Energy- and Network-Aware Orchestration of Serverless Applications Across the Cloud–Edge Continuum

Modern data-intensive applications, such as AI-driven Internet of Things (IoT) applications [1], require efficient processing of large-scale data generated at the edge of the network. The current trend leans towards deploying such applications closer to data sources along the cloud-edge continuum, ensuring lower latency, reduced bandwidth use, and energy efficiency. A promising model for developing and deploying applications on the cloud-edge continuum is serverless computing, and in particular the Function-as-a-Service (FaaS) model [2]. In the FaaS model, applications are built as dynamic compositions of functions that can be flexibly scaled and migrated along the cloud-edge continuum to optimise application objectives. Although applying the FaaS model to such applications is gaining increasing research attention [3,4], much further research is needed before practical, efficient solutions begin to emerge.

Indeed, managing complex, data-intensive FaaS applications across the cloud-edge continuum poses significant challenges. First, energy efficiency becomes a critical constraint at the edge, where nodes often operate under limited power budgets [5]. Existing orchestration solutions prioritise performance and cost but lack mechanisms to account for energy consumption when placing, scaling, or migrating functions. Second, the performance of FaaS applications strongly depends on the allocation of network resources [6] and on networking overheads [7]. Despite this dependency, network-aware optimisation remains largely unexplored for FaaS deployments across the cloud–edge continuum. Third, FaaS applications require cost-effective and efficient mechanisms for exchanging data among functions [8,9]. Cloud-based storage services, such as S3 from AWS, impose delays and incur operational costs, while edge-based services suffer from scarce bandwidth and limited resources.

This thesis will explore methods and tools for energy- and network-aware orchestration of data-intensive serverless applications across the cloud–edge continuum. Specifically, the thesis will develop intelligent management policies that jointly optimize performance and energy consumption under dynamic workloads in large-scale heterogeneous, cloud-edge environments. The work will include developing network management mechanisms for optimising latency and bandwidth as well as data management mechanisms for optimizing data exchange. The work will build upon and extend a framework for placing FaaS applications in fog environments, under development in the Magellan team [10]. Additionally, the work will leverage complementary research within the team on using reinforcement learning to develop a FaaS control plane that jointly optimises latency and energy reduction objectives [11]. The results will be evaluated through the deployment of various AI-based applications in both the Grid’5000 testbed and a fog infrastructure dedicated to environmental monitoring located at the Beaulieu campus.

Qualifications

• Excellent communication and writing skills
• Strong programming and scripting skills in Linux environments
• Knowledge and experience in one or more of the following areas: distributed systems, adaptive systems, FaaS, IoT, machine learning, cloud, edge