Advancing Streaming Performance with Opportunistic Linked Increase Algorithm in Network Congestion Control

Congestion control is essential to provide a smooth transmission of data in a current network especially in latency sensitive applications like video streaming. Existing traditional congestion control algorithms fail to cope with dynamic network conditions causing suboptimal use of bandwidth, high latency and packet loss. This paper introduces an improved OLIA to real-time adaptive streaming. The given framework presents a dynamic congestion window adaptation algorithm that is grounded on real-time network feedback and a rational adaptive retransmission to enhance bandwidth use and minimize unnecessary retransmissions. Adaptive window adjustment relies on the feedback-based scaling factor based on the occupancy of the queue and lost packets, and the retransmission mechanism rearranges the priority of the lost packets on the network conditions. NS-3 $\mathbf{5 G}$ traffic datasets were used in experiments with different network topologies. Findings indicate that network performance improved significantly: throughput improved to $\mathbf{1 5. 8} \mathrm{Mbps}$, packet loss dropped to 1.8 percent, latency dropped to 25.3 ms, jitter dropped to 3.6 ms and fairness index was also enhanced to 0.98. The suggested improvements allow playing video faster, less buffering and better user experience, which indicates the efficiency of OLIA in high bandwidth, latency sensitive streaming.

Ҳали таржима қилинмаган