Cooperative RSU Sleep Scheduling for Green V2I Corridors

A Constrained MDP Framework for Energy-Efficient Roadside Unit Coordination

Yousef AlSaqabi· 2026· DOI 10.48550/arXiv.2606.29609

The core problem

As vehicle-to-infrastructure (V2I) deployments scale, roadside units (RSUs) that consume 10-25W continuously yet serve negligible traffic during off-peak hours represent a growing source of energy waste. Sleep scheduling can exploit the pronounced diurnal variation in urban traffic, but the WAVE service restoration overhead of up to 100ms nearly exhausts the 3GPP TS 22.185 latency budget, making independent sleep decisions risky. This paper proposes a cooperative framework in which upstream RSUs share traffic detection signals with downstream neighbors via infrastructure-to-infrastructure links, enabling predictive wake-up that exploits spatial correlation between adjacent intersections.

The cooperative algorithm reduces corridor energy consumption by 59.5% relative to always-on operation while maintaining 99% latency compliance. It provides 7.7 percentage points of additional savings over independent per-RSU optimization at downstream RSUs with spatial correlation ρ \geq 0.97 . Extrapolated to a 200-RSU urban deployment, the cooperative approach yields an estimated 5.25 tonnes of CO2 reduction per year. The energy savings are achieved without violating the 3GPP TS 22.185 latency budget, as the predictive wake-up mechanism ensures service restoration before vehicle arrival.

As vehicle-to-infrastructure (V2I) deployments scale, roadside units (RSUs) that consume 10-25W continuously yet serve negligible traffic during off-peak hours represent a growing source of energy waste. Sleep scheduling can exploit the pronounced diurnal variation in urban traffic, but the WAVE service restoration overhead of up to 100ms nearly exhausts the 3GPP TS 22.185 latency budget, making independent sleep decisions risky. This paper proposes a cooperative framework in which upstream RSUs share traffic detection signals with downstream neighbors via infrastructure-to-infrastructure links, enabling predictive wake-up that exploits spatial correlation between adjacent intersections.

The cooperative sleep scheduling problem is formulated as a constrained Markov decision process (CMDP) to minimize energy consumption while satisfying latency constraints. The CMDP is decomposed into per-RSU subproblems solvable by value iteration. Four algorithms of increasing sophistication are evaluated: (1) always-on baseline, (2) independent per-RSU optimization, (3) cooperative with upstream signaling, and (4) cooperative with predictive wake-up. The framework is tested on real hourly traffic data from four consecutive signalized intersections in Kuwait City, comprising a total of 762,050 vehicles over five days. The spatial correlation between adjacent intersections is measured, with downstream RSUs exhibiting correlation ρ \geq 0.97 .

The results demonstrate that exploiting spatial correlation between adjacent intersections through cooperative signaling significantly enhances energy efficiency in V2I corridors. The 7.7 percentage point improvement over independent optimization highlights the value of infrastructure-to-infrastructure communication. The CMDP formulation effectively balances the trade-off between energy consumption and latency, with value iteration providing a computationally tractable solution. The estimated CO2 reduction of 5.25 tonnes per year for a 200-RSU deployment underscores the environmental impact of green V2I design. Future work could extend the framework to heterogeneous traffic patterns and larger urban networks.

CS practitioners and researchers

Opening member content…