Supercomputer assisted generation of machine learning agents for the calibration of building energy models

Sanyal, Jibonananda; Im, Piljae; Edwards, Richard E.

doi:10.1145/2484762.2484818

Cited by 15 publications

(11 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MLSuite is used in several specific ways as part of the Autotune project : First is the exploration of a more data‐driven sBEM through machine learning prediction of building performance as a function of observed data using statistical methods rather than complex, physics‐based, engineering algorithms . Second , usage is speeding up annual E+ simulations by creating surrogate simulation engines that trade off accuracy for order of magnitude speedup . Third , creating inverse simulation engines that use sensor data (corresponding to simulation output) to predict an anticipated set of simulation input parameters, which can act as seed points for further exploration of the true inputs. Fourth , it is being used as a sensor quality assurance mechanism. It both fills in missing values and detects outliers in time‐series data by intelligently predicting the anticipated value as a function of temporal patterns for a specific data channel in combination with spatial patterns of other data channels (e.g., inferential sensing).…”

Section: Machine Learning Agentsmentioning

confidence: 99%

“…This paper describes the ‘Autotune’ methodology being developed at the Oak Ridge National Laboratory, which automatically calibrates a building energy model using supplied utility data for building retrofit purposes. This is achieved by using trained machine agents that are generated from large parametric simulations run on supercomputing systems using machine learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…The development of an autotuning capability (Figure ) to intelligently adapt building models or templates to building performance data would significantly facilitate market adoption of energy modeling software, aid in accurate use cases such as the effective retrofit strategies for existing buildings, and promote Department of Energy's Building Technologies Program's goals of increased market penetration for energy modeling capabilities.…”

Section: Introductionmentioning

confidence: 99%

“…To a large extent, this addresses the challenge of accurately modeling and scaling the building types across American Society of Heating, Refrigerating, and Air-Conditioning Engineers (ASHRAE) climate zones [3,4,6] and projecting how specific policies or retrofit packages would maximize return on investment with subsidies through federal, state, local, and utility tax incentives, rebates, and loan programs. This paper describes the 'Autotune' methodology [8,9] being developed at the Oak Ridge National Laboratory, which automatically calibrates a building energy model using supplied utility data for building retrofit purposes. This is achieved by using trained machine agents that are generated from large parametric simulations run on supercomputing systems using machine learning algorithms.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Calibrating building energy models using supercomputer trained machine learning agents

Sanyal

Edwards

et al. 2014

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

SUMMARYBuilding energy modeling (BEM) is an approach to model the energy usage in buildings for design and retrofit purposes. EnergyPlus is the flagship Department of Energy software that performs BEM for different types of buildings. The input to EnergyPlus can often extend in the order of a few thousand parameters that have to be calibrated manually by an expert for realistic energy modeling. This makes it challenging and expensive thereby making BEM unfeasible for smaller projects. In this paper, we describe the ‘Autotune’ research that employs machine learning algorithms to generate agents for the different kinds of standard reference buildings in the US building stock. The parametric space and the variety of building locations and types make this a challenging computational problem necessitating the use of supercomputers. Millions of EnergyPlus simulations are run on supercomputers that are subsequently used to train machine learning algorithms to generate agents. These agents, once created, can then run in a fraction of the time thereby allowing cost‐effective calibration of building models. Published 2014. This article is a US Government work and is in the public domain in the USA.

show abstract

Section: Machine Learning Agentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Calibrating building energy models using supercomputer trained machine learning agents

Sanyal

Edwards

et al. 2014

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Conversely, a penalty function may also be employed to reduce the likelihood of deviating too far from the base-case [36][37][38]. Sanyal and New [39] proposed a methodology in their ''auto-tune" project, leveraging supercomputing, large databases of simulations, and machine learning to implement automatic model calibration. The state-ofthe-art automated calibration is more akin to solving a problem of multi-objective optimization, which is more mathematical-based rather than physical-based [38,40,41].…”

Section: Introductionmentioning

confidence: 99%

A pattern-based automated approach to building energy model calibration

et al. 2016

View full text Add to dashboard Cite

Performance analysis and optimization for scalable deployment of deep learning models for country‐scale settlement mapping on Titan supercomputer

Kurte

Sanyal

Berres

et al. 2019

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

This paper presents a scalable object detection workflow for detecting objects, such as settlements, from remotely sensed (RS) imagery. We have successfully deployed this workflow on Titan supercomputer and utilized it for the task of mapping human settlement at a country scale.The performance of various stages in the workflow was analyzed before making it operational.The workflow implemented various strategies to address issues such as suboptimal resource utilization and long-tail effects due to unbalanced image workload, data loss due to runtime failures, and maximum wall-time constraints imposed by Titan's job scheduling policy. A mean shift clustering-based static load balancing strategy was implemented, which partitions the image load such that each partition contained similar-sized images. Furthermore, a checkpoint-restart strategy was added in the workflow as a fault-tolerance mechanism to prevent the data losses due to unforeseen runtime failures. The performance of the above-mentioned strategies was observed in various scenarios, such as node failure, exceeding wall time, and successful completion. Using this workflow, we have processed an RS data set that has a spatial resolution of 0.31 m and is comprised of 685 675 km 2 of area of the Republic of Zambia in under six hours using 5426 nodes of the Titan supercomputer. KEYWORDS convolutional neural network, deep learning, fault tolerance, HPC, human settlement mapping, load balancing 1 INTRODUCTION The recent development in sensor electronics is enabling remote sensing (RS) satellites to capture data at a submeter scale. This advancement in RS technology offers new opportunities to understand Earth's features at a finer spatial scale and motivates the development of novel approaches for complex problems such as mapping human settlements. However, as an effect of the development in sensor technology, a rapid growth in the cumulative volume of Earth observation (EO) archives has been observed during the last few years. 1 A typical very-high-resolution RS imagery contains billions of pixels, and for a country-scale mapping, thousands of such images need to be processed, which is computationally demanding. This computational load can pose problems during time-critical events, such as with flooding and wild fire natural disasters, when real-time/near-real-time mapping of human settlement in the affected area is necessary. However, high-performance computing (HPC)-driven approaches for processing such huge volume of data can mitigate this problem.

show abstract

Supercomputer assisted generation of machine learning agents for the calibration of building energy models

Cited by 15 publications

References 1 publication

Calibrating building energy models using supercomputer trained machine learning agents

Calibrating building energy models using supercomputer trained machine learning agents

A pattern-based automated approach to building energy model calibration

Performance analysis and optimization for scalable deployment of deep learning models for country‐scale settlement mapping on Titan supercomputer

Contact Info

Product

Resources

About