Forecasting the electricity generation of photovoltaic plants

• Autorzy: Kuievda Iuliia , Baliuta Serhii , Zinkevich Petro , Stoliarov Oleksandr

Identyfikatory

DOI

10.53412/jntes-2021-1.5

• Języki publikacji: EN

Abstrakty

EN

Due to the need in accordance with Ukrainian legislation to submit a day-ahead hourly forecast of electricity generation of solar power plants, the problem of forecasting model quality becomes very important. In the study it is proposed a method of choosing the optimal structure and sensitivity assessment of ANFIS-based forecasting model. In the model the input is solar irradiance, the output is solar panel generation power. The method is based on computational procedures using MATLAB software. For the data set, used in the study, the results, optimal for normalized mean absolute error (NMAE), were achieved on 5 triangular input member functions (trimf), while the error varied within 0.23% depending on number and shape of input member functions. According to the calculations of input error sensitivity of the forecasting model with 5 input trimf membership functions, the increasing of input error up to 8.19% NMAE leads to the raising of the output error in the testing sample up to 5.78%, NMAE. The rather low sensitivity of the model to the input data error allows us to conclude that forecasted meteorological data with a pre-known fixed forecast error can be used as input data.

Słowa kluczowe

EN

solar power plants; forecasting; ANFIS; fuzzy inference system

• Wydawca: Kielce University of Technology
• Czasopismo: Journal of New Technologies in Environmental Science
• Rocznik: 2021
• Tom: Vol. 5, nr 1
• Strony: 40--45
• Opis fizyczny: Bibliogr. 7 poz., rys., wykr., wzory

Twórcy

autor

Kuievda Iuliia

• National University of Food Technologies, 68 Volodymyrska str., 01601 Kyiv, Ukraine

autor

Baliuta Serhii

• National University of Food Technologies, 68 Volodymyrska str., 01601 Kyiv, Ukraine

autor

Zinkevich Petro

• National University of Food Technologies, 68 Volodymyrska str., 01601 Kyiv, Ukraine

autor

Stoliarov Oleksandr

• National University of Food Technologies, 68 Volodymyrska str., 01601 Kyiv, Ukraine

Bibliografia

• [1] Akhter M.N., ANFIS: Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques. Akhter M.N., Mekhilef S., Mokhlis H., Shah N.M., IET Renewable Power Generation 2019, Vol. 13, Iss. 7, pp. 1009-1023.
• [2] Installed capacity of the IPS of Ukraine values. Available at: https://ua.energy/vstanovlena-potuzhnist-energosystemy-ukrayiny (Accessed: 30 April 2021).
• [3] Jang J.-S.R., ANFIS: Adaptive-Network-Based Fuzzy Inference System. Jang J.-S.R., IEEE Transactions on Systems, Man, and Cybernetics 2018, Vol. 23, No. 3, pp. 665-685.
• [4] Photovoltaic (PV) Solar Panel Energy Generation data. Available at: https://data.london.gov.uk/dataset/photovoltaic--pv--solar-panel-energy-generation-data (Accessed: 30 April 2021).
• [5] Semero Y.K., PV Power Forecasting Using an Integrated GA-PSO-ANFIS Approach and Gaussian Process Regression Based Feature Selection Strategy. Semero Y.K., Zhang J., Zheng D., CSEE Journal of Power and Energy Systems 2018, Vol. 4, No. 2, pp. 210-218.
• [6] Wu Y.-K., A Novel Hybrid Model for Short-Term Forecasting in PV Power Generation. Wu Y.-K., Chen C.-R., Rahman H.A. International Journal of Photoenergy 2014, 9 p.
• [7] MATLAB documentation. Available at: https://www.mathworks.com/help (Accessed: 30 April 2021).

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).