Energy-Efficient UAV-Assisted MEC With Dual-Priority Scheduling and Multi-Agent Reinforcement Learning

Keyphrases

• Multi-agent Reinforcement Learning 100%
• Mobile Edge Computing 100%
• Energy Efficient 100%
• Unmanned Aerial Vehicle 100%
• Scheduling Agents 100%
• Dual Priority Scheduling 100%
• Base Station 60%
• Energy-aware 40%
• Optimization Problem 20%
• Deep Reinforcement Learning (deep RL) 20%
• Proposed Architecture 20%
• Offloading Decision 20%
• Energy Efficiency 20%
• Priority Mechanism 20%
• Vehicle Mobility 20%
• User Equipment 20%
• Multi-agent 20%
• Computing Infrastructure 20%
• Cooperative Energy 20%
• Communication Energy 20%
• Execution Framework 20%
• Centralized Training 20%
• Edge Computing Architecture 20%
• QoS-aware 20%
• Service Differentiation 20%
• Terrestrial Base Station 20%
• Multi-tier 20%
• Joint Impact 20%
• Propulsion Power 20%
• Vehicle Energy Consumption 20%
• Application Type 20%
• Task Priority 20%
• Underexploited 20%
• Edge Deployment 20%
• Energy Restriction 20%
• Mobile Edge Server 20%
• Aerial Relay 20%
• Multi-agent Proximal Policy Optimization (MAPPO) 20%
• Nonlinear Agents 20%
• Decentralized Execution 20%
• Direct User 20%
• Mobility Policy 20%
• Multi-agent Markov Decision Process 20%
• Geographical Zones 20%
• Deadline Violation 20%
• Flight Constraint 20%

Computer Science

• Unmanned Aerial Vehicle 100%
• Multi-Agent Reinforcement Learning 100%
• Multi-Access Edge Computing 100%
• Energy Efficient 100%
• multi agent 37%
• Quality of Service 12%
• Deep Reinforcement Learning 12%
• Optimization Problem 12%
• Energy Consumption 12%
• Markov Decision Process 12%
• Energy Efficiency 12%
• Computing Infrastructure 12%
• Computer Architecture 12%
• Service Differentiation 12%
• Application Type 12%
• Policy Optimization 12%