Investigating the Impact of Chunk Time on Video Streaming Performance in TCP-Based Networks

The exponential increase in video traffic on the Internet has generated a heightened demand for efficient video streaming solutions. HTTP Adaptive Streaming (HAS) has emerged as a viable strategy, facilitating dynamic quality adaptation in response to fluctuating network conditions. In HAS, media content is segmented into short time intervals, with each segment encoded in multiple bitrate-resolution combinations known as representations. This framework enables users to choose the most appropriate representation according to their current network connectivity. To enhance the selection of bit rates and elevate the Quality of Experience (QoE), it is crucial to conduct a precise assessment of network conditions. This research investigated the impact of chunk time on video streaming performance in TCP-based networks. Analyzing the effects of chunk time on both QoE and throughput, our findings indicate that similar to the adaptive nature of video representations that depend on network conditions, chunk time must also be adaptive. It is essential that the chunk time is tailored to the specific network environment, necessitating an adaptive chunk-time strategy for each resolution to ensure optimal streaming performance.