公开(公告)号：US12086710B2

公开(公告)日：2024-09-10

申请号：US17171282

申请日：2021-02-09

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Klaus-Dieter Lange ,  Mukund Kumar ,  Shreeharsha Gudal Neelakantachar ,  Hung D Cao

IPC: G06N3/08 ,  G06F17/18 ,  G06F18/214 ,  G06F18/23 ,  G06N20/10

CPC classification number: G06N3/08 ,  G06F17/18 ,  G06F18/2155 ,  G06F18/23 ,  G06N20/10

Abstract: Predictive big data capacity planning is described. An example includes instructions for receiving workload data and computing operation data related to workload processing for a customer in a computing infrastructure, the computing infrastructure including one or more clusters, the one or more clusters including one or more data nodes; analyzing the received data to identify relationship information between the workload data and the computing operation data; performing predictive analytics to identify a significant value that relates to performance variations in workload performance or usage pattern characteristics for data growth scale factors in the computing infrastructure; generating a knowledge base based at least in part on the predictive analytics; training a machine learning model based at least in part on the knowledge base; and utilizing the trained machine learning model to generate a computing infrastructure configuration recommendation for the customer.