Long Short-Term Memory Approach for Routing Optimization in Cloud ACKnowledgement Scheme for Node Network

摘要

Routing optimization using machine learning has been receiving a lot of attention recently. Additionally, cloud computing is evolving exponentially in processing power and memory units. This paper proposes a routing optimization approach for a Cloud ACKnowledgement Scheme using machine learning techniques. Our proposed approach is based on synthetic generated data for respective node values in a network. Moreover, it involves a variant of Recurrent Neural Network called Long Short-Term Memory (LSTM). The machine learning model is developed using LSTM through a sliding-window technique. The results achieved are very encouraging. They show that the cloud can mostly predict whether the forthcoming transmission of a certain node in the network will be a success.