Wind power forecasting: Difference between revisions

Revision as of 02:21, 10 October 2021

Latest revision as of 16:11, 17 February 2025

(17 intermediate revisions by 10 users not shown)

Line 1:

{{Short description|Estimate of the expected production of one or more wind turbines}}

{{Multiple issues|

{{update|reason=cites are mostly old|date=July 2019}}

{{More footnotes needed|date=April 2009}}

}}

A '''wind power forecast''' corresponds to an estimate of the expected production of one or more [[wind turbine]]s (referred to as a [[wind farm]]) in the near future, up to a year.{{sfn|Devi|2021|p=80}}. Forecast are usually expressed in terms of the available [[wind power|power]] of the wind farm, occasionally in units of energy{{citation needed|date=October 2021}}, indicating the power production potential over a time interval.

==Time scales of forecasts==

Forecasting of the wind power generation may be considered at different time scales, depending on the intended application:{{sfn|Devi|2021|p=80-81}}{{sfn|Hanifi|2020|p=3766}}

* ''very short-term'' forecasts (from seconds up to minutes) are used for the real-time turbine control and [[electrical grid]] management, as well as for [[market clearing]];

* ''short-term'' forecasts (from 30 minutes up to hours) are used tofor [[Dispatchable generation|dispatch planning]], intelligent [[load shedding]] decisions;

* ''medium-term'' forecasts (from 6 hours up to a day) are used for to make decisions for switching the turbine on or off for safety or conditions on the market;

* ''long-term'' forecasts (from a day up to a week or even a year) are used for long term planning (to schedule the maintenance or [[unit commitment]], optimize the [[cost of operation]]). Maintenance of offshore wind farms may be particularly costly, so optimal planning of maintenance operations is of particular importance.

Line 20 ⟶ 21:

The forecasts are typically requested by utilities on two separate time scales:{{sfn|Haupt|2015|p=48}}

# short-term (minutes to 6 hours) forecast is used to adjust the spinning reserves;

# long-term (day to week) forecast is used by the utility to plan the [[energy mix]] or buy electricity from other providers. Typically this information is needed on a "day ahead" basis (e. g., by 6AM), but markets tend not to operate on weekends and holidays, so occasionally longer forecasts are used.

The challenges the utilities are facingface when wind generation is injected into a power system depend on the share of that renewable energy and how well connected the grid is.{{sfn|Haupt|2015|pp=47}} For [[Denmark]], which is a country with one of the highest shares of windWind power in the electricity mix, the average [[wind power penetrationDenmark]] inmeets 2017-2018almost was 40-45% (meaning that 40-45%half of the country's electricity consumption was met with wind energy)demand, while the instantaneous penetration (that is, the instantaneous wind power production compared to the consumption to be met at a given time) is sometimes was above 100%. (withUnlike occasionalsome negativewindy pricingparts forof the electricity)US, which lack sufficient grid capacity, this is easily exported.<ref>{{citeCite journalweb |doidate=10.1016/j.ijhydene.2020.2022-09.166-19 |title=AnalysisWind ofpower theis windgetting energybetter marketand in Denmarkbetter, and futureproviding interactionsmore withvalue anto emergingthe hydrogengrid market|year=2021|last1=Berg|first1=Thomas Leopold|last2=Apostolou|first2=Dimitrios|last3=Enevoldsen|first3=Peter|journal=International Journal of Hydrogen Energy|volume=46|pages=146–156|s2cid=225175782|url=https://wwwreneweconomy.sciencedirectcom.comau/sciencewind-power-is-getting-better-and-better-and-providing-more-value-to-the-grid/article/pii/S0360319920336065 |access-date=2022-09-19 |website=RenewEconomy |language=en-AU}}</ref>

The [[transmission system operator]] (TSO) is responsible for managing the electricity balance on the grid: at any time, electricity production has to match consumption. Therefore, the use of production means is scheduled in advance in order to respond to load profiles. The load corresponds to the total electricity consumption over the area of interest. Load profiles are usually given by load forecasts which are of high accuracy. For making up the daily schedule, TSOs may consider their own power production means, if they have any, and/or they can purchase power generation from [[Independent Power Producer]]s (IPPs) and [[electric utility|utilities]], via bilateral contracts or electricity pools. In the context of deregulation, more and more players appear on the market, thus breaking the traditional situation of vertically- integrated utilities with quasi local monopolies. Two main mechanisms compose electricity markets. The first one is the spot market where participants propose quantities of energy for the following day at a given production cost. An auction system permits to settle the electricity spot price for the various periods depending on the different bids. The second mechanism is the balancing of power generation, which is coordinated by the TSO. Depending on the energy lacks and surplus (e.g. due to power plant failures or to intermittence in the case of wind power installations), the TSO determines the penalties that will be paid by IPPs who missed in their obligations. In some cases, an intra-day market is also present, in order to take corrective actions.{{citation needed|date=February 2012}}

In order to illustrate this electricity market mechanism, consider the Dutch [[electricity market]]. Market participants, referred to as Program Responsible Parties (PRPs), submit their price-quantity bids before 11 am for the delivery period covering the following day from midnight to midnight. The Program Time Unit (PTU) on the balancing market is of 15 minutes. Balancing of the 15-minute averaged power is required from all electrical producers and consumers connected to the grid, who for this purpose may be organised in sub-sets. Since these sub-sets are referred to as Programmes, balancing on the 15-minute scale is referred to as Programme Balance. Programme Balance now is maintained by using the production schedules issued the day before delivery and measurement reports (distributed the day after delivery). When the measured power is not equal to the scheduled power, the ''Programme Imbalance'' is the difference between the realised sum of production and consumption and the forecast sum of production and consumption. If only production from wind energy is taken into account, Programme Imbalance reduces to realised wind production minus forecast wind production. The programme imbalance is the wind production forecast error.{{citation needed|date=February 2012}}

Line 35 ⟶ 36:

==General methodology==

Several techniques ovof variousvarying degreedegrees of sophistication are used for short-term prediction of wind generation{{sfn|Hanifi|2020|p=3766}}:{{sfn|Hanifi|2020|pp=3766-3771}}:

* ''persistence'' method is trivialnaïve: assumeit assumes that the wind power in the next time interval will stay the same as the current measured instantaneous power. Forecast efficiency naturally quickly deteriorates with time going forward, and typically this method is used as a base-level set of numbers for the predictions of other methods to be compared against;

* physical methods that use the [[numerical weather prediction]] results, recalculate them into the wind speed at the generation site utilizing the physical characteristics of the area around the wind farm and convert the speed to power predictions using the turbine power curve;

* physical methods;

* statistical methods are based on models that assume linear or nonlinear relationship between the numerical weather prediction results and the wind power, with the coefficients trained using the historical data. Two broad subclasses of the statistical models are:

* statistical methods:

** time series;

** ANNs;

* hybrid methods.

The simplest ones are based on climatology or averages of past production values. They may be considered as reference forecasting methods since they are easy to implement, as well as benchmark when evaluating more advanced approaches. The most popular of these reference methods is certainly ''persistence''. This naive predictor – commonly referred to as 'what you see is what you get' — states that the future wind generation will be the same as the last measured value. Despite its apparent simplicity, this naive method might be hard to beat for look-ahead times up to 4–6 hours ahead

Advanced approaches for short-term wind power forecasting necessitate predictions of meteorological variables as input. Then, they differ in the way predictions of meteorological variables are converted to predictions of wind power production, through the so-called ''power curve''. Such advanced methods are traditionally divided into two groups. The first group, referred to as physical approach, focuses on the description of the wind flow around and inside the wind farm, and use the manufacturer's power curve, for proposing an estimation of the wind power output. In parallel the second group, referred to as statistical approach, concentrates on capturing the relation between meteorological predictions (and possibly historical measurements) and power output through statistical models whose parameters have to be estimated from data, without making any assumption on the physical phenomena.

Line 52 ⟶ 51:

Predictions of meteorological variables are provided by meteorological institutes. Meteorologists employ atmospheric models for weather forecasts on short and medium term periods. An atmospheric model is a numerical approximation of the physical description of the state of the atmosphere in the near future, and usually is run on a supercomputer. Each computation starts with initial conditions originating from recent measurements. The output consists of the expected instantaneous value of physical quantities at various vertical levels in a horizontal grid and stepping in time up to several hours after initiation. There are several reasons why atmospheric models only approximate reality. First of all, not all relevant atmospheric processes are included in the model. Also, the initial conditions may contain errors (which in a worse case propagate), and the output is only available for discrete points in space (horizontal as well as vertical) and time. Finally, the initial conditions age with time – they are already old when the computation starts let alone when the output is published. Predictions of meteorological variables are issued several times per day (commonly between 2 and 4 times per day), and are available few hours after the beginning of the forecast period. This is because some time is needed for acquiring and analyzing the wealth of measurements used as input to NWP models, then run the model and check and distribute the output forecast series. This gap is a blind spot in the forecasts from an atmospheric model. As an example in the Netherlands, KNMI publishes 4 times per day expected values of wind speed, wind direction, temperature and pressure for the period the between 0 and 48 hours after initialization of the atmospheric model Hirlam with measured data, and then the period before forecast delivery is of 4 hours.

Many different atmospheric models are available, ranging from academic research tools to fully operational instruments. Besides for the very nature of the model (physical processes or numerical schemes) there are some clear distinctive differences between them: time ___domain (from several hours to 6 days ahead), area (several 10.000&nbsp;km²² to an area covering half the planet), horizontal resolution (1&nbsp;km to 100&nbsp;km) and temporal resolution (1 hour to several hours).

One of the atmospheric models is the High Resolution Limited Area Model, abbreviated [[HIRLAM]], which is frequently used in Europe. HIRLAM comes in many versions; that is why it is better to speak about "a" HIRLAM rather than "the" HIRLAM. Each version is maintained by a national institute such as the Dutch [[Royal Netherlands Meteorological Institute | KNMI]], the Danish [[Danish Meteorological Institute|DMI]] or Finnish [[Finnish Meteorological Institute|FMI]]. And each institute has several versions under her wing, divided into categories such as: operational, pre-operational, semi operational and for research purposes.

Other atmospheric models are

Line 60 ⟶ 59:

* '''COSMO''' and '''ICON''' in Germany, run by [[Deutscher Wetterdienst|DWD]],

* '''ALADIN''' in France, run by [[Météo-France]],

* and '''[[Global Forecast System|GFS]]''' in the USAUS, run by [[National Centers for Environmental Prediction|NCEP]].

Note that ALADIN and COSMO are also used by other countries within Europe, while UM has been used by [[Bureau of Meteorology|BOM]] in Australia.

Line 76 ⟶ 75:

Today, major developments of statistical approaches to wind power prediction concentrate on the use of multiple meteorological forecasts (from different meteorological offices) as input and forecast combination, as well as on the optimal use of spatially distributed measurement data for prediction error correction, or alternatively for issuing warnings on potentially large uncertainty.

Google's [[DeepMind]] uses [[neural network]] to improve forecasting.<ref>{{cite web |last1=LiElkin |first1=AbnerCarl | last2 = Witherspoon | first2 = Sims |title=Google optimizing wind farms with DeepMind ML to predict power output by 36 hours |url=https://9to5googledeepmind.comgoogle/2019discover/02blog/26/googlemachine-deepmindlearning-can-boost-the-value-of-wind-farmsenergy/ |website=9to5Googledeepmind.google |date=26 February 2019}}</ref>

==Uncertainty of wind power forecasts==

{{ external media

|align float =right

| image1 = [http://www.nordpoolspot.com/Market-data1/Power-system-data/Production1/Wind-Power-Prognosis/ALL/Hourly/ Tomorrow's prognosis] for three system areas; Denmark West and East, and Estonia

}}

Current designs are optimal only for nonturbulent, steady conditions. Design tools accounting for unsteadiness and turbulence are far less developed.<ref name="Zehnder and Warhaft">{{cite web|last=Zehnder and Warhaft|first=Alan and Zellman|title=University Collaboration on Wind Energy|url=https://www.atkinson.cornell.edu/Assets/ACSF/docs/attachments/2011-UnivWindCollaboration.pdf|publisher=Cornell University|access-date=17 August 2011}}</ref>

Line 133 ⟶ 132:

* {{cite book |doi=10.1007/978-981-15-5329-5_9 |ref={{SfnRef|Devi|2021}}|chapter=Long-Term Wind Speed Forecasting—A Review|title=Artificial Intelligence Techniques for Advanced Computing Applications|series=Lecture Notes in Networks and Systems|year=2021|last1=Shobana Devi|first1=A.|last2=Maragatham|first2=G.|last3=Boopathi|first3=K.|last4=Lavanya|first4=M. C.|last5=Saranya|first5=R.|volume=130|pages=79–99|isbn=978-981-15-5328-8|s2cid=225028045|url=https://www.researchgate.net/publication/343190893}}

* {{cite journal |doi=10.1109/MSPEC.2015.7335902 |ref={{sfnref|Haupt|2015}}|title=Taming wind power with better forecasts|year=2015|last1=Haupt|first1=Sue Ellen|last2=Mahoney|first2=William P.|journal=IEEE Spectrum|volume=52|issue=11|pages=47–52|s2cid=2408824|url=https://www.researchgate.net/publication/284749705}}

* {{cite journal |doi=10.1002/for.2657 |title=Timescale classification in wind forecasting: A review of the state‐of‐the‐artstate-of-the-art |year=2020 |last1=Roungkvist |first1=Jannik Schütz |last2=Enevoldsen |first2=Peter |journal=Journal of Forecasting |volume=39 |issue=5 |pages=757–768 |s2cid=213701146 }}

* {{cite journal |doi=10.3390/en13153764|doi-access=free|title=A Critical Review of Wind Power Forecasting Methods—Past, Present and Future|year=2020|last1=Hanifi|first1=Shahram|last2=Liu|first2=Xiaolei|last3=Lin|first3=Zi|last4=Lotfian|first4=Saeid|journal=Energies|volume=13|issue=15|page=3764|ref={{sfnref|Hanifi|2020}}|url=https://www.researchgate.net/publication/343140492}}