SmartCityNet: Adaptive Resource Management for Urban IoT Networks
Pooja Raghunath Negi, Anju Gautam, Shanti Verma · 2024
The proposed system, named as “SmartNetOpt,” employed a machine Learning-Driven algorithm Reinforcements based Learning (RL) techniques for optimizing resource management on Smart City based Internet of Things (IoT) networks. In Smart City environmental conditions, where diverse IoT devices will be interconnected to improve urban operations, an efficient allocation and utilization of resources are critical to enhance the overall Networks performance and its sustainability. SmartNetOpt addressed the challenging situation by leveraging RL algorithms to dynamically allocate bandwidth, managing power conservation and consumption with optimized data routing on the IoT network infrastructure. With Thorough iterative type of learning and adaptation, SmartNetOpt will autonomously improvise the resource allocation strategies depending on real-time network conditions and related performance objectives. By employing RL-based optimization, SmartNetOpt could offer a scalable and adaptable solution for enhancing resource management for Smart City IoT type of networks which lead to improved Efficacy, reliability, and sustainability of urban infrastructure.