Machine Learning for Broad-Sensed Internet Congestion Control and Avoidance: A Comprehensive Survey

It is challenging to deal with the Internet congestion problem because of several factors such as ever-growing traffic and distributed network architecture. The can be solved or alleviated by various methods, including rate control, bandwidth-guarantee routing bandwidth reservation. We use term broad-sensed control avoidance (BICC&A) generally denote all above methods. Most BICC&A solutions depend on benefit from knowledge conditions, status (type volume), available topology. In this paper, we present a comprehensive survey applications machine learning condition acquirement methods for specific First, provide an overview background learning. Then, detailed reviews techniques Finally, outline important research opportunities.