Autodeepslice: A Data Driven Network Slicing Technique of 5G Network using Automatic Deep Learning

Deepraj Chowdhury, Rupanjan Das, Risav Rana, Ashutosh Dhar Dwivedi, Pushpita Chatterjee, Raghava Rao Mukkamala

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


With the advancement of mobile networks, and the revolution of mobile communication from 1G to 5G, human dependency has increased, so it has become the most priority to provide an efficient and highly reliable network. The 5G networks need high capacity and high-speed data transfer, with the least latency and increased security. 5G service providers are trying to find a programmable solution that can handle a huge number of independent service users on the same physical infrastructure. Network slicing is used to provide end-to-end network resource allocation. To accelerate the 5G network performance, Artificial Intelligence (AI) powered data-driven based decisions will be used for future communication. In this proposed work, Automatic deep learning has been implemented, where the hyperparameter will automatically select the algorithm and tune the hyperparameter. The proposed model AUTODEEPSLICE efficiently makes intelligent decisions and will choose the best network slice at the time of network breakdown.
Original languageEnglish
Title of host publication2022 IEEE GLOBECOM Workshops, GC Wkshps 2022 - Proceedings
Number of pages5
Place of PublicationLos Alamitos, CA
Publication date2022
ISBN (Print)9781665459754
ISBN (Electronic)9781665459761
Publication statusPublished - 2022
Event2022 IEEE Globecom Workshops: GC Workshops 2022 - Rio de Janeiro, Brazil
Duration: 4 Dec 20228 Dec 2022


Workshop2022 IEEE Globecom Workshops
CityRio de Janeiro
Internet address


  • Automatic deep learning
  • Autokeras
  • 5G cellular networks
  • Optimised network slicing

Cite this