Two-Phase Split Computing Framework in Edge-Cloud Continuum

Haneul Ko, Bokyeong Kim, Yumi Kim, Sangheon Pack

Research output: Contribution to journalArticlepeer-review


Split computing is a promising approach to reduce the inference latency of deep neural network (DNN) models. In this paper, we propose a two-phase split computing framework (TSCF). In TSCF, for vertical inter-layer splitting between the computing nodes at different levels (e.g., central and edge clouds), a shortest path problem in a directed graph is formulated and a pruning-based low-complexity solution is devised. In addition, for horizontal intra-layer splitting between the computing nodes at the same level (e.g., edge clouds), the execution units of a specific layer are further divided and distributed to the computing nodes at the same level proportionally to their available resources. The evaluation results demonstrate that TSCF can reduce inference latency more than 38.8% compared to the traditional inter-layer splitting scheme by efficiently using the resources of distributed computing nodes. In addition, it is demonstrated that near-optimal performance in terms of inference latency can be achieved even with a pruning-based low-complexity solution.

Original languageEnglish
Pages (from-to)1
Number of pages1
JournalIEEE Internet of Things Journal
Publication statusAccepted/In press - 2024

Bibliographical note

Publisher Copyright:


  • Artificial neural networks
  • Cloud computing
  • Computational modeling
  • Internet of Things
  • Mobile handsets
  • Optimization
  • Performance evaluation
  • Two-phase split computing
  • deep neural network
  • inference latency
  • inter-layer splitting
  • intra-layer splitting

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications


Dive into the research topics of 'Two-Phase Split Computing Framework in Edge-Cloud Continuum'. Together they form a unique fingerprint.

Cite this