arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.14451cs.LGeess.SP
收藏

基于深层生成模型的能源时间序列情景验证方法

Validation Methods for Energy Time Series Scenarios from Deep Generative Models

Forschungszentrum Jülich GmbH, Institute of Energy and Climate Research, Energy Systems Engineering (IEK-10)(于利希研究中心有限公司,能源与气候研究所,能源系统工程(IEK-10));RWTH Aachen University(亚琛工业大学);Forschungszentrum Jülich GmbH, Institute of Energy and Climate Research, Systems Analysis and Technology Evaluation (IEK-STE)(于利希研究中心有限公司,能源与气候研究所,系统分析与技术评估(IEK-STE));Institute for Theoretical Physics, University of Cologne(科隆大学理论物理研究所);German Aerospace Center (DLR), Institute of Networked Energy Systems(德国航空航天中心,网络化能源系统研究所);Department of Computer Science, OsloMet – Oslo Metropolitan University(奥斯陆城市大学计算机科学系);JARA-ENERGY;RWTH Aachen University, Process Systems Engineering (AVT.SVT)(亚琛工业大学,过程系统工程(AVT.SVT));School of Mathematical Sciences, Queen Mary University of London(伦敦玛丽女王大学数学科学学院);Faculty of Science and Technology, Norwegian University of Life Sciences(挪威生命科学大学科学与技术学院)

Eike Cramer, Leonardo Rydin Gorjão, Alexander Mitsos, Benjamin Schäfer, Dirk Witthaut, Manuel Dahmen

摘要:

现代能源系统的设计和运行受到时间相关和不确定参数的严重影响,例如,可再生能源发电、负荷需求和电价。这些通常由一组称为场景的离散实现表示。一种流行的场景生成方法使用深度生成模型(DGM),该模型允许在没有关于数据分布的先验假设的情况下生成场景。然而,生成的场景的验证是困难的,目前缺乏关于适当的验证方法的全面讨论。为了开始这一讨论,我们提供了一个关键的评估,目前使用的验证方法在能源情景生成文献。特别是,我们评估基于概率密度,自相关性和功率谱密度的验证方法。此外,我们建议使用多重分形去趋势波动分析(MFDFA)作为一个额外的验证方法的非平凡的功能,如峰值,爆发,和高原。作为代表性的例子,我们训练生成对抗网络(GANs),Wasserstein GANs(WGANs)和变分自编码器(VAE)在两个可再生能源发电时间序列(2013年至2015年德国的光伏和风能)和2017年至2019年欧洲能源交易所的日内电价时间序列上。我们将这四种验证方法应用于历史数据和生成的数据,并讨论验证结果的解释以及验证方法的常见错误、陷阱和局限性。我们的评估表明,没有一种单一的方法足以表征一个场景,但理想的验证应该包括多种方法,并在短时间内的场景中仔细解释。

英文摘要:

The design and operation of modern energy systems are heavily influenced by time-dependent and uncertain parameters, e.g., renewable electricity generation, load-demand, and electricity prices. These are typically represented by a set of discrete realizations known as scenarios. A popular scenario generation approach uses deep generative models (DGM) that allow scenario generation without prior assumptions about the data distribution. However, the validation of generated scenarios is difficult, and a comprehensive discussion about appropriate validation methods is currently lacking. To start this discussion, we provide a critical assessment of the currently used validation methods in the energy scenario generation literature. In particular, we assess validation methods based on probability density, auto-correlation, and power spectral density. Furthermore, we propose using the multifractal detrended fluctuation analysis (MFDFA) as an additional validation method for non-trivial features like peaks, bursts, and plateaus. As representative examples, we train generative adversarial networks (GANs), Wasserstein GANs (WGANs), and variational autoencoders (VAEs) on two renewable power generation time series (photovoltaic and wind from Germany in 2013 to 2015) and an intra-day electricity price time series form the European Energy Exchange in 2017 to 2019. We apply the four validation methods to both the historical and the generated data and discuss the interpretation of validation results as well as common mistakes, pitfalls, and limitations of the validation methods. Our assessment shows that no single method sufficiently characterizes a scenario but ideally validation should include multiple methods and be interpreted carefully in the context of scenarios over short time periods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑