The advent of mobile phones paved the way for a new paradigm for gathering sensor data termed Public Sensing (PS). PS uses built-in sensors of mobile devices to opportunistically gather sensor data. For instance, the microphones of a crowd of mobile phones can be used to capture sound samples, which can be used to construct a city noise map. A great challenge of PS is to reduce the energy consumption of mobile devices since otherwise users might not be willing to participate. One crucial part in the overall power consumption is the energy required for the communication between the mobile devices and the infrastructure. In particular, the communication required for sending sensing queries to mobile devices has been largely neglected in the related work so far. Therefore, in this paper, we address the problem of minimizing communication costs for the distribution of sensing queries. While existing systems simply broadcast sensing queries to all devices, we use a selective strategy by addressing only a subset of devices. In order not to negatively affect the quality of sensing w.r.t. completeness, this subset is carefully chosen based on a probabilistic sensing model that defines the probability of mobile devices to successfully perform a given sensing query. Our evaluations show that with our optimized sensing query distribution, the energy consumption can be reduced by more than 70% without significantly reducing the quality of sensing.