Optimizing Spectrum and Energy Efficiency in a Wifi-Based Industrial IoT Network

Industrial IoT networks are characterized by diverse use cases, each with distinct Quality of Service (QoS) requirements. Ensuring these requirements is critical for the successful deployment of applications and maintaining operational efficiency in industrial environments. Furthermore, IoT sensors and devices often operate under strict energy constraints, necessitating energy-efficient solutions. Consequently, effective network management must simultaneously optimize both energy and spectrum efficiency. To overcome this challenge, we propose a deep reinforcement learning (DRL) framework that dynamically optimizes the Modulation and Coding Scheme (MCS) and transmission power in WiFi-based IIoT networks. Our results demonstrate that the DRL-based approach can effectively enhance both the energy and spectrum efficiency. Our findings also reveal that aggressive energy-saving strategies can compromise spectrum efficiency and QoS, underscoring the need for careful trade-offs in network optimization.