The reviewed record of science sign in
Pith

arxiv: 2606.29609 · v1 · pith:JEHORJKZ · submitted 2026-06-28 · cs.NI · cs.SY· eess.SY

Cooperative RSU Sleep Scheduling for Green V2I Corridors

Yousef AlSaqabi This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel 2026-06-30 01:37 UTCgrok-4.3pith:JEHORJKZrecord.jsonopen to challenge →

classification cs.NI cs.SYeess.SY
keywords RSUsleep schedulingV2Ienergy efficiencycooperative frameworkMarkov decision processlatencyspatial correlation
0
0 comments X

The pith

Cooperative RSU scheduling reduces corridor energy consumption by 59.5% while maintaining 99% latency compliance

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Roadside units for vehicle-to-infrastructure communication use continuous power even during low traffic periods, leading to unnecessary energy use. The paper develops a cooperative approach where upstream units share detection information to wake downstream units in advance. This uses spatial correlation in traffic flows to schedule sleep periods safely within tight latency limits. Evaluation on real data shows substantial energy cuts compared to both always-on and independent scheduling approaches. The work targets the growing energy footprint of scaled V2I deployments in urban corridors.

Core claim

The paper claims that formulating RSU sleep decisions as a constrained Markov decision process and decomposing it for cooperative solution via value iteration allows predictive wake-up using shared signals from upstream RSUs. On data from four consecutive intersections recording 762050 vehicles, this yields 59.5% energy reduction versus always-on operation with 99% latency compliance, plus 7.7 percentage points more savings than independent optimization when spatial correlation reaches 0.97 or above. Scaling to 200 RSUs projects 5.25 tonnes annual CO2 reduction.

What carries the argument

The cooperative constrained Markov decision process decomposed into per-RSU subproblems solved by value iteration, driven by shared upstream traffic detection signals to enable predictive wake-up.

Load-bearing premise

Upstream RSUs can share traffic detection signals with downstream neighbors via I2I links to enable predictive wake-up without adding overhead that violates the 3GPP TS 22.185 latency budget.

What would settle it

If measurements on the four Kuwait City intersections show that the cooperative policy results in less than 99% of vehicles meeting the latency requirement, the energy savings claim would not hold under the paper's constraints.

Figures

Figures reproduced from arXiv: 2606.29609 by Yousef AlSaqabi.

Figure 1
Figure 1. Figure 1: Average hourly traffic profiles for intersections I1–I4 and the corridor aggregate, comparing [PITH_FULL_IMAGE:figures/full_fig_p008_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Energy savings by algorithm and intersection. The cooperative algorithm achieves 59.5% corridor [PITH_FULL_IMAGE:figures/full_fig_p021_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Energy savings by day type. All algorithms save more on weekends (Gulf Friday–Saturday). [PITH_FULL_IMAGE:figures/full_fig_p023_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: RSU power state schedule for Sunday, August 17 (weekday). PFS sleeps during a fixed overnight [PITH_FULL_IMAGE:figures/full_fig_p023_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Corridor-level latency violation rates by algorithm, with the [PITH_FULL_IMAGE:figures/full_fig_p024_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Cooperation benefit as a function of MDP state granularity. Left: MDP (dashed) vs. cooperative [PITH_FULL_IMAGE:figures/full_fig_p026_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Energy savings vs. latency SLA threshold [PITH_FULL_IMAGE:figures/full_fig_p027_7.png] view at source ↗
read the original abstract

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 3GPPTS~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 framework is formulated as a constrained Markov decision process and decomposed into per-RSU subproblems solvable by value iteration. Four algorithms of increasing sophistication are evaluated on real hourly traffic data from four consecutive signalized intersections in Kuwait City, comprising a total of 762,050 vehicles over five days. The cooperative algorithm reduces corridor energy consumption by 59.5% relative to always-on operation while maintaining 99% latency compliance, and provides 7.7 percentage points of additional savings over independent per-RSU optimization at downstream RSUs with spatial correlation \r{ho} >= 0.97. Extrapolated to a 200-RSU urban deployment, the cooperative approach yields an estimated 5.25 tonnes of CO2 reduction per year.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper proposes a cooperative RSU sleep scheduling framework for V2I corridors formulated as a constrained Markov decision process (CMDP) that is decomposed into per-RSU subproblems solved by value iteration. Upstream RSUs share traffic detection signals with downstream neighbors over I2I links to enable predictive wake-up that exploits spatial correlation. On real hourly traffic data from four consecutive intersections in Kuwait City (762050 vehicles over five days), the cooperative algorithm is reported to reduce corridor energy consumption by 59.5% relative to always-on operation while achieving 99% latency compliance and 7.7 percentage points of additional savings over independent per-RSU optimization when spatial correlation rho >= 0.97; the result is extrapolated to 5.25 tonnes CO2/year for a 200-RSU deployment.

Significance. If the I2I overhead is shown to fit inside the remaining latency budget, the work supplies a concrete, data-driven method for reducing the energy footprint of scaled V2I infrastructure while respecting 3GPP latency bounds, with the real-traffic evaluation and CMDP decomposition constituting clear strengths.

major comments (2)
  1. [CMDP formulation] CMDP formulation and value-iteration decomposition: the latency constraint treats the cooperative I2I action as cost-free, yet the manuscript does not demonstrate that the added transmission/queuing delay of the predictive wake-up signal, when summed with the up to 100 ms WAVE restoration overhead, remains inside the 3GPP TS 22.185 budget; this omission directly affects the validity of the 99% compliance claim.
  2. [Evaluation] Evaluation on Kuwait City traces: realistic I2I latency is not injected into the per-RSU subproblems, so the reported energy savings and latency compliance figures rest on an unverified assumption that the cooperative signaling overhead is negligible.
minor comments (2)
  1. The abstract states quantitative results but the main text should supply error bars, exact data-split details, and the precise definition of the latency metric used for the 99% figure.
  2. Notation for the spatial correlation coefficient rho should be introduced earlier and used consistently.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback highlighting the need to explicitly address I2I signaling delays. We agree that the original formulation and evaluation treated these delays as negligible without verification against the 3GPP budget when combined with WAVE overhead. Below we respond point-by-point and commit to revisions that incorporate latency analysis.

read point-by-point responses

  1. Referee: [CMDP formulation] CMDP formulation and value-iteration decomposition: the latency constraint treats the cooperative I2I action as cost-free, yet the manuscript does not demonstrate that the added transmission/queuing delay of the predictive wake-up signal, when summed with the up to 100 ms WAVE restoration overhead, remains inside the 3GPP TS 22.185 budget; this omission directly affects the validity of the 99% compliance claim.

    Authors: We acknowledge that the CMDP latency constraint modeled I2I signaling as cost-free. The manuscript assumed dedicated I2I links incur delays well below the remaining budget after the 100 ms WAVE overhead. To address the concern, the revised manuscript will add an explicit assumption statement in Section 3 and a new sensitivity subsection in the evaluation that derives an upper bound on I2I delay (transmission + queuing) and recomputes the compliance probability under that bound, confirming whether 99% is preserved. revision: yes

  2. Referee: [Evaluation] Evaluation on Kuwait City traces: realistic I2I latency is not injected into the per-RSU subproblems, so the reported energy savings and latency compliance figures rest on an unverified assumption that the cooperative signaling overhead is negligible.

    Authors: The evaluation on the Kuwait City traces did not inject I2I latency into the value-iteration subproblems. We will revise the evaluation to include additional experiments that sample I2I delays from a realistic distribution (e.g., 5–20 ms) and re-execute the cooperative policy, reporting updated energy savings and compliance figures. This will either substantiate the negligible-overhead assumption or quantify its sensitivity. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation is self-contained

full rationale

The paper formulates the problem as a constrained Markov decision process (CMDP) decomposed into per-RSU subproblems solved via value iteration, then evaluates the resulting policies on external real-world hourly traffic traces from Kuwait City (762050 vehicles). No load-bearing step reduces to a fitted parameter renamed as prediction, a self-citation chain, an ansatz smuggled via prior work, or a self-definitional equivalence. The 59.5% energy reduction and 99% latency compliance are reported outcomes of applying the algorithms to the independent dataset, not quantities forced by construction from the model inputs themselves.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Review based on abstract only; no free parameters, invented entities, or detailed axioms are extractable beyond the stated latency constraint.

axioms (1)
  • domain assumption WAVE service restoration overhead reaches up to 100ms and nearly exhausts the 3GPP TS 22.185 latency budget, making independent sleep decisions risky.
    Invoked in abstract to motivate the cooperative approach.

pith-pipeline@v0.9.1-grok · 5778 in / 1073 out tokens · 30344 ms · 2026-06-30T01:37:18.177697+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

34 extracted references

  1. [1]

    How much energy is needed to run a wireless network?

    G. Auer, V . Giannini, C. Desset, I. Godor, P. Skillermark, M. Olsson, M. A. Imran, D. Sabella, M. J. Gonzalez, O. Blumeet al., “How much energy is needed to run a wireless network?”IEEE wireless communications, vol. 18, no. 5, pp. 40–49, 2011

    2011

  2. [2]

    MK5 RSU datasheet,

    Cohda Wireless, “MK5 RSU datasheet,” Product datasheet, 2020. [Online]. Available: https://cohdawireless.com/solutions/hardware/ mk5-rsu/

    2020

  3. [3]

    MK6 RSU product brief,

    ——, “MK6 RSU product brief,” Product brief, 2022. [Online]. Available: https://cohdawireless.com/solutions/hardware/mk6-rsu/

    2022

  4. [4]

    ITS-RS4 high-performance V2X enabled roadside unit,

    Commsignia, “ITS-RS4 high-performance V2X enabled roadside unit,” Product brief, 2020. [Online]. Available: https: //commsignia.com/products/rsu

    2020

  5. [5]

    Traffic monitoring guide,

    Federal Highway Administration, “Traffic monitoring guide,” U.S. Department of Transportation, Federal Highway Administration, Washington, DC, Report FHW A-PL-17-003, 2022, office of Highway Policy Information

    2022

  6. [6]

    Energy-efficient base-stations sleep-mode techniques in green cellular networks: A survey,

    J. Wu, Y . Zhang, M. Zukerman, and E. K.-N. Yung, “Energy-efficient base-stations sleep-mode techniques in green cellular networks: A survey,”IEEE communications surveys & tutorials, vol. 17, no. 2, pp. 803–826, 2015

    2015

  7. [7]

    Sleep-enabled roadside units for motorway vehicular networks,

    S. Bhattacharya, B. R. Qazi, A. Muhtar, W. Kumar, and J. M. Elmirghani, “Sleep-enabled roadside units for motorway vehicular networks,”Vehicular Communications, vol. 7, pp. 21–39, 2017

    2017

  8. [8]

    Service requirements for V2X services,

    3GPP, “Service requirements for V2X services,” 3rd Generation Partnership Project, TS 22.185, Jun. 2018, v15.0.0

    2018

  9. [9]

    IEEE standard for wireless access in vehicular environments (W A VE) – multi-channel operation,

    IEEE, “IEEE standard for wireless access in vehicular environments (W A VE) – multi-channel operation,” Institute of Electrical and Electronics Engineers, Std 1609.4-2016, 2016

    2016

  10. [10]

    Cell zooming for cost-efficient green cellular networks,

    Z. Niu, Y . Wu, J. Gong, and Z. Yang, “Cell zooming for cost-efficient green cellular networks,”IEEE communications magazine, vol. 48, no. 11, pp. 74–79, 2010

    2010

  11. [11]

    Traffic-aware base station sleeping control and power matching for energy-delay tradeoffs in green cellular networks,

    J. Wu, S. Zhou, and Z. Niu, “Traffic-aware base station sleeping control and power matching for energy-delay tradeoffs in green cellular networks,”IEEE Transactions on Wireless Communications, vol. 12, no. 8, pp. 4196–4209, 2013

    2013

  12. [12]

    Deepnap: Data-driven base station sleeping operations through deep reinforcement learning,

    J. Liu, B. Krishnamachari, S. Zhou, and Z. Niu, “Deepnap: Data-driven base station sleeping operations through deep reinforcement learning,”IEEE Internet of Things Journal, vol. 5, no. 6, pp. 4273–4282, 2018

    2018

  13. [13]

    Deep reinforcement learning with spatio-temporal traffic forecasting for data-driven base station sleep control,

    Q. Wu, X. Chen, Z. Zhou, L. Chen, and J. Zhang, “Deep reinforcement learning with spatio-temporal traffic forecasting for data-driven base station sleep control,”IEEE/ACM transactions on networking, vol. 29, no. 2, pp. 935–948, 2021

    2021

  14. [14]

    Energy-efficient scheduling in green vehicular infrastructure with multiple roadside units,

    A. Khezrian, T. D. Todd, G. Karakostas, and M. Azimifar, “Energy-efficient scheduling in green vehicular infrastructure with multiple roadside units,”IEEE Transactions on Vehicular Technology, vol. 64, no. 5, pp. 1942–1957, 2014

    1942

  15. [15]

    Event driven duty cycling: an efficient power management scheme for a solar-energy harvested road side unit,

    Q. I. Ali, “Event driven duty cycling: an efficient power management scheme for a solar-energy harvested road side unit,”IET Electrical Systems in Transportation, vol. 6, no. 3, pp. 222–235, 2016

    2016

  16. [16]

    Performance evaluation of joint placement and sleep scheduling of grid-connected solar powered road side units in vehicular networks,

    M. Patra and C. S. R. Murthy, “Performance evaluation of joint placement and sleep scheduling of grid-connected solar powered road side units in vehicular networks,”IEEE Transactions on Green Communications and Networking, vol. 2, no. 4, pp. 1197–1209, 2018

    2018

  17. [17]

    Energy efficiency of cooperative base station sleep scheduling for vehicular networks,

    T. Han, Z. Zhang, M. Hu, G. Mao, X. Ge, Q. Li, and L. Wang, “Energy efficiency of cooperative base station sleep scheduling for vehicular networks,” in2014 IEEE 79th Vehicular Technology Conference (VTC Spring). IEEE, 2014, pp. 1–5

    2014

  18. [18]

    A power-saving model for roadside unit deployment in vehicular networks,

    S.-I. Sou, “A power-saving model for roadside unit deployment in vehicular networks,”IEEE Communications Letters, vol. 14, no. 7, pp. 623–625, 2010. IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING 31

    2010

  19. [19]

    On/off sleep scheduling in energy efficient vehicular roadside infrastructure,

    S. Mostofi, A. Hammad, T. D. Todd, and G. Karakostas, “On/off sleep scheduling in energy efficient vehicular roadside infrastructure,” in2013 IEEE International Conference on Communications (ICC). IEEE, 2013, pp. 6266–6271

    2013

  20. [20]

    Downlink traffic scheduling in green vehicular roadside infrastructure,

    A. A. Hammad, T. D. Todd, G. Karakostas, and D. Zhao, “Downlink traffic scheduling in green vehicular roadside infrastructure,” IEEE Transactions on Vehicular Technology, vol. 62, no. 3, pp. 1289–1302, 2012

    2012

  21. [21]

    A flexible and future-proof power model for cellular base stations,

    B. Debaillie, C. Desset, and F. Louagie, “A flexible and future-proof power model for cellular base stations,” in2015 IEEE 81st vehicular technology conference (VTC Spring). IEEE, 2015, pp. 1–7

    2015

  22. [22]

    Greenbsn: Enabling energy-proportional cellular base station networks,

    C. Peng, S.-B. Lee, S. Lu, and H. Luo, “Greenbsn: Enabling energy-proportional cellular base station networks,”IEEE Transactions on Mobile Computing, vol. 13, no. 11, pp. 2537–2551, 2014

    2014

  23. [23]

    Energy saving of base stations sleep scheduling for multi-hop vehicular networks,

    T. Han, X. Liu, L. Wang, J. Wang, K. S. Kwak, and Q. Li, “Energy saving of base stations sleep scheduling for multi-hop vehicular networks,” in2016 IEEE International Conference on Communications (ICC). IEEE, 2016, pp. 1–5

    2016

  24. [24]

    Optimal base station sleeping in green cellular networks: A distributed cooperative framework based on game theory,

    J. Zheng, Y . Cai, X. Chen, R. Li, and H. Zhang, “Optimal base station sleeping in green cellular networks: A distributed cooperative framework based on game theory,”IEEE Transactions on Wireless Communications, vol. 14, no. 8, pp. 4391–4406, 2015

    2015

  25. [25]

    Power consumption and gos tradeoff in cellular mobile networks with base station sleeping and related performance studies,

    J. Wu, E. W. Wong, Y .-C. Chan, and M. Zukerman, “Power consumption and gos tradeoff in cellular mobile networks with base station sleeping and related performance studies,”IEEE Transactions on Green Communications and Networking, vol. 4, no. 4, pp. 1024–1036, 2020

    2020

  26. [26]

    A survey of energy-efficient techniques for 5g networks and challenges ahead,

    S. Buzzi, I. Chih-Lin, T. E. Klein, H. V . Poor, C. Yang, and A. Zappone, “A survey of energy-efficient techniques for 5g networks and challenges ahead,”IEEE Journal on selected areas in communications, vol. 34, no. 4, pp. 697–709, 2016

    2016

  27. [27]

    Power consumption modeling of different base station types in heterogeneous cellular networks,

    O. Arnold, F. Richter, G. Fettweis, and O. Blume, “Power consumption modeling of different base station types in heterogeneous cellular networks,” inProceedings of the ICT MobileSummit (ICT Summit’10), Florence, Italy, 07 2010, pp. 1 – 8

    2010

  28. [28]

    Analytical approach to base station sleep mode power consumption and sleep depth,

    O. Onireti, A. Mohamed, H. Pervaiz, and M. Imran, “Analytical approach to base station sleep mode power consumption and sleep depth,” in2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC). IEEE, 2017, pp. 1–7

    2017

  29. [29]

    Improving energy efficiency of femtocell base stations via user activity detection,

    I. Ashraf, L. T. Ho, and H. Claussen, “Improving energy efficiency of femtocell base stations via user activity detection,” in2010 IEEE wireless communication and networking conference. IEEE, 2010, pp. 1–5

    2010

  30. [30]

    Base-station sleeping control and power matching for energy–delay tradeoffs with bursty traffic,

    J. Wu, Y . Bao, G. Miao, S. Zhou, and Z. Niu, “Base-station sleeping control and power matching for energy–delay tradeoffs with bursty traffic,”IEEE Transactions on Vehicular Technology, vol. 65, no. 5, pp. 3657–3675, 2015

    2015

  31. [31]

    Energy savings through dynamic base station switching in cellular wireless access networks,

    E. Oh and B. Krishnamachari, “Energy savings through dynamic base station switching in cellular wireless access networks,” in2010 IEEE Global Telecommunications Conference GLOBECOM 2010. IEEE, 2010, pp. 1–5

    2010

  32. [32]

    Intelligent transport systems (ITS); vehicular communications; basic set of applications; part 2: Specification of cooperative awareness basic service,

    ETSI, “Intelligent transport systems (ITS); vehicular communications; basic set of applications; part 2: Specification of cooperative awareness basic service,” European Telecommunications Standards Institute, EN 302 637-2, Apr. 2019, v1.4.1

    2019

  33. [33]

    Dsrc versus 4g-lte for connected vehicle applications: a study on field experiments of vehicular communication performance,

    Z. Xu, X. Li, X. Zhao, M. H. Zhang, and Z. Wang, “Dsrc versus 4g-lte for connected vehicle applications: a study on field experiments of vehicular communication performance,”Journal of advanced transportation, vol. 2017, no. 1, p. 2750452, 2017

    2017

  34. [34]

    The complexity of markov decision processes,

    C. H. Papadimitriou and J. N. Tsitsiklis, “The complexity of markov decision processes,”Mathematics of operations research, vol. 12, no. 3, pp. 441–450, 1987

    1987