DATACENTER SCHEDULING OF APPLICATIONS USING MACHINE LEARNING TECHNIQUES

摘要

A computer-implemented method including: (i) receiving a computational task to be processed by the datacenter environment; (ii) receiving a set of computational task parameters, The computational task parameters specifying characteristics of the computational task to be processed; (iii) receiving a set of computing entity parameters, The computing entity parameters specifying characteristics of the computing entities; (iv) transmitting the computational task parameters and the computing entity parameters to a scheduling entity; and (v) selecting one or more computing entities of The plurality of computing entities for processing the computational task by the scheduling entity, based on various factors.

主权项

1. A computer-implemented method for scheduling a computational task in a datacenter environment that includes a plurality of computing entities, the method comprising:
determining feedback information based, at least in part, on:
historical selections of computing entities of the plurality of computing entities for processing historical computing tasks, andhistorical processing results associated with the historical computing tasks as processed by the historical computing entity selections; receiving data corresponding to:
a new computational task to be processed by the datacenter environment,associated computational task parameters specifying characteristics of the new computational task, anda set of computing entity parameters, The computing entity parameters specifying characteristics of the computing entities of the plurality of computing entities; and selecting, by machine logic of a scheduling entity, one or more computing entities of The plurality of computing entities as selected computing entity(ies) for processing the new computational task based, at least in part, upon:
the set of computational task parameters,the set of computing entity parameters, andthe feedback information.