In-network placement of delay-constrained computing tasks in a softwarized intelligent edge

Future sixth-generation (6G) networks will rely on the synergies of edge computing and machine learning (ML) to build an intelligent edge, where communication resources be jointly orchestrated. In this work, we leverage ML algorithms judiciously orchestrate placement delay-constrained tasks in a softwarized domain. A set popular supervised algorithms, i.e., Decision Tree (DT), Bagged Trees (BTs), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), have been leveraged purpose. They are trained off-line through results optimization problem targeting minimization network resource usage while respecting tasks’ delay constraints. Extensive simulation reported showcase performance considered techniques terms model accuracy, complexity network-related metrics, e.g., amount exchanged data Among compared techniques, DT MLP shown most efficient solutions algorithm execution time, by achieving almost same performance.