Researchers funded by the University of Hail have developed a smart framework that combines optimization algorithms and machine learning to operate road communication units using solar energy with high efficiency.
Research collaboration in Hail and Qassim and the challenges of vehicular ad hoc networks
Grey wolf optimization and random forest algorithms in network coordination
Digital simulation results in reducing latency and saving energy consumption
Operational balance requirements and next steps for field deployment
Frequently asked questions
Research collaboration in Hail and Qassim and the challenges of vehicular ad hoc networks
Researchers affiliated with the University of Hail and Qassim University in Saudi Arabia, in cooperation with a contributing researcher from Tunisia, have published an AI-powered design framework for solar-powered roadside traffic communication units. This scientific work, published in the peer-reviewed journal Scientific Reports on October 24, 2026, was funded by the Deanship of Scientific Research at the University of Hail and evaluated using actual city road topography, solar radiation measurements, and traffic logs, providing a direct and documented Saudi institutional and research connection.
Vehicular ad hoc networks, commonly known in engineering literature as vehicle-to-vehicle and vehicle-to-infrastructure communication, enable real-time information exchange between vehicles and roadside infrastructure units. This infrastructure can support traffic management, road safety alerts, and other smart mobility services. However, roadside units require continuous power and connectivity. In remote or arid environments, solar power generation can reduce reliance on public electrical grids, but systems must still contend with intermittent sunlight, battery capacity, and changing traffic demand.
Grey wolf optimization and random forest algorithms in network coordination
The research team proposed a coordinated and comprehensive framework rather than addressing installation sites, operational schedules, and demand volume separately. The discrete grey wolf optimization algorithm ranks potential unit installation sites, taking into account coverage range, geographic centrality, solar power potential, and redundancy. Meanwhile, a traffic-aware duty cycle controller turns units on and off according to specific conditions.
In addition, a joint activation logging system and a machine learning random forest unit predict traffic demand volume and anticipate the timing when equipment should be activated before road congestion occurs. Traffic prediction and decision-making supported by mathematical optimization represent the core AI components in this study, which differs from claims that the road network uses large language models or that autonomous vehicles are already operating in the tested area.
Digital simulation results in reducing latency and saving energy consumption
In simulations based on actual traffic logs, the proposed system achieved packet data delivery rates ranging between 94.5% and 97.9%, successfully reduced end-to-end communication latency by 7 to 35 milliseconds, and cut per-unit energy consumption by 20% to 33% compared to baseline reference methods. Furthermore, prediction algorithms helped activate units up to 2.1 minutes early during sudden peak periods without any additional simulated energy cost.
These percentages and timings must remain closely tied to the research evaluation conditions. Tests were based on traffic information in the city of Hail and wireless transmission modeling including a specific radio wave propagation model, meaning these results are not field measurements from a fully deployed city-wide system.
Operational balance requirements and next steps for field deployment
Solar energy provides a genuine operational advantage only when a precise balance is achieved among energy harvesting, battery storage, and operational load volume. A successful network design must handle unusual traffic scenarios, weather fluctuations, wireless interference, component failures, and routine maintenance requirements, whereas the research paper evaluates a specific configuration and does not cover all of these field possibilities.
The most useful future evidence includes the actual physical deployment of roadside units, conducting tests across different seasons of the year, establishing independent performance standards, and performing financial cost comparisons with traditional grid-connected alternatives. In short, the October 24 contribution is a scientifically peer-reviewed simulation research with promising results in a specific Saudi environment, rather than an announcement of a comprehensive national rollout of smart roads.
Frequently asked questions
Question: Who participated in developing the solar-powered smart road communications framework?
Answer: The study involved researchers from the University of Hail and Qassim University in Saudi Arabia in collaboration with a researcher from Tunisia, funded by the Deanship of Scientific Research at the University of Hail.
Question: What are the most prominent results achieved by the system in simulations?
Answer: The system achieved data delivery rates between 94.5% and 97.9%, reduced communication latency by 7 to 35 milliseconds, and cut energy consumption by 20% to 33%.
Question: How did machine learning algorithms help improve the response of road units?
Answer: The predictive random forest unit enabled communication units to be activated 2.1 minutes before traffic congestion waves occurred without consuming extra energy.
Question: Was this system actually installed on the streets of Hail?
Answer: No, the published results are based on computer simulations relying on road, weather, and traffic data in Hail, and the system has not yet been deployed in the field on a commercial scale.
