COGNITIVE RADIO NETWORKS FOR DYNAMIC SPECTRUM MANAGEMENT IN SMART CITY ENVIRONMENTS

Abstract

Smart cities demand highly efficient wireless communication to support diverse IoT devices, sensors, and urban applications. Cognitive radio networks (CRNs) provide dynamic spectrum access, enabling intelligent utilization of underused frequency bands. This paper proposes an AI-enabled framework for dynamic spectrum management in smart city environments, leveraging machine learning algorithms to optimize spectrum allocation, reduce interference, and improve network throughput. The system continuously monitors spectrum usage and predicts optimal channel assignment for IoT devices and communication nodes. Simulation results demonstrate improved spectral efficiency, reduced latency, and enhanced energy efficiency compared to traditional static allocation methods. The framework supports scalability, adaptability, and real-time decision-making, making it suitable for dense urban deployments. Integration of AI ensures continuous learning and intelligent spectrum management in highly dynamic networks.