The Role of TCP Congestion Control in the Throughput Forecasting

• Ariel Portela UECE
• Maria Melo Linhares UECE
• Francisco Valderlan Jorge Nobre UECE
• Rafael Menezes UECE
• Maria Mesquita UECE
• Rafael Lopes Gomes UECE

Resumo

Performance forecasting is essential in network management, allowing administrators to anticipate and prepare for future changes in network performance by analyzing historical data and applying forecasting models. Additionally, throughput forecasting minimizes issues like slowness and service interruptions by addressing bottlenecks before they affect users. However, the performance of TCP congestion control algorithms, such as TCP Cubic and TCP BBR, plays a crucial role in forecasting, as they manage network resources and congestion differently, impacting throughput outcomes. Within this context, this paper presents an analysis of the throughput performance forecasting according to the type of TCP applied, considering the resulting statistical behavior. The experiments, using real data from the National Education and Research Network (RNP), show the impact of the TCP congestion control over the forecasting process.

Palavras-chave: Artificial Intelligence, Forecasting, Performance