Machine learning from schools about energy efficiency
In the United States, consumers invest billions of dollars annually in energy efficiency, often on the assumption that these investments will pay for themselves via future energy cost reductions. We study energy efficiency upgrades in K-12 schools in California. We develop and implement a novel mach...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Working Paper |
| Language: | en_US |
| Published: |
MIT Energy Initiative
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/1721.1/130619 |
| _version_ | 1826201201363910656 |
|---|---|
| author | Knittel, Christopher Burlig, Fiona Rapson, David Reguant, Mar Wolfram, Catherine |
| author2 | MIT Energy Initiative |
| author_facet | MIT Energy Initiative Knittel, Christopher Burlig, Fiona Rapson, David Reguant, Mar Wolfram, Catherine |
| author_sort | Knittel, Christopher |
| collection | MIT |
| description | In the United States, consumers invest billions of dollars annually in energy efficiency, often on the assumption that these investments will pay for themselves via future energy cost reductions. We study energy efficiency upgrades in K-12 schools in California. We develop and implement a novel machine learning approach for estimating treatment effects using high-frequency panel data, and demonstrate that this method outperforms standard panel fixed effects approaches. We find that energy efficiency upgrades reduce electricity consumption by 3 percent, but that these reductions total only 24 percent of ex ante expected savings. HVAC and lighting upgrades perform better, but still deliver less than half of what was expected. Finally, beyond location, school characteristics that are readily available to policymakers do not appear to predict realization rates across schools, suggesting that improving realization rates via targeting may prove challenging. |
| first_indexed | 2024-09-23T11:48:08Z |
| format | Working Paper |
| id | mit-1721.1/130619 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2025-03-10T10:06:22Z |
| publishDate | 2021 |
| publisher | MIT Energy Initiative |
| record_format | dspace |
| spelling | mit-1721.1/1306192025-02-28T17:32:03Z Machine learning from schools about energy efficiency Knittel, Christopher Burlig, Fiona Rapson, David Reguant, Mar Wolfram, Catherine MIT Energy Initiative energy energy efficiency machine learning In the United States, consumers invest billions of dollars annually in energy efficiency, often on the assumption that these investments will pay for themselves via future energy cost reductions. We study energy efficiency upgrades in K-12 schools in California. We develop and implement a novel machine learning approach for estimating treatment effects using high-frequency panel data, and demonstrate that this method outperforms standard panel fixed effects approaches. We find that energy efficiency upgrades reduce electricity consumption by 3 percent, but that these reductions total only 24 percent of ex ante expected savings. HVAC and lighting upgrades perform better, but still deliver less than half of what was expected. Finally, beyond location, school characteristics that are readily available to policymakers do not appear to predict realization rates across schools, suggesting that improving realization rates via targeting may prove challenging. 2021-05-17T19:04:57Z 2021-05-17T19:04:57Z 2017-09-27 Working Paper https://hdl.handle.net/1721.1/130619 en_US application/pdf MIT Energy Initiative |
| spellingShingle | energy energy efficiency machine learning Knittel, Christopher Burlig, Fiona Rapson, David Reguant, Mar Wolfram, Catherine Machine learning from schools about energy efficiency |
| title | Machine learning from schools about energy efficiency |
| title_full | Machine learning from schools about energy efficiency |
| title_fullStr | Machine learning from schools about energy efficiency |
| title_full_unstemmed | Machine learning from schools about energy efficiency |
| title_short | Machine learning from schools about energy efficiency |
| title_sort | machine learning from schools about energy efficiency |
| topic | energy energy efficiency machine learning |
| url | https://hdl.handle.net/1721.1/130619 |
| work_keys_str_mv | AT knittelchristopher machinelearningfromschoolsaboutenergyefficiency AT burligfiona machinelearningfromschoolsaboutenergyefficiency AT rapsondavid machinelearningfromschoolsaboutenergyefficiency AT reguantmar machinelearningfromschoolsaboutenergyefficiency AT wolframcatherine machinelearningfromschoolsaboutenergyefficiency |