Sensing and Communication Integrated Optimization for Multi-Spectral Electric Equipment Monitoring

Electric equipment monitoring is essential to ensure the secure operation and maintenance in high-voltage substations. To support accurate electric equipment monitoring, multi-spectral technology is emerging as an advanced method. Unmanned aerial vehicle (UAV) equipped with multi-spectral imaging camera can provide intelligent monitoring through the data sensing and communication. In this paper, we focus on the integrated sensing and communication joint optimization problem. The objective is to maximize the average amount of image data sensed by UAV through jointly optimizing sensing and communication, i.e., image acquisition frequency, image depth, and transmission power. We propose a deep Q network-based integrated sensing and communication joint optimization algorithm for multi-spectral electric equipment monitoring named DIGITAL to solve it. DIGITAL can learn optimal monitoring strategy under complex and dynamic environment of high-voltage substations. Moreover, DIGITAL also realizes energy awareness through the dynamic adjustment of optimization strategy based on energy consumption as well as harvested energy. The superiority of DIGITAL is verified through simulations.