Goal-oriented multiple access connectivity for networked intelligent systems

We design a self-decision goal-oriented multiple access scheme, where sensing agents observe a common event and individually decide to communicate the event’s attributes to the monitoring agents, to satisfy a certain goal. Decisions are based on the usefulness of contents, which are generated under uniform, change- and semantics-aware content acquisition, as well as statistics and contents of other agents. We obtain optima l activation probabilities and threshold criteria for decision-making under all schemes, maximizing a grade of effectiveness metric. Combined with a semantics-aware acquisition scheme, the selfdecision scheme offers, on average, 29.52% higher effectiveness, 25 .13% fewer drop-offs, and 67 .21% fewer transmissions.