DT-aided resource allocation via generative adversarial imitation learning in complex cloud-edge-end scenarios.

12 a, it can be seen that when the communication distance between end nodes and edge servers increases from 50 meters to 100 meters (all within the communication range of both devices), all algorithms show a decreasing trend in service latency.

also in 47,180 other papers

6 demonstrate that as the number of terminal nodes increases, the average service latency of all three experimental schemes (DT networks + multi-expert trajectory generation algorithm, only multi-expert trajectory generation algorithm, only DT networks) shows an increasing trend, which aligns with the inherent law that the growing number of terminal nodes intensifies competition for computing and communication resources.

also in 63,971 other papers