King's College London

Research portal

Network Orchestration in Mobile Networks via a Synergy of Model-driven and AI-based Techniques

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Original languageEnglish
Title of host publication2020 8th International Conference on Communications and Networking, ComNet2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728153209
DOIs
Published27 Oct 2020
Event8th International Conference on Communications and Networking, ComNet2020 - Virtual, Hammamet, Tunisia
Duration: 28 Oct 202030 Oct 2020

Publication series

Name2020 8th International Conference on Communications and Networking, ComNet2020 - Proceedings

Conference

Conference8th International Conference on Communications and Networking, ComNet2020
CountryTunisia
CityVirtual, Hammamet
Period28/10/202030/10/2020

Bibliographical note

Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

King's Authors

Abstract

As data traffic volume continues to increase, caching of popular content at strategic network locations closer to the end user can enhance user experience and ease the utilization of highly congested links in the network. A key challenge in the area of proactive caching is finding the optimal locations to host the popular content items under various optimization criteria. These problems are combinatorial in nature and therefore finding optimal and/or near optimal decisions is computationally expensive. In this paper a framework is proposed to reduce the computational complexity of the underlying integer mathematical program by first predicting decision variables related to optimal locations using a deep convolutional neural network (CNN). The CNN is trained in an offline manner with optimal solutions and is then used to feed a much smaller optimization problems which is amenable for real-time decision making. Numerical investigations reveal that the proposed approach can provide in an online manner high quality decision making; a feature which is crucially important for real-world implementations.

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454