Tackling Climate Change with Machine Learning

456878921324

于 2020-07-09 11:16:05 发布

阅读量314

点赞数

本文链接：https://blog.csdn.net/qq_40590753/article/details/104216405

版权

本文探讨了机器学习在应对气候变化方面的多种应用，包括电力系统优化、交通、建筑、工业、农业和森林管理等方面，以及在社会影响、教育和金融学中的角色。机器学习助力预测和减少碳排放，优化能源利用，改善供应链管理，预测气候影响，并在金融投资中引导可持续发展策略。

摘要由CSDN通过智能技术生成

最主要的官方网站：https://www.climatechange.ai

game theory：
[54] James Anderson, Fengyu Zhou, and Steven H Low. Disaggregation for networked power systems. In 2018 Power Systems Computation Conference (PSCC), pages 1–7. IEEE, 2018.
[55] Emre C Kara, Ciaran M Roberts, Michaelangelo Tabone, Lilliana Alvarez, Duncan S Callaway, and Emma M Stewart. Disaggregating solar generation from feeder-level measurements. Sustainable Energy, Grids and Networks, 13:112–121, 2018.
[56] Gregory S Ledva, Laura Balzano, and Johanna L Mathieu. Real-time energy disaggregation of a distribution feeder’s demand using online learning. IEEE Transactions on Power Systems, 33(5):4730–4740, 2018.
[57] Lynn H Kaack, Jay Apt, M Granger Morgan, and Patrick McSharry. Empirical prediction intervals improve energy forecasting. Proceedings of the National Academy of Sciences, 114(33):8752–8757, 2017.
[58] Priya Donti, Brandon Amos, and J Zico Kolter. Task-based end-to-end model learning in stochastic optimiza- tion. In Advances in Neural Information Processing Systems, pages 5484–5494, 2017.
[59] Adam N Elmachtoub and Paul Grigas. Smart “predict, then optimize”. Preprint arXiv:1710.08005, 2017.
[60] BryanWilder,BistraDilkina,andMilindTambe.Meldingthedata-decisionspipeline:Decision-focusedlearn-
ing for combinatorial optimization. Preprint arXiv:1809.05504, 2018.

在这里插入图片描述

1.电力系统
previous work has optimized storage and/or flexible demand using techniques such as agent-based models [68–71], online optimization [72], and dynamic programming [73]. To provide appro- priate signals for flexible demand, system operators can design electricity prices based on e.g. forecasts of variable electricity (see the discussion above) or grid emissions (see §1.2). Previous work has used dynamic programming to set real-time electricity prices that maximize revenue [74], and similar techniques could be applied to create prices that instead optimize for GHG emissions.

13For instance, researchers and entrepreneurs have proposed distributed energy trading or management systems that enable variable low-carbon energy. Some of these suggested distributed systems include transactive energy systems [65, 66] and peer-to- peer energy trading systems [67]. Some companies also propose to run truly distributed markets within existing electricity market structures (see e.g. Camus En