Cut, Distil and Encode (CDE): Split cloud-edge deep inference

Marion Sbai, Muhamad Risqi U. Saputra, Niki Trigoni, Andrew Markham

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

8 Citations (Scopus)


In cloud-edge environments, running all Deep Neural Network (DNN) models on the cloud causes significant network congestion and high latency, whereas the exclusive use of the edge device for execution limits the size and structure of the DNN, impacting accuracy. This paper introduces a novel partitioning approach for DNN inference between the edge and the cloud. This is the first work to consider simultaneous optimization of both the memory usage at the edge and the size of the data to be transferred over the wireless link. The experiments were performed on two different network architectures, MobileNetV1 and VGG16. The proposed approach makes it possible to execute part of the network on very constrained devices (e.g., microcontrollers), and under poor network conditions (e.g., LoRa) whilst retaining reasonable accuracies. Moreover, the results show that the choice of the optimal layer to split the network depends on the bandwidth and memory constraints, whereas prior work suggests that the best choice is always to split the network at higher layers. We demonstrate superior performance compared to existing techniques.

Original languageEnglish
Title of host publication2021 18th IEEE International Conference on Sensing, Communication and Networking, SECON 2021
EditorsLuca Chiaraviglio, Chenyang Lu, Kay Romer
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages9
ISBN (Electronic)9781665441087
ISBN (Print)9781665431118
Publication statusPublished - 2021
Externally publishedYes
EventIEEE International Conference on Sensing, Communication and Networking 2021 - Online, United States of America
Duration: 6 Jul 20219 Jul 2021
Conference number: 18th (Proceedings)

Publication series

NameAnnual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks workshops
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISSN (Print)2155-5486
ISSN (Electronic)2155-5494


ConferenceIEEE International Conference on Sensing, Communication and Networking 2021
Abbreviated titleSECON 2021
Country/TerritoryUnited States of America
Internet address


  • CNN
  • deep learning
  • Edge computing
  • tasks partitioning

Cite this