Generalized neural network methodology for short term solar power forecasting

Abstract

The main objective of this paper is to perform data analysis of ground based measurement and review the state of the art of IIT Jodhpur Rooftop solar photovoltaic installed 101 kW system. Solar power forecasting is playing a key role in solar PV park installation, operation and accurate solar power dispatchability as well as scheduling. Solar Power varies with time and geographical locations and meteorological conditions such as ambient temperature, wind velocity, solar radiation and module temperature. The location of Solar PV system is the main reason of solar power variability. Solar variability totally depends on system losses (deterministic losses) and weather parameter (stochastic losses). In the case of solar power, deterministic losses can be found out accurately but stochastic losses are very uncertain and unpredicted in nature. The proposed soft computing technique will be suitable for solar power forecasting modeling. In this paper Fuzzy theory, Adaptive Neuro-fuzzy interface system, artificial neural network and generalized neural network are used as powerful tool of solar power Forecasting. This soft computing cum nature inspired techniques are able to accurately and fast forecasting compared to conventional methods of forecasting. This is done analyzing the operational data of 101 kW PV systems (43.30 kW located in Block 1 and 58.08 kW in Block 2), during the year 2011.

Data-Mining-based filtering to support Solar Forecasting Methodologies

“…In this work, ANN has proved to be a promising technique on this field, showing improved results while combined with GAs. The same conclusions about the use of ANNs were achieved by (Ioakimidis, et al, 2013) and (Singh et al, 2013). ANNs have also been successfully applied to the forecasting of other renewable sources based production types, such as the wind power, in (Hao et al, 2014).…”

Solar Power Forecasting: A Review

“…Cao and Cao [104][105][106][107][108] they all combined wavelet with ANN. Other authors like [109][110][111][112][113][114][115][116][117][118][119][120][121][122][123] used other soft computing techniques like GA, fuzzy logic, Quantum based GA, adaptive neurofuzzy, etc. to develop hybrid models.…”

Model-free computation of ultra-short-term prediction intervals of solar irradiance

“…The main approaches, presented in the literature, to the problem of the PV short-term forecasting are summarized by Singh et al (2013), Kardakos et al (2013), Trapero et al (2014), Lorenz et al (2009), Marquez andCoimbra (2011), Bacher et al (2009). The authors of Singh et al (2013) propose an adaptive-neuro-fuzzy inference (ANFIS) to predict the PV power output in the time horizon of onehour ahead.…”

“…The authors of Singh et al (2013) propose an adaptive-neuro-fuzzy inference (ANFIS) to predict the PV power output in the time horizon of onehour ahead. The input quantities of the forecasting tool are solar irradiance, ambient temperature and wind velocity.…”

“…The available literature on prediction intervals for PV energy-conversion systems is characterized by the following four main limitations (Singh et al, 2013;Kardakos et al, 2013;Trapero et al, 2014;Lorenz et al, 2009;Marquez and Coimbra, 2011;Bacher et al, 2009;Segura and Vercher, 2001): (i) absence of methods proposing prediction intervals targeting the time scale of seconds or sub-seconds; (ii) absence of methods proposing prediction intervals able to track the highly-dynamic volatility of the solar irradiance; (iii) absence of methods able to account for distributions of the point-forecast errors other than Gaussian; (iv) strong dependency of the prediction interval with the specific method used for the point forecast computation. To the best of our knowledge, the only works that are independent of the point-forecast method are (Wan et al, 2014;Pinson and Tastu, 2014).…”