ENACT - A Framework for Adaptive Scheduling and Deployments of Data Intensive Workloads on Energy Efficient Edge to Cloud Continuum
Alexandros Nizamis, Juergen Neises, Diego Ospina, Usman Wajid, Clara I. Valero, Panagiotis T. Trakadas, Konstantinos Votis, Óscar Lázaro, Septimiu Nechifor, Carlos Enrique Palau · 2024
In the last couple of decades, enterprises have relished and leveraged the capacity, performance, scalability, and quality of cloud computing services. However, a few years ago, the edge computing concept enabled data processing and application execution near compute and data resources, aiming to reduce latency and promote higher security and sovereignty regarding data transfers. The simultaneous use of these two service models by enterprises has lately resulted in the concept of edge-to-cloud continuum, which combines edge and cloud technologies and promotes standards and algorithms for resource orchestration, data management, and the deployment of solutions across the connected edge and cloud resources. Taking a step further in this direction, this paper introduces a framework to realise the Cognitive Computing Continuum (CCC). The framework leverages AI techniques to address the needs for optimal (edge and cloud) resource management and dynamic scaling, elasticity, and portability of hyper-distributed data-intensive applications. The proposed ENACT framework enables the automated management of distributed (edge and cloud) resources and the development of hyper-distributed applications that can take advantage of distributed deployment and execution opportunities to optimize their behaviors in terms of execution time, resource utilisation and energy efficiency.