Edge–IoT Integrated Architecture for Real-Time Data Processing and Intelligent Decision-Making in Smart City Environments

Abstract

The rapid expansion of smart city infrastructures has intensified the demand for scalable, low-latency, and intelligent data processing systems capable of handling heterogeneous Internet of Things (IoT) data streams. Traditional cloud-centric architectures face significant limitations in terms of latency, bandwidth consumption, and real-time responsiveness. To address these challenges, this paper proposes an Edge–IoT integrated architecture designed to enable real-time data processing and intelligent decision-making in smart city environments. The study synthesizes existing advancements in edge computing, IoT integration, and urban analytics to develop a structured conceptual framework that enhances distributed computation, reduces communication overhead, and improves system responsiveness.
The proposed architecture leverages edge nodes for localized processing, enabling near-real-time analytics for applications such as traffic monitoring, surveillance, environmental sensing, smart energy grids, and waste management systems. A key emphasis is placed on distributed intelligence, where edge devices collaboratively process and filter data before transmitting only relevant insights to centralized cloud systems. This hybrid model ensures improved scalability and operational efficiency while maintaining data security and system resilience.
The study critically analyzes prior research on edge-enabled smart city applications and identifies persistent challenges related to interoperability, security, computational constraints, and system integration. Findings suggest that while edge computing significantly enhances IoT efficiency, challenges remain in standardization, resource optimization, and cross-domain integration. The paper concludes by highlighting future directions in adaptive edge intelligence, machine learning integration, and autonomous urban systems.