Goal-oriented semantic resource allocation with cumulative prospect theoretic agents

Vaidanis, Symeon; Stavrou, Photios A.; Kountouris, Marios
ICC 2025, IEEE International Conference on Communications, 8-12 June 2025, Montreal, Canada

We introduce a resource allocation framework for goal-oriented semantic networks, where participating agents assess system quality through subjective (e.g., context-dependent)
perceptions. To accommodate this, our model accounts for agents whose preferences deviate from traditional expected utility theory (EUT), specifically incorporating cumulative prospect theory (CPT) preferences. We develop a comprehensive analytical
framework that captures human-centric aspects of decision-making and risky choices under uncertainty, such as risk perception, loss aversion, and perceptual distortions in
probability metrics. By identifying essential modifications in traditional resource allocation design principles required for agents with CPT preferences, we showcase the framework’s relevance through its application to the problem of power allocation in multi-channel wireless communication systems.

Type:
Conference
City:
Montreal
Date:
2025-06-08
Department:
Communication systems
Eurecom Ref:
8257
Copyright:
© 2025 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PERMALINK : https://www.eurecom.fr/publication/8257