An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data
Citations
626 citations
Cites methods from "An Improved Photovoltaic Power Fore..."
...Abbreviations: PV, photovoltaic; NWP, numerical weather prediction; AI, artificial intelligence; AR, auto regressive; MA, moving average; ARMA, auto regressive moving average; ARIMA, AR integrated MA; ARMAX, ARMA exogenous; ANN, artificial neural network; SVM, support vector machine; SVR, support vector regression; HS, hybrid system; FS, fuzzy system; ANFIS, adaptive neuro fuzzy inference system; GA, genetic algorithm; GHG, greenhouse gas; IEA, international energy agency; MSE, mean square error; RMSE, root mean square error; nRMSE, normalized root mean square error; MAE, mean absolute error; MAPE, mean absolute percentage error; MRE, mean relative error; MBE, mean bias error Renewable and Sustainable Energy Reviews 81 (2018) 912–928 Available online 31 August 2017 1364-0321/ © 2017 Elsevier Ltd....
[...]
...∑MSE N W W= 1 ( − ) i N forecasted true =1 2 ∑RMSE N W W= 1 ( − ) i N forecasted true =1 2 ⎛ ⎝ ⎜⎜ ⎞ ⎠ ⎟⎟∑nRMSE N W W W= 1 ( − ) ×100/ i N forecasted true true max% =1 2 ( ) ∑MAE N W W= 1 − i N forecasted true =1 ∑MAPE N W W W = 1 − ×100% i N forecasting true true=1 ∑MRE N W W W = 1 − ×100% i N forecasting true total=1 ∑MBE N W W= 1 ( − ) i N forecasted true =1 where, W ,forecasting W ,true W ,true max( ) and Wtotal represent the forecasted PV power at each time point, the observed/measured PV power at each time point, the maximum observed PV power of this scale, and the PV installation capacity, respectively....
[...]
...[108] utilized an ANN approach to forecast the subsequent 24-h PV power outputs....
[...]
...MSE [86], RMSE [36], nRMSE [98], MAE [113], MAPE [108], MRE [121], and MBE [107], as shown below, have been commonly used in evaluating the accuracy of PV power forecasting models [36,86,98,107,108,113,121]....
[...]
537 citations
446 citations
443 citations
Cites methods from "An Improved Photovoltaic Power Fore..."
...An improved forecasting model that considers aerosol index data instead of using the traditional environmental data was proposed in [35]....
[...]
428 citations
Cites methods from "An Improved Photovoltaic Power Fore..."
...In [34], a novel PV power forecasting model is proposed based on BP NN, which considers the aerosol index as an additional input parameter to forecast the next 24-h PV power outputs....
[...]
References
26,531 citations
2,394 citations
"An Improved Photovoltaic Power Fore..." refers methods in this paper
...PPMCC is a method of the linear dependence between variables X and Y , which is widely used in statistics to measure the strength of linear dependence between two variables....
[...]
...A linear regression analysis between AI values and PV power outputs has been conducted, based on a 2-month period of historical data, by using Pearson product-moment correlation coefficient (PPMCC) [41]....
[...]
2,254 citations
915 citations
"An Improved Photovoltaic Power Fore..." refers background in this paper
..., some references use the ratio of spectral radiant flux of 340 and 380 nm channel [38], [39]....
[...]
813 citations
"An Improved Photovoltaic Power Fore..." refers background in this paper
...The other is to predict the active power outputs of PV directly [2]–[4]....
[...]