Jump to content

18470772. CAPACITY-BASED LOAD BALANCING IN SHARED RESOURCE POOL (MICROSOFT TECHNOLOGY LICENSING, LLC)

From WikiPatents

CAPACITY-BASED LOAD BALANCING IN SHARED RESOURCE POOL

Organization Name

MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor(s)

Wenbin Meng of Bellevue WA US

Hemant Kumar of Bellevue WA US

Rakesh Kelkar of Bellevue WA US

Karthik Raman of Sammamish WA US

Sanjay Ramanujan of Sammamish WA US

Kevin Joseph Riehm of Woodbury WA US

Theodore Dragov Todorov of Seattle WA US

CAPACITY-BASED LOAD BALANCING IN SHARED RESOURCE POOL

This abstract first appeared for US patent application 18470772 titled 'CAPACITY-BASED LOAD BALANCING IN SHARED RESOURCE POOL

Original Abstract Submitted

A system provides capacity-based load balancing across model endpoints of a cloud-based artificial intelligence (AI) model. The system includes a consumption determination engine executable to determine a net resource consumption for processing tasks in a workload generated by a client application for input to the trained machine learning model. The system also includes a load balancer that determines a distribution of available resource capacity in a shared resource pool comprising compute resources at each of the multiple model endpoints. The load balancer allocates parallelizable tasks of the workload among the compute resources at the multiple model endpoints based on the net resource consumption of the tasks and on the distribution of available resource capacity in the shared resource pool.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.