Publication

Abstract : Cloud gaming is revolutionizing the gaming industry by enabling consumers to access high-quality games without the need to buy expensive hardware. However, maintaining smooth performance, low latency, and bandwidth efficiency remains a challenge. These challenges are tackled by optimizing cloud gaming using hierarchical optical networks (HONs) and achieving energy-efficient, cost-effective, and scalable means of supporting growing demands for games. Despite advancements in optical networking, cloud gaming continues to be afflicted by jitter, bandwidth constraints, and resource underutilization, particularly in heterogeneous environments. To tackle these issues, we introduce a multi-layer optimization framework that incorporates dynamic traffic management, predictive resource allocation, and adaptive compression. The methodology utilizes machine learning models for forecasting traffic patterns, enhancing bandwidth efficiency, and reducing latency. The experimental results reflect a 25% reduction in latency, an improvement of 30% in bandwidth efficiency, and a reduction of 20% in jitter compared to existing methodologies. The approach optimizes efficiency, reliability, and scalability and, therefore, enables the wide deployment of HON-based systems for cloud gaming.