Large-scale Wave Energy Farm
Donated on 9/16/2023
Wave energy is a rapidly advancing and promising renewable energy source that holds great potential for addressing the challenges of global warming and climate change. However, optimizing energy output in large wave farms presents a complex problem due to the expensive calculations required to account for hydrodynamic interactions between wave energy converters (WECs). Developing a fast and accurate surrogate model is crucial to overcome these challenges. In light of this, we have compiled an extensive WEC dataset that includes 54,000 and 9,600 configurations involving 49 and 100 WECs, coordination, power, q-factor, and total farm power output. The dataset was derived from a study published at the GECCO conference and received the prestigious Best Paper award. We want to acknowledge the support of the University of Adelaide Phoenix HPC service in conducting this research. For more details, please refer to the following link: https://dl.acm.org/doi/abs/10.1145/3377930.3390235.
Dataset Characteristics
Multivariate
Subject Area
Engineering
Associated Tasks
Regression
Feature Type
Real
# Instances
63600
# Features
149
Dataset Information
For what purpose was the dataset created?
This dataset was created to develop a fast and effective surrogate model for estimating the total power out of the large wave farm accurately.
Who funded the creation of the dataset?
This work was supported by Phoenix HPC service at the University of Adelaide.
What do the instances in this dataset represent?
Each instance represents the coordination of wave energy converters in a wave farm plus the total power output and individual power of each converter and q-factor.
Does the dataset contain data that might be considered sensitive in any way?
No.
Was there any data preprocessing performed?
No.
Has Missing Values?
No
Introductory Paper
By M. Neshat, Bradley Alexander, N. Sergiienko, Markus Wagner. 2020
Published in Annual Conference on Genetic and Evolutionary Computation
Variables Table
| Variable Name | Role | Type | Description | Units | Missing Values |
|---|---|---|---|---|---|
| X1 | Feature | Integer | no | ||
| Y1 | Feature | Integer | no | ||
| X2 | Feature | Integer | no | ||
| Y2 | Feature | Integer | no | ||
| X3 | Feature | Integer | no | ||
| Y3 | Feature | Integer | no | ||
| X4 | Feature | Integer | no | ||
| Y4 | Feature | Integer | no | ||
| X5 | Feature | Integer | no | ||
| Y5 | Feature | Integer | no |
0 to 10 of 149
Additional Variable Information
The dataset includes 4 CSV files for 49 and 100 wave energy converters based on Perth and Sydney wave scenarios. The main goal is predicting the total power output of the wave farm based on the coordination of WECs (X1, Y1, X2, Y2,..., Xn, Yn). As the second plan, predicting the power output of each converter in the wave farm can be interesting.
Reviews
There are no reviews for this dataset yet.
pip install ucimlrepo
from ucimlrepo import fetch_ucirepo # fetch dataset large_scale_wave_energy_farm = fetch_ucirepo(id=882) # data (as pandas dataframes) X = large_scale_wave_energy_farm.data.features y = large_scale_wave_energy_farm.data.targets # metadata print(large_scale_wave_energy_farm.metadata) # variable information print(large_scale_wave_energy_farm.variables)
Neshat,Mehdi, Alexander,Bradley, Sergiienko,Nataliia, and Wagner,Markus. (2023). Large-scale Wave Energy Farm. UCI Machine Learning Repository. https://doi.org/10.24432/C5GG7Q.
@misc{misc_large-scale_wave_energy_farm_882,
author = {Neshat,Mehdi, Alexander,Bradley, Sergiienko,Nataliia, and Wagner,Markus},
title = {{Large-scale Wave Energy Farm}},
year = {2023},
howpublished = {UCI Machine Learning Repository},
note = {{DOI}: https://doi.org/10.24432/C5GG7Q}
}Creators
Mehdi Neshat
neshat.mehdi@gmail.com
University of Adelaide
Bradley Alexander
alexander.bradley@adelaide.edu.au
University of Adelaide
Nataliia Sergiienko
nataliia.sergiienko@adelaide.edu.au
University of Adelaide
Markus Wagner
Markus.Wagner@monash.edu
Monash University
DOI
License
This dataset is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) license.
This allows for the sharing and adaptation of the datasets for any purpose, provided that the appropriate credit is given.