Using neural networks to forecast marginal emissions factors: A CAISO case study

Using neural networks to forecast marginal emissions factors: A CAISO case study
复制标题

使用神经网络预测边际排放因子:CAISO 案例研究

DOI:
10.1016/j.jclepro.2023.139895
复制
发表时间:
2024
影响因子:
11.1
通讯作者:
Sanders, Kelly T
Sanders, Kelly T
中科院分区:
环境科学与生态学1区
文献类型:
--
作者:
Mayes, Stepp;Klein, Nicholas;Sanders, Kelly T

文献摘要

参考文献

被引文献

相似文献

摘要边际排放因子(MEFs)量化了由电力消耗变化引起的CO2排放随时间的变化。准确的MEF对于计算需求侧管理(DSM)活动和计划的排放影响至关重要,但目前计算MEF的方法受到其时间分辨率,准确性(特别是在可变可再生能源高度渗透的电网中)以及提前预测MEF的能力的限制,降低了其对DSM的效用。我们通过引入一种新的多层感知器来改进现有技术,该模型使用公开的网格数据来计算历史MEF并预测前一天的MEF。我们在2019-2021年期间,加州独立系统运营商的公开数据上测试了我们的模型,这是一个白天VRE发电量很高的电网。结果表明,我们的模型产生更准确和更细粒度的基于需求的MEF估计比可比的回归技术,并保持高精度时,用于预测未来的MEF。我们的MEF框架可以应用到其他区域电网,以评估和设计需求侧管理战略,利用二氧化碳减排作为改变电力消费行为的动机。
Abstract Marginal Emissions Factors (MEFs) quantify the time-dependent changes in CO 2 emissions resulting from changes in electricity consumption. Accurate MEFs are critical for calculating the emissions impact of demand-side management (DSM) activities and programs, but current methods of calculating MEFs are limited by their temporal resolution, accuracy (particularly in grids with high penetrations of variable renewable energy), and ability to predict MEFs ahead of time, reducing their utility for DSM. We improve upon existing techniques by introducing a novel multi-layer perceptron to linear composite model that uses publicly available grid data to calculate historical MEFs and predict day-ahead MEFs. We test our model on publicly-available data from the California Independent System Operator over the period of 2019–2021, a grid with high daytime VRE generation. Results indicate that our model produces more accurate and more granular demand-based MEF estimations than comparable regression techniques and maintains high accuracy when use to forecast future MEFs. Our MEF framework can be applied to other regional grids to evaluate and design DSM strategies that leverage CO 2 emissions-reductions as motivation for altering electricity consuming behaviors.
用于量化基于消耗的每月和每小时边际排放因子的数据驱动框架
DOI: 10.1016/j.jclepro.2023.136296
发表时间: 2023
影响因子: 11.1
作者:
Zohrabian, Angineh;Mayes, Stepp;Sanders, Kelly T.
通讯作者: Sanders, Kelly T.
DOI: 10.1016/j.apenergy.2021.117194
发表时间: 2021-09
期刊: Applied Energy
影响因子: 11.2
作者:
Angineh Zohrabian;K. Sanders
通讯作者: Angineh Zohrabian;K. Sanders
使用边际排放因子预测的碳高效智能充电
DOI: --
发表时间: 2021
期刊:
影响因子: --
作者:
Julian Huber;K. Lohmann;M. Schmidt;Christof Weinhardt
通讯作者: Christof Weinhardt
动态预期平均和边际温室气体排放因子 - 2050 年之前德国电力系统基于情景的方法
DOI: --
发表时间: 2021
期刊: Energies
影响因子: 3.2
作者:
Nils Seckinger;P. Radgen
通讯作者: P. Radgen
比较计算动态电网排放因子的经验方法和基于模型的方法:在德国二氧化碳最小化存储调度中的应用
DOI: --
发表时间: 2020
影响因子: 11.1
作者:
F. Braeuer;R. Finck;R. McKenna
通讯作者: R. McKenna