Related Concept Videos
Maximum Power Transfer
By substituting the entire circuit with...
Network Function of a Circuit
Maximum Power Flow and Line Loadability
Short-distance Transport of Resources
Fast Decoupled and DC Powerflow
Reducing Line Loss
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Deep Learning-Based Dynamic Time Division ISAC Beamforming for Vehicular Networks.
Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular Networks.
Energy-Efficient Deployment Simulator of UAV-Mounted Base Stations Under Dynamic Weather Conditions.
Related Experiment Video
Updated: Aug 10, 2025

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
Published on: September 8, 2023
Energy-Efficient Resource Allocation Based on Deep Q-Network in V2V Communications.
1Department of Electronic Engineering, Sogang University, Seoul 04107, Republic of Korea.
This study introduces a deep reinforcement learning approach for efficient radio resource management in vehicle-to-everything (V2X) communications. The method optimizes resource allocation to reduce power consumption and latency in vehicle-to-vehicle (V2V) links without impacting overall network performance.
Area of Science:
- * Wireless Communication Networks
- * Artificial Intelligence in Telecommunications
- * Autonomous Driving Systems
Background:
- * Vehicle-to-Everything (V2X) communication is crucial for autonomous driving safety and efficiency.
- * Increasing vehicle density necessitates effective radio resource management for Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) links.
- * Existing resource allocation schemes face challenges in balancing low latency, high reliability, and energy efficiency.
Purpose of the Study:
- * To propose a decentralized resource allocation scheme for V2X networks using deep reinforcement learning (DRL).
- * To optimize resource blocks and transmit power for V2V links to enhance V2I and V2V communication performance.
- * To ensure energy-efficient transmissions that meet V2V latency constraints while minimizing interference.
Main Methods:
- * Implementation of a deep Q-network (DQN) for decentralized decision-making in resource allocation.
- * Utilization of channel state information (CSI) and signal-to-interference-plus-noise ratio (SINR) for optimal allocation.
- * Simulation of the proposed scheme in a Manhattan-based V2X communication scenario (3GPP TR 36.885).
Main Results:
- * The DRL-based scheme effectively reduces the transmit power of V2V links.
- * The proposed method maintains or improves the sum rate of the V2X network.
- * Average power consumption of V2V links is significantly reduced, and outage probability is managed effectively.
Conclusions:
- * The proposed DQN-based resource allocation scheme offers an energy-efficient solution for V2X communication networks.
- * The DRL approach successfully balances competing demands of latency, reliability, and power consumption in V2V communications.
- * This scheme provides a viable strategy for efficient radio resource management in future autonomous driving systems.

