Riverbed Modeler Reinforcement Learning M&S Framework Supported by Supervised Learning

Abstract

Riverbed Modeler is a useful simulation tool that can simulate a variety of standard network models. However, it does not provide a related tool that does not suit the situation in which research on applying machine learning to the network domain is actively progressing. In this paper, we implemented a framework to apply reinforcement learning in a riverbed modeler environment. In order to efficiently perform reinforcement learning, we proposed a reinforcement learning structure that supports supervised learning to improve network performance using Riverbed Modeler and MATLAB. The proposed method was evaluated that the learning time was shortened compared to the existing reinforcement learning environment through experiments.