High speed data transmission technology for medical high precision virtual reality cloud platform
Existing real-time medical data transmission models are prone to issues such as frame loss and high latency.This paper proposes a high-speed data transmission model for medical cloud platforms based on deep reinforcement learning.In response to the congestion phenomenon in the data queuing process,the algorithm calculates the queuing delay on priority,service quality indicators,and system fault tolerance rate to obtain the urgency of tasks and improve the execution efficiency of key tasks.Train the data through a deep reinforcement learning model and continuously update the Q network parameters using urgency to obtain the queue order for task execution,thereby optimizing the network latency of the entire platform.In comparative experimental testing,the proposed algorithm achieved optimal performance in terms of latency,rate,and throughput,demonstrating its ability to stably and reliably transmit data under low latency conditions.
high speed transmission of medical dataqueuing modeldata groupingdeep reinforcement learningcongestion model
万方数据
维普
