Utilizing Machine Learning as a Prediction Scheme for Network Performance Metrics of Self-Clocked Congestion Control Algorithm

Congestion Control (CC) is a fundamental mecha nism to achieve effective and equitable sharing of network fa- cilities. As future networks evolve towards more complex para- digms, traditional CC methods are required to become more powerful and reliable. On the other hand, Machine Learning (ML) has become increasingly popular for solving challeng- ing and sophisticated problems, and scientists have started to turn their interest from rule-based approaches to ML-based methods. This paper employs machine learning models to con- struct a performance evaluation scheme to predict network metrics for the Self-Clocked Rate Adaptation for Multimedia (SCREAM) algorithm. It uses a rigorous data preprocessing pipeline and a systematic application cation of ML methods to en- hance the performance of the regression model for SCREAM'S performance metrics. Also, we constructed a dataset that pro- vides SCREAM's input parameters and output metrics, such as network queue delay, smoothed Round Trip Time (sRTT), and network throughput. Each prediction process has several phases: choosing the best initial regressor model, hyperparam- eter tuning, ensemble learning, stacking regressors, and uti- lizing the holdout data. Each model's performance was evalu- ated through various regression metrics; this study will mainly focus on the coefficient of determination (R2) score. The im- provement between the initial best-selected model and the fi- nal improved model determined that we were able to increase R2 up to 96.64% for network throughput, 99.4% for network queue delay, and 100% for SRTT.