Enhancing AI Efficiency with Fog and Edge Computing: A Paradigm Shift in Real-Time Data Processing
Code: G-1209
Authors: Mansour Farzin Fard, Sara Hemmatzadeh Zare * ℗
Schedule: Not Scheduled!
Download: Download Poster
Abstract:
Abstract
Background and aim: Fog and edge computing aim to bring computational resources closer to data sources, reducing latency and improving efficiency in processing. These paradigms support real-time decision-making by processing data locally, rather than relying on distant cloud servers. In artificial intelligence, they enable faster responses and enhanced performance. The main goal is to improve quality, increase safety and satisfaction. Method: we use deep learning and Data analysis by python. Data processing is distributed across edge nodes or fog layers, minimizing dependence on centralized cloud systems. This approach utilizes resource allocation algorithms, containerization, and AI models to ensure real-time data analysis and system optimization. Additionally, fog and edge computing methodologies often incorporate network virtualization techniques to enhance resource efficiency and scalability. These systems rely on intelligent load balancing and task scheduling algorithms to allocate workloads dynamically across nodes. Security measures, such as encryption and authentication protocols, are integrated to safeguard data and ensure privacy during local and distributed processing. Furthermore, edge devices are equipped with lightweight AI models, allowing real-time inference while conserving computational power and energy. This holistic approach ensures seamless integration with cloud systems when needed, creating a hybrid framework for robust and efficient computing. Result: The results of fog and edge computing demonstrate significant reductions in latency and bandwidth usage compared to traditional cloud-based systems. AI applications show improved performance, especially in time-sensitive tasks like autonomous vehicles and healthcare monitoring. These systems also enhance scalability and reliability by distributing computational loads across multiple edge and fog nodes. Conclusion: Fog and edge computing are transformative paradigms that address the limitations of cloud computing, particularly in latency-sensitive AI applications. By processing data closer to the source, they ensure faster response times, reduced bandwidth usage, and improved system efficiency. These technologies are especially beneficial for real-time AI use cases in fields like healthcare, IoT, and smart cities. While they offer scalability and flexibility, challenges such as security, energy efficiency, and resource management remain areas for further research. Overall, fog and edge computing are pivotal in shaping the future of distributed AI systems.
Keywords
Fog ,Edge Computing, Artificial Intelligence
