Adaptive Gaussian Process Spectral Kernel Learning for 5G Wireless Traffic Prediction

Wireless traffic prediction plays a crucial role in network management. However, achieving an accurate prediction for the fifth-generation (5G) network is intensely difficult because the time series data collected from 5G multi-antenna system shows rather complex patterns. To accurately capture intricate wireless traffic patterns and calibrate the prediction uncertainty, this paper resorts to the Gaussian process regression (GPR) model and proposes an adaptive kernel learning method. Specifically, we adopt a universal kernel, namely the grid spectral mixture (GSM) kernel, in the GPR model and further propose a novel trans-dimensional kernel learning algorithm by combining optimization and sampling methods to obtain the best GSM kernel configuration, boosting the prediction performance and saving the storage overhead. Experimental results demonstrate that GPR with the proposed adaptive spectral kernel learning algorithm yields superior prediction performance compared to its competitors.