Minimizing Age of Information with Generate at Will Status Updates and Age-Agnostic Cyclic Scheduling

TL;DR

This work tackles minimizing weighted AoI in a multi-source GAW system by leveraging age-agnostic cyclic scheduling that depends only on the first two moments of per-source service times. It presents a closed-form optimal solution for the two-source case and a data-driven Insertion Search (IS) heuristic for general N, achieving O(1) decision-time and competitive AoI with lower complexity than age-aware methods. The authors derive exact mean AoI expressions for a given pattern and demonstrate substantial AoI reductions compared to round robin and probabilistic schemes, with IS approaching age-aware performance in many scenarios. The study also benchmarks IS against Whittle-index policies, showing favorable AoI with lower sampling costs and runtime, thus offering a practical, scalable approach for real-time scheduling in heterogeneous networks.

Abstract

We study the scheduling problem for a multi-source single-server generate-at-will (GAW) status update system with sources having heterogeneous service times and weights, with the goal of minimizing the weighted sum age of information (AoI). In particular, we study \emph{age-agnostic} schedulers which rely only on the first two moments of the source service times and they are relatively easier to implement than their age-aware counterparts which make use of the actual realizations of the service times. In particular, we focus on age-agnostic cyclic schedulers with $O(1)$ runtime complexity where status updates from multiple sources are scheduled according to a fixed finite transmission pattern. We first develop an analytical method to obtain the exact average AoI of each source when a transmission pattern is given. Then, we derive the optimum transmission pattern in closed form for the specific case of two sources. For general number of sources, we propose a novel algorithm, called IS (Insertion Search), for constructing transmission patterns, and we show that IS is capable of producing the optimum pattern for two-source systems, and it outperforms other existing age-agnostic schemes, for the case of more than two sources. Numerical examples are presented to showcase the effectiveness of the proposed approach.

Figures (8)

• Figure 1: Status update packets from $N$ information sources are collected by the base station (BS) employing an age-agnostic scheduler. A polling message is first sent to the scheduled source which in turn samples and transmits its status update packet to the BS using a certain modulation and coding scheme specific to the source.
• Figure 2: Sample path of the AoI/PAoI processes for source-$1$ for C-GAW with $P=[1,2,3,2]$.
• Figure 3: (a) System AoI $\mathbb{E} [\Delta]$ (b) $p_1^*$ for P-GAW$^*$ and $K_{n'}^*$ for C-GAW$^*$, depicted as a function of $s_2$ for exponentially distributed service times when $w_1 = 0.8, w_2=0.2, s_1=5.$
• Figure 4: (a) System AoI $\mathbb{E} [\Delta]$ (b) $p_1^*$ for P-GAW$^*$ and $K_1^*$ for C-GAW$^*$ ($n'=1$ for this example in all cases), depicted as a function of $q_2 \geq 225$, when $w_1 = 0.8, w_2=0.2, s_1=5, s_2=15$.
• Figure 5: System AoI as a function of the iteration index $K$ in the IS-$1$ algorithm when $N=50$ and for two values of the fixed scov parameter $c$ and the ratio parameter $r$: (a) scenario A (b) scenario B.

Theorems & Definitions (6)

• Lemma 1
• proof
• Lemma 2
• proof
• Theorem 1
• proof