Adaptive and Energy-Efficient Deployment of Robotic Airborne Base Stations: A Deep Reinforcement Learning Approach

Keyphrases

• Deep Reinforcement Learning (deep RL) 100%
• Robotics 100%
• Reinforcement Learning Algorithm 100%
• Airborne Base Stations 100%
• Energy-efficient Deployment 100%
• Energy Efficiency 20%
• Decision Basis 20%
• Future Wireless Networks 20%
• Multi-agent 20%
• Large-scale Networks 20%
• Energy Demand 20%
• Exhaustive Search 20%
• Global Network 20%
• Decentralized Approach 20%
• State Action 20%
• Gauss-Markov 20%
• Network Information 20%
• Deployment Strategy 20%
• Communication Environment 20%
• Local Observations 20%
• Modern Communication 20%
• Centralized Model 20%
• Traffic Variations 20%
• Actor-critic Deep Reinforcement Learning 20%
• Optimal Energy Efficiency 20%
• Spatiotemporal Fluctuation 20%
• Action Representation 20%
• Q-learning Model 20%
• Low Computational Complexity 20%
• Public Events 20%
• Energy Consumption Dynamics 20%
• Traffic Energy 20%
• Learning-based Framework 20%
• Coordinated Decision-making 20%
• Spatio-temporal Traffic 20%
• Adaptive Deployment 20%
• Adaptive Decision-making 20%
• Intelligent Deployment 20%

Computer Science

• Deep Reinforcement Learning 100%
• Learning Approach 100%
• Robotics 100%
• Energy Efficient 100%
• Energy Efficiency 40%
• Wireless Network 20%
• multi agent 20%
• Decision-Making 20%
• Energy Consumption 20%
• Computational Complexity 20%
• Communication Environment 20%
• Traditional Method 20%
• Exhaustive Search 20%
• Global Network 20%
• Decentralized Approach 20%
• Deployment Strategy 20%
• Centralized Model 20%