Abstract
Photovoltaic (PV) power forecasting urges in economic and secure operations of power systems. To avoid an inaccurate individual forecasting model, we propose an approach for a one-day to three-day ahead PV power hourly forecasting based on the stacking ensemble model with a recurrent neural network (RNN) as a meta-learner. The proposed approach is built by using real weather data and forecasted weather data in the training and testing stages, respectively. To accommodate uncertain weather, a daily clustering method based on statistical features, e.g., daily average, maximum, and standard deviation of PV power is applied in the data sets. Historical PV power output and weather data are used to train and test the model. The single learner considered in this research are artificial neural network, deep neural network, support vector regressions, long short-term memory, and convolutional neural network. Then, RNN is used to combine the forecasting results of each single learner. It is also important to observe the best combination of the single learners in this paper. Furthermore, to compare the performance of the proposed method, a random forest ensemble instead of RNN is used as a benchmark for comparison. Mean relative error (MRE) and mean absolute error (MAE) are used as criteria to validate the accuracy of different forecasting models. The MRE of the proposed RNN ensemble learner model is 4.29%, which has significant improvements by about 7–40%, 7–30%, and 8% compared to the single models, the combinations of fewer single learners, and the benchmark method, respectively. The results show that the proposed method is promising for use in real PV power forecasting systems.
Highlights
The forecasting results of artificial neural network (ANN), deep neural network (DNN), support vector regression (SVR), long short-term memory (LSTM), and convolutional neural network (CNN) were combined by the recurrent neural network (RNN) meta-learner to construct the ensemble model
Our proposed method is compared with the well-known benchmark ensemble model of random forest
This paper compared the RNN-ensemble combination of the three best single learner methods using DNN, SVR, and ANN
Summary
AbstrAabcts:trPahcot:toPvhoolttoaivco(lAPtaVbics)t(prPaoVcwt):epProhfwootreoervcafoosltrtaieniccgas(uPtirVngg)espuoirngweeescroifnnooeremccoiancsotaimnngdicusaerncgduersseeincoupereceroaontpoioemnraisctioaofnnpdsooswfeecpurorwe eorperations systemsyss.teTmo sa.vTooidavaonidinsaayncsctiuenrmaactsce.uTirnoadtaievviiondidudiavalindfouirnaealccafcosutrirenacgtaesmtiinnoddgievmli,dowudaeellp,froworpeecopasrseotipannogsaempaopndroeaalp,cpwhroefoaprcrhaopfooonrseea- aonnea-pproach day tdoatyhrteoe-tdhraeyea-dhaeyadahdPeaVaydptooPwVtherpreohew-oduearrylyhaofhouerraeldycafPsoVtrinepcgoabswtaiesnregdhbooaunsreltyhdefoosnrteatcchakesintsitgnagceknbisanesgmedebnloesnemmthobedleestlmawcokitdihneglawenitshemble mod recurarernetcunerruernatl nneeutwraolrrknece(utRwrNroeNnrkt) n(aResuNarNaml)enateast-wlaeoamrrkneet(arR.-lNTeahNre)npearrs.oapTomhseeetdpar-aloeppaporrnsoeadrc.haTpihspebrpouraiolctphboiysseudbsuianiplgtpbrryoeaaulchsinisgbuilt by u weathreearldwateaaathnedrfdoaretacaawsnteedadtfhwoereeracdtahasettaredadnawdtaefaiontrhetehcraesdttreaadtianwiinnegatthahenedtrrdtaeaisnttaiinnigng atshtnaedgtertsea,sinrtieinnsgpgesactntaidgveetesly,st.rieTnsogpasectcactgoivemesl,-yr.esTpoectively. Energies 2021, 14, 4733 model of PV energy due to the combination of numerical weather prediction and satellite data This method provides the forecasting only for a short time horizon (6 h ahead). Pattern classification and particle swarm optimization [9] are used to optimize the weight of sky image cloud motion calculation to improve the accuracy of PV power forecasting. The drawback of this method is the high computational cost caused by the implementation of the optimization method compared to low prediction accuracy, which needs to be corrected. Without including the meteorological variables, it is still difficult to obtain better accuracy for a longer time period
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
