Machine Learning and Dynamic Resource Management Platform

Back to all technologies
Download as PDF
2019-KUBI-68494
(No categories found)
Researchers at Purdue University have developed a new algorithm to monitor and control computational tasks in software programs by benchmarking software programs that cause delays or mishandle heterogeneous or cloud data. Currently, most code used for research and development tasks consumes large quantities of power, memory, and time. The resource management platform created by Purdue researchers prompts individual computer users to manually adjust computer hardware to optimize software usage, as well. In testing with existing computers, performance was improved by at least a factor of three.

Applications:
-Resource Management
-Reliable

Potential Applications:
-Research and Development
-Software
Mar 31, 2020
Utility Patent
United States
(None)
(None)

Apr 5, 2019
Provisional-Patent
United States
(None)
(None)

(None)
Copyright
United States
(None)
(None)
Purdue Office of Technology Commercialization
The Convergence Center
101 Foundry Drive, Suite 2500
West Lafayette, IN 47906

Phone: (765) 588-3475
Fax: (765) 463-3486
Email: otcip@prf.org