Benefits And Challenges of Edge Computing For Real-Time Data Processing in Manufacturing And Autonomous Vehicles Industries

This study investigates how edge computing can fundamentally improve real-time data processing in both manufacturing and autonomous vehicle industries by exploring both its key benefits and inherent challenges. It outlines how edge computing reduces latency, minimizes bandwidth demands, and enhances data privacy by enabling processing directly on-site or in-vehicle. The research examines use cases such as predictive maintenance in smart factories and rapid decisionmaking in autonomous navigation. At the same time, it addresses the technological and operational hurdles, including edge node scalability, system interoperability, network reliability, resource limitations, and security vulnerabilities. By combining real-world industry scenarios and comparative analysis, the study offers strategic insights into optimizing edge computing deployments to drive efficiency, reliability, and responsiveness in mission-critical environments. As manufacturing evolves toward smart, interconnected production and autonomous vehicles become more prevalent, the demand for immediate and reliable data handling has never been greater. This thesis explores the dual-sided dynamics of edge computing in these contexts— highlighting its potential to power real-time processing, system resilience, and privacy by conducting computations close to where data is generated. In manufacturing, it enables real-time monitoring and fault detection, reducing downtime and improving throughput. In autonomous vehicles, it supports split-second processing for safe navigation and environmental awareness. However, the adoption of edge computing also presents significant challenges: ensuring consistent interoperability across diverse hardware, managing limited computing and energy resources, maintaining low-latency communication, and safeguarding data integrity in distributed environments. Drawing upon both case studies and emerging deployment models, the work offers a framework for stakeholders—from engineers to strategists—to harness the promise of edge computing while navigating its complexities in high-stakes applications.