# Optimized Age of Information Tail for Ultra-Reliable Low-Latency Communications in Vehicular Networks

arXiv: https://arxiv.org/abs/1912.07981 · HTML: https://mlsanity.com/paper/1912.07981/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2019.

## Built on by (most cited first, 4 of 4)

- [Deep-Reinforcement-Learning-Based AoI-Aware Resource Allocation for RIS-Aided IoV Networks](https://mlsanity.com/paper/2406.11245/) (2024)
- [Non-orthogonal Age-Optimal Information Dissemination in Vehicular Networks: A Meta Multi-Objective Reinforcement Learning Approach](https://mlsanity.com/paper/2402.12260/) (2024)
- [Event-Triggered Reinforcement Learning Based Joint Resource Allocation for Ultra-Reliable Low-Latency V2X Communications](https://mlsanity.com/paper/2407.13947/) (2024)
- [Federated Learning with Correlated Data: Taming the Tail for Age-Optimal Industrial IoT](https://mlsanity.com/paper/2108.07504/) (2021)

## Abstract (arXiv)

While the notion of age of information (AoI) has recently been proposed for analyzing ultra-reliable low-latency communications (URLLC), most of the existing works have focused on the average AoI measure. Designing a wireless network based on average AoI will fail to characterize the performance of URLLC systems, as it cannot account for extreme AoI events, occurring with very low probabilities. In contrast, this paper goes beyond the average AoI to improve URLLC in a vehicular communication network by characterizing and controlling the AoI tail distribution. In particular, the transmission power minimization problem is studied under stringent URLLC constraints in terms of probabilistic AoI for both deterministic and Markovian traffic arrivals. Accordingly, an efficient novel mapping between AoI and queue-related distributions is proposed. Subsequently, extreme value theory (EVT) and Lyapunov optimization techniques are adopted to formulate and solve the problem considering both long and short packets transmissions. Simulation results show over a two-fold improvement, in shortening the AoI distribution tail, versus a baseline that models the maximum queue length distribution, in addition to a tradeoff between arrival rate and AoI.