Enhancing Efficiency with Adaptive Optimized Balancing Factor for MPTCP Congestion Control Using Deep Deterministic Policy Gradient: EE-AOBF-MPTCP-DDPG

MPTCP is rapidly emerging as one of the most advanced networking protocols. Standardized by the IETF as an extension of TCP, it enables seamless communication across multiple interfaces from source to destination. Despite its potential, existing multipath congestion control mechanisms face significant challenges due to the diverse QoS characteristics of heterogeneous interfaces. While recent algorithms primarily emphasize enhancing the growth dynamics of the congestion window (CWND), the reduction mechanisms remain largely overlooked. Furthermore, conventional congestion control approaches often rely on manual adjustments, which are insufficient in highly dynamic network environments. Given the demonstrated success of machine learning algorithms across industries such as IoT, video streaming, and autonomous vehicles, this study introduces the Deep Deterministic Policy Gradient Multi-Path (DDPG-MP) framework. This innovative approach dynamically optimizes congestion control using a balancing factor, enabling adaptive and efficient performance in multipath networking environments.