Cluster Edge Intelligence

Intelligence discoverability and observability in edge infrastructure

It is predicted by Gartner that 50% of the enterprise-generated data will be created and processed in the edge infrastructure comprised of ever-increasing billions of edge devices. Instead of implementing the intelligence in the cloud environment giving the full responsibility to manage a large number of edge devices, a minimal and required intelligence is imposed on the edge devices, enabling the edge intelligence that works in a master-worker approach. The major problem with this approach is that an edge device relies mostly on the data collected by the onboard sensors and the built-in or cloud-instructed intelligence, resulting in little scope for cooperation and collaboration among peers and hence no device-to-device knowledge transfer.
Unlike the traditional approach to cluster the IoT devices based on the location and other meta information, a new research direction focuses on clustering the intelligence that the edge infrastructure is equipped with, also known as Clustered Edge Intelligence (CEI). Intelligence discoverability and observability are some of the primary challenges that need to be addressed to realize the full capacity of CEI. This Ph.D. project will focus on designing and developing dynamic intelligence clustering methodology with the discoverability and observability feature for large-scale edge infrastructure.

CloudTraceBucket

CloudTraceBucket - is a web application, which allows cloud researchers to easily upload, download and visualize data based on user-selected query filters.
A Demo verison of the project can be seen here. Make sure that, you are in the University's network.
GitHub Repo: https://github.com/chinmaya-dehury/CloudTraces

TOSCA for ML (TOSCA-ML)

GitHub Repo

OASIS TOSCA provides an experience to model the applications deployable across public and private cloud environments. The cloud application can be described as a set of nodes, representing application components, and a set of edges, representing the relationships among application components. RADON TOSCA provides a set of abstract and concrete node types for modelling the cloud applicaitons with serverless integration, data pipeline, autoscaling and monitoring capabilities, trigger, etc. This project focuses on providing standard-based AI/ML applications development experience that can be deployed across multiple cloud environments.

Some questions to answer:

E2C-Block ; Blockchain for Edge-Cloud Computing Continuum

E2C-Block is a proposed model architecture that aims to provide an effective solution for managing and securing data generated by IoT sensors in a distributed environment. It ensures that data generated by these IoT sensors are securely transmitted and stored tamper-proof. To store the vast amount of data generated by IoT sensors, the E2C-Block architecture uses an offsite data store. This provides an optimal storage option as it allows data to be stored in a secure and scalable manner.
Visit our GitHub Repo to know more.

TOSCA-BLOCK: Standard for design and development of Blockchain applications

Blockchain-based application may consists of several components including Orderer, Certifying authority, peers, users, clients, data, computing nodes/servers, transactions.
  1. What platform to consider?
  2. More questions coming soon.....

Energy profiling in HPC

Understand the behavior of energy consumption with the workload in HOC environment. For this, this project focuses on collecting the data related to the workload and the energy consumed by the servers.

  1. What data should be collected?
  2. To what granularity, the energy consumption measurements should be colleted for each servers/pod/rack?
  3. What are the different energy sources HPC is using?
  4. Does HPC center has the informaiton about energy consumed by each servers?
  5. How the workloads are being distributed among the clusters?
  6. What technology/strategy is used to save energy?