Timescale classification in wind forecasting: A review of the state‐of‐the‐art

• DOI: http://doi.org/10.1002/for.2657
• Published date: 01 August 2020
• Author: Jannik Schütz Roungkvist,Peter Enevoldsen
• Date: 01 August 2020

RESEARCH ARTICLE

Timescale classification in wind forecasting: A review of

the state-of-the-art

Jannik Schütz Roungkvist

1,2

| Peter Enevoldsen

2

1

MHI Vestas Offshore Wind, Aarhus,

Denmark

2

Center for Energy Technologies, Aarhus

University, Aarhus, Denmark

Correspondence

Jannik Schütz Roungkvist, Center for

Energy Technologies, Aarhus University,

8000. Aarhus, Denmark.

Email: jannik@roungkvist.dk

Abstract

The intermittency of the wind has been reported to present significant chal-

lenges to power and grid systems, which intensifies with increasing penetra-

tion levels. Accurate wind forecasting can mitigate these challenges and help

in integrating more wind power into the grid. A range of studies have pres-

ented algorithms to forecast the wind in terms of wind speeds and wind power

generation across different timescales. However, the classification of timescales

varies significantly across the different studies (2010–2014). The timescale is

important in specifying which methodology to use when, as well in uniting

future research, data requirements, etc. This study proposes a generic state-

ment on how to classify the timescales, and further presents different applica-

tions of these forecasts across the entire wind power value chain.

KEYWORDS

energy forecasting, multiple-step-ahead forecasting, renewable energy integration, time series

forecasting, wind power forecasting, wind speed forecasting

1|INTRODUCTION

Extensive focus on the green transition of energy sources

and technologies has led to immense amounts of large-

scale wind power generation being integrated into the

power system to make society less reliable on fossil fuels

(Flynn et al., 2017; Hemmati, Saboori, & Saboori, 2016;

Hodge et al., 2012; Lei, Shiyan, Chuanwen, Hongling, &

Yan, 2009; Y. Zhang, Wang, & Wang, 2014). However, it

is not without concern when integrating large-scale wind

power, as the power generated from wind turbines is

considered “nondispatchable”due to the intermittence

of wind (Flynn et al., 2017; Hemmati et al., 2016;

Y. Zhang et al., 2014). Grid integration of wind power

has become more of a concern in recent years, as the

penetration levels have increased to higher levels in sev-

eral countries (Flynn et al., 2017), and this is a trend

that is expected to continue for decades (Enevoldsen

et al., 2019). Utilities around the world have expressed

their concerns about the perceived unpredictability of

the wind as this could cause excessive power in the

power system (Georgilakis, 2008). This would result in

curtailment of wind turbines, and the key benefits of the

wind power generation would diminish, as well as

increasing the levelized cost of energy from wind power

(Georgilakis, 2008).

Research has reported that the implications of the

integration of large-scale wind power generation vary

with different factors such as system size, penetration

level, geographical distribution and turbine types, net-

work topology, electricity market structure and unit com-

mitment procedures (Flynn et al., 2017). The power

system is affected by many aspects, including the trans-

mission grid, balancing reserves, and adequacy of power

(Georgilakis, 2008; Holttinen et al., 2011; Y. Zhang et al.,

2014), and these implications become more challenging

and more intense with increasing penetration levels

(X. Wang, Guo, & Huang, 2011) as increasing amounts of

wind power increase the uncertainty in generation (S. Li,

Dong, Huang, Wu, & Zhang, 2019).

Received: 12 October 2019 Accepted: 12 January 2020

DOI: 10.1002/for.2657

Journal of Forecasting. 2020;39:757–768. wileyonlinelibrary.com/journal/for © 2020 John Wiley & Sons, Ltd. 757