable meaningful energy-aware Cloud-Edge Continuum modelling and simulation.

This paper outlines the main idea and approach of the H2020 ASSISTANT (LeArning and robuSt deciSIon SupporT systems for agile mANufacTuring environments) project. ASSISTANT is aimed at the investigation of AI-based tools for adaptive manufacturing environments, and focuses on the development of a set of digital twins for integration with, management of, and decision support for production planning and control. The ASSISTANT tools are based on the approach of extending generative design, an established methodology for product design, to a broader set of manufacturing decision making processes; and to make use of machine learning, optimisation, and simulation techniques to produce executable models capable of ethical reasoning and data-driven decision making for manufacturing systems. Combining human control and accountable AI, the ASSISTANT toolsets span a wide range of manufacturing processes and time scales, including process planning, production planning, scheduling, and real-time control. They are designed to be adaptable and applicable in a both general and specific manufacturing environments.

To develop AI-based models capable of governing or providing decision support to complex manufacturing environments, abstractions and mechanisms for unified management of data storage and processing capabilities are needed. Specifically, as such models tend to include and rely on detailed representations of systems, components, and tools with complex interactions, mechanisms for simplifying, integrating, and scaling management capabilities in the presence of complex data requirements (e.g., high volume, velocity, and diversity of data) are of particular interest. A data fabric is a system that provides a unified architecture for management and provisioning of data. In this work we present the background, design requirements, and high-level outline of the ASSISTANT data fabric - a flexible data management tool designed for use in adaptive manufacturing contexts. The paper outlines the implementation of the system with specific focus on the use of domain models and the data modeling approach used, as well as provides a generic use case structure reusable in many industrial contexts.

Currently, pioneer companies are working hard to construct applied ethical frameworks in different sectors for using AI components that generate trust in their clients and workforce. However, independent of these few companies, there is still a considerable gap between understanding the impact of using responsible AI components, the implications of the lack of use, and what is currently applied in the industrial sector. Given that industry has shown an increased commitment to incorporating AI components, works focus on broadening the understanding of manufacturing sector stakeholders of what approaches could be considered within AI life-cycle, reducing the gap between principles and actionable requirements, and defining fundamental considerations based on risk management for incorporating, and managing, AI-based on responsible AI are required. In this work, we present a summary of the most suitable approaches that can be used for implementation and the lessons learned from a European Funded project (ASSISTANT).

6G systems, such as Large Intelligent Surfaces, will require distributed, complex, and coordinated decisions through-out a very heterogeneous and cell free infrastructure. This will require a fundamentally redesigned software infrastructure accompanied by massively distributed and heterogeneous computing resources, vastly different from current wireless networks. To address these challenges, in this paper, we propose and motivate the concept of a 6G Computing Continuum (6GCC) and two research testbeds, to advance the rate and quality of research. 6G Computing Continuum is an end-to-end compute and software platform for realizing large intelligent surfaces and its tenant users and applications. One for addressing the challenges or orchestrating shared computational resources in the wireless domain, implemented on a Large Intelligent Surfaces testbed. Another simulation-based testbed is intended to address scalability and global-scale orchestration challenges.