skip to main content
DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Multi-model blending

Abstract

A method and a system to perform multi-model blending are described. The method includes obtaining one or more sets of predictions of historical conditions, the historical conditions corresponding with a time T that is historical in reference to current time, and the one or more sets of predictions of the historical conditions being output by one or more models. The method also includes obtaining actual historical conditions, the actual historical conditions being measured conditions at the time T, assembling a training data set including designating the two or more set of predictions of historical conditions as predictor variables and the actual historical conditions as response variables, and training a machine learning algorithm based on the training data set. The method further includes obtaining a blended model based on the machine learning algorithm.

Inventors:
; ; ; ;
Issue Date:
Research Org.:
International Business Machines Corp., Armonk, NY (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1329307
Patent Number(s):
9471884
Application Number:
14/291,720
Assignee:
INTERNATIONAL BUSINESS MACHINES CORPORATION (Armonk, NY)
Patent Classifications (CPCs):
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G - PHYSICS G01 - MEASURING G01W - METEOROLOGY
DOE Contract Number:  
EE0006017
Resource Type:
Patent
Resource Relation:
Patent File Date: 2014 May 30
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS; 97 MATHEMATICS AND COMPUTING

Citation Formats

Hamann, Hendrik F., Hwang, Youngdeok, van Kessel, Theodore G., Khabibrakhmanov, Ildar K., and Muralidhar, Ramachandran. Multi-model blending. United States: N. p., 2016. Web.
Hamann, Hendrik F., Hwang, Youngdeok, van Kessel, Theodore G., Khabibrakhmanov, Ildar K., & Muralidhar, Ramachandran. Multi-model blending. United States.
Hamann, Hendrik F., Hwang, Youngdeok, van Kessel, Theodore G., Khabibrakhmanov, Ildar K., and Muralidhar, Ramachandran. Tue . "Multi-model blending". United States. https://www.osti.gov/servlets/purl/1329307.
@article{osti_1329307,
title = {Multi-model blending},
author = {Hamann, Hendrik F. and Hwang, Youngdeok and van Kessel, Theodore G. and Khabibrakhmanov, Ildar K. and Muralidhar, Ramachandran},
abstractNote = {A method and a system to perform multi-model blending are described. The method includes obtaining one or more sets of predictions of historical conditions, the historical conditions corresponding with a time T that is historical in reference to current time, and the one or more sets of predictions of the historical conditions being output by one or more models. The method also includes obtaining actual historical conditions, the actual historical conditions being measured conditions at the time T, assembling a training data set including designating the two or more set of predictions of historical conditions as predictor variables and the actual historical conditions as response variables, and training a machine learning algorithm based on the training data set. The method further includes obtaining a blended model based on the machine learning algorithm.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2016},
month = {10}
}

Patent:

Save / Share:

Works referenced in this record:

Fault Diagnosis for Batch Processes Using Multi-model FDA with Moving Window
conference, January 2005


A novel virtual age reliability model for Time-to-Failure prediction
conference, October 2010


A path prediction model to support mobile multimedia streaming
conference, June 2012

  • Nadembega, Apollinaire; Hafid, Abdelhakim; Taleb, Tarik
  • ICC 2012 - 2012 IEEE International Conference on Communications, 2012 IEEE International Conference on Communications (ICC)
  • https://doi.org/10.1109/ICC.2012.6364149

A resource prediction model for virtualization servers
conference, July 2012