A methodology for meta-model based optimization in building energy models

A methodology for meta-model based optimization in building energy models. Eisenhower, B., O’Neill, Z., Narayanan, S., Fonoberov, V. A., & Mezíc, I. Energy and Buildings, 47(0):292--301, 2012.
doi abstract bibtex

As building energy models become more accurate and numerically efficient, model-based optimization of building design and operation is becoming more practical. The state-of-the-art typically couples an optimizer with a building energy model which tends to be time consuming and often leads to suboptimal results because of the mathematical properties of the energy model. To mitigate this issue, we present an approach that begins by sampling the parameter space of the building model around its baseline. An analytical meta-model is then fit to this data and optimization can be performed using different optimization cost functions or optimization algorithms with very little computational effort. Uncertainty and sensitivity analysis is also performed to identify the most influential parameters for the optimization. A case study is explored using an EnergyPlus model of an existing building which contains over 1000 parameters. When using a cost function that penalizes thermal comfort and energy, 45% annual energy reduction is achieved while simultaneously increasing thermal comfort by a factor of two. We compare the optimization using the meta-model approach with an approach using the EnergyPlus model integrated with the optimizer on a smaller problem using only seven optimization parameters illustrating good performance.

@article{ Eisenhower2011,
  abstract = {As building energy models become more accurate and numerically efficient, model-based optimization of building design and operation is becoming more practical. The state-of-the-art typically couples an optimizer with a building energy model which tends to be time consuming and often leads to suboptimal results because of the mathematical properties of the energy model. To mitigate this issue, we present an approach that begins by sampling the parameter space of the building model around its baseline. An analytical meta-model is then fit to this data and optimization can be performed using different optimization cost functions or optimization algorithms with very little computational effort. Uncertainty and sensitivity analysis is also performed to identify the most influential parameters for the optimization. A case study is explored using an EnergyPlus model of an existing building which contains over 1000 parameters. When using a cost function that penalizes thermal comfort and energy, 45% annual energy reduction is achieved while simultaneously increasing thermal comfort by a factor of two. We compare the optimization using the meta-model approach with an approach using the EnergyPlus model integrated with the optimizer on a smaller problem using only seven optimization parameters illustrating good performance.},
  author = {Eisenhower, Bryan and O’Neill, Zheng and Narayanan, Satish and Fonoberov, Vladimir A. and Mezí{c}, Igor},
  doi = {10.1016/j.enbuild.2011.12.001},
  file = {:Users/adam/Library/Application Support/Mendeley Desktop/Downloaded/SSQ386AE/S0378778811005962.html:html;:Users/adam/Library/Application Support/Mendeley Desktop/Downloaded/UEJ3PME2/Eisenhower et al. - A methodology for meta-model based optimization in.pdf:pdf},
  issn = {0378-7788},
  journal = {Energy and Buildings},
  keywords = {Comfort and energy optimization,EnergyPlus,Machine learning,Sensitivity analysis},
  mendeley-tags = {Comfort and energy optimization,EnergyPlus,Machine learning,Sensitivity analysis},
  number = {0},
  pages = {292--301},
  title = {{A methodology for meta-model based optimization in building energy models}},
  volume = {47},
  year = {2012}
}

Downloads: 0

{"_id":{"_str":"524b09c4c0bcb22b6d0005f6"},"__v":0,"authorIDs":[],"author_short":["Eisenhower, B.","O’Neill, Z.","Narayanan, S.","Fonoberov, V.<nbsp>A.","Mezíc, I."],"bibbaseid":"eisenhower-oneill-narayanan-fonoberov-mezic-amethodologyformetamodelbasedoptimizationinbuildingenergymodels-2012","bibdata":{"html":"<div class=\"bibbase_paper\"> \n\n\n<span class=\"bibbase_paper_titleauthoryear\">\n\t<span class=\"bibbase_paper_title\"><a name=\"Eisenhower2011\"> </a>A methodology for meta-model based optimization in building energy models.</span>\n\t<span class=\"bibbase_paper_author\">\nEisenhower, B.; O’Neill, Z.; Narayanan, S.; Fonoberov, V. A.; and Mezíc, I.</span>\n\t\n</span>\n\n\n\n<i>Energy and Buildings</i>,\n\n47(0):292--301.\n\n 2012.\n\n\n\n\n<br class=\"bibbase_paper_content\"/>\n\n<span class=\"bibbase_paper_content\">\n \n \n \n <a href=\"javascript:showBib('Eisenhower2011')\"\n class=\"bibbase link\">\n \n\t\n\t\n\t\n BibTeX\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n  \n <a class=\"bibbase_abstract_link bibbase link\"\n href=\"javascript:showAbstract('Eisenhower2011')\">\n Abstract\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n \n\n \n \n \n</span>\n\n<div class=\"well well-small bibbase\" id=\"bib_Eisenhower2011\"\n style=\"display:none\">\n <pre>@article{ Eisenhower2011,\n abstract = {As building energy models become more accurate and numerically efficient, model-based optimization of building design and operation is becoming more practical. The state-of-the-art typically couples an optimizer with a building energy model which tends to be time consuming and often leads to suboptimal results because of the mathematical properties of the energy model. To mitigate this issue, we present an approach that begins by sampling the parameter space of the building model around its baseline. An analytical meta-model is then fit to this data and optimization can be performed using different optimization cost functions or optimization algorithms with very little computational effort. Uncertainty and sensitivity analysis is also performed to identify the most influential parameters for the optimization. A case study is explored using an EnergyPlus model of an existing building which contains over 1000 parameters. When using a cost function that penalizes thermal comfort and energy, 45% annual energy reduction is achieved while simultaneously increasing thermal comfort by a factor of two. We compare the optimization using the meta-model approach with an approach using the EnergyPlus model integrated with the optimizer on a smaller problem using only seven optimization parameters illustrating good performance.},\n author = {Eisenhower, Bryan and O’Neill, Zheng and Narayanan, Satish and Fonoberov, Vladimir A. and Mezí{c}, Igor},\n doi = {10.1016/j.enbuild.2011.12.001},\n file = {:Users/adam/Library/Application Support/Mendeley Desktop/Downloaded/SSQ386AE/S0378778811005962.html:html;:Users/adam/Library/Application Support/Mendeley Desktop/Downloaded/UEJ3PME2/Eisenhower et al. - A methodology for meta-model based optimization in.pdf:pdf},\n issn = {0378-7788},\n journal = {Energy and Buildings},\n keywords = {Comfort and energy optimization,EnergyPlus,Machine learning,Sensitivity analysis},\n mendeley-tags = {Comfort and energy optimization,EnergyPlus,Machine learning,Sensitivity analysis},\n number = {0},\n pages = {292--301},\n title = {{A methodology for meta-model based optimization in building energy models}},\n volume = {47},\n year = {2012}\n}</pre>\n</div>\n\n\n<div class=\"well well-small bibbase\" id=\"abstract_Eisenhower2011\"\n style=\"display:none\">\n As building energy models become more accurate and numerically efficient, model-based optimization of building design and operation is becoming more practical. The state-of-the-art typically couples an optimizer with a building energy model which tends to be time consuming and often leads to suboptimal results because of the mathematical properties of the energy model. To mitigate this issue, we present an approach that begins by sampling the parameter space of the building model around its baseline. An analytical meta-model is then fit to this data and optimization can be performed using different optimization cost functions or optimization algorithms with very little computational effort. Uncertainty and sensitivity analysis is also performed to identify the most influential parameters for the optimization. A case study is explored using an EnergyPlus model of an existing building which contains over 1000 parameters. When using a cost function that penalizes thermal comfort and energy, 45% annual energy reduction is achieved while simultaneously increasing thermal comfort by a factor of two. We compare the optimization using the meta-model approach with an approach using the EnergyPlus model integrated with the optimizer on a smaller problem using only seven optimization parameters illustrating good performance.\n</div>\n\n\n</div>\n","downloads":0,"keyword":["Comfort and energy optimization","EnergyPlus","Machine learning","Sensitivity analysis"],"urls":{},"abstract":"As building energy models become more accurate and numerically efficient, model-based optimization of building design and operation is becoming more practical. The state-of-the-art typically couples an optimizer with a building energy model which tends to be time consuming and often leads to suboptimal results because of the mathematical properties of the energy model. To mitigate this issue, we present an approach that begins by sampling the parameter space of the building model around its baseline. An analytical meta-model is then fit to this data and optimization can be performed using different optimization cost functions or optimization algorithms with very little computational effort. Uncertainty and sensitivity analysis is also performed to identify the most influential parameters for the optimization. A case study is explored using an EnergyPlus model of an existing building which contains over 1000 parameters. When using a cost function that penalizes thermal comfort and energy, 45% annual energy reduction is achieved while simultaneously increasing thermal comfort by a factor of two. We compare the optimization using the meta-model approach with an approach using the EnergyPlus model integrated with the optimizer on a smaller problem using only seven optimization parameters illustrating good performance.","author":["Eisenhower, Bryan","O’Neill, Zheng","Narayanan, Satish","Fonoberov, Vladimir A.","Mezíc, Igor"],"author_short":["Eisenhower, B.","O’Neill, Z.","Narayanan, S.","Fonoberov, V.<nbsp>A.","Mezíc, I."],"bibtex":"@article{ Eisenhower2011,\n abstract = {As building energy models become more accurate and numerically efficient, model-based optimization of building design and operation is becoming more practical. The state-of-the-art typically couples an optimizer with a building energy model which tends to be time consuming and often leads to suboptimal results because of the mathematical properties of the energy model. To mitigate this issue, we present an approach that begins by sampling the parameter space of the building model around its baseline. An analytical meta-model is then fit to this data and optimization can be performed using different optimization cost functions or optimization algorithms with very little computational effort. Uncertainty and sensitivity analysis is also performed to identify the most influential parameters for the optimization. A case study is explored using an EnergyPlus model of an existing building which contains over 1000 parameters. When using a cost function that penalizes thermal comfort and energy, 45% annual energy reduction is achieved while simultaneously increasing thermal comfort by a factor of two. We compare the optimization using the meta-model approach with an approach using the EnergyPlus model integrated with the optimizer on a smaller problem using only seven optimization parameters illustrating good performance.},\n author = {Eisenhower, Bryan and O’Neill, Zheng and Narayanan, Satish and Fonoberov, Vladimir A. and Mezí{c}, Igor},\n doi = {10.1016/j.enbuild.2011.12.001},\n file = {:Users/adam/Library/Application Support/Mendeley Desktop/Downloaded/SSQ386AE/S0378778811005962.html:html;:Users/adam/Library/Application Support/Mendeley Desktop/Downloaded/UEJ3PME2/Eisenhower et al. - A methodology for meta-model based optimization in.pdf:pdf},\n issn = {0378-7788},\n journal = {Energy and Buildings},\n keywords = {Comfort and energy optimization,EnergyPlus,Machine learning,Sensitivity analysis},\n mendeley-tags = {Comfort and energy optimization,EnergyPlus,Machine learning,Sensitivity analysis},\n number = {0},\n pages = {292--301},\n title = {{A methodology for meta-model based optimization in building energy models}},\n volume = {47},\n year = {2012}\n}","bibtype":"article","doi":"10.1016/j.enbuild.2011.12.001","file":":Users/adam/Library/Application Support/Mendeley Desktop/Downloaded/SSQ386AE/S0378778811005962.html:html;:Users/adam/Library/Application Support/Mendeley Desktop/Downloaded/UEJ3PME2/Eisenhower et al. - A methodology for meta-model based optimization in.pdf:pdf","id":"Eisenhower2011","issn":"0378-7788","journal":"Energy and Buildings","key":"Eisenhower2011","keywords":"Comfort and energy optimization,EnergyPlus,Machine learning,Sensitivity analysis","mendeley-tags":"Comfort and energy optimization,EnergyPlus,Machine learning,Sensitivity analysis","number":"0","pages":"292--301","title":"A methodology for meta-model based optimization in building energy models","type":"article","volume":"47","year":"2012","role":"author","bibbaseid":"eisenhower-oneill-narayanan-fonoberov-mezic-amethodologyformetamodelbasedoptimizationinbuildingenergymodels-2012"},"bibtype":"article","biburl":"http://www.eeci.cam.ac.uk/publications/references.bib","downloads":0,"search_terms":["methodology","meta","model","based","optimization","building","energy","models","eisenhower","o’neill","narayanan","fonoberov","mezíc"],"title":"A methodology for meta-model based optimization in building energy models","year":2012,"dataSources":["HiecPnf5mmbLNkHM8"]}