Edge Intelligence in Modern Networks: Survey of Architectures and Frameworks for Scalable Deployment

Computer Engineering

Edge computing has emerged as a transformative paradigm addressing the growing need for processing data closer to its source. With the exponential increase in EC devices and latency-sensitive applications, edge computing aims to reduce latency, improve bandwidth efficiency, and enable real-time decision-making. Unlike traditional cloud computing, which relies heavily on centralized data centers, edge computing leverages a decentralized architecture that distributes computational tasks to edge devices and local servers. This review explores the current edge computing architectures and frameworks, focusing on their design, deployment models, and suitability for various applications. Furthermore, this paper examines how edge computing integrates with complementary technologies such as artificial intelligence, 5G, and EC to form robust ecosystems capable of addressing diverse industry needs. Special attention is given to security and privacy considerations in edge architectures, as well as resource management techniques for optimizing performance. By analyzing state-of-the-art frameworks, including federated edge solutions and container-based deployments, this paper aims to identify their strengths, limitations, and potential research directions for further innovation in edge computing systems.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.