Network Scheduling for Inter-Dependent Edge-Cloud Processing

People

Klara Nahrstedt, University of Illinois, Urbana-Champaign (UIUC): Principle Investigator
Claudiu B Danilov , The Boeing Company: Principle Investigator
Ragini Gupta, University of Illinois, Urbana-Champaign (UIUC): PhD Student

Time Line

2022 ~ present

Project Description

Interdependent multi-sources are becoming very common in complex cyber-physical environments
deploying three-tier distributed sensors-edge-cloud computing and communication architectures. The
multi-sensory-edge-cloud environments are organized in a hierarchical inverted multicast paradigm,
which can cause congestion problems as the scale and bandwidth of sensors increases. This work explores
the inverted multicast congestion challenges in Internet of Things under interdependent multi-source
conditions, which lead to correlated and distributed resource scheduling decisions with strong causal
relationships. These dependencies, furthermore, lead to major uncertainties of availability of information
and the need for probabilistic learning frameworks, to assess how to best coordinate and schedule network and compute resources for heterogenous sources, resolve congestions, and still execute correct resource decision with high probabilities under uncertainties and imperfect information at edges and cloud processing nodes.

Publication

Ragini Gupta, Beitong Tian, Klara Nahrstedt, Claudiu Danilov, “RESONATE: Advancing Sustainability in IoT Networks through Smart and Selective Streaming”, IEEE International Conference on Collaboration and Internet Computing (IEEE CIC) 2023, Atlanta, USA, November 1-3, 2023.

Funding Agencies

This work was supported by the Boeing Company.