Abstract

The rapid growth of the Internet of Things (IoT) has significantly increased the need for real-time data processing and low-latency communication in embedded systems. Traditional centralized computing architectures often struggle to meet the stringent latency and reliability requirements of modern IoT applications, particularly in industrial automation, autonomous vehicles, and healthcare monitoring systems. Distributed computing models, which allocate computation across multiple interconnected nodes, provide a promising solution by enabling parallel processing, workload balancing, and localized decision-making. This study explores low-latency distributed computing models tailored for real-time embedded IoT systems. It investigates the architectural frameworks, communication protocols, scheduling strategies, and optimization techniques that minimize latency while ensuring system reliability and scalability. Key challenges, including resource constraints, network variability, and synchronization overhead, are analyzed. The research also examines emerging paradigms such as edge computing, fog computing, and hybrid cloud-edge frameworks, which combine the benefits of centralized and distributed approaches. By evaluating these models through simulations and prototype implementations, this study aims to provide actionable insights for designing efficient real-time embedded IoT systems. The findings highlight critical trade-offs between latency, resource utilization, and system complexity, guiding future research and practical deployments in latency-sensitive IoT applications