Optimized energy efficient cluster based routing protocol for real time communication in 5G enabled VANETs using reinforcement learning
Year: 2026
Type: article
Abstract: The combination of 5G networks and Vehicular Ad-hoc Networks (VANETs) has transformed real-time communication to smart transportation systems, but challenges such as high energy usage, changes in topology, and rigid latency requirements still exist. This work offers a 5G-enabled VANET Optimized Energy-Efficient Cluster-Based Routing Protocol (OEECRP), which combines dynamic clustering, reinforcement learning (RL)-based routing, and 5G network slicing to provide sustainable, low-latency communication and therefore addresses these problems. Ensuring network lifespan, the protocol initially uses a weighted clustering technique to choose Cluster Heads (CHs) depending on residual energy, mobility, and 5G link reliability. A Q-learning model then dynamically adapts to traffic density, node energy levels, and latency limitations to achieve the best routing decisions, with a reward mechanism that balances energy efficiency and real-time performance. The Ultra-Reliable Low-Latency Communication (URLLC) that 5G network slicing provides priority to important traffic also reduces the reliance on centralized cloud infrastructure. The protocol is tested in the urban environment with the number of cars of 50–200 and is implemented in MATLAB R2023a and the 5G Toolbox and Communications Toolbox. Experimental results show that OEECRP beats five conventional models such as AODV, DSR, DSDV, GPSR and LEACH by approximately 30 percent reduction of energy consumption, less than 50ms end-to-end delay and increased packet delivery ratio (PDR). These results prove the reliability and scalability of OEECRP, thus offering a powerful solution to real-time, energy-conscious VANET communication.
Source: Scientific Reports
Institution: Sri Eshwar College of Engineering
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,690
OpenAlex ID: W7160132477