Solar irradiance forecasting by using wavelet based denoising

Lyu, Lingyu; Kantardzic, Mehmed; Arabmakki, Elaheh

doi:10.1109/cies.2014.7011839

Cited by 17 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance in [21], authors propose a hybrid algorithm that uses a combination of a data filtering technique based on the wavelet transform (WT) using wavelet db4 together with a soft computing model based on fuzzy ARTMAP (FA) that is optimised using the firefly algorithm. Similarly, in [22], authors use the DWT with the purpose of denoising the original solar irradiance signal and then feed the resultant coefficients into a neural network or SVM model to predict the solar irradiance profile. In [23], Capizzi et al proposed a novel wavelet recurrent neural network (WRNN) designed to take advantage of the correlation between solar radiation and variations of wind speed, humidity, and temperature.…”

Section: Overview Of Solar Forecasting Techniquesmentioning

confidence: 99%

Forecasting of PV plant output using hybrid wavelet‐based LSTM‐DNN structure model

Ospina

Newaz

Faruque

2019

IET Renewable Power Generation

View full text Add to dashboard Cite

This paper proposes a novel forecasting model designed to accurately forecast the PV power output for both largescale and small-scale PV systems. The proposed model uses available temperature data, approximate and detailed coefficients obtained from the decomposed PV power time series using the stationary wavelet transform (SWT), and statistical features extracted from the historical PV data. The model is comprised of four long-short-term memory (LSTM) recurrent neural networks (RNN) designed to perform multi-step forecasting on the individual approximate and detailed coefficients decomposed by the SWT and a final deep neural network (DNN) designed to perform the next time step PV power forecast. The DNN makes use of the reconstructed values estimated by the four LSTM networks together with temperature data and statistical features to predict the final forecasted value of the next time step PV power. 30-min resolution data from a 12.6 MW PV system located in the state of Florida are used for testing and evaluating the proposed method against several models found in the literature. The results obtained suggest that the proposed model improved the forecasting accuracy significantly in the metrics used to compare with other models while reducing the number of features needed to perform the forecasting operation.

show abstract

Section: Overview Of Solar Forecasting Techniquesmentioning

confidence: 99%

Forecasting of PV plant output using hybrid wavelet‐based LSTM‐DNN structure model

Ospina

Newaz

Faruque

2019

IET Renewable Power Generation

View full text Add to dashboard Cite

show abstract

“…The WT is a method that transforms time series data into time-frequency representation and becomes a superior alternative of the Fourier transform (FT) to analyze stationary and non-stationary data [24,27]. In the theory of WT, an original signal is decomposed into two parts; a low-frequency signal and a high-frequency signal.…”

Section: Elimination Of Noisy Data Using Wavelet Transform (Wt)mentioning

confidence: 99%

“…Catalao et al combined a wavelet transform (WT) and an ANN for wind power forecasting, where the WT was utilized as a denoising tool of the data [23]. Likewise, Lyu et al applied a WT in filtering the noise of solar irradiance forecasting [24]. The existence of noise causes the data to become non-stationary, leading to the wrong model coefficient.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting Solar Power Using Hybrid Firefly and Particle Swarm Optimization (HFPSO) for Optimizing the Parameters in a Wavelet Transform-Adaptive Neuro Fuzzy Inference System (WT-ANFIS)

et al. 2019

View full text Add to dashboard Cite

Solar power generation deals with uncertainty and intermittency issues that lead to some difficulties in controlling the whole grid system due to imbalanced power production and power demand. The forecasting of solar power is an effort in securing the integration of renewable energy into the grid. This work proposes a forecasting model called WT-ANFIS-HFPSO which combines the wavelet transform (WT), adaptive neuro-fuzzy inference system (ANFIS) and hybrid firefly and particle swarm optimization algorithm (HFPSO). In the proposed work, the WT model is used to eliminate the noise in the meteorological data and solar power data whereby the ANFIS is functioning as the forecasting model of the hourly solar power data. The HFPSO is the hybridization of the firefly (FF) and particle swarm optimization (PSO) algorithm, which is employed in optimizing the premise parameters of the ANFIS to increase the accuracy of the model. The results obtained from WT-ANFIS-HFPSO are then compared with several other forecasting strategies. From the comparative analysis, the WT-ANFIS-HFPSO showed superior performance in terms of statistical error analysis, confirming its reliability as an excellent forecaster of hourly solar power data.

show abstract

“…These algorithms have also been successfully improved through combination with data filtering techniques such as wavelet transforms (Mellit et al, 2006;Lyu et al, 2014).…”

Section: Introductionmentioning

confidence: 98%