Principal Component Analysis and Machine Learning Approaches for Photovoltaic Power Prediction: A Comparative Study

Nowadays, in the context of the industrial revolution 4.0, considerable volumes of data are being generated continuously from intelligent sensors and connected objects. The proper understanding and use of these amounts of data are crucial levers of performance and innovation. Machine learning is the technology that allows the full potential of big datasets to be exploited. As a branch of artificial intelligence, it enables us to discover patterns and make predictions from data based on statistics, data mining, and predictive analysis. The key goal of this study was to use machine learning approaches to forecast the hourly power produced by photovoltaic panels. A comparison analysis of various predictive models including elastic net, support vector regression, random forest, and Bayesian regularized neural networks was carried out to identify the models providing the best predicting results. The principal components analysis used to reduce the dimensionality of the input data revealed six main factor components that could explain up to 91.95% of the variation in all variables. Finally, performance metrics demonstrated that Bayesian regularized neural networks achieved the best results, giving an accuracy of R2 = 99.99% and RMSE = 0.002 kW.

[1]  Improving Accuracy of Real Estate Valuation Using Stacked Regression , 2018 .

[2]  Ismail Boumhidi,et al.  Bayesian regularized artificial neural network for fault detection and isolation in wind turbine , 2017, 2017 Intelligent Systems and Computer Vision (ISCV).

[3]  Baris Asikgil,et al.  Regression error characteristic curves based on the choice of best estimation method , 2016 .

[4]  Emanuele Crisostomi,et al.  Day-Ahead Hourly Forecasting of Power Generation From Photovoltaic Plants , 2018, IEEE Transactions on Sustainable Energy.

[5]  Muhsin Tunay Gencoglu,et al.  The performance comparison of Multiple Linear Regression, Random Forest and Artificial Neural Network by using photovoltaic and atmospheric data , 2017, 2017 14th International Conference on Engineering of Modern Electric Systems (EMES).

[6]  A. Lfakir,et al.  PHOTOVOLTAIC OUTPUT POWER FORECAST USING ARTIFICIAL NEURAL NETWORKS , 2018 .

[7]  Akinola A. Babatunde,et al.  Predictive analysis of photovoltaic plants specific yield with the implementation of multiple linear regression tool , 2018, Environmental Progress & Sustainable Energy.

[8]  Erees Queen B. Macabebe,et al.  Real-Time Power Consumption Monitoring and Forecasting Using Regression Techniques and Machine Learning Algorithms , 2019, 2019 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS).

[9]  Tarek AlSkaif,et al.  Benchmark analysis of day-ahead solar power forecasting techniques using weather predictions , 2019, 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC).

[10]  Shengli Zhang,et al.  Recurrent Neural Networks Based Photovoltaic Power Forecasting Approach , 2019, Energies.

[11]  M. Babel,et al.  Principal Component and Multiple Regression Analyses for the Estimation of Suspended Sediment Yield in Ungauged Basins of Northern Thailand , 2014 .

[12]  Berny Carrera,et al.  Comparison Analysis of Machine Learning Techniques for Photovoltaic Prediction Using Weather Sensor Data , 2020, Sensors.

[13]  Renato De Leone,et al.  Photovoltaic energy production forecast using support vector regression , 2015, Neural Computing and Applications.

[14]  Hisham Mahmood,et al.  Short-Term Photovoltaic Power Forecasting Using an LSTM Neural Network , 2020, 2020 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).

[15]  Efstratios I. Batzelis,et al.  Machine Learning Algorithms in Forecasting of Photovoltaic Power Generation , 2019, 2019 International Conference on Smart Energy Systems and Technologies (SEST).

[16]  Maria Grazia De Giorgi,et al.  Photovoltaic forecast based on hybrid PCA-LSSVM using dimensionality reducted data , 2016, Neurocomputing.

[17]  Sravankumar Jogunuri,et al.  Artificial Intelligence Methods for Solar Forecasting for optimum Sizing of PV systems: A Review , 2020 .