Deep reinforcement learning improves cloud gaming video quality dynamically
DIA: A Deep Reinforcement Learning-Based Interest-Aware ABR Scheme for Cloud Gaming
Multimedia
Summary
Playing high-quality video games over the internet on phones and tablets is hard because videos must load quickly and look good even when the internet is slow. The authors designed a smart system called DIA that uses artificial intelligence to focus on showing the important parts of game images clearly while using less data on less important parts. This system changes video quality based on how fast the game moves and the current network conditions without needing extra hardware like eye trackers. Tests showed that DIA works better than other methods, especially on fast 5G networks, making games look better and run smoother.
What this means in practice
- •For cloud gaming platform engineers: Integrate DIA to deliver higher perceived video quality in cloud games despite variable wireless network conditions.$Commercial implications: Enables enhanced cloud gaming experiences on smartphones by prioritizing important image regions, enabling platforms to attract and retain users with better video quality.
- •For mobile network operators: Deploy DIA-enabled streaming policies to optimize bandwidth usage for cloud gaming customers on 5G networks, improving network efficiency.
Authors
Zhe Zhang, Haiwei Dong, Marc St-Hilaire, Abdulmotaleb El Saddik
Abstract
The continuous evolution of cloud gaming has enabled users to play high-quality cloud games on thin clients, such as smartphones and tablets. However, how to effectively transmit the gameplay frames with high resolution and low latency, especially over wireless networks, remains a significant challenge. To address this challenge, we propose a Deep Reinforcement Learning (DRL)-based Interest-Aware Adaptive Bitrate (ABR) scheme, called DIA, that guarantees the quality of perceptually key objects in each frame, while dynamically allocating lower resolutions for non-key objects to conserve bandwidth under constrained network conditions. By leveraging an off-the-shelf semantic segmentation model, the proposed DIA scheme can adjust the bitrate at the object-level. We also design a transformer-based feature extractor and an interest-aware reward function to enable the proposed DIA scheme to identify key objects and dynamically adjust their bitrates. This adaptation is guided by users' in-game movement speed, object features, and prevailing network conditions and operates without requiring additional hardware, such as gaze trackers. Extensive experiments show that the proposed DIA scheme outperforms existing ABR schemes in dynamic wireless network environments. Notably, DIA achieves at least a 20% higher normalized average Quality of Experience (QoE) than the State-Of-The-Art (SOTA) ABR algorithms in 5G scenarios.