Congestion Control
Congestion control aims to optimize network resource utilization and performance by managing the flow of data to prevent bottlenecks and ensure fairness among competing users. Current research heavily emphasizes machine learning approaches, particularly reinforcement learning (RL) and deep learning, often employing multi-agent systems and graph neural networks to adapt to dynamic network conditions and optimize various metrics like throughput, latency, and fairness. These advancements are crucial for improving the efficiency and reliability of diverse systems, ranging from data centers and 5G networks to robotic swarms and distributed edge computing.
Papers
Congestion control algorithms for robotic swarms with a common target based on the throughput of the target area
Yuri Tavares dos Passos, Xavier Duquesne, Leandro Soriano Marcolino
On the throughput of the common target area for robotic swarm strategies -- extended version
Yuri Tavares dos Passos, Xavier Duquesne, Leandro Soriano Marcolino