Norwegian version of this page

Joao Leal

Professor Department of Engineering Sciences

Email: joao.leal@uia.no
Phone: +47 37 23 31 39
Office: H4032 (Jon Lilletuns vei 9, 4879 Grimstad, Norway)

Press photo Download business card

Areas of responsibility

EDUCATIONAL BACKGROUND

Ph.D. in Civil Engineering, University of Beira Interior, Portugal, 2005.

M.Sc. in Hydraulics and Water Resources, Instituto Superior Técnico, University of Lisbon, Portugal, 1999.

Licentiate Degree in Civil Engineering (Specialization of Hydraulics and Water Resources), Instituto Superior Técnico, University of Lisbon, Portugal, 1996.

WORKING EXPERIENCE

Since 2014: Professor, Department of Engineering, University of Agder, Norway.

2012-2013: Researcher, Prometeo Project, Secretary of Higher Education, Science, Technology and Innovation, Ecuador.

2008-2014: Assistant Professor, Department of Civil Engineering, Faculty of Science and Technology, New University of Lisbon, Portugal.

2005-2008: Assistant Professor, Department of Civil Engineering and Architecture, University of Beira Interior, Portugal.

1999-2005: Assistant, Department of Civil Engineering and Architecture, University of Beira Interior, Portugal.

1997-1999: Trainee Assistant, Department of Civil Engineering and Architecture, University of Beira Interior, Portugal.

1995-1996: Fellowship for Initiation to Research, Integrated System for Simulating Floods and Risk Assessment (PRAXIS/3/3.2/CEG/32/94), Instituto Superior Técnico, University of Lisbon, Portugal.

ACADEMIC MANAGEMENT EXPERIENCE

2015-2020: Study Coordinator of Master Programme in Renewable Energy, Department of Engineering, University of Agder, Norway.

2009-2014: Member of the Department Council, Department of Civil Engineering, Faculty of Science and Technology, New University of Lisbon, Portugal.

2009-2011: Member of the Scientific Committee of the Integrated Master Programme in Civil Engineering, Faculty of Science and Technology, New University of Lisbon, Portugal.

2006-2007: Director of the Civil Engineering Programme, Department of Civil Engineering and Architecture, University of Beira Interior, Portugal.

2006-2007: Member of the University Pedagogic Council, University of Beira Interior, Portugal.

2005-2008: Director of the Laboratory of Hydraulics, University of Beira Interior, Portugal.

1998-2000: Member of the Faculty Pedagogic Council, Faculty of Engineering, University of Beira Interior, Portugal.

Research

Academic interests

ACADEMIC INTERESTS

Main interests lie within data analysis, conceptual, mathematical and numerical modelling of engineering problems involving water resources. Lately, he has been focused on metaheuristic optimization of engineering systems and data-driven models for water and wind forecasting.

Teaching and supervision experience at B.Sc., M.Sc. and Ph.D. level since 1997. The courses have mainly been devoted to education within civil and renewable energy engineering. Course subjects have included:

Fluid Mechanics (hydraulic design of pipe and open channel systems)
Urban Hydraulics (water supply and drainage systems)
Hydropower (energy evaluation, design of conveyance systems, choice of turbines)
Physical and Mathematical Modelling (dimensional analysis and similarity, numerical integration, differentiation and solution of ODEs and PDEs)
Data analysis, Optimization and Modelling (data mining, data-driven models, meta-heuristic approaches)
Hydrology and Water Resources (resource evaluation, semi-empirical and statistical analysis of precipitation, runoff and floods)
Fluvial Hydraulics (conceptual modelling including compound channel configurations, vegetation, sediment transport and high transient flows)

CURRENT COURSES

ENE-418, Data Analysis and Modelling Techniques in Renewable Energy, M.Sc. Renewable Energy
ENE-410, Fluid Dynamics and Hydro Power, M.Sc. Renewable Energy
ENE-240, Hydro Power, B.Sc. Renewable Energy
BYG-226, Water and Wastewater Treatment, B.Sc. Civil Engineering

Projects

Vocational Education and Training Partnership for Hydropower (VET4Hydro)

Research groups

Energy systems

Bernardo, Francisco; Brito, Moisés; Ferreira, Rui M.L. & Leal, J B (2025). Experimental dataset on wave–structure interaction in a sloshing tank with a flexible floating body. Data in Brief. 63. doi: 10.1016/j.dib.2025.112118. Full text in Research Archive Show summary
There is a critical need for robust validation methods in Computational fluid Dynamics (CFD), particularly for innovative applications involving fluid-structure interactions (FSI). This work presents a comprehensive dataset, including velocity vectors and wall-pressure measurements, obtained from a purpose-built experimental sloshing tank. The design of the tank was CFD-conscious and specific for validation purposes, i.e. choices on operation principles, dimensions, materials and optical access were made to facilitate CFD model implementation while constituting a challenging fluid mechanics problem involving floating flexible bodies. The construction process, the instrumentation, and data collection methods are explained in detail. Though liquid sloshing in a tank is a well-studied subject, this work emphasizes the influence of the flexible floating body on the velocity field and wall-pressure associated to the waves formed by the sloshing rotation of the tank. This dataset allows for validating and improving CFD codes for simulating FSI of flexible bodies. In particular, it provides insights for refining simulations of waves interacting with Very Flexible Floating Structures (VFFS), like the case of offshore Floating Photovoltaic cells (FPV).
Fernandes, J. N.; Singh, P.; Leal, J B & Cardoso, A. H. (2025). Floodplain Transition Zone Hydrodynamics: The Role of Riparian and Floodplain Vegetation in Compound Channel Flows. Ecohydrology. ISSN 1936-0584. 18(7). doi: 10.1002/eco.70123. Full text in Research Archive Show summary
During floods, many rivers exhibit a compound channel configuration, resulting in significant interactions between the flows in the main channel and the floodplains. Due to its water and nutrient-rich soils, floodplains are often covered by shallow vegetation and riparian woodland at the interface of the floodplain and the main channel. Owing to the numerous overtopping scenarios, compound channels are viable in both urban and natural watercourses having floodplains with riparian shrubs, in-line woodland and transplanted trees with different arrangements dictated by shading, species, spacing and occupation of the floodplains. This study investigates the influence of submerged floodplains and combinations of riparian grass, woodlands and shrubs on flow resistance and structure. An experimental campaign was conducted, generating 11 uniform compound channel flows under four different configurations: (i) without vegetation, (ii) with synthetic grass in the floodplains, (iii) with synthetic grass in the floodplains and rods at the floodplain edge and (iv) with synthetic grass in the floodplains and artificial shrubs at the floodplain edge. Primarily, flow mechanisms and turbulence characteristics for three uniform flow depths are analyzed using acoustic Doppler velocity measurements. Then, the increase in flow resistance and reduction of compound channel conveyance capacity were analyzed for individual cases. The synthetic grass in the floodplains minimally influenced the cross-sectional distribution of streamwise velocity, turbulence intensities and lateral shear. On the other hand, riparian vegetation significantly affected these distributions by impeding lateral shear spreading. The effects of vegetation on flow structure were enhanced by foliage on vegetation elements. Additionally, the study examined coherent two-dimensional large structures and secondary currents, revealing that riparian vegetation is critical in altering flow patterns. These findings provide valuable insights into the complex interactions between vegetation and flow dynamics in compound channels.
Fernandes, João N.; Leal, J B & Cardoso, António H. (2024). Shear Layer Development and Fully Developed Flows in Compound Channels. Water resources management. ISSN 0920-4741. p. 1–18. doi: 10.1007/s11269-024-04005-5. Full text in Research Archive
Alipour, Saba Mirza; Engeland, Kolbjørn & Leal, J B (2023). Uncertainty analysis of 100-year flood maps under climate change scenarios. Journal of Hydrology. ISSN 0022-1694. 628. doi: 10.1016/j.jhydrol.2023.130502. Full text in Research Archive
Yakoub, Ghali; Mathew, Sathyajith & Leal, J B (2023). Direct and indirect short-term aggregated turbine- and farm-level wind power forecasts integrating several NWP sources. Heliyon. 9(11). doi: 10.1016/j.heliyon.2023.e21479. Full text in Research Archive Show summary
The wind power sector is experiencing rapid growth, which creates new challenges for its electricity grid integration. Accurate wind power forecasting (WPF) is crucial for trading, balancing, and dispatching wind energy. In this paper, we examine the use of aggregated turbine- and farmlevel WPFs in the Nordic energy market. The turbine-level WPFs were retrieved from a previous study, while the farm-level WPFs were developed using the same methodology, incorporating inputs from three different numerical weather predictions (NWPs) and implementing both direct and indirect forecasting approaches. In the indirect WPF approach, we explore the impact of using wind direction as an input for the wind farm-level power performance model. The different WPFs are combined into one using weights related to up-to-date forecast errors. An automated and optimized machine-learning pipeline using data from a Norwegian wind farm is used to implement the proposed forecasting methods. The indirect approach, that uses the wind-downscaling model, improves the wind speed forecast accuracy compared to raw forecasts from the relevant NWPs. Additionally, we observed that the farm-level downscaling model exhibited lower error than those developed at the turbine level. The combined use of multiple NWP sources reduced forecasting errors by 8 %–30 % for direct and indirect WPFs, respectively. Direct and indirect forecasting methods present similar performance. Finally, the aggregated turbine-level improved WPF accuracy by 10 % and 15 % for RMSE and MAE, respectively, compared to farm-level WPF.
Yakoub, Ghali; Mathew, Sathyajith & Leal, J B (2022). Power production forecast for distributed wind energy systems using support vector regression. Energy Science & Engineering. ISSN 2050-0505. 10(12), p. 1–12. doi: 10.1002/ese3.1295. Full text in Research Archive Show summary
Due to the inherent intermittency in wind power production, reliable short-term wind power production forecasting has become essential for the efficient grid and market integration of wind energy. The current wind power production forecasting schemes are predominantly developed for wind farms. With the rapid growth in the microgrid sector and the increasing number of wind turbines integrated with these local grids, power production forecasting schemes are becoming essential for distributed wind energy systems as well. This paper proposes a power production forecasting scheme developed explicitly for distributed wind energy projects. The proposed system integrates two submodels based on support vector regression: one for downscaling the wind speed predictions to the hub coordinates of the turbine and the other for predicting the site-specific performance of the turbine under this wind condition. The forecasting horizons considered are the hour ahead (t + 1) and the day ahead (t + 36), which align with the Nord pool's energy market requirements. For the day-ahead scheme, a multistep recursive approach is adopted. The accuracy and adaptability of the proposed forecasting scheme are demonstrated in the case of a distributed wind turbine.
Yakoub, Ghali; Mathew, Sathyajith & Leal, João Gouveia Aparício Bento (2022). Intelligent estimation of wind farm performance with direct and indirect ‘point’ forecasting approaches integrating several NWP models. Energy. ISSN 0360-5442. 263(D). doi: 10.1016/j.energy.2022.125893. Full text in Research Archive Show summary
Reliable wind power forecasting is essential for profitably trading wind energy in the electricity market and efficiently integrating wind-generated electricity into the power grids. In this paper, we propose short- and medium-term wind power forecasting systems targeted to the Nordic energy market, which integrate inputs on the wind flow conditions from three numerical weather prediction sources. A point forecasting scheme is adopted, which forecasts the power at the individual turbine level. Both direct and indirect forecasting approaches are considered and compared. An automated machine-learning pipeline, built and optimized using genetic programming, is implemented for developing the proposed forecasting models. The turbine level power forecasts using different approaches are then combined into a single forecast using a weighting method based on recent forecast errors. These are then aggregated for the wind farm level power estimates. The proposed forecasting schemes are implemented with data from a Norwegian wind farm. We found that in both the direct and indirect forecasting approaches, the forecasting errors could be reduced between 8% and 22%, while inputs from several NWP sources are used together. The wind downscaling model, which is used in the indirect forecasting approach, could significantly contribute to the model's accuracy. The performance of both the direct and indirect forecasting schemes is comparable for the studied wind farm.
Alipour, Saba Mirza; Engeland, Kolbjørn & Leal, J B (2021). Representation of 100-year design rainfall uncertainty in catchment-scale flood modeling: A MCMC Bayesian approach. VANN. ISSN 0042-2592. 56(4). Full text in Research Archive
Alipour, Saba Mirza & Leal, J B (2021). Emulation of 2d hydrodynamic flood simulations at catchment scale using ann and svr. Water. 13(20), p. 1–19. doi: 10.3390/w13202858. Full text in Research Archive
Alipour, Saba Mirza; Engeland, Kolbjørn & Leal, J B (2021). A practical methodology to perform global sensitivity analysis for 2D hydrodynamic computationally intensive simulations. Hydrology Research. ISSN 1998-9563. 52(6), p. 1309–1327. doi: 10.2166/nh.2021.243. Full text in Research Archive Show summary
Sensitivity analysis is a commonly used technique in hydrological modeling for different purposes, including identifying the influential parameters and ranking them. This paper proposes a simplified sensitivity analysis approach by applying the Taguchi design and the ANOVA technique to 2D hydrodynamic flood simulations, which are computationally intensive. This approach offers an effective and practical way to rank the influencing parameters, quantify the contribution of each parameter to the variability of the outputs, and investigate the possible interaction between the input parameters. A number of 2D flood simulations have been carried out using the proposed combinations by Taguchi (L27 and L9 orthogonal arrays) to investigate the influence of four key input parameters, namely mesh size, runoff coefficient, roughness coefficient, and precipitation intensity. The results indicate that the methodology is adequate for sensitivity analysis, and that the precipitation intensity is the dominant parameter. Furthermore, the model calibration based on local variables (cross-sectional water level) can be inaccurate to simulate global variables (flooded area).
Yakoub, Ghali; Mathew, Sathyajith & Leal, J B (2020). Downscaling and improving the wind forecasts from NWP for wind energy applications using support vector regression. Journal of Physics: Conference Series (JPCS). ISSN 1742-6588. 1618. doi: 10.1088/1742-6596/1618/6/062034. Full text in Research Archive
Yakoub, Ghali; Leal, J B & Tunheim, Ketil (2019). A flood forecasting model for unregulated catchments based on Artificial Neural Networks: the October 2017 flood in Tovdal’s catchment. VANN. ISSN 0042-2592. p. 103–113. Full text in Research Archive
Alipour, Saba Mirza & Leal, J B (2019). Return levels uncertainty under effect of climate change. Proceedings of the IAHR World Congress. ISSN 2521-7119. p. 256–264. doi: 10.3850/38WC092019-1230. Full text in Research Archive
Fernandes, João Nuno; Leal, J B & Cardoso, António H. (2018). Influence of floodplain and riparian vegetation in the conveyance and structure of turbulent flow in compound channels. E3S Web of Conferences. 40. doi: 10.1051/e3sconf/20184006035. Full text in Research Archive
Azevedo, Ricardo; Roja-Solorzano, Luis R & Leal, J B (2017). Turbulent structures, integral length scale and turbulent kinetic energy (TKE) dissipation rate in compound channel flow. Flow Measurement and Instrumentation. ISSN 0955-5986. 57, p. 10–19. doi: 10.1016/j.flowmeasinst.2017.08.009. Full text in Research Archive
Proust, S; Fernandes, J N; Leal, J B; Riviere, N & Peltier, Y (2017). Mixing layer and coherent structures in compound channel flows: Effects of transverse flow, velocity ratio, and vertical confinement. Water Resources Research. ISSN 0043-1397. 53(4), p. 3387–3406. doi: 10.1002/2016WR019873. Full text in Research Archive
Brito, Moises; Fernandes, J N & Leal, J B (2016). Porous media approach for RANS simulation of compound open-channel flows with submerged vegetated floodplains. Environmental Fluid Mechanics. ISSN 1567-7419. 16(6), p. 1247–1266. doi: 10.1007/s10652-016-9481-0. Full text in Research Archive
Proust, S; Berni, Celine; Boudou, Martin; Chiaverini, Antoine; Dupuis, Victor & Faure, Jean-Baptiste [Show all 28 contributors for this article] (2016). Predicting the flow in the floodplains with evolving land occupations during extreme flood events (FlowRes ANR project). E3S Web of Conferences. 7. doi: 10.1051/e3sconf/20160704004. Full text in Research Archive
Fernandes, J N & Leal, J B (2016). Discussion of “Improved Shiono and Knight Method for Overflow Modeling” by Hossien Kordi, Ramin Amini, Abdolreza Zahiri, and Esmaeil Kordi". Journal of hydrologic engineering. ISSN 1084-0699. 21(10). doi: 10.1061/(ASCE)HE.1943-5584.0001434. Full text in Research Archive
Bousmar, Didier; Mathurin, B; Fernandes, J N; Filonovich, M S; Hazlewood, C & Huthoff, F [Show all 9 contributors for this article] (2016). Uniform flow in prismatic compound channel: Benchmarking numerical models. In Constantinescu, George; Garcia, Marcelo & Hanes, Dan (Ed.), River Flow 2016. CRC Press. ISSN 9781138029132. p. 272–280. doi: 10.1201/9781315644479-46. Full text in Research Archive
Fernandes, João Nuno; Leal, J B & Cardoso, António H. (2015). Assessment of stage-discharge predictors for compound open-channels. Flow Measurement and Instrumentation. ISSN 0955-5986. 45, p. 62–67. doi: 10.1016/j.flowmeasinst.2015.04.010. Full text in Research Archive
Filonovich, M S; Leal, J B & Rojas-Solórzano, L (2014). Prediction of compound channel secondary flows using anisotropic turbulence models. In Schleiss, Anton J.; Cesare, Giovanni De; Franca, Mario J. & Pfister, Michael (Ed.), Proceedings of the River Flow 2014 International Conference on Fluvial Hydraulics. CRC Press. ISSN 9781138026742. p. 163–170. Full text in Research Archive
Fernandes, J N; Leal, J B & Cardoso, A H (2014). Longitudinal development of compound channel flows. In Almeida, A (Eds.), 3rd IAHR Europe Congress April 14 – 16, 2014 Department of Civil Engineering, Faculty of Engineering, University of Porto, Portugal. IAHR. ISSN 9789899647923. p. 36–46. Full text in Research Archive
Fernandes, J N; Leal, J B & Cardoso, A H (2014). Improvement of the Lateral Distribution Method based on the mixing layer theory. Advances in Water Resources. ISSN 0309-1708. 69, p. 159–167. doi: 10.1016/j.advwatres.2014.04.003. Full text in Research Archive Show summary
The accurate prediction of depth-averaged streamwise velocity, boundary shear stress and lateral shear stress are important requisites for the estimation of the flow depth associated with flood events in compound river channels composed of main channel and floodplain. This engineering problem may be tackled through the analytical solution of the depth-averaged momentum equation. Under uniform flow, this solution relies on the calibration of three descriptors of the bottom friction, secondary currents and lateral shear stress. In this paper, the analytical solution materialized in the Lateral Distribution Method is revisited through the consideration of a new panel division. Accurate measurements of streamwise and spanwise velocities as well as of boundary shear stress are used to obtain new predictors of the coefficients describing the effects of bottom friction, secondary currents and lateral shear. The new lateral division of the compound channel into four panels is physically based on the mixing layer width, which is computed by an iterative procedure easily implemented in practical applications.
Proust, S; Fernandes, J N; Peltier, Y; Leal, J B; Riviere, N & Cardoso, A H (2013). Turbulent non-uniform flows in straight compound open-channels. Journal of Hydraulic Research. ISSN 0022-1686. 51(6), p. 656–667. doi: 10.1080/00221686.2013.818586. Full text in Research Archive
Filonovich, M S; Azevedo, R; Rojas-Solórzano, L & Leal, J B (2013). Credibility Analysis of Computational Fluid Dynamic Simulations for Compound Channel Flow. Journal of Hydroinformatics. ISSN 1464-7141. 15(3), p. 926–938. doi: 10.2166/hydro.2013.187. Full text in Research Archive
Fernandes, J N; Leal, J B & Cardoso, A H (2012). Flow Structure in a Compound Channel with Smooth and Rough Floodplains. European Water. ISSN 1105-7580. 38, p. 3–12. Full text in Research Archive
Ferreira, R M L; Franca, Mario J.; Leal, J B & Cardoso, A H (2012). Flow over rough mobile beds: friction factor and vertical distribution of the longitudinal mean velocity. Water Resources Research. ISSN 0043-1397. 48. doi: 10.1029/2011WR011126. Full text in Research Archive
Fernandes, J N; Leal, J B & Cardoso, A H (2011). Discussion of “Apparent friction coefficient in straight compound channels”. Journal of Hydraulic Research. ISSN 0022-1686. 49(6), p. 836–839. doi: 10.1080/00221686.2011.618058. Full text in Research Archive
Leal, J B; Ferreira, R M L & Cardoso, A H (2010). Geomorphic dam-break flows. Part I: 1D conceptual model. Proceedings of the Institution of Civil Engineers : Water Management. ISSN 1741-7589. 163(6), p. 297–304. doi: 10.1680/wama.2010.163.6.297. Full text in Research Archive
Leal, J B; Ferreira, R M L & Cardoso, A H (2010). Geomorphic dam-break flows. Part II: numerical simulation. Proceedings of the Institution of Civil Engineers : Water Management. ISSN 1741-7589. 163(6), p. 305–313. doi: 10.1680/wama.2010.163.6.305. Full text in Research Archive
Leal, J B; Ferreira, R M L & Cardoso, A H (2009). Maximum Level and Time to Peak of Dam-break Waves on Mobile Horizontal Bed. Journal of Hydraulic Engineering. ISSN 0733-9429. 135(11). doi: 10.1061/(ASCE)HY.1943-7900.0000099. Full text in Research Archive
Ferreira, R M L; Franca, Mario J.; Leal, J B & Cardoso, A H (2009). Mathematical modelling of shallow flows: Closure models drawn from grain-scale mechanics of sediment transport and flow hydrodynamics. Canadian journal of civil engineering (Print). ISSN 0315-1468. 36(10), p. 1605–1621. Full text in Research Archive
Leal, J B; Ferreira, R M L & Cardoso, A H (2008). Closure to “Dam-break wave-front celerity”. Journal of Hydraulic Engineering. ISSN 0733-9429. 134(6), p. 867–869. doi: 10.1061/6(867. Full text in Research Archive
Leal, J B; Ferreira, R M L & Cardoso, A H (2006). Dam-break wave-front celerity. Journal of Hydraulic Engineering. ISSN 0733-9429. 132(1), p. 69–76. doi: 10.1061/1(69. Full text in Research Archive
Ferreira, R M L; Leal, J B & Cardoso, A H (2003). Discussion of “Coupled and decoupled numerical modeling of flow and morphological evolution in alluvial rivers”. Journal of Hydraulic Engineering. ISSN 0733-9429. 129(9), p. 741–742. doi: 10.1061/9(741. Full text in Research Archive
Leal, J B; Ferreira, R M L; Franco, A B & Cardoso, A H (2002). Experimental study on dam-break flood waves over movable bed channels. International Journal of Sediment Research. ISSN 1001-6279. 17(3), p. 186–196. Full text in Research Archive
Leal, J B; Ferreira, R M L; Franco, A B & Cardoso, A H (2001). Dam-break waves over movable beds. Experimental study. Recursos Hídricos. ISSN 0870-1741. 22(1), p. 25–36. Full text in Research Archive
Ferreira, R M L; Leal, J B & Cardoso, A H (1999). Mathematical modelling of dam-break waves propagation over movable beds. Recursos Hídricos. ISSN 0870-1741. 20(1). Full text in Research Archive

View all works in NVA

Ferreira, R M L; Alves, E; Leal, J B & Cardoso, A H (2006). River Flow 2006. CRC Press. ISBN 9780415408158. 2304 p. Full text in Research Archive

View all works in NVA

Alipour, Saba Mirza; Leal, J B & England, Kolbjørn (2022). Uncertainty Assessment of Flood Maps: A Comparison of Bootstrap and Monte Carlo Methods. Full text in Research Archive
Brito, Moises; Canelas, O B; Leal, J B & Cardoso, A H (2014). 3D numerical simulation of flow at a 70º open-channel confluence. Full text in Research Archive
Leal, J B (2014). Dams: advantages and disavantages. Pedra & Cal. ISSN 1645-4863. 56, p. 9–11. Full text in Research Archive
Ferreira, R M L & Leal, J B (1998). 1-D Mathematical modelling of the instantaneous-dam-break flood wave over mobile bed. Full text in Research Archive
Lie, Camilla; Imenes, Anne Gerd; Leal, J B & Sathyajith, Mathew (2019). Power Prediction of Photovoltaic System using Neural Network Models. Universitetet i Agder. Full text in Research Archive Show summary
This workconsidersa photovoltaic (PV)system installed on the rooftop of Agder Energi’s headquarters located at Kjøita, Kristiansand. The system includes three different types of solar PV modules; Suntech (multi-Si), Sharp (a-Si/μ-Si) and REC (multi-Si), that have a total installed DC capacity of 45 kWp. The system is grid-connected and instrumented for research and monitoring purposes.Artificial Neural Network(ANN)models were trained to obtain the lowest mean square error(MSE), by testing different configurations using a model-based trial and error approach. The modelconfigurations that gavethe lowest(MSE) wereused to predict the power production from each of the PV modules using forecasted weather parameters obtainedfrom MEPS (MetCoOp Ensemble Prediction System), with a one-day ahead and two-days ahead forecast horizon. The input selection of the models wasbased on both model-free and model-based approach, where the final input selectionresulted inglobal horizontal irradiance, wind speed, air temperature and air mass, with the power (AC) productionas output (target).The results indicated that the modelconfigurations of 20hidden neurons in first hidden layer, and 2 hidden neurons in second hidden layergavethe lowest MSEfor allPV modules. Results from the testsetsshowedthat the best model for Suntech gaveMSE = 0.0454,Sharp gaveMSE = 0.0325andREC gaveMSE = 0.0492. R2-valuesbetween 0.95 and 0.96 wereobtained for all three models, indicating good fitting of the predicted valuesand the targets. Testing the Suntech and REC modelswith a hold-out set provided slightly less precise predictions compared to the results from the testset, while a higher precision was found forSharpmodules. Testing the model configurations with forecasted weather parameters indicated that the forecast accuracy of the weather will influence the power prediction, andthe performance parameters will be accordingly. The one-day ahead forecasts provided MSE equal to 0.2647, 0.2378and 0.2647, and for the two-days aheadforecast horizon an MSE equal to 0.2996, 0.2252and 0.2719for Suntech, Sharp and REC, respectively.An error much higher compared to the test set and hold-out set for the models, which inevitablywas expecteddue to the weather forecast uncertainties.Based on the findings in this work, itcan be concludedthat a further optimization of the models will be necessary before obtaining even more precise predictions. However, the models did show good fitting for several days and a potential for using ANN modelsfor power prediction of PV modules.
Leal, J B & Filonovich, M S (2015). Numerical modelling of compound channel flow. Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa. Full text in Research Archive
Leal, J B (2005). Experimental and mathematical modelling of dam-break waves propagation over movable beds. University of 'Beira Interior'. Full text in Research Archive
Leal, J B (1999). Mathematical modelling of dam-break waves propagation over movable beds. Instituto Superior Técnico. Full text in Research Archive

View all works in NVA

Published Apr. 16, 2024 10:57 AM