Optimizing telecommunications networks and reducing data transmission latency using intelligent algorithms

Ahmad banisaeid¹

1) Master of Science in Electrical Engineering, Telecommunications System, Shahid Chamran University of Ahvaz

IOI Code : AADG-ABBFGA
Publication : The second international conference on new approaches in engineering and basic sciences(icnabs.ir/2nd)
Abstract :
    With the rapid expansion of technologies such as the Internet of Things, augmented and virtual reality, edge computing, and latency-sensitive services such as cloud gaming and remote surgery, the demand for telecommunication networks with ultra-low latency, ultra-high bandwidth, and unprecedented reliability has increased. Latency, as a critical quality-of-experience parameter, directly affects the performance of these emerging services. Traditional approaches to network management and optimization often face limitations in the face of the increasing dynamics, heterogeneity, and complexity of next-generation networks (such as 5G and 6G). In this regard, intelligent algorithms based on artificial intelligence and machine learning have emerged as a transformative paradigm to address these challenges. This paper provides a comprehensive and systematic review of the applications of intelligent algorithms in network optimization and data transmission latency reduction. First, the key concepts of network latency and its various sources are analyzed. Then, a comprehensive classification of intelligent algorithms is presented, including reinforcement learning, deep learning, federated learning, and evolutionary computing. In the following, practical applications of these algorithms in key areas such as dynamic resource allocation, intelligent routing, on-demand network management, edge and cloud computing management, and next-generation wireless networks are reviewed. Important implementation challenges, including training data requirements, computational complexity, model interpretability, and integration with existing infrastructures, are discussed in detail. Finally, future trends and research directions in this dynamic field are presented. The aim of this paper is to provide a clear roadmap for researchers and network engineers to optimally utilize the capabilities of artificial intelligence in the design and management of next-generation low-latency networks.

Keywords : network optimization latency reduction artificial intelligence machine learning reinforcement learning