Research Article
A QoS and Load Balancing Predictive Model Based on LSTM and Random Forest Regression in SDN: A Rest API Approach
@INPROCEEDINGS{10.1007/978-3-031-80713-8_1, author={Muhammad Salman Ansari and JianXun Zhang and Shaban }, title={A QoS and Load Balancing Predictive Model Based on LSTM and Random Forest Regression in SDN: A Rest API Approach}, proceedings={Data Information in Online Environments. 4th EAI International Conference, DIONE 2023, Nanchang, China, November 25--27, 2023, Proceedings}, proceedings_a={DIONE}, year={2025}, month={2}, keywords={Machine Learning in Networking SDN RESTful API QoS and Load balancing}, doi={10.1007/978-3-031-80713-8_1} }- Muhammad Salman Ansari
JianXun Zhang
Shaban
Year: 2025
A QoS and Load Balancing Predictive Model Based on LSTM and Random Forest Regression in SDN: A Rest API Approach
DIONE
Springer
DOI: 10.1007/978-3-031-80713-8_1
Abstract
Fog Computing, Software Define Networking, RESTful API and Machine Learning are new technologies in the area of ICT as well as in Networking. Fog computing brought high performance computing at the edge of network and Software Defined networking. As we intended to head towards QoS and Load balancing in SDN. In this work we cover an initial segment which is Machine leaning model implementation on a network traffic information to predict future outcomes for traffic flow. Meanwhile, in comprehensive research we intended to reduce network congestion, jitter, QoS and load balancing by learning past traffic flow information. As well as, we aim to improve maximum utilization of link-bandwidth. Through RESTful API of SDN, we can embed Machine learning based prediction model to the network server which can modify the network policies by learning from past experiences. In this paper, we proposed a QoS and load balancing framework. A Server and SDN based application for network monitoring, management and controlling the policies over network gateway for better performance in regard of traffic flow. Experiment result shows that implementation of Machine learning over network traffic flow information immensely important for new emerging technologies. The evaluation results of Machine learning model we implemented in this work depicts that model performs well. Meanwhile the model improves by increasing with the number of epochs.
