Edge AI-Enabled Distributed Resource Optimization Framework for Latency-Aware Smart City Applications

Abstract

Edge Artificial Intelligence (Edge AI) has emerged as a transformative paradigm for enabling intelligent, low-latency, and scalable resource optimization across modern smart city infrastructures. Rapid urbanization and the proliferation of Internet of Things (IoT) technologies have led to the deployment of large-scale smart city ecosystems consisting of connected sensors, autonomous transportation systems, surveillance networks, smart healthcare services, intelligent energy grids, environmental monitoring platforms, and edge-enabled communication infrastructures. These distributed urban environments continuously generate massive volumes of heterogeneous real-time data requiring efficient computational resource management, adaptive task scheduling, and latency-aware intelligent decision-making. Traditional cloud-centric architectures often suffer from high communication delay, bandwidth limitations, centralized bottlenecks, and inefficient real-time responsiveness, making them unsuitable for latency-sensitive smart city applications. This research proposes an Edge AI-Enabled Distributed Resource Optimization Framework for Latency-Aware Smart City Applications. The proposed framework integrates edge intelligence, deep reinforcement learning, transformer-based contextual analytics, graph neural resource reasoning, adaptive task scheduling, and latency-aware optimization mechanisms to support scalable distributed smart city intelligence. The framework dynamically optimizes computational resources, network bandwidth, edge-node allocation, and real-time service scheduling across distributed urban infrastructures while minimizing latency and improving intelligent service delivery. The proposed architecture supports applications including intelligent transportation systems, smart traffic management, public safety surveillance, healthcare monitoring, environmental analytics, smart energy management, and autonomous urban infrastructure optimization.