Abstract
Solar energy penetration has been on the rise worldwide during the past decade, attracting a growing interest in solar power forecasting over short time horizons. The increasing integration of these resources without accurate power forecasts hinders the grid operation and discourages the use of this renewable resource. To overcome this problem, Virtual Power Plants (VPPs) provide a solution to centralize the management of several installations to minimize the forecasting error. This paper introduces a method to efficiently produce intra-day accurate Photovoltaic (PV) power forecasts at different locations, by using free and available information. Prediction intervals, which are based on the Mean Absolute Error (MAE), account for the forecast uncertainty which provides additional information about the VPP node power generation. The performance of the forecasting strategy has been verified against the power generated by a real PV installation, and a set of ground-based meteorological stations in geographical proximity have been used to emulate a VPP. The forecasting approach is based on a Long Short-Term Memory (LSTM) network and shows similar errors to those obtained with other deep learning methods published in the literature, offering a MAE performance of 44.19 W/m2 under different lead times and launch times. By applying this technique to 8 VPP nodes, the global error is reduced by 12.37% in terms of the MAE, showing huge potential in this environment.
Highlights
Around the world, the full deployment of solar energy is being facilitated by several factors including, but not limited to, the reduced price of solar panels; environmental, political and social concerns; and solar energy undercutting utility prices, inter alia
The main contributions of this paper are summarized as follows: (i) the PV forecasting method is applied to a Virtual Power Plants (VPPs) environment to reduce the forecasting error, which is modelled as a function of two well-defined parameters called lead time and launch time; (ii) prediction intervals are used to model the forecast uncertainty as a function of the lead time and the launch time, and the Cloud Cover Factor (CCF), which allows the type of day to be identified; (iii) the input data for the forecasting strategy are derived from free-of-charge open-access data sources, offering a viable and cost-effective solution; and (iv) a trade-off between accuracy and computational burden facilitates the application of multiple PV power forecasts at different locations, within the context of a VPP
TGhHeIGerHroIre, rarsoar,fausncatifounncotfiothneolef atdhetilmeaedantidmteheanladutnhcehltaiumnec,hshtiomwes, shows a low performance when the launch time is lower than 1.5 h, corresponding to a low performance when the launch time is lower than 1.5 h, corresponding to sunrise
Summary
The full deployment of solar energy is being facilitated by several factors including, but not limited to, the reduced price of solar panels; environmental, political and social concerns; and solar energy undercutting utility prices, inter alia. The main contributions of this paper are summarized as follows: (i) the PV forecasting method is applied to a VPP environment to reduce the forecasting error, which is modelled as a function of two well-defined parameters called lead time and launch time; (ii) prediction intervals are used to model the forecast uncertainty as a function of the lead time and the launch time, and the Cloud Cover Factor (CCF), which allows the type of day to be identified; (iii) the input data for the forecasting strategy are derived from free-of-charge open-access data sources, offering a viable and cost-effective solution; and (iv) a trade-off between accuracy and computational burden facilitates the application of multiple PV power forecasts at different locations, within the context of a VPP. THhIids adtaatsaebtafsoer itsrauisneidngtoppurropvoisdees.tFhienfaolrlyec, athsteinthgimrdocdaetleswgoitrhy caolmarpgreisGesHnIodn-asttaoscehtafsotrictdraaitnai,nsgucphuarsposusensp. oFsiintiaolnly,,utsheed tfhoirrdthecaCteCgForcyalccuomlatpiorinsetso ndoetne-rsmtoicnheatshtiec tdyaptea,osfudcahya;sthsue nexptorastietirornes, turisaeldrafodriathtieonCCfoFr cgaelnceurlaattiinogn tthoedfeotreercmasintseathnde twyoprekoinf gdaoyu;tththeeexirtrraatdeirarnescterioanl rtahdeiattiilotendfoprlagneeneorfattihneg PthVe mfooredcualsetss;aannddwthorekiinnsgtaolulatttihoen iprararadmiaentceersonwthhiechtialtreedrpeqlauniereodf ftohretPhVe PmVodpuowlese;rafnodretchaestiinnsgta, lalsatiisoenxppalarianmedeteinrsthwehfioclhloawrerineqgusiercetdiofnosr.the PV power forecasting, as is explained
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call