Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Analysis of Random Forest Modeling Strategies for Multi-Step Wind Speed Forecasting

Journal Article · · Energies
DOI:https://doi.org/10.3390/en13205488· OSTI ID:1699450
 [1];  [2];  [3];  [1]
  1. Univ. of Notre Dame, IN (United States)
  2. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
  3. CRCL Solutions, EEC, South Bend, IN (United States)
+ Show Author Affiliations

Although the random forest (RF) model is a powerful machine learning tool that has been utilized in many wind speed/power forecasting studies, there has been no consensus on optimal RF modeling strategies. This study investigates three basic questions which aim to assist in the discernment and quantification of the effects of individual model properties, namely: (1) using a standalone RF model versus using RF as a correction mechanism for the persistence approach, (2) utilizing a recursive versus direct multi-step forecasting strategy, and (3) training data availability on model forecasting accuracy from one to six hours ahead. These questions are investigated utilizing data from the FINO1 offshore platform and Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) C1 site, and testing results are compared to the persistence method. At FINO1, due to the presence of multiple wind farms and high inter-annual variability, RF is more effective as an error-correction mechanism for the persistence approach. The direct forecasting strategy is seen to slightly outperform the recursive strategy, specifically for forecasts three or more steps ahead. Finally, increased data availability (up to ~8 equivalent years of hourly training data) appears to continually improve forecasting accuracy, although changing environmental flow patterns have the potential to negate such improvement. We hope that the findings of this study will assist future researchers and industry professionals to construct accurate, reliable RF models for wind speed forecasting.

Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Biological and Environmental Research (BER); National Science Foundation (NSF)
Grant/Contract Number:
AC05-76RL01830
OSTI ID:
1699450
Alternate ID(s):
OSTI ID: 1706624
Report Number(s):
PNNL-SA--156586
Journal Information:
Energies, Journal Name: Energies Journal Issue: 20 Vol. 13; ISSN 1996-1073
Publisher:
MDPI AGCopyright Statement
Country of Publication:
United States
Language:
English

References (27)

ARM: Temperature, humidity, winds and pressure system (THWAPS): meterological data
  • Ermold, Brian; Kyrouac, Jenni
  • Atmospheric Radiation Measurement (ARM) Archive, Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (US); https://doi.org/10.5439/1025304
dataset January 1999
Wind Resource Assessment book May 2012
An improved random forest model of short-term wind-power forecasting to enhance accuracy, efficiency, and robustness journal August 2018
An Introduction to Statistical Learning book January 2013
A data-driven multi-model methodology with deep feature selection for short-term wind forecasting journal March 2017
An intelligent framework for short-term multi-step wind speed forecasting based on Functional Networks journal September 2018
A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition journal June 2012
Hour-ahead wind power forecast based on random forests journal August 2017
Sub-hourly forecasting of wind speed and wind energy journal January 2020
Analysis and application of forecasting models in wind power integration: A review of multi-step-ahead wind speed forecasting models journal July 2016
Oklahoma's future wind energy resources and their relationship with the Central Plains low-level jet journal November 2019
Random Forests journal January 2001
Determining the Order of Differencing in Autoregressive Processes journal October 1987
Wake Measurements at alpha ventus – Dependency on Stability and Turbulence Intensity journal December 2014
A review of wind power and wind speed forecasting methods with different time horizons conference September 2010
Multistep Wind Speed and Wind Power Prediction Based on a Predictive Deep Belief Network and an Optimized Random Forest journal July 2018
Low-Level Jet Climatology from Enhanced Rawinsonde Observations at a Site in the Southern Great Plains journal October 1997
The ARM Southern Great Plains (SGP) Site journal April 2016
Climatology of the Low-Level Jet at the Southern Great Plains Atmospheric Boundary Layer Experiments Site journal October 2005
The Low-Level Jet over the Southern Great Plains Determined from Observations and Reanalyses and Its Impact on Moisture Transport journal September 2015
Understanding covariate shift in model performance journal January 2016
Popular Ensemble Methods: An Empirical Study journal July 1999
Temperature, Humidity, Wind and Pressure Sensors (THWAPS) Handbook report January 2011
Box-Jenkins Seasonal Forecasting: Problems in a Case-Study journal January 1973
Ultra-Short-Term Wind-Power Forecasting Based on the Weighted Random Forest Optimized by the Niche Immune Lion Algorithm journal April 2018
A Review on Hybrid Empirical Mode Decomposition Models for Wind Speed and Wind Power Prediction journal January 2019
Interannual variability of wind climates and wind turbine annual energy production journal January 2018

Similar Records

Statistical Wind Power Forecasting for U.S. Wind Farms: Preprint
Conference · Fri Oct 31 23:00:00 EST 2003 · OSTI ID:15005924
Statistical Wind Power Forecasting Models: Results for U.S. Wind Farms; Preprint
Conference · Thu May 01 00:00:00 EDT 2003 · OSTI ID:15003903
Wind speed and power forecasting based on spatial correlation models
Journal Article · Wed Sep 01 00:00:00 EDT 1999 · IEEE Transactions on Energy Conversion (Institute of Electrical and Electronics Engineers) · OSTI ID:20001196

Related Subjects

54 ENVIRONMENTAL SCIENCES
machine learning
random forest
wind speed forecasting