Adaptive Bitrate Streaming for Energy-Efficiency Mobile Augmented Reality

With the rapid development of Mobile Augmented Reality (MAR) technology, the types and functions of MAR applications are becoming more and more diverse. At the same time, users have put forward higher requirements for the video quality and response time of MAR applications. . Generally speaking, MAR applications will offload computationally intensive tasks (target recognition and rendering) to the cloud or edge server for processing, and download the rendered images to the mobile terminal. However, due to the instability of the mobile network state and the network Due to the limitation of bandwidth, the transmission of massive data will prolong the response time of MAR applications, thereby increasing the transmission energy consumption of mobile devices, and seriously affecting the user experience. Therefore, this paper proposes a Gradient Boosting Regression (GBR) based method. The adaptive bit rate control model is based on the adaptive bit rate control model. The model predicts the user's perception needs