Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adrenaline: Adaptive Rendering Optimization System for Scalable Cloud Gaming

Jin Heo, Ketan Bhardwaj, Ada Gavrilovska

TL;DR

Adrenaline tackles the scalability bottleneck of edge cloud gaming by adaptively adjusting per-user rendering quality (RQ) based on predicted user-side visual quality under given RQ and network compression (QP). It combines a VMAF-based quality predictor, a multi-user scoring mechanism, and a backoff stabilization strategy to maximize aggregate service quality while maintaining playable FPS. The approach yields up to 24% higher service quality and 2x more users served on the same GPU compared with baselines, demonstrated across multiple games and scenarios and complemented by a user study. Its open-source plugin and server-side runtime enable practical deployment and further optimization for scalable cloud gaming at the network edge.

Abstract

Cloud gaming requires a low-latency network connection, making it a prime candidate for being hosted at the network edge. However, an edge server is provisioned with a fixed compute capacity, causing an issue for multi-user service and resulting in users having to wait before they can play when the server is occupied. In this work, we present a new insight that when a user's network condition results in use of lossy compression, the end-to-end visual quality more degrades for frames of high rendering quality, wasting the server's computing resources. We leverage this observation to build Adrenaline, a new system which adaptively optimizes the game rendering qualities by considering the user-side visual quality and server-side rendering cost. The rendering quality optimization of Adrenaline is done via a scoring mechanism quantifying the effectiveness of server resource usage on the user-side gaming quality. Our open-sourced implementation of Adrenaline demonstrates easy integration with modern game engines. In our evaluations, Adrenaline achieves up to 24% higher service quality and 2x more users served with the same resource footprint compared to other baselines.

Adrenaline: Adaptive Rendering Optimization System for Scalable Cloud Gaming

TL;DR

Adrenaline tackles the scalability bottleneck of edge cloud gaming by adaptively adjusting per-user rendering quality (RQ) based on predicted user-side visual quality under given RQ and network compression (QP). It combines a VMAF-based quality predictor, a multi-user scoring mechanism, and a backoff stabilization strategy to maximize aggregate service quality while maintaining playable FPS. The approach yields up to 24% higher service quality and 2x more users served on the same GPU compared with baselines, demonstrated across multiple games and scenarios and complemented by a user study. Its open-source plugin and server-side runtime enable practical deployment and further optimization for scalable cloud gaming at the network edge.

Abstract

Cloud gaming requires a low-latency network connection, making it a prime candidate for being hosted at the network edge. However, an edge server is provisioned with a fixed compute capacity, causing an issue for multi-user service and resulting in users having to wait before they can play when the server is occupied. In this work, we present a new insight that when a user's network condition results in use of lossy compression, the end-to-end visual quality more degrades for frames of high rendering quality, wasting the server's computing resources. We leverage this observation to build Adrenaline, a new system which adaptively optimizes the game rendering qualities by considering the user-side visual quality and server-side rendering cost. The rendering quality optimization of Adrenaline is done via a scoring mechanism quantifying the effectiveness of server resource usage on the user-side gaming quality. Our open-sourced implementation of Adrenaline demonstrates easy integration with modern game engines. In our evaluations, Adrenaline achieves up to 24% higher service quality and 2x more users served with the same resource footprint compared to other baselines.
Paper Structure (27 sections, 7 equations, 13 figures, 5 tables, 1 algorithm)

This paper contains 27 sections, 7 equations, 13 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background
  3. Motivation
  4. Adrenaline
  5. System Overview
  6. User-side Visual Quality Prediction
  7. Rendering Quality Optimization
  8. Scoring Mechanism for Multi-user Prioritization
  9. RQ Optimization Process
  10. RQ Stabilization Mechanism
  11. RQ Oscillation Issue
  12. RQ Stabilization Mechanism with Backoff
  13. Implementation
  14. Evaluation
  15. Experiment Methodology
  16. ...and 12 more sections

Figures (13)

  • Figure 1: The screenshots of a sample game scene with different RQs and compression parameters of H.264 (QPs) corresponding to good and poor network conditions
  • Figure 2: General architecture of cloud gaming
  • Figure 3: The visualization of multi-application rendering on a GPU
  • Figure 4: The FPS and frame quality measurements of the scene in Figure \ref{['fig:motiv']} with different RQs and QPs
  • Figure 5: The architecture of Adrenaline
  • ...and 8 more figures