Network congestion control is an important means to improve network throughput and reduce data transmission delay. To further optimize the capability, this research suggests a proximal policy optimization-based intelligent TCP management method, creates proxy that can communicate with real-time environment, abstracts mechanism into partially observable Markov decision process. Changes in state ...

Many devices contain more than one network interface. There is scope for multi-path transfer to utilise these interfaces simultaneously. Multi-path TCP (MPTCP) designed provide improved resilience and resource utilisation through transfer. One of the key goals MPTCP preserve fair sharing with regular at bottlenecks. Although coupled congestion control algorithms can achieve this goal by couplin...

We approach the task of network congestion control in datacenters using Reinforcement Learning (RL). Successful algorithms can dramatically improve latency and overall throughput. Until today, no such learning-based have shown practical potential this domain. Evidently, most popular recent deployments rely on rule-based heuristics that are tested a predetermined set benchmarks. Consequently, th...