Research Article
Deep Reinforcement Learning-Based Content Placement and Trajectory Design in Urban Cache-Enabled UAV Networks
| Notations | Descriptions |
| | Number of UAVs | | Total time slots | | Maximum speed of UAVs | | Coordinate of users | | Total number of files | | Caching probability | | LoS and NLoS probability | | Instantaneous rate of user | | Total bandwidth of each UAV | | Additional path loss for LoS, NLoS | | Propulsion power relevant parameters | | UAV set with link to user | | Number of users | | Time slot length | | Altitude of UAVs | | Zipf exponent | | Content popularity | | Storage capacity | | Elevation angle | | Noise power spectral density | | Environmental parameters (urban) | | Path loss exponent | | Battery capacity | | State, action, and reward in RL |
|
|