Edge Computing Architectures for Ultra-Low Latency Applications

Abstract

As enterprise data grows across cloud, edge, and geographically distributed environments, traditional Edge computing has emerged as a transformative extension of cloud computing by addressing the limitations of latency, bandwidth, and scalability in real-time applications. With the increasing demand for ultra-low latency in autonomous vehicles, industrial automation, telemedicine, smart cities, and augmented reality, traditional cloud architectures face challenges due to centralized processing and network delays. Edge computing overcomes these issues by processing data closer to end devices, enabling faster decision-making and reduced communication overhead. This paper presents a comprehensive survey of edge computing architectures for ultra-low latency applications, covering key technologies such as 5G, Software-Defined Networking (SDN), Network Function Virtualization (NFV), Artificial Intelligence (AI), microservices, and container orchestration. It also examines major challenges, including resource management, interoperability, security, and energy efficiency. A multi-layer edge computing framework with intelligent task scheduling and dynamic resource allocation is proposed to optimize latency and resource utilization. Experimental findings demonstrate significant improvements over conventional cloud architectures, achieving over 70% reduction in end-to-end latency and 65% improvement in resource efficiency. The study concludes that intelligent edge computing architectures will play a vital role in supporting future real-time applications and next-generation 6G-enabled digital ecosystems.