Ensemble Approach of Optimized Artificial Neural Networks for Solar Photovoltaic Power Prediction
Open accessThe DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
Abstract
The use of data-driven ensemble approaches for the prediction of the solar Photovoltaic (PV) power production is promising due to their capability of handling the intermittent nature of the solar energy source. In this work, a comprehensive ensemble approach composed by optimized and diversified Artificial Neural Networks (ANNs) is proposed for improving the 24h-ahead solar PV power production predictions. The ANNs are optimized in terms of number of hidden neurons and diversified in terms of the diverse training datasets used to build the ANNs, by resorting to trial-and-error procedure and BAGGING techniques, respectively. In addition, the Bootstrap technique is embedded to the ensemble for quantifying the sources of uncertainty that affect the ensemble models' predictions in the form of Prediction Intervals (PIs). The effectiveness of the proposed ensemble approach is demonstrated by a real case study regarding a grid-connected solar PV system (231 kWac capacity) installed on the rooftop of the Faculty of Engineering at the Applied Science Private University (ASU), Amman, Jordan. The results show that the proposed approach outperforms three benchmark models, including smart persistence model and single optimized ANN model currently adopted by the PV system's owner for the prediction task, with a performance gain reaches up to 11%, 12%, and 9%, for RMSE, MAE, and WMAE standard performance metrics, respectively. Simultaneously, the proposed approach has shown superior in quantifying the uncertainty affecting the power predictions, by establishing slightly wider PIs that achieve the highest confidence level reaches up to 84% for a predefined confidence level of 80% compared to three other approaches of literature. These enhancements would, indeed, allow balancing power supplies and demands across centralized grid networks through economic dispatch decisions between the energy sources that contribute to the energy mix.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728 · cited 2×
“Although different data-driven methods are shown capable in providing sufficiently accurate solar PV power production predictions, the ANNs are adopted in this work to constitute the proposed ensemble, due to their simplicity, being easy to understand, and due to their capability of successfully solving highly non-lin…”
BackgroundMethodParticle swarm optimization: An overview
Poli, R., Kennedy, J., & Blackwell, T. (2007) · Swarm Intelligence · doi:10.1007/s11721-007-0002-0 · Cited by 21,101
A decision-theoretic generalization of on-line learning and an application to boosting
Freund, Y., & Schapire, R. E. (1997) · Journal of Computer and System Sciences · doi:10.1006/jcss.1997.1504 · Cited by 20,466
Neural networks for pattern recognition
(1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,538
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325 · cited 4×
“Several methods were proposed in literature to achieve diversity among the ensemble models, like adopting different types of prediction models, adopting the same prediction model type but with different parameter settings, or building/ training each prediction model with different training datasets, by resorting to te…”
MethodInfluentialThe Elements of Statistical Learning: Data Mining, Inference, and Prediction
John Lu, Z. Q. (2010) · Journal of the Royal Statistical Society Series A: Statistics in Society · doi:10.1111/j.1467-985x.2010.00646_6.x · Cited by 12,390
Cuckoo Search via Lévy flights
Yang, X.-S., & Deb, S. (2009) · 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC) · doi:10.1109/nabic.2009.5393690 · Cited by 6,185 · cited 1×
“In fact, one can employ advanced meta-heuristic optimization algorithms, such as Particle Swarm Optimization (PSO) [76], [77], Cuckoo Search (CS) [78], Genetic Algorithm (GA) [76], or a combination of these algorithms, to define optimally the ANN base models internal parameters (e.”
MethodThe Strength of Weak Learnability
Schapire, R. E. (1990) · Machine Learning · doi:10.1007/bf00116037 · Cited by 4,600
Role of renewable energy sources in environmental protection: A review
Panwar, N. L., Kaushik, S. C., & Kothari, S. (2011) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2010.11.037 · Cited by 3,897
Kennedy, J. (2011) · Encyclopedia of Machine Learning · doi:10.1007/978-0-387-30164-8_630 · Cited by 2,989
Ensemble based systems in decision making
Polikar, R. (2006) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2006.1688199 · Cited by 2,938
Kernel density estimation via diffusion
Botev, Z. I., Grotowski, J. F., & Kroese, D. P. (2010) · The Annals of Statistics · doi:10.1214/10-aos799 · Cited by 1,689
Review of photovoltaic power forecasting
Antonanzas, J., Osorio, N., Escobar, R., Urraca, R., Martinez-de-Pison, F. J., & Antonanzas-Torres, F. (2016) · Solar Energy · doi:10.1016/j.solener.2016.06.069 · Cited by 1,343 · cited 1×
“The effective contribution of solar PV production to the energy mix requires the availability of prediction (forecasting) models capable of providing accurate power production predictions [13]–[15].”
BackgroundForecasting of photovoltaic power generation and model optimization: a review
Das, U. K., Tey, K. S., Seyedmahmoudian, M., Mekhilef, S., Idris, M. Y. I., Van Deventer, W., Horan, B., & Stojcevski, A. (2018) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2017.08.017 · Cited by 1,211 · cited 1×
“Generally, the prediction approaches can be categorized into model-based and data-driven [23]–[26].”
MethodLower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals
Khosravi, A., Nahavandi, S., Creighton, D., & Atiya, A. F. (2011) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2096824 · Cited by 758 · cited 5×
“81742 VOLUME 7, 2019 Techniques like Bootstrap (BS) [51], Delta [52], MeanVariance Estimation (MVE) [53], and Lower Upper Bound Estimation (LUBE) [54] were successfully applied for uncertainty quantification in different industrial applications [45], [49], [55].”
MethodInfluentialJaulin, L., Kieffer, M., Didrit, O., & Walter, E. (1993) · HAL · Cited by 748
Estimating the mean and variance of the target probability distribution
Nix, D. A., & Weigend, A. S. (1994) · Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94) · doi:10.1109/icnn.1994.374138 · Cited by 700 · cited 7×
“More details on the MVE can be found in [49], [53].”
BackgroundMethodInfluentialComprehensive Review of Neural Network-Based Prediction Intervals and New Advances
Khosravi, A., Nahavandi, S., Creighton, D., & Atiya, A. F. (2011) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2011.2162110 · Cited by 694 · cited 23×
“More details on the MVE can be found in [49], [53].”
BackgroundMethodInfluentialAttribute bagging: improving accuracy of classifier ensembles by using random feature subsets
Bryll, R., Gutierrez-Osuna, R., & Quek, F. (2003) · Pattern Recognition · doi:10.1016/s0031-3203(02)00121-8 · Cited by 481 · cited 1×
“In this work, BAGGING technique (which is based on training the multiple base models using different training sets, whose training patterns are sampled randomly with replacement from the original available training dataset) is employed since it is shown capable of enhancing the prediction performance and it is easy to…”
MethodEvolutionary ensembles with negative correlation learning
Higuchi, T., Yao, X., & Liu, Y. (2000) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.887237 · Cited by 445 · cited 2×
“In this work, statistics-based strategy is adopted by calculating the median of the individual base models’ predictions because it is the simplest to develop and easiest to understand [47], [48].”
MethodEnsemble methods for wind and solar power forecasting—A state-of-the-art review
Ren, Y., Suganthan, P. N., & Srikanth, N. (2015) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2015.04.081 · Cited by 435 · cited 1×
“To overcome this challenge, ensemble approaches, which aggregate the predictions provided by multiple prediction models (hereafter called base models), are developed and showed to be a better mean in boosting the predictions accuracy, with respect to any sole model of the ensemble, and at the same time quantifying the…”
BackgroundMulti-site solar power forecasting using gradient boosted regression trees
Persson, C., Bacher, P., Shiga, T., & Madsen, H. (2017) · Solar Energy · doi:10.1016/j.solener.2017.04.066 · Cited by 408 · cited 3×
“, Artificial Neural Networks (ANNs) [27], Gradient Boosting Regression Trees (GBRT) [28], Support Vector Machines (SVMs) [29], and Extreme Learning Machines (ELMs) [25].”
BackgroundAn analog ensemble for short-term probabilistic solar power forecast
Alessandrini, S., Delle Monache, L., Sperati, S., & Cervone, G. (2015) · Applied Energy · doi:10.1016/j.apenergy.2015.08.011 · Cited by 362 · cited 1×
“However, production prediction from such energy sources depends on intermittent (stochastic) weather variables, such as solar radiation, wind speed, and ambient temperature, which lead to large uncertainties in solar power production predictions [18]–[22].”
BackgroundPrediction Intervals for Artificial Neural Networks
Hwang, J. T. G., & Ding, A. A. (1997) · Journal of the American Statistical Association · doi:10.1080/01621459.1997.10474027 · Cited by 341 · cited 4×
“Techniques like Bootstrap (BS) [51], Delta [52], MeanVariance Estimation (MVE) [53], and Lower Upper Bound Estimation (LUBE) [54] were successfully applied for uncertainty quantification in different industrial applications [45], [49], [55].”
MethodInfluentialSolar Power Prediction Based on Satellite Images and Support Vector Machine
Jang, H. S., Bae, K. Y., Park, H.-S., & Sung, D. K. (2016) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2016.2535466 · Cited by 340 · cited 1×
“, Artificial Neural Networks (ANNs) [27], Gradient Boosting Regression Trees (GBRT) [28], Support Vector Machines (SVMs) [29], and Extreme Learning Machines (ELMs) [25].”
BackgroundAnalysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power
Leva, S., Dolara, A., Grimaccia, F., Mussetta, M., & Ogliari, E. (2015) · Mathematics and Computers in Simulation · doi:10.1016/j.matcom.2015.05.010 · Cited by 328
Neural Networks for Pattern Recognition
Kothari, S. C., & Oh, H. (1993) · Advances in Computers · doi:10.1016/s0065-2458(08)60404-0 · Cited by 316
Wind Effect on PV Module Temperature: Analysis of Different Techniques for an Accurate Estimation
Schwingshackl, C., Petitta, M., Wagner, J., Belluardo, G., Moser, D., Castelli, M., Zebisch, M., & Tetzlaff, A. (2013) · Energy Procedia · doi:10.1016/j.egypro.2013.08.010 · Cited by 309 · cited 1×
“However, several modelbased approaches were developed to accurately estimate the cell temperature and compare it with the real (measured) one [65].”
BackgroundPractical Confidence and Prediction Intervals
Heskes, T. (1996) · doi:10.5555/2998981.2999006 · Cited by 288
Optimal scheduling of thermal-wind-solar power system with storage
Salkuti, S. R. (2016) · Renewable Energy · doi:10.1016/j.renene.2016.10.022 · Cited by 261
Short–mid-term solar power prediction by using artificial neural networks
İzgi, E., Öztopal, A., Yerli, B., Kaymak, M. K., & Şahin, A. D. (2012) · Solar Energy · doi:10.1016/j.solener.2011.11.013 · Cited by 233 · cited 2×
“, Artificial Neural Networks (ANNs) [27], Gradient Boosting Regression Trees (GBRT) [28], Support Vector Machines (SVMs) [29], and Extreme Learning Machines (ELMs) [25].”
BackgroundMethodSolar photovoltaic power forecasting using optimized modified extreme learning machine technique
Behera, M. K., Majumder, I., & Nayak, N. (2018) · Engineering Science and Technology, an International Journal · doi:10.1016/j.jestch.2018.04.013 · Cited by 216 · cited 2×
“, one-day ahead) of production from such systems [16].”
BackgroundMethodThe value of day-ahead solar power forecasting improvement
Brancucci Martinez-Anido, C., Botor, B., Florita, A. R., Draxl, C., Lu, S., Hamann, H. F., & Hodge, B.-M. (2016) · Solar Energy · doi:10.1016/j.solener.2016.01.049 · Cited by 212 · cited 3×
“The effective contribution of solar PV production to the energy mix requires the availability of prediction (forecasting) models capable of providing accurate power production predictions [13]–[15].”
BackgroundWhat Size Neural Network Gives Optimal Generalization? Convergence Properties of Backpropagation
Lawrence, S., Giles, C. L., & Tsoi, A. C. (1998) · University Libraries (University of Maryland) · Cited by 209
The dynamics of solar PV costs and prices as a challenge for technology forecasting
Candelise, C., Winskel, M., & Gross, R. J. K. (2013) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2013.05.012 · Cited by 195
Li, Z., Rahman, S., Vega, R. E., & Dong, B. (2016) · Energies · doi:10.3390/en9010055 · Cited by 172
Probabilistic solar power forecasting in smart grids using distributed information
Bessa, R. J., Trindade, A., Silva, C. S. P., & Miranda, V. (2015) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2015.02.006 · Cited by 154
Modelling and Prediction of Photovoltaic Power Output Using Artificial Neural Networks
Saberian, A., Hizam, H., Radzi, M. A. M., Kadir, M. Z. A. A., & Mirzaei, M. (2014) · International Journal of Photoenergy · doi:10.1155/2014/469701 · Cited by 151 · cited 2×
“Although different data-driven methods are shown capable in providing sufficiently accurate solar PV power production predictions, the ANNs are adopted in this work to constitute the proposed ensemble, due to their simplicity, being easy to understand, and due to their capability of successfully solving highly non-lin…”
BackgroundMethodSVR-Based Model to Forecast PV Power Generation under Different Weather Conditions
Das, U. K., Tey, K. S., Seyedmahmoudian, M., Idris, M. I., Mekhilef, S., Horan, B., & Stojcevski, A. (2017) · Energies · doi:10.3390/en10070876 · Cited by 145
Confidence intervals and prediction intervals for feedforward neural networks
Dybowski, R., & Roberts, S. (2001) · Cambridge University Press eBooks · doi:10.1017/cbo9780511543494.013 · Cited by 135
Kim, S.-G., Jung, J.-Y., & Sim, M. K. (2019) · Sustainability · doi:10.3390/su11051501 · Cited by 130 · cited 1×
“, one-day ahead, has, indeed, several economic benefits, including reliable operation planning, scheduling of generation, efficient electricity market operations, and proactive power trading [15], [17].”
BackgroundEnsemble of optimized echo state networks for remaining useful life prediction
Rigamonti, M., Baraldi, P., Zio, E., Roychoudhury, I., Goebel, K., & Poll, S. D. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.11.062 · Cited by 121 · cited 3×
“Techniques like Bootstrap (BS) [51], Delta [52], MeanVariance Estimation (MVE) [53], and Lower Upper Bound Estimation (LUBE) [54] were successfully applied for uncertainty quantification in different industrial applications [45], [49], [55].”
BackgroundMethodExtreme Learning Machines for Solar Photovoltaic Power Predictions
Al‐Dahidi, S., Ayadi, O., Adeeb, J., Alrbai, M., & Qawasmeh, B. R. (2018) · Energies · doi:10.3390/en11102725 · Cited by 116 · cited 4×
“, Artificial Neural Networks (ANNs) [27], Gradient Boosting Regression Trees (GBRT) [28], Support Vector Machines (SVMs) [29], and Extreme Learning Machines (ELMs) [25].”
BackgroundMethodSelf-citationMulti-Model Ensemble for day ahead prediction of photovoltaic power generation
Pierro, M., Bucci, F., Felice, M. D., Maggioni, E. C., Moser, D., Perotto, A., Spada, F., & Cornaro, C. (2016) · Solar Energy · doi:10.1016/j.solener.2016.04.040 · Cited by 115 · cited 1×
“[34], developed an outperforming Multi-Model Ensemble (MME) that averages the 24h-ahead solar PV power production obtained by the best different data-driven base models fed with different numerical weather prediction input data.”
MethodReview of stochastic optimization methods for smart grid
Salkuti, S. R., Vuddanti, S., & Jung, C.-M. (2017) · Frontiers in Energy · doi:10.1007/s11708-017-0457-7 · Cited by 114
Real time economic dispatch considering renewable energy resources
Salkuti, S. R., & Bijwe, P. R. (2015) · Renewable Energy · doi:10.1016/j.renene.2015.06.011 · Cited by 108 · cited 1×
“However, production prediction from such energy sources depends on intermittent (stochastic) weather variables, such as solar radiation, wind speed, and ambient temperature, which lead to large uncertainties in solar power production predictions [18]–[22].”
BackgroundRandom forest ensemble of support vector regression models for solar power forecasting
Abuella, M., & Chowdhury, B. (2017) · IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT) · doi:10.1109/isgt.2017.8086027 · Cited by 97 · cited 1×
“With respect to 1), it is shown that the more diversified base prediction models are, the better prediction accuracy of the ensemble outcome can be obtained [38]–[40].”
BackgroundShort-Term Forecasting Models for Photovoltaic Plants: Analytical versus Soft-Computing Techniques
Monteiro, C., Fernández-Jiménez, L. A., Ramírez-Rosado, I. J., Muñoz-Jimenez, A., & Lara-Santillán, P. M. (2013) · Mathematical Problems in Engineering · doi:10.1155/2013/767284 · Cited by 90 · cited 1×
“Generally, the prediction approaches can be categorized into model-based and data-driven [23]–[26].”
MethodEnsemble Learning Approach for Probabilistic Forecasting of Solar Power Generation
Mohammed, A. A., & Aung, Z. (2016) · Energies · doi:10.3390/en9121017 · Cited by 85 · cited 1×
“To overcome this challenge, ensemble approaches, which aggregate the predictions provided by multiple prediction models (hereafter called base models), are developed and showed to be a better mean in boosting the predictions accuracy, with respect to any sole model of the ensemble, and at the same time quantifying the…”
BackgroundFast meta-models for local fusion of multiple predictive models
Bonissone, P. P., Xue, F., & Subbu, R. (2008) · Applied Soft Computing · doi:10.1016/j.asoc.2008.03.006 · Cited by 64 · cited 2×
“The prediction accuracy provided by an ensemble of multiple models can be improved by generating diversity among its individual base prediction models [39], [40], [57].”
BackgroundPaulescu, M., Brabec, M., Boata, R. S., & Bădescu, V. (2017) · Energy · doi:10.1016/j.energy.2017.01.015 · Cited by 54 · cited 1×
“For completeness, it is worth mentioning that body (or cell) temperature was used as input to the prediction model because it has a strong influence on the solar power production predictions [63], [64].”
MethodSolar Photovoltaic Power Forecasting in Jordan using Artificial Neural Networks
Alomari, M. H., Adeeb, J., & Younis, O. (2018) · International Journal of Electrical and Computer Engineering (IJECE) · doi:10.11591/ijece.v8i1.pp497-504 · Cited by 54 · cited 2×
“For a proper utilization of the dataset for the prediction task, the data are pre-processed as follows [25], [66]: • incorrect (e.”
MethodSelf-citationPhotovoltaic Forecasting: A state of the art
Espinar, B., Aznarte, J.-L., Girard, R., Moussa, A. M., & Kariniotakis, G. (2010) · HAL · Cited by 53
Online 3-h forecasting of the power output from a BIPV system using satellite observations and ANN
Rosiek, S., Alonso-Montesinos, J., & Batlles, F. J. (2018) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2018.01.025 · Cited by 51
The forecast of the electrical energy generated by photovoltaic systems using neural network method
Yu, T.-C., & Chang, H.-T. (2011) · International Conference on Electric Information and Control Engineering · doi:10.1109/iceice.2011.5778257 · Cited by 43 · cited 1×
“For completeness, it is worth mentioning that body (or cell) temperature was used as input to the prediction model because it has a strong influence on the solar power production predictions [63], [64].”
MethodNeural network modeling with confidence bounds: a case study on the solder paste deposition process
Ho, S. L., Xie, M., Tang, L. C., Xu, K. J., & Goh, T. N. (2001) · IEEE Transactions on Electronics Packaging Manufacturing · doi:10.1109/6104.980042 · Cited by 42 · cited 2×
“Techniques like Bootstrap (BS) [51], Delta [52], MeanVariance Estimation (MVE) [53], and Lower Upper Bound Estimation (LUBE) [54] were successfully applied for uncertainty quantification in different industrial applications [45], [49], [55].”
MethodAlomari, M. H., Younis, O., & Sofyan, M. (2018) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2018.090148 · Cited by 38 · cited 3×
“This is typically the current case of the ASU PV system [62], [66]; • Benchmark 3 (Best ofM = 20ANNs): in which the final performancemetrics are those obtained by the best ANN model among the 20 available models of the ensemble.”
MethodOgliari, E., Niccolai, A., Leva, S., & Zich, R. E. (2018) · Energies · doi:10.3390/en11061487 · Cited by 38 · cited 3×
“NOMENCLATURE A. ABBREVIATIONS RE Renewable Energy PV Photovoltaics LCOE Levelised Cost Of Electricity ANNs Artificial Neural Networks BP Back Propagation LM Levenberg–Marquardt BR Bayesian regularization GBRT Gradient Boosting Regression Trees RBFNN Radial Basis Function Neural Network SVMs Support Vector Machines LS-…”
BackgroundDay-ahead forecasting for photovoltaic power using artificial neural networks ensembles
Omar, M., Dolara, A., Magistrati, G., Mussetta, M., Ogliari, E., & Viola, F. (2016) · International Conference on Renewable Energy Research and Applications (ICRERA) · doi:10.1109/icrera.2016.7884513 · Cited by 32 · cited 1×
“[33], developed ensembles of multilayer perceptron feedforward ANNs models that receive the weather forecasts of the next day as an input and produce more generalized one day-ahead production predictions as an output of a solar facility; Pierro et al.”
BackgroundAn Optimized Prediction Intervals Approach for Short Term PV Power Forecasting
Ni, Q., Zhuang, S., Sheng, H., Wang, S., & Xiao, J. (2017) · Energies · doi:10.3390/en10101669 · Cited by 25
A dynamic weighting ensemble approach for wind energy production prediction
Al‐Dahidi, S., Baraldi, P., Zio, E., Zio, E., & Legnani, E. (2017) · International Conference on System Reliability and Safety (ICSRS) · doi:10.1109/icsrs.2017.8272838 · Cited by 17 · cited 4×
“Although different data-driven methods are shown capable in providing sufficiently accurate solar PV power production predictions, the ANNs are adopted in this work to constitute the proposed ensemble, due to their simplicity, being easy to understand, and due to their capability of successfully solving highly non-lin…”
BackgroundMethodSelf-citationA locally adaptive ensemble approach for data-driven prognostics of heterogeneous fleets
Al‐Dahidi, S., Maio, F. D., Baraldi, P., & Zio, E. (2017) · Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability · doi:10.1177/1748006x17693519 · Cited by 16 · cited 1×
“Aggregation strategies can be generally categorized into statistics-based and model performance-based [39], [45], [46].”
BackgroundSelf-citation
Cited by
Ahmed, R., Sreeram, V., Mishra, Y., & Arif, M. D. (2020) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2020.109792 · Cited by 1,259
“The time stamp (hour of the day studied) introduces uncertainty in the forecast [98] which is significant during mid-day (due to higher weather variations) compared to that at early hours or late evenings.”
BackgroundMethodResultInfluentialSustainable energies and machine learning: An organized review of recent applications and challenges
Ifaei, P., Nazari-Heris, M., Tayerani Charmchi, A. S., Asadi, S., & Yoo, C. (2023) · Energy · doi:10.1016/j.energy.2022.126432 · Cited by 79
Metadata
- Authors
- Al-Dahidi, S., Ayadi, O., Alrbai, M., & Adeeb, J.
- Venue
- IEEE Access
- Published
- 2019
- Volume
- 7
- Pages
- 81741-81758
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2949806812
- Cited by
- 159
- References
- 63
- FWCI
- 7.71
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.