Machine Learning from Schools about Energy Efficiency

被引：36

作者：

Burlig, Fiona ^{[1
,2
,3
]}

Knittel, Christopher ^{[3
,4
,5
]}

Rapson, David ^{[6
]}

Reguant, Mar ^{[3
,7
]}

Wolfram, Catherine ^{[3
,8
,9
]}

机构：

[1] Univ Chicago, Harris Sch Publ Policy, Chicago, IL 60637 USA

[2] Univ Chicago, Energy Policy Inst, Chicago, IL 60637 USA

[3] NBER, Cambridge, MA 02138 USA

[4] MIT, Sloan Sch Management, Cambridge, MA 02139 USA

[5] MIT, Ctr Energy & Environm Policy Res, Cambridge, MA 02139 USA

[6] Univ Calif Davis, Dept Econ, Davis, CA 95616 USA

[7] Northwestern Univ, Dept Econ, Ctr Econ & Policy Res CEPR, Evanston, IL 60208 USA

[8] Univ Calif Berkeley, Haas Sch Business, Berkeley, CA 94720 USA

[9] Univ Calif Berkeley, Energy Inst Haas, Berkeley, CA 94720 USA

来源：

JOURNAL OF THE ASSOCIATION OF ENVIRONMENTAL AND RESOURCE ECONOMISTS | 2020年 / 7卷 / 06期

基金：

美国国家科学基金会;

关键词：

energy efficiency; machine learning; schools; INVESTMENTS DELIVER; PROPENSITY SCORE; REGRESSION; ECONOMICS; INFERENCE; PROGRAM;

D O I：

10.1086/710606

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

We use high-frequency panel data on electricity consumption to study the effectiveness of energy efficiency upgrades in K-12 schools in California. Using a panel fixed effects approach, we find that these upgrades deliver between 12% and 86% of expected savings, depending on specification and treatment of outliers. Using machine learning to inform our specification choice, we estimate a narrower range: 52%-98%, with a central estimate of 60%. These results imply that upgrades are performing less well than ex ante predictions on average, although we can reject some of the very low realization rates found in prior work.

引用

页码：1181 / 1217

页数：37

共 50 条

[1] From "learning about" to "learning to be" in the National Curriculum for Primary Schools
Orlandina, Ivan Amelia
Elena, Marin
[J]. INTERNATIONAL CONFERENCE PSYCHOLOGY AND THE REALITIES OF THE CONTEMPORARY WORLD (PSIWORLD 2013), 4TH EDITION, 2014, 127 : 204 - 208
[2] A Unified Framework for Assessing Energy Efficiency of Machine Learning
Fischer, Raphael
Jakobs, Matthias
Muecke, Sascha
Morik, Katharina
[J]. MACHINE LEARNING AND PRINCIPLES AND PRACTICE OF KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2022, PT I, 2023, 1752 : 39 - 54
[3] Machine Learning Applied to Energy Efficiency of Large Consumers
Pereira, L. S. B.
Rodrigues, R. N.
Massuyama, G. A.
Aranha Neto, E. A. C.
[J]. 2019 IEEE CHILEAN CONFERENCE ON ELECTRICAL, ELECTRONICS ENGINEERING, INFORMATION AND COMMUNICATION TECHNOLOGIES (CHILECON), 2019,
[4] Machine Learning for Optimising Renewable Energy and Grid Efficiency
Oladapo, Bankole I.
Olawumi, Mattew A.
Omigbodun, Francis T.
[J]. Atmosphere, 2024, 15 (10)
[5] Improving Energy Efficiency in NFV Clouds with Machine Learning
Zorello, Ligia M. M.
Vieira, Migyael G. T.
Tejos, Rodrigo A. G.
Rojas, Marco A. T.
Meirosu, Catalin
Carvalho, Tereza C. M. B.
[J]. PROCEEDINGS 2018 IEEE 11TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (CLOUD), 2018, : 710 - 717
[6] Improving Energy Efficiency in Healthcare Machine Learning Models
Kommula, Ishanvi
[J]. Proceedings - 2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023, 2023, : 399 - 404
[7] Machine learning for energy efficiency Automatic detection of electric loads from power consumption
Tomazzoli, Claudio
Scannapieco, Simone
[J]. 2017 AEIT INTERNATIONAL ANNUAL CONFERENCE, 2017,
[8] Teaching and Learning about Biomass Energy: The Significance of Biomass Education in Schools
Han, Guang
Martin, Robert A.
[J]. SUSTAINABILITY, 2018, 10 (04)
[9] Machine efficiency = energy efficiency
Koelsch, James R.
[J]. MANUFACTURING ENGINEERING, 2008, 141 (03): : 121 - +
[10] Energy Efficiency in Machine Tools - A Self-Learning Approach
Di Orio, Giovanni
Candido, Goncalo
Barata, Jose
Bittencourt, Jose Luiz
Bonefeld, Ralf
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2013), 2013, : 4878 - 4883

← 1 2 3 4 5 →