Weather Impact on Solar Farm Performance: A Comparative Analysis of Machine Learning Techniques

Forecasting the performance and energy yield of photovoltaic (PV) farms is crucial for establishing the economic sustainability of a newly installed system. The present study aims to develop a prediction model to forecast an installed PV system’s annual power generation yield and performance ratio (PR) using three environmental input parameters: solar irradiance, wind speed, and ambient air temperature. Three data-based artificial intelligence (AI) techniques, namely, adaptive neuro-fuzzy inference system (ANFIS), response surface methodology (RSM), and artificial neural network (ANN), were employed. The models were developed using three years of data from an operational 2MWp Solar PV Project at Kuzhalmannam, Kerala state, India. Statistical indices such as Pearson’s R, coefficient of determination (R2), root-mean-squared error (RMSE), Nash-Sutcliffe efficiency (NSCE), mean absolute-percentage error (MAPE), Kling-Gupta efficiency (KGE), Taylor’s diagram, and correlation matrix were used to determine the most accurate prediction model. The results demonstrate that ANFIS was the most precise performance ratio prediction model, with an R2 value of 0.9830 and an RMSE of 0.6. It is envisaged that the forecast model would be a valuable tool for policymakers, solar energy researchers, and solar farm developers.

[1]  M. S. Nazir,et al.  An integrated framework of gated recurrent unit based on improved sine cosine algorithm for photovoltaic power forecasting , 2022, Energy.

[2]  Mao Yang,et al.  A composite framework for photovoltaic day-ahead power prediction based on dual clustering of dynamic time warping distance and deep autoencoder , 2022, Renewable Energy.

[3]  Dragana Nikodinoska,et al.  Solar and wind power generation forecasts using elastic net in time-varying forecast combinations , 2022, Applied Energy.

[4]  Alessandro Niccolai,et al.  Machine Learning techniques for solar irradiation nowcasting: Cloud type classification forecast through satellite data and imagery , 2022, Applied Energy.

[5]  M. Labbadi,et al.  CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production , 2022, Electric Power Systems Research.

[6]  O. Bouattane,et al.  Data driven approach to forecast the next day aggregate production of scattered small rooftop solar photovoltaic systems without meteorological parameters , 2022, Energy Reports.

[7]  Ngui Wai Keng,et al.  Comparison of normal and weather corrected performance ratio of photovoltaic solar plants in hot and cold climates , 2021, Energy for Sustainable Development.

[8]  R. Mamat,et al.  Role of Biofuels in Energy Transition, Green Economy and Carbon Neutrality , 2021, Sustainability.

[9]  Z. Said,et al.  Synthesis, stability, thermophysical properties and AI approach for predictive modelling of Fe3O4 coated MWCNT hybrid nanofluids , 2021 .

[10]  Eleonora Riva Sanseverino,et al.  A new method for forecasting energy output of a large-scale solar power plant based on long short-term memory networks a case study in Vietnam , 2021 .

[11]  Dibakar Rakshit,et al.  Artificial neural network coupled building-integrated photovoltaic thermal system for indian montane climate , 2021 .

[12]  Cícero Manoel dos Santos,et al.  Prediction of solar direct beam transmittance derived from global irradiation and sunshine duration using anfis , 2021, International Journal of Hydrogen Energy.

[13]  Tengyu Ma,et al.  Performance optimization of a nanofluid-based photovoltaic thermal system integrated with nano-enhanced phase change material , 2021 .

[14]  I. Kirpichnikova,et al.  Energy analysis of utility-scale PV plant in the rain-dominated tropical monsoon climates , 2021 .

[15]  A. Chouder,et al.  The impact of the ANN’s choice on PV systems diagnosis quality , 2021, Energy Conversion and Management.

[16]  Ngui Wai Keng,et al.  Performance Modeling of the Weather Impact on a Utility-Scale PV Power Plant in a Tropical Region , 2021, International Journal of Photoenergy.

[17]  E. Sirotkin,et al.  Hybrid Floating Solar Plant Designs: A Review , 2021, Energies.

[18]  Prabhakar Sharma.  Artificial intelligence‐based model prediction of biodiesel‐fueled engine performance and emission characteristics: A comparative evaluation of gene expression programming and artificial neural network , 2021, Heat Transfer.

[19]  Yonghua Song,et al.  Artificial intelligence in sustainable energy industry: Status Quo, challenges and opportunities , 2021, Journal of Cleaner Production.

[20]  Prabhakar Sharma,et al.  Application of Response Surface Methodology for Optimization of Fuel Injection Parameters of a Dual Fuel Engine Fuelled with Producer Gas-Biodiesel blends , 2021 .

[21]  Zhenjun Ma,et al.  Optimisation of a renewable cooling and heating system using an integer-based genetic algorithm, response surface method and life cycle analysis , 2021 .

[22]  Bennouna Amin,et al.  Power forecasting of three silicon-based PV technologies using actual field measurements , 2021 .

[23]  Jafar Amiri Parian,et al.  Intelligent MPPT for photovoltaic panels using a novel fuzzy logic and artificial neural networks based on evolutionary algorithms , 2021 .

[24]  Sinan Q. Salih,et al.  Global solar radiation prediction over North Dakota using air temperature : Development of novel hybrid intelligence model , 2021 .

[25]  P. F. Ribeiro,et al.  Design of experiments using artificial neural network ensemble for photovoltaic generation forecasting , 2021 .

[26]  L. A. Dao,et al.  Improving Solar and PV Power Prediction with Ensemble Methods , 2020, ArXiv.

[27]  Reza Sabzehgar,et al.  Solar power forecast for a residential smart microgrid based on numerical weather predictions using artificial intelligence methods , 2020 .

[28]  Timo Laakko,et al.  Data analysis of a monitored building using machine learning and optimization of integrated photovoltaic panel, battery and electric vehicles in a Central European climatic condition , 2020 .

[29]  Paul A. Adedeji,et al.  Neuro-fuzzy resource forecast in site suitability assessment for wind and solar energy: A mini review , 2020 .

[30]  Purvi Chandrakar,et al.  Application of ANN model to predict the performance of solar air heater using relevant input parameters , 2020 .

[31]  A. Sorooshian,et al.  Machine-learning algorithms for predicting land susceptibility to dust emissions: The case of the Jazmurian Basin, Iran , 2020 .

[32]  M. Bettayeb,et al.  Statistical study of a solar nanofluid photovoltaic thermal collector performance using response surface methodology , 2020 .

[33]  Luis Volnei Sudati Sagrilo,et al.  Application of Taylor diagram in the evaluation of joint environmental distributions' performances , 2020, Marine Systems & Ocean Technology.

[34]  L. Naderloo.  Prediction of solar radiation on the horizon using neural network methods, ANFIS and RSM (case study: Sarpol-e-Zahab Township, Iran) , 2020, Journal of Earth System Science.

[35]  A. Awan,et al.  Design, optimization and performance comparison of solar tower and photovoltaic power plants , 2020 .

[36]  V. Sreeram,et al.  A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization , 2020 .

[37]  Robert S. Balog,et al.  Time series forecasting of solar power generation for large-scale photovoltaic plants , 2020 .

[38]  Hossein Parastvand,et al.  Comparative and performative investigation of various data-based and conventional theoretical methods for modelling heat pipe solar collectors , 2020 .

[39]  Feixiang Zhao,et al.  EnLSTM-WPEO: Short-Term Traffic Flow Prediction by Ensemble LSTM, NNCT Weight Integration, and Population Extremal Optimization , 2020, IEEE Transactions on Vehicular Technology.

[40]  Shameem Ahmed,et al.  Prediction of solar irradiation and performance evaluation of grid connected solar 80KWp PV plant in Bangladesh , 2019, Energy Reports.

[41]  Hussain Alazki,et al.  An ANFIS-Based Modeling Comparison Study for Photovoltaic Power at Different Geographical Places in Mexico , 2019, Energies.

[42]  Jian Weng,et al.  A Two-Layer Nonlinear Combination Method for Short-Term Wind Speed Prediction Based on ELM, ENN, and LSTM , 2019, IEEE Internet of Things Journal.

[43]  Shahaboddin Shamshirband,et al.  State of the Art of Machine Learning Models in Energy Systems, a Systematic Review , 2019, Energies.

[44]  M. Premalatha,et al.  Analysis of different combinations of meteorological parameters in predicting the horizontal global solar radiation with ANN approach: A case study , 2018, Renewable and Sustainable Energy Reviews.

[45]  K. Sudhakar,et al.  Fully solar powered Raja Bhoj International Airport: A feasibility study , 2017, Resource-Efficient Technologies.

[46]  K. Sudhakar,et al.  Modeling and performance simulation of 100 MW LFR based solar thermal power plant in Udaipur India , 2017, Resource-Efficient Technologies.

[47]  Farid Bouchafaa,et al.  Monitoring and performance analysis of grid connected photovoltaic under different climatic conditions in south Algeria , 2016 .

[48]  K. Sudhakar,et al.  Performance evaluation of 10 MW grid connected solar photovoltaic power plant in India , 2015 .

[49]  M. Premalatha,et al.  Large-scale open pond algae biomass yield analysis in India: a case study , 2014 .

[50]  Hao Jiang,et al.  Application of BP Neural Network to Short-Term-Ahead Generating Power Forecasting for PV System , 2012 .

[51]  Peng Wang,et al.  Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines , 2011, IEEE Transactions on Industry Applications.

[52]  Paras Mandal,et al.  Forecasting Power Output of Solar Photovoltaic System Using Wavelet Transform and Artificial Intelligence Techniques , 2012, Complex Adaptive Systems.

[53]  H. Gupta,et al.  On typical range, sensitivity, and normalization of Mean Squared Error and Nash‐Sutcliffe Efficiency type metrics , 2011 .

[54]  K. Taylor.  Summarizing multiple aspects of model performance in a single diagram , 2001 .