https://eta.lbl.gov/seminar/data-science-meets-ashrae-great-energy\nhttps://vimeo.com/363413594
\n\nDr. Miller will present the plans for the upcoming Great Energy Predictor Competition III that is scheduled to be launched in Oct 2019. This competition will be the long-awaited continuation of the ASHRAE Predictor Shootout I (1993) and Predictor Shootout II (1995) competitions. In this contest, ASHRAE has developed a new competition to determine who has the most accurate procedure(s) for automatically predicting whole-building energy use for a large number of buildings. The prediction of building energy use is important for many different purposes, including developing baselines, improving diagnostics, optimizing building energy use, improving electric grid management to name a few.
", "messages": [ { "id": "653841", "postDate": "10/21/2019 03:27:24", "content": "https://eta.lbl.gov/seminar/data-science-meets-ashrae-great-energy\nhttps://vimeo.com/363413594
\n\nDr. Miller will present the plans for the upcoming Great Energy Predictor Competition III that is scheduled to be launched in Oct 2019. This competition will be the long-awaited continuation of the ASHRAE Predictor Shootout I (1993) and Predictor Shootout II (1995) competitions. In this contest, ASHRAE has developed a new competition to determine who has the most accurate procedure(s) for automatically predicting whole-building energy use for a large number of buildings. The prediction of building energy use is important for many different purposes, including developing baselines, improving diagnostics, optimizing building energy use, improving electric grid management to name a few.
", "rawMarkdown": "https://eta.lbl.gov/seminar/data-science-meets-ashrae-great-energy\nhttps://vimeo.com/363413594\n\nDr. Miller will present the plans for the upcoming Great Energy Predictor Competition III that is scheduled to be launched in Oct 2019. This competition will be the long-awaited continuation of the ASHRAE Predictor Shootout I (1993) and Predictor Shootout II (1995) competitions. In this contest, ASHRAE has developed a new competition to determine who has the most accurate procedure(s) for automatically predicting whole-building energy use for a large number of buildings. The prediction of building energy use is important for many different purposes, including developing baselines, improving diagnostics, optimizing building energy use, improving electric grid management to name a few.", "votes": null }, { "id": "653848", "postDate": "10/21/2019 03:37:16", "content": "https://www.budslab.org/\nBuilding Data Genome Project (ResearchGate) – Collaboration with Princeton CHAOS Lab – A open data set of hundreds of non-residential buildings from around the world with various temporal data mining techniques implemented
\n\nhttps://github.com/buds-lab/temporal-features-for-nonres-buildings-library
\n\nuseful publications:\nhttps://scholar.google.com.sg/citations?hl=en&user=akL857IAAAAJ&view_op=list_works&sortby=pubdate
", "rawMarkdown": "https://www.budslab.org/\nBuilding Data Genome Project (ResearchGate) – Collaboration with Princeton CHAOS Lab – A open data set of hundreds of non-residential buildings from around the world with various temporal data mining techniques implemented\n\nhttps://github.com/buds-lab/temporal-features-for-nonres-buildings-library\n\n\nuseful publications:\nhttps://scholar.google.com.sg/citations?hl=en&user=akL857IAAAAJ&view_op=list_works&sortby=pubdate", "votes": null }, { "id": "653852", "postDate": "10/21/2019 03:54:16", "content": "\"More buildings make more generalizable models—Benchmarking prediction methods on open electrical meter data\" - Clayton Miller, 2019
\n\nThis paper outlines a library of open-source regression techniques from the Scikit-Learn Python library and describes the process of applying them to open hourly electrical meter data from 482 non-residential buildings from the Building Data Genome Project
", "rawMarkdown": "\"More buildings make more generalizable models—Benchmarking prediction methods on open electrical meter data\" - Clayton Miller, 2019\n\nThis paper outlines a library of open-source regression techniques from the Scikit-Learn Python library and describes the process of applying them to open hourly electrical meter data from 482 non-residential buildings from the Building Data Genome Project", "votes": null }, { "id": "653857", "postDate": "10/21/2019 04:10:35", "content": "This is gold.
", "rawMarkdown": "This is gold.", "votes": null }, { "id": "653938", "postDate": "10/21/2019 07:35:41", "content": "maybe related?\nhttps://vimeo.com/362155388
", "rawMarkdown": "maybe related?\nhttps://vimeo.com/362155388", "votes": null } ], "comments": [ { "id": 653848, "author_name": "hengck23", "author_url": "", "post_date": "10/21/2019 03:37:16", "content": "https://www.budslab.org/\nBuilding Data Genome Project (ResearchGate) – Collaboration with Princeton CHAOS Lab – A open data set of hundreds of non-residential buildings from around the world with various temporal data mining techniques implemented
\n\nhttps://github.com/buds-lab/temporal-features-for-nonres-buildings-library
\n\nuseful publications:\nhttps://scholar.google.com.sg/citations?hl=en&user=akL857IAAAAJ&view_op=list_works&sortby=pubdate
", "votes": null, "replies": [] }, { "id": 653852, "author_name": "hengck23", "author_url": "", "post_date": "10/21/2019 03:54:16", "content": "\"More buildings make more generalizable models—Benchmarking prediction methods on open electrical meter data\" - Clayton Miller, 2019
\n\nThis paper outlines a library of open-source regression techniques from the Scikit-Learn Python library and describes the process of applying them to open hourly electrical meter data from 482 non-residential buildings from the Building Data Genome Project
", "votes": null, "replies": [] }, { "id": 653857, "author_name": "arnabbiswas1", "author_url": "", "post_date": "10/21/2019 04:10:35", "content": "This is gold.
", "votes": null, "replies": [] }, { "id": 653938, "author_name": "hengck23", "author_url": "", "post_date": "10/21/2019 07:35:41", "content": "maybe related?\nhttps://vimeo.com/362155388
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "653841": "https://eta.lbl.gov/seminar/data-science-meets-ashrae-great-energy\nhttps://vimeo.com/363413594\n\nDr. Miller will present the plans for the upcoming Great Energy Predictor Competition III that is scheduled to be launched in Oct 2019. This competition will be the long-awaited continuation of the ASHRAE Predictor Shootout I (1993) and Predictor Shootout II (1995) competitions. In this contest, ASHRAE has developed a new competition to determine who has the most accurate procedure(s) for automatically predicting whole-building energy use for a large number of buildings. The prediction of building energy use is important for many different purposes, including developing baselines, improving diagnostics, optimizing building energy use, improving electric grid management to name a few.", "653848": "https://www.budslab.org/\nBuilding Data Genome Project (ResearchGate) – Collaboration with Princeton CHAOS Lab – A open data set of hundreds of non-residential buildings from around the world with various temporal data mining techniques implemented\n\nhttps://github.com/buds-lab/temporal-features-for-nonres-buildings-library\n\n\nuseful publications:\nhttps://scholar.google.com.sg/citations?hl=en&user=akL857IAAAAJ&view_op=list_works&sortby=pubdate", "653852": "\"More buildings make more generalizable models—Benchmarking prediction methods on open electrical meter data\" - Clayton Miller, 2019\n\nThis paper outlines a library of open-source regression techniques from the Scikit-Learn Python library and describes the process of applying them to open hourly electrical meter data from 482 non-residential buildings from the Building Data Genome Project", "653857": "This is gold.", "653938": "maybe related?\nhttps://vimeo.com/362155388" }, "source": "meta" }