Solar power forecasting: Difference between revisions

Revision as of 16:04, 16 April 2019

Revision as of 06:52, 8 May 2019

Line 21:

==Nowcasting==

The term "[[Nowcasting]]" in the context of solar power forecasting, generally refers to same spatial and temporal scales as [[Nowcasting (meteorology)|meteorological Nowcasting]], which focuses on forecast horizons from a few minutes ahead, out to 4-6 hours ahead. In general, the 'Nowcasting' forecast horizon refers to those not well-served by global numerical weather prediction models, which produce outputs at up to hourly resolutions and only update every 6 hours. [[Solar power]] nowcasting then refers to the prediction of solar power output (or energy generation) over time horizons of tens to hundreds of minutes ahead of time, and has historically been very important for [[Electrical grid|electrical grid operators]] in order to guarantee the matching of supply and demand on energy markets. Such solar power nowcasting services are usually related to temporal resolutions of 5 to 15 minutes, with updates as frequent as every 5 minutes. The regular updates and relatively high resolutions required from these methods require automatic weather data acquisition and processing techniques, which are chiefly accomplished by two primary means<ref>{{Cite web|url=https://www.elsevier.com/books/solar-energy-forecasting-and-resource-assessment/kleissl/978-0-12-397177-7|title=Solar Energy Forecasting and Resource Assessment - 1st Edition|website=www.elsevier.com|access-date=2019-05-08}}</ref>:

Nowcasting comprises the detailed description of the current weather along with forecasts for up to 3–4 hours. This very short-term forecasting service is very important for grid operators in order to guarantee the grid stability and for those power plants that can be considered manageable, at least in a certain degree, such as solar thermal power plants.

Nowcasting services are usually related to very high temporal resolution (a forecast every 10 or 15 minutes), so automatic weather data acquisition and processing is a major requirement in order to develop these techniques. Several approaches can be found in the literature, which mainly depend on the type of data that is treated to estimate future values of meteorological variables:

# '''Statistical techniques.''' These are usually based on [[time series]] processing of meteorological measuredmeasurement data, whichincluding [[Surface weather observation|meteorological observations]] and power output measurements from a solar power facility. What then follows is usedthe ascreation of a [[Training, validation, and test sets|training datadataset]] to tune the parameters of a model (I. Espino eta al, 2011), before evaluation of model performance against a separate testing dataset. These This class of techniques includeincludes the use of any kind of statistical approach, such as [[Autoregressive–moving-average model|autoregressive moving averageaverages]] (ARMA, ARIMA,… etc), as well as machine learning techniques such as [[Artificial neural network|neural networks]], [[support vector machine]]s, (etc). These approaches are usually benchmarked to a persistence approach in order to evaluate their improvements. This persistence approach just assumes that any variable at time step t is the value it took in a previous time.

#[[File:Satellite Based Solar Nowcasting.gif|thumb|An example of satellite-based cloud cover nowcasting, which is used to generate predication of solar power outputs. Credit: [http://solcastglobal.com Solcast]]]'''Satellite based methods.''' These methods leverage the several [[Geostationary orbit|geostationary]] Earth observing [[Weather satellite|weather satellites]] (such as [[Meteosat|Meteosat Second Generation (MSG) fleet]]'')'' to detect, characterise, track and predict the future locations of cloud cover. These satellites make it possible to generate solar power forecasts over broad regions through the application of image processing and forecasting algorithms. Key forecasting algorithms include cloud motion vectors (CMVs)<ref>{{Cite web|url=http://glossary.ametsoc.org/wiki/Cloud_motion_vector|title=Cloud motion vector - AMS Glossary|website=glossary.ametsoc.org|access-date=2019-05-08}}</ref>. Relevant methods for applying physical models based on satellite image processing techniques provide an estimation of future atmospheric values can be found in ''Alvarez et al.'', 2010.

# Since the launch of Earth observing satellites, such as ''MSG'', nowcasting techniques have also been developed from an image processing point of view. The main advantage of these techniques is the possibility to monitorize a lot of meteorological information in almost real time. This high value information is used as input to physical models based on image processing techniques that provide an estimation of future atmospheric values, as described in ''Alvarez et al.'', 2010.

==Solar PV shortShort-term solar power forecasting==

''Short-term'' forecasting provides predictions up to 7 days ahead. This kind of forecast is also valuable for grid operators in order to make decisions of grid operation, as well as, for electric market operators.<ref>{{cite journal|last1=Sanjari|first1=M.J.|last2=Gooi|first2=H.B.|title=Probabilistic Forecast of PV Power Generation based on Higher-order Markov Chain|journal=IEEE Transactions on Power Systems|date=2016|doi=10.1109/TPWRS.2016.2616902}}</ref>

Line 35 ⟶ 34:

Finally, some communities argue for the use of post-processing techniques, once the models’ output is obtained, in order to obtain a probabilistic point of view of the accuracy of the output. This is usually done with ensemble techniques that mix different outputs of different models perturbed in strategic meteorological values and finally provide a better estimate of those variables and a degree of uncertainty, like in the model proposed by Bacher et al. (2009)

==Solar PV longLong-term solar power forecasting==

''Long-term'' forecasting usually refers to forecasting of the annual or monthly available resource. This is useful for energy producers and to negotiate contracts with financial entities or utilities that distribute the generated energy.