Wireless Channel Availability Forecasting with a Sparse Geolocation Spectrum Database by Penalty-Regularization Logistic Models

Abstract

Television uses electromagnetic waves that carry audio and video. The unused frequencies orchannels in broadcasting services are referred to as television white spaces. The unused spectrum can bemanaged to provide internet access in coordination with surrounding TV channels to avoid interference.Different ways of dynamically managing spectrum management have been conceived, and geolocationdatabases are considered the better option. Geolocation databases, when updated and complete, are helpfulwhen frequencies are dynamically shared. In real life, the spectrum availability for a secondary user lacksnumerous information; hence, it is sparse. This paper forecasts wireless channel availability given a sparsegeolocation spectrum database. A dynamic sparse forecasting model is proposed through logistic penalizedregression. Results show that forecasting accuracy is mostly above 90% on average when sparsity penalty termsare incorporated into the model. Forecasting accuracy is improved when penalty terms are integrated into thelogistic regression models to account for sparsity.