Reinforcement Learning for Energy Efficient Resource Allocation in ISAC Systems with Integrated WiFi-Radar

Integrated sensing and communication (ISAC) systems are emerging as a key technology to optimize the use of wireless resources by simultaneously supporting communication and sensing functions. This paper introduces an innovative ISAC system that integrates Wi-Fi channel state information (CSI)-based sensing and frequency-modulated continuous-wave (FMCW) radar within the Wi-Fi frequency band to enhance energy efficiency (EE). Wi-Fi CSI-based sensing enables simultaneous communication and environmental sensing using existing infrastructure, but it often suffers from high power consumption. Conversely, FMCW radar offers lower power consumption with the capability of self-transmission and reception but is limited by bandwidth constraints when operating in Wi-Fi bands. To overcome these challenges, we formulate the resource allocation problem as an optimization task that maximizes EE while maintaining sensing accuracy, managing power consumption, and respecting bandwidth limitations. The proposed system utilizes a dueling deep Q-Network (DQN) with reward shaping to learn optimal resource allocation strategies, showing a 36% to 40% increase in EE compared to traditional DQN models, providing a viable direction for the advancement of ISAC technologies.