Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Goal-Oriented Medium Access with Distributed Belief Processing

Federico Chiariotti, Andrea Munari, Leonardo Badia, Petar Popovski

TL;DR

The paper tackles goal-oriented communication in dense sensor networks by introducing DELTA, a distributed MAC that leverages dynamic epistemic logic and common knowledge to minimize the Age of Incorrect Information ($\mathrm{AoII}$). By modeling four public-feedback-driven phases and applying Bayes-like belief updates, DELTA achieves collision-aware access with provable collision-resolution optimization and scalable belief management, including the DELTA+ variant and belief-threshold strategies. Simulation results show substantial improvements over random access and competitive gains over centralized scheduling, especially as the network scales, and the framework demonstrates resilience to imperfect feedback. The approach offers a principled, scalable path toward efficient anomaly reporting in large sensor networks and lays groundwork for richer epistemic-model extensions and more complex anomaly dynamics.

Abstract

Goal-oriented communication entails the timely transmission of updates related to a specific goal defined by the application. In a distributed setup with multiple sensors, each individual sensor knows its own observation and can determine its freshness, as measured by Age of Incorrect Information (AoII). This local knowledge is suited for distributed medium access, where the transmission strategies have to deal with collisions. We present Dynamic Epistemic Logic for Tracking Anomalies (DELTA), a medium access protocol that limits collisions and minimizes AoII in anomaly reporting over dense networks. Each sensor knows its own AoII, while it can compute the belief about the AoII for all other sensors, based on their Age of Information (AoI), which is inferred from the acknowledgments. This results in a goal-oriented approach based on dynamic epistemic logic emerging from public information. We analyze the resulting DELTA protocol both from a theoretical standpoint and with Monte Carlo simulations, showing that it is significantly more efficient and robust than classical random access, while outperforming state-of-the-art scheduled schemes by at least 30%, even with imperfect feedback.

Goal-Oriented Medium Access with Distributed Belief Processing

TL;DR

The paper tackles goal-oriented communication in dense sensor networks by introducing DELTA, a distributed MAC that leverages dynamic epistemic logic and common knowledge to minimize the Age of Incorrect Information (). By modeling four public-feedback-driven phases and applying Bayes-like belief updates, DELTA achieves collision-aware access with provable collision-resolution optimization and scalable belief management, including the DELTA+ variant and belief-threshold strategies. Simulation results show substantial improvements over random access and competitive gains over centralized scheduling, especially as the network scales, and the framework demonstrates resilience to imperfect feedback. The approach offers a principled, scalable path toward efficient anomaly reporting in large sensor networks and lays groundwork for richer epistemic-model extensions and more complex anomaly dynamics.

Abstract

Goal-oriented communication entails the timely transmission of updates related to a specific goal defined by the application. In a distributed setup with multiple sensors, each individual sensor knows its own observation and can determine its freshness, as measured by Age of Incorrect Information (AoII). This local knowledge is suited for distributed medium access, where the transmission strategies have to deal with collisions. We present Dynamic Epistemic Logic for Tracking Anomalies (DELTA), a medium access protocol that limits collisions and minimizes AoII in anomaly reporting over dense networks. Each sensor knows its own AoII, while it can compute the belief about the AoII for all other sensors, based on their Age of Information (AoI), which is inferred from the acknowledgments. This results in a goal-oriented approach based on dynamic epistemic logic emerging from public information. We analyze the resulting DELTA protocol both from a theoretical standpoint and with Monte Carlo simulations, showing that it is significantly more efficient and robust than classical random access, while outperforming state-of-the-art scheduled schemes by at least 30%, even with imperfect feedback.

Paper Structure

This paper contains 15 sections, 5 theorems, 33 equations, 12 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Model
  4. The DELTA Protocol
  5. Protocol Definition and Correctness
  6. Collision Resolution Phase Optimization
  7. DELTA+
  8. Belief Threshold Optimization
  9. Dealing with Imperfect Feedback
  10. Simulation Settings and Results
  11. DELTA Optimization and Robustness
  12. Benchmark Protocols
  13. Performance Evaluation: Ideal Feedback
  14. Performance Evaluation: Imperfect Feedback
  15. Conclusion and Future Work

Key Result

Lemma \inteval0+1.1

Under an ideal or noisy feedback channel, as long as the system remains in the phase, all sensors are in state $0$, and the state is common knowledge.

Figures (12)

  • Figure 1: Example of the AoI and AoII evolution for a node.
  • Figure 2: DELTA state diagram.
  • Figure 3: Approximated semi-Markov model of the system with $K=3N$ and $\Psi=4$.
  • Figure 4: $\pi(\text{ZW})$ as a function of $K$.
  • Figure 5: Optimal transmission probability for each consecutive round for different values of $\rho$, with $N=20$ and $\varepsilon=0.05$.
  • ...and 7 more figures

Theorems & Definitions (5)

  • Lemma \inteval0+1.1
  • Lemma \inteval0+1.2
  • Theorem 1
  • Theorem 2
  • Theorem 3