Graduate School and Research Center in Digital Sciences

Problem-adapted artificial intelligence for online network optimization

Vassilaras, Spyridon; Vigneri, Luigi; Liakopoulos, Nikolaos; Paschos, Georgios S.; Destounis, Apostolos; Spyropoulos, Thrasyvoulos; Debbah, Merouane

Submitted to ArXiV, 26 March 2019

Future 5G wireless networks will rely on agile and automated network management, where the usage of diverse resources must be jointly optimized with surgical accuracy. A number of key wireless network functionalities (e.g., traffic steering, power control) give rise to hard optimization problems. What is more, high spatio-temporal traffic variability coupled with the need to satisfy strict per slice/service SLAs in modern networks, suggest that these problems must be constantly (re-)solved, to maintain close-to-optimal performance. To this end, we propose the framework of Online Network Optimization (ONO), which seeks to maintain both agile and efficient control over time, using an arsenal of data-driven, online learning, and AI-based techniques. Since the mathematical tools and the studied regimes vary widely among these methodologies, a theoretical comparison is often out of reach. Therefore, the important question "what is the right ONO technique?" remains open to date. In this paper, we discuss the pros and cons of each technique and present a direct quantitative comparison for a specific use case, using real data. Our results suggest that carefully combining the insights of problem modeling with state-of-the-art AI techniques provides significant advantages at reasonable complexity. 

Arxiv Bibtex

Title:Problem-adapted artificial intelligence for online network optimization
Type:Conference
Language:English
City:
Date:
Department:Communication systems
Eurecom ref:5930
Copyright: © EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Submitted to ArXiV, 26 March 2019 and is available at :
Bibtex: @inproceedings{EURECOM+5930, year = {2019}, title = {{P}roblem-adapted artificial intelligence for online network optimization}, author = {{V}assilaras, {S}pyridon and {V}igneri, {L}uigi and {L}iakopoulos, {N}ikolaos and {P}aschos, {G}eorgios {S}. and {D}estounis, {A}postolos and {S}pyropoulos, {T}hrasyvoulos and {D}ebbah, {M}erouane}, booktitle = {{S}ubmitted to {A}r{X}i{V}, 26 {M}arch 2019}, address = {}, month = {03}, url = {http://www.eurecom.fr/publication/5930} }
See also: