Adaptive Neuro-Fuzzy Congestion Control Algorithm for Real-Time Multimedia Networking in Cloud-Based E-Learning Platforms
Hanadi HakamiDepartment of Software Engineering, College of Engineering, University of Business and Technology, Jeddah, Saudi Arabia. h.hakami@ubt.edu.sa0000-0001-5627-6805
Mohammad Kamrul HasanCenter for Cyber Security, Faculty of Information Science and Technology, Universiti, Kebangsaan Malaysia (UKM), Bangi, Selangor, Malaysia. hasnakamrul@ieee.org0000-0001-5511-0205
Ahmad AlshamaylehDepartment of Data Science and Artificial Intelligence, Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman, Jordan. a.alshamayleh@ammanu.edu.jo0000-0002-7222-2433
Dr. Ali Q. SaeedTechnical Engineering College for Computer and AI–Mosul, Northern Technical University, Mosul, Iraq. ali.qasim@ntu.edu.iq0000-0002-2276-3776
Dr. Saed Adnan MustafaCollege of Business, The American University of Kurdistan, Iraq. said_es@yahoo.com0000-0002-3099-7230
Dr. Taher M. GhazalFaculty of Computing and IT, Sohar University, Oman; Department of Networks and Cybersecurity, Al-Ahliyya Amman University, Amman, Jordan; Center for Cyber Security, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi, Selangor, Malaysia. taher.ghazal@ieee.org0000-0003-0672-7924
Innovations in cloud-based platforms for e-learning have been accompanied by an increased demand for real-time multimedia components, such as video lectures, collaboration tools, and interactive quizzes. Multichannel multimedia e-learning platforms face the challenge of maintaining quality of service (QoS) requirements while the network circumstances vary and cause delays, packet dropping, or jitter. Existing congestion control techniques like TCP and AQM fall short for multimedia traffic. In this paper, the Adaptive Neuro-Fuzzy Congestion Control Algorithm (ANFCCA) is introduced, which uses neural networks and fuzzy logic to make congestion control decisions in real time. We implement the proposed algorithm in the context of cloud-based e-learning, where users access the content under varying network conditions. Performance results demonstrate considerable improvements in traditional techniques in real-time multimedia networking for e-learning, with significant gains in throughput, packet delivery ratio (PDR), and end-to-end delay.