Optimizing Server Load Distribution in Multimedia IoT Environments through LSTM-Based Predictive Algorithms

The Internet of Multimedia Things (IoMT) represents a significant advancement in the evolution of IoT technologies, focusing on the transmission and management of multimedia streams. As the volume of data continues to surge and the number of connected devices grows exponentially, internet traffic has reached unprecedented levels, resulting in challenges such as server overloads and deteriorating service quality. Traditional computer network architectures were not designed to accommodate this rapid increase in demand, leading to the necessity for innovative solutions. In response, Software-Defined Networks (SDNs) have emerged as a promising framework, offering enhanced management capabilities by decoupling the control layer from the data layer. This study explores the load balancing of servers within software-defined multimedia IoT networks. The Long Short-Term Memory (LSTM) prediction algorithm is employed to accurately estimate server loads and fuzzy systems are integrated to optimize load distribution across servers. The findings from the simulations indicate that the proposed approach enhances the optimization and management of IoT networks, resulting in improved service quality, reduced operational costs, and increased productivity.

Optimizing Server Load Distribution in Multimedia IoT Environments through LSTM-Based Predictive Algorithms Keywords:

Internet of Multimedia Things , Software-Defined Network , Long Short-Term Memory Prediction , Fuzzy System