Task-oriented Age of Information for Remote Monitoring Systems

TL;DR

This paper introduces the Task-oriented Age of Information (TAoI) metric for remote monitoring systems, formulates an optimal transmission policy using MDPs, and demonstrates its effectiveness through simulations.

Contribution

It proposes a novel TAoI metric for task relevance, models the transmission problem as an MDP, and develops a threshold-based optimal policy for remote monitoring.

Findings

Optimal transmission policy is threshold-based regarding TAoI.

The proposed policy outperforms baseline policies in simulations.

The approach effectively minimizes task-relevant information age.

Abstract

The emergence of intelligent applications has fostered the development of a task-oriented communication paradigm, where a comprehensive, universal, and practical metric is crucial for unleashing the potential of this paradigm. To this end, we introduce an innovative metric, the Task-oriented Age of Information (TAoI), to measure whether the content of information is relevant to the system task, thereby assisting the system in efficiently completing designated tasks. Also, we study the TAoI in a remote monitoring system, whose task is to identify target images and transmit them for subsequent analysis. We formulate the dynamic transmission problem as a Semi-Markov Decision Process (SMDP) and transform it into an equivalent Markov Decision Process (MDP) to minimize TAoI and find the optimal transmission policy. Furthermore, we demonstrate that the optimal strategy is a threshold-based policy regarding TAoI and propose a relative value iteration algorithm based on the threshold structure to obtain the optimal transmission policy. Finally, simulation results show the superior performance of the optimal transmission policy compared to the baseline policies.