TrialsNet

The AdaptoFlow service supports AI/ML inference and data stream processing for applications deployed in geo-distributed realms so that data movement, energy consumption, and app-level latency are reduced by adapting the intensity of the execution at runtime. Adaptation will consider the evolution of IoT-generated data and the state of the underlying computational resources of edge nodes while maintaining acceptable QoS guarantees requested by application operators. Specifically, the service dynamically adjusts monitoring intensity based on data behaviour (e.g., variance) to reduce processing load and optimise resource use during low-volatility periods. Additionally, it enables on-the-fly AI/ML model replacement with less complex alternatives under resource constraints, saving energy while maintaining acceptable latency and performance. These intelligent mechanisms optimise resource utilisation, improve responsiveness, and ensure user-desired quality levels.