D1.1 - State of the Art Analysis

The aim of the AI-SPRINT “Artificial intelligence in Secure PRIvacy-preserving computing coNTinuum” project is to develop a platform composed of design and runtime management tools to seamlessly design, partition and operate Artificial Intelligence (AI) applications among the current plethora of cloud-based solutions and AI-based sensor devices (i.e., devices with intelligence and data processing capabilities), providing resource efficiency, performance, data privacy, and security guarantees.
The aim of this deliverable is to review the state-of-the-art in techniques used in the development and operation of AI applications in computing continua and the related technologies. The deliverable starts with an overview of AI applications and edge computing market trends. It examines the standardisation and opensource landscape, where many of the emerging standards are mainly focused on the network layer, also highlighting opportunities for open-source community involvement to expand technology availability. Then, the deliverable provides a background on AI applications design, also considering some advanced design trends (e.g., Network Architecture Search, Federated Learning, Deep Neural Networks partitioning) introducing the software development frameworks and hardware solutions which allow to run such applications in a computing continuum.
We then report an overview of the state-of-the-art of the solutions offered by the main cloud market players and the European providers. We also extensively discuss existing solutions for applications deployment, monitoring, runtime management, and scheduling considering the emerging Function as a Service paradigm.
In the last part of the deliverable, we report an overview of the performance modelling solutions, security, and privacy problems for AI applications in edge environments. It is found that some areas, such as component placement and design space exploration with privacy preservation and performance guarantees, are fairly under-developed, since solutions tailored for AI applications are lacking, and thus offer an opportunity for innovation.