Abstract
Deep-quantile regression is leveraged to capture traffic prediction uncertainty over future network planning intervals. We show that quantile predictions, acting as discriminative margins, result to significant spectrum savings compared to empirically estimated myopic margins considered.
© 2022 The Author(s)
PDF Article | Presentation VideoMore Like This
Yan Liu, Qian Hu, Xiaoli Huo, and Anxu Zhang
P_CM9_01 Conference on Lasers and Electro-Optics/Pacific Rim (CLEO/PR) 2022
L. A. J. Mesquita, K. D. R. Assis, R. C. Almeida, R. Nejabati, and D. Simeonidou
Tu5.66 European Conference and Exhibition on Optical Communication (ECOC) 2022
Stefan Bodamer, Jan Späth, and Christoph Glingener
ThG5 Optical Fiber Communication Conference (OFC) 2004