Decentralized Spatial Reuse Optimization in Wi-Fi: An Internal Regret Minimization Approach

TL;DR

The paper tackles decentralized spatial reuse optimization in dense Wi‑Fi by introducing an internal regret minimization approach based on regret-matching. By minimizing swap-based internal regret, autonomous devices implicitly coordinate to achieve higher global welfare without explicit signaling, addressing non-stationary multi-agent dynamics. Empirical results in toy and random deployments show that internal regret can outperform external regret and baseline configurations, delivering near-optimal performance and improved fairness. This work suggests a scalable alternative to centralized coordination (e.g., MAPC) for future Wi‑Fi architectures, aligning with the direction of IEEE 802.11bn toward flexible, low-signaling coordination.

Abstract

Spatial Reuse (SR) is a cost-effective technique for improving spectral efficiency in dense IEEE 802.11 deployments by enabling simultaneous transmissions. However, the decentralized optimization of SR parameters -- transmission power and Carrier Sensing Threshold (CST) -- across different Basic Service Sets (BSSs) is challenging due to the lack of global state information. In addition, the concurrent operation of multiple agents creates a highly non-stationary environment, often resulting in suboptimal global configurations (e.g., using the maximum possible transmission power by default). To overcome these limitations, this paper introduces a decentralized learning algorithm based on regret-matching, grounded in internal regret minimization. Unlike standard decentralized ``selfish'' approaches that often converge to inefficient Nash Equilibria (NE), internal regret minimization guides competing agents toward Correlated Equilibria (CE), effectively mimicking coordination without explicit communication. Through simulation results, we showcase the superiority of our proposed approach and its ability to reach near-optimal global performance. These results confirm the not-yet-unleashed potential of scalable decentralized solutions and question the need for the heavy signaling overheads and architectural complexity associated with emerging centralized solutions like Multi-Access Point Coordination (MAPC).

Figures (5)

• Figure 1: Two , each comprising one and one , coexist within the same area. The sensitivity range from AP$_B$ indicates whether the transmissions from AP$_A$ are ignored (AP$_A$ is outside the circle) or not (AP$_A$ is inside the circle). P$_X$ and S$_Y$ denote the power and sensitivity used by $X$ and $Y$, respectively.
• Figure 2: Considered 2-BSS scenario.
• Figure 3: Mean average throughput (in Mbps) obtained by the two BSSs in the scenario encompassing strong and weak equilibrium situations.
• Figure 4: Actions selected by the two BSSs per iteration in each scenario. Actions available (CST, transmit power): $A_1$ = {-72, 10} dBm, $A_2$ = {-72, 20} dBm, $A_3$ = {-82, 10} dBm, $A_4$ = {-82, 20} dBm.
• Figure 5: Mean (solid bars) and minimum (dashed bars) average throughput achieved across random deployments.