Application-Aware Slicing for FRMCS: A Deep Reinforcement Learning Approach

Keyphrases

• Deep Reinforcement Learning (deep RL) 100%
• Reinforcement Learning Algorithm 100%
• Application-oriented 100%
• Future Railway Mobile Communication System 100%
• Application-aware 100%
• Service Level Agreement 66%
• Video Surveillance 33%
• Resource Allocation 33%
• 5G Networks 33%
• Spectral Efficiency 33%
• Signal-to-noise Ratio 33%
• Application Requirements 33%
• Network Slicing 33%
• Safety-critical 33%
• Scheduling Approach 33%
• Scheduler 33%
• Railway Communications 33%
• Wi-Fi 33%
• Heterogeneous Applications 33%
• High-speed Train 33%
• Ultra-reliable 33%
• High-speed Applications 33%
• Real Signals 33%
• Train Control 33%
• GSM-R 33%
• Resource Block 33%
• Current Network 33%
• Service Range 33%
• Channel-aware 33%
• Railway Services 33%
• European Train Control System 33%
• Channel Fluctuation 33%
• Automatic Train Operation 33%
• Ratio Trace 33%

Computer Science

• Deep Reinforcement Learning 100%
• Learning Approach 100%
• Service-Level Agreement 100%
• Application Level 100%
• Video Surveillance 50%
• Resource Allocation 50%
• 5G Mobile Communication 50%
• Application Requirement 50%
• Network Slicing 50%
• Speed-up 50%
• High Throughput 50%
• Spectral Efficiency 50%
• Wi-Fi 50%
• Signal-to-Noise Ratio 50%
• Optical Spectrum 50%