Complex-valued forecasting of the global solar irradiation

Abstract

In this paper, a forecasting of the global solar irradiation in the complex-valued domain is proposed. A method to transform the meteorological data into complex values is developed and the Complex Valued Neural Network (CVNN) is used to model and forecast the daily and the hourly solar irradiation. The measured data of Tamanrasset city, Algeria (altitude: 1362 m; latitude: 22 48 N; longitude: 05 26 E) is used to validate the developed model. In the hourly solar irradiation case, the 24 h ahead will be forecasted using the combination of the past daily meteorological dataset. Several models are presented to test the feasibility and the performance of the CVNN for forecasting either daily or hourly solar irradiation for both multi input single output and multi input multi output strategies. Results obtained throughout this paper show that the CVNN technique is suitable for modeling and forecasting daily and hourly solar irradiation. V C 2013 AIP Publishing LLC.

A review on solar radiation assessment and forecasting in Algeria

“…6). In [19], the authors used the complex-valued ANN to predict daily and hourly solar radiation. They have studied four structures (three of MISO and one of MIMO).…”

Load peak shaving and power smoothing of a distribution grid with high renewable energy penetration

“…which includes m complex valued inputs (m = i + p). The whole values of m ,n, i, l, and p are positive integers [32,33,22]. In this paper, the split sigmoid function has been taken for the activation function as follows:…”

“…where e l (k) is the error between the l th actual output y l (k) and forecast outputŷ l (k) [33,22].…”

Prediction of the daily global solar Irradiation of the great Maghreb region using the complex-valued neural networks

“…Due to the high nonlinearity of the solar irradiation model and the dependence between this last parameter with other meteorological and geo-astronomical data, many models based on computational techniques dedicated to predict the solar irradiation could be found in literature [2][3][4][5][6][7][8][9][10][11][12], whereas, the neural networks are widely used to forecast solar irradiation with good accuracy [13][14][15][16][17][18][19].…”

“…In our previous work [19], the complex valued neural networks (CVNN) are proposed to forecast the hourly and the daily solar irradiation where the application is specified to Tamanrasset city (Algeria).…”