Non-Gaussian Multivariate Processes for Renewable Energy and Finance

可再生能源和金融的非高斯多元过程

• 批准号: 2310487
• 负责人: William Kleiber
• 金额: $ 30万
• 依托单位: University of Colorado at Boulder
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2026-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2310487&HistoricalAwards=false
• 关键词: Non; Gaussian; Multivariate; Processes; Renewable

The electrical grid is experiencing challenges with the expanding introduction of distributed photovoltaic (PV) panels over neighborhood rooftops. Such PV installations generate variable, uncertain and intermittent electricity supply due to microscale weather patterns and diurnal variation. Understanding the impacts of such an uncertain renewable energy resource requires high resolution space-time irradiance data; however, fine scale irradiance data are rare, and impacts assessments must therefore rely on simulated scenarios. In a parallel vein, cryptocurrencies are increasingly common investment areas for businesses and individual investors. However, the nascent state of the technology and price record leave a dearth of historical data. Thus, financial modeling and investment studies require simulated scenarios that consider the joint behavior of multiple cryptocurrencies simultaneously. This project will develop new methodology to produce realistic, synthetic data sets that can be used in risk and impacts studies. Moreover, this project will support education and training of students who will gain interdisciplinary research experience at the intersection of statistics, renewable energy science and finance.This research will develop new modeling frameworks for multivariate non-Gaussian processes that exhibit intermittent jump-like behavior. Such approaches will afford better understanding of the variability and intermittency of solar irradiances and the joint behavior in major cryptocurrency portfolios. Space-time in situ pyranometer-based measurements of irradiances and a suite of popular modern cryptocurrency historical prices will be used to illustrate the new approaches. The methods developed will directly benefit the fields of energy science, meteorology, finance and economics with applicability in many further disciplines including geography, ecology, environmental science and physics, among others.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

随着社区屋顶上分布式光伏(PV)电池板的不断引入，电网正面临着挑战。由于微尺度的天气模式和日变化，这种光伏装置产生可变的、不确定的和间歇的电力供应。了解这种不确定的可再生能源的影响需要高分辨率的时空辐照度数据；然而，精细的辐照度数据很少，因此影响评估必须依赖于模拟情景。同样，加密货币对企业和个人投资者来说也是越来越常见的投资领域。然而，这种技术的新状态和价格记录留下了历史数据的匮乏。因此，金融建模和投资研究需要模拟场景，同时考虑多种加密货币的联合行为。该项目将开发新的方法，以产生可用于风险和影响研究的现实的、合成的数据集。此外，该项目将支持在统计学、可再生能源科学和金融学的交叉领域获得跨学科研究经验的学生的教育和培训。这项研究将为呈现间歇性跳跃行为的多变量非高斯过程开发新的建模框架。这些方法将使人们更好地了解太阳辐射的可变性和间歇性，以及主要加密货币投资组合中的联合行为。基于时空原位辐射计的辐照度测量和一套流行的现代加密货币历史价格将被用来说明新的方法。开发的方法将直接惠及能源科学、气象学、金融学和经济学领域，并适用于许多进一步的学科，包括地理学、生态学、环境科学和物理学等。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。