Edge Computing and Artificial Intelligence Integration for Low-Latency Decision-Making in Smart Cities and Industrial IoT

Abstract

The rapid expansion of smart cities and Industrial Internet of Things (IIoT) systems has increased the need for intelligent low-latency computing frameworks capable of handling massive real-time data from distributed sensors, industrial machines, autonomous vehicles, surveillance systems, and urban infrastructure. Traditional cloud-based architectures face challenges such as high latency, bandwidth congestion, centralized dependency, and delayed decision-making, making them less effective for time-critical applications. Edge Computing addresses these limitations by processing data closer to its source, reducing latency, improving bandwidth efficiency, and enabling real-time analytics. At the same time, Artificial Intelligence (AI) techniques such as machine learning, deep learning, reinforcement learning, and optimization algorithms enhance edge systems by enabling autonomous decision-making and predictive intelligence. This research proposes an integrated Edge Computing and AI framework for low-latency decision-making in smart cities and Industrial IoT environments. The framework combines distributed edge intelligence, adaptive resource allocation, AI-driven analytics, and edge-cloud coordination to improve system efficiency, scalability, and responsiveness. Advanced AI models including neural networks, reinforcement learning, and federated learning are utilized for real-time distributed decision-making. The study also addresses key challenges such as resource constraints, communication overhead, cybersecurity risks, energy efficiency, scalability issues, and heterogeneous data management in edge systems. Experimental results show that AI-enabled edge computing significantly improves response time, communication efficiency, computational performance, and real-time intelligence generation compared to traditional cloud-centric models, making it highly suitable for next-generation smart city and industrial automation applications.