Data From: Machine Learning Predictions of Electricity Capacity

Authors

Marcus Harris, Portland State UniversityFollow
Elizabeth Kirby, Bonneville Power AdministrationFollow
Ameeta Agrawal, Portland State UniversityFollow
Rhitabrat Pokharel, Portland State UniversityFollow
Francis Puyleart, Bonneville Power AdministrationFollow
Martin Zwick, Portland State UniversityFollow

Document Type

Dataset

Publication Date

12-2022

Subjects

Machine Learning, Artificial Intelligence, Electricity, Energy, Capacity, Ancillary Services, Reconstructability Analysis, Bayesian Networks, Support Vector Machines, Neural Networks

Abstract

This research applies machine learning methods to build predictive models of Net Load Imbalance for the Resource Sufficiency Flexible Ramping Requirement in the Western Energy Imbalance Market. Several methods are used in this research, including Reconstructability Analysis, developed in the systems community, and more well-known methods such as Bayesian Networks, Support Vector Regression, and Neural Networks. The aims of the research are to identify predictive variables and obtain a new stand-alone model that improves prediction accuracy and reduces the INC (ability to increase generation) and DEC (ability to decrease generation) Resource Sufficiency Requirements for Western Energy Imbalance Market participants. This research accomplishes these aims. The models built in this paper identify wind forecast, sunrise/sunset and the hour of day as primary predictors of net load imbalance, among other variables, and show that the average size of the INC and DEC capacity requirements can be reduced by over 25% with the margin of error currently used in the industry while also significantly improving closeness and exceedance reliability metrics. The reduction in INC and DEC capacity requirements would yield an approximate cost savings of $4 million annually for one of 19 Western Energy Imbalance market participants. Reconstructability Analysis performs the best among the machine learning methods tested.

The data supports the following article published in Energies: Machine Learning Predictions of Electricity Capacity

Description

The file is a .csv spreadsheet. Data is divided into 5 folds, as described in the paper.

Rights

This work is marked with CC0 1.0 Universal.

DOI

10.15760/sysc-data.1

Persistent Identifier

https://archives.pdx.edu/ds/psu/38933

Recommended Citation

Harris, Marcus; Kirby, Elizabeth; Agrawal, Ameeta; Pokharel, Rhitabrat; Puyleart, Francis; and Zwick, Martin, "Data From: Machine Learning Predictions of Electricity Capacity" (2022). Systems Science Faculty Datasets. 1.
https://doi.org/10.15760/sysc-data.1