Learning Power Spectrum Maps From Quantized Power Measurements
Abstract: Power spectral density (PSD) maps providing the distribution of RF power across space and frequency are constructed using power measurements collected by a network of low-cost cost sensors. By introducing linear compression and quantization to a small number of bits, sensor measurements can be communicated to the fusion center with minimal bandwidth requirements. Strengths of datadata and model-driven driven approaches are combined to develop estimators capable of incorporating multiple forms of spectral and propagation prior prior information while fitting the rapid variations of shadow fading across space. To this end, novel nonparametric and semiparametric formulations are investigated. It is shown that PSD maps can be obtained using support vector machine machine-type type solvers. In ad addition to batch approaches, an online algorithm attuned to realreal-time operation is developed. Numerical tests assess the performance of the novel algorithms.