An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data
TL;DR: Based on seasonal weather classification, the back propagation (BP) artificial neural network (ANN) approach is utilized to forecast the next 24-h PV power outputs, and the estimated results of the proposed PV power forecasting model coincide well with measurement data as discussed by the authors.
Abstract: Due to the intermittency and randomness of solar photovoltaic (PV) power, it is difficult for system operators to dispatch PV power stations. In order to find a precise expectation for day-ahead PV power generation, conventional models have taken into consideration the temperature, humidity, and wind speed data for forecasting, but these predictions were always not accurate enough under extreme weather conditions. Aerosol index (AI), which indicates the particulate matter in the atmosphere, has been found to have strong linear correlation with solar radiation attenuation, and might have potential influence on the power generated by PV panels. A novel PV power forecasting model is proposed in this paper, considering AI data as an additional input parameter. Based on seasonal weather classification, the back propagation (BP) artificial neural network (ANN) approach is utilized to forecast the next 24-h PV power outputs. The estimated results of the proposed PV power forecasting model coincide well with measurement data, and the proposed model has shown the ability of improving prediction accuracy, compared with conventional methods using ANN.
Citations
More filters
TL;DR: In this paper, a comprehensive and systematic review of the direct forecasting of PV power generation is presented, where the importance of the correlation of the input-output data and the preprocessing of model input data are discussed.
Abstract: To mitigate the impact of climate change and global warming, the use of renewable energies is increasing day by day significantly. A considerable amount of electricity is generated from renewable energy sources since the last decade. Among the potential renewable energies, photovoltaic (PV) has experienced enormous growth in electricity generation. A large number of PV systems have been installed in on-grid and off-grid systems in the last few years. The number of PV systems will increase rapidly in the future due to the policies of the government and international organizations, and the advantages of PV technology. However, the variability of PV power generation creates different negative impacts on the electric grid system, such as the stability, reliability, and planning of the operation, aside from the economic benefits. Therefore, accurate forecasting of PV power generation is significantly important to stabilize and secure grid operation and promote large-scale PV power integration. A good number of research has been conducted to forecast PV power generation in different perspectives. This paper made a comprehensive and systematic review of the direct forecasting of PV power generation. The importance of the correlation of the input-output data and the preprocessing of model input data are discussed. This review covers the performance analysis of several PV power forecasting models based on different classifications. The critical analysis of recent works, including statistical and machine-learning models based on historical data, is also presented. Moreover, the strengths and weaknesses of the different forecasting models, including hybrid models, and performance matrices in evaluating the forecasting model, are considered in this research. In addition, the potential benefits of model optimization are also discussed.
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]....
[...]
TL;DR: A comprehensive and extensive review of renewable energy forecasting methods based on deep learning to explore its effectiveness, efficiency and application potential and the current research activities, challenges, and potential future research directions are explored.
537 citations
TL;DR: In this paper, the authors reviewed and evaluated contemporary forecasting techniques for photovoltaics into power grids, and concluded that ensembles of artificial neural networks are best for forecasting short-term PV power forecast and online sequential extreme learning machine superb for adaptive networks; while Bootstrap technique optimum for estimating uncertainty.
Abstract: Integration of photovoltaics into power grids is difficult as solar energy is highly dependent on climate and geography; often fluctuating erratically. This causes penetrations and voltage surges, system instability, inefficient utilities planning and financial loss. Forecast models can help; however, time stamp, forecast horizon, input correlation analysis, data pre and post-processing, weather classification, network optimization, uncertainty quantification and performance evaluations need consideration. Thus, contemporary forecasting techniques are reviewed and evaluated. Input correlational analyses reveal that solar irradiance is most correlated with Photovoltaic output, and so, weather classification and cloud motion study are crucial. Moreover, the best data cleansing processes: normalization and wavelet transforms, and augmentation using generative adversarial network are recommended for network training and forecasting. Furthermore, optimization of inputs and network parameters, using genetic algorithm and particle swarm optimization, is emphasized. Next, established performance evaluation metrics MAE, RMSE and MAPE are discussed, with suggestions for including economic utility metrics. Subsequently, modelling approaches are critiqued, objectively compared and categorized into physical, statistical, artificial intelligence, ensemble and hybrid approaches. It is determined that ensembles of artificial neural networks are best for forecasting short term photovoltaic power forecast and online sequential extreme learning machine superb for adaptive networks; while Bootstrap technique optimum for estimating uncertainty. Additionally, convolutional neural network is found to excel in eliciting a model's deep underlying non-linear input-output relationships. The conclusions drawn impart fresh insights in photovoltaic power forecast initiatives, especially in the use of hybrid artificial neural networks and evolutionary algorithms.
446 citations
TL;DR: The use of long short-term memory recurrent neural network (LSTM-RNN) to accurately forecast the output power of PV systems and offers a further reduction in the forecasting error compared with the other methods.
Abstract: Photovoltaic (PV) is one of the most promising renewable energy sources. To ensure secure operation and economic integration of PV in smart grids, accurate forecasting of PV power is an important issue. In this paper, we propose the use of long short-term memory recurrent neural network (LSTM-RNN) to accurately forecast the output power of PV systems. The LSTM networks can model the temporal changes in PV output power because of their recurrent architecture and memory units. The proposed method is evaluated using hourly datasets of different sites for a year. We compare the proposed method with three PV forecasting methods. The use of LSTM offers a further reduction in the forecasting error compared with the other methods. The proposed forecasting method can be a helpful tool for planning and controlling smart grids.
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]....
[...]
TL;DR: This paper provides a comprehensive review of the theoretical forecasting methodologies for both solar resource and PV power and applications of solar forecasting in energy management of smart grid are investigated in detail.
Abstract: Due to the challenge of climate and energy crisis, renewable energy generation including solar generation has experienced significant growth. Increasingly high penetration level of photovoltaic (PV) generation arises in smart grid. Solar power is intermittent and variable, as the solar source at the ground level is highly dependent on cloud cover variability, atmospheric aerosol levels, and other atmosphere parameters. The inherent variability of large-scale solar generation introduces significant challenges to smart grid energy management. Accurate forecasting of solar power/irradiance is critical to secure economic operation of the smart grid. This paper provides a comprehensive review of the theoretical forecasting methodologies for both solar resource and PV power. Applications of solar forecasting in energy management of smart grid are also investigated in detail.
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
More filters
01 Jan 1998
TL;DR: Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Abstract: A comprehensive look at learning and generalization theory. The statistical theory of learning and generalization concerns the problem of choosing desired functions on the basis of empirical data. Highly applicable to a variety of computer science and robotics fields, this book offers lucid coverage of the theory as a whole. Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
26,531 citations
TL;DR: In this paper, the authors consider a population in which sexual selection and natural selection may or may not be taking place, and assume only that the deviations from the mean in the case of any organ of any generation follow exactly or closely the normal law of frequency.
Abstract: Consider a population in which sexual selection and natural selection may or may not be taking place. Assume only that the deviations from the mean in the case of any organ of any generation follow exactly or closely the normal law of frequency, then the following expressions may be shown to give the law of inheritance of the population.
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]....
[...]
Book•
30 Aug 2004
TL;DR: artificial neural networks, artificial neural networks , مرکز فناوری اطلاعات و اصاع رسانی, کδاوρزی
Abstract: artificial neural networks , artificial neural networks , مرکز فناوری اطلاعات و اطلاع رسانی کشاورزی
2,254 citations
TL;DR: In this paper, the spectral variations of the backscattered radiances are used to separate aerosol absorption from scattering effects, which can be used to identify several aerosol types, ranging from nonabsorbing sulfates to highly UV-absorbing mineral dust.
Abstract: We discuss the theoretical basis of a recently developed technique to characterize aerosols from space. We show that the interaction between aerosols and the strong molecular scattering in the near ultraviolet produces spectral variations of the backscattered radiances that can be used to separate aerosol absorption from scattering effects. This capability allows identification of several aerosol types, ranging from nonabsorbing sulfates to highly UV-absorbing mineral dust, over both land and water surfaces. Two ways of using the information contained in the near-UV radiances are discussed. In the first method, a residual quantity, which measures the departure of the observed spectral contrast from that of a molecular atmosphere, is computed. Since clouds yield nearly zero residues, this method is a useful way of separately mapping the spatial distribution of UV-absorbing and nonabsorbing particles. To convert the residue to optical depth, the aerosol type must be known. The second method is an inversion procedure that uses forward calculations of backscattered radiances for an ensemble of aerosol models. Using a look-up table approach, a set of measurements given by the ratio of backscattered radiance at 340-380 nm and the 380 nm radiance are associated, within the domain of the candidate aerosol models, to values of optical depth and single-scattering albedo. No previous knowledge of aerosol type is required. We present a sensitivity analysis of various error sources contributing to the estimation of aerosol properties by the two methods.
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]....
[...]
TL;DR: In this article, the authors review the theory behind these forecasting methodologies, and a number of successful applications of solar forecasting methods for both the solar resource and the power output of solar plants at the utility scale level.
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]....
[...]