scispace - formally typeset
Proceedings ArticleDOI: 10.1109/IICPE.2016.8079388

Energy forecasting for grid connected MW range solar PV system

01 Nov 2016-pp 1-6
Abstract: An accurate forecasting of PV output is essential to improve real-time control performance and to reduce possible negative impacts. For an energy management system (EMS) of distributed energy resources, accurate forecasting of solar irradiation and thus PV power output can reduce the impact of uncertainty for PV power generation, improve system reliability, and increase the penetration level of the PV power generation system. Solar power output can be predicted based on historical solar irradiance and weather data, using Artificial Neural Networks and then is converted to PV power output. Neural Networks is designed to train, visualize, and validate network models using feed forward network with back propagation algorithm. The model is trained; using data collected from a 10 kW PV system which includes beam solar irradiance, relative humidity, temperature and wind speed as input for the training set. The future DC and AC power outputs are predicted for any given day. Also the power forecasting is being extended for a 100 kW and 1 MW PV system. more

Topics: Grid-connected photovoltaic power system (71%), Photovoltaic system (68%), Solar power (66%) more

Journal ArticleDOI: 10.1016/J.SETA.2021.101085
Abstract: Although photovoltaic generation has been proposed as a solution for the world’s energy challenges, it depends to a large extent on solar irradiation and air temperature. Therefore, small variations in these meteorological parameters produce sudden changes in power generation, which makes it difficult to integrate photovoltaic generators into the electrical grid. The aim of this study is to develop a very short-term temperature forecaster that makes photovoltaic generation more reliable in order to provide not only power but also ancillary services. To predict ambient temperature in a specific area (Vitoria-Gasteiz, Basque Country) in the next 10 min, this forecaster combines a multilayer perceptron and the optimal nearest number of meteorological. In addition, the distance and relative location between each station and the target station were taken into account. The accumulated deviation between actual and forecasted temperature was lower than 1% in 96.60% of the examined days from the validation database. Moreover, the root mean square error was 0.2557 °C, which represents an improvement of 13.20% as compared with the benchmark result. The results indicated that the forecaster can be considered for implementation in photovoltaic generators to compute key control parameters and improve their integration into the electrical grid. more

6 Citations

Proceedings ArticleDOI: 10.1109/ICECCE47252.2019.8940664
24 Jul 2019-
Abstract: Solar energy is one of the major renewable energy sources with the potential to cope with the future energy challenges. But the penetration of solar PV generation in the electrical grid is a serious concern because of variable availability. Therefore, solar PV generation forecasting is essential for planning and efficient operation. The forecasting model is based on Artificial Neural Network (ANN) with forecasted and historical weather parameters i.e., temperature, dew point, relative humidity and wind speed as inputs. The aim of this study is to determine the most effective combination of weather variables to be used as input to the model. For this, all the possible combinations of the inputs are applied to ANN and the best one is obtained by analysis of the results. Mean Absolute Percentage Error (MAPE) is used as a measure to compare the results. To train the ANN model, one year's weather and generation data of 20.8 kW PV system with an hourly resolution is used. 24 hours ahead forecasting of the generation is done using forecasted weather data of 14 days selected from the dataset of 130 days. Combination of three parameters (temperature, relative humidity and dew point) results in an average MAPE of 14.86% while the use of all four parameters as inputs gives 14.33% of MAPE. more

Topics: Photovoltaic system (56%), Dew point (55%), Mean absolute percentage error (54%) more

3 Citations

Journal ArticleDOI: 10.1016/J.ENERGY.2021.120647
15 Aug 2021-Energy
Abstract: Photovoltaic generation has arisen as a solution for the present energy challenge. However, power obtained through solar technologies has a strong correlation with certain meteorological variables such as solar irradiation, wind speed or ambient temperature. As a consequence, small changes in these variables can produce unexpected deviations in energy production. Although many research articles have been published in the last few years proposing different models for predicting these parameters, the vast majority of them do not consider spatiotemporal parameters. Hence, this paper presents a new solar irradiation forecaster which combines the advantages of machine learning and the optimisation of both spatial and temporal parameters in order to predict solar irradiation 10 min ahead. A validation step demonstrated that the deviation between the actual and forecasted solar irradiation was lower than 4% in 82.95% of the examined days. With regard to the error metrics, the root mean square error was 50.80 W/m2, an improvement of 11.27% compared with the persistence model, which was used as a benchmark. The results indicate that the developed forecaster can be integrated into photovoltaic generators’ to predict their output power, thus promoting their inclusion in the main power network. more

Topics: Photovoltaic system (61%)

3 Citations

Proceedings ArticleDOI: 10.1109/R10-HTC49770.2020.9356988
01 Dec 2020-
Abstract: Energy production of photovoltaic (PV) system depends on the amount of solar irradiance present on a certain location. Accurate prediction of solar irradiance ensures economic integration of PV system to grid and leads to optimal dispatching of available energy resources. Weather conditions has strong correlation with solar irradiance, and its erratic nature causes fluctuation to energy production. Therefore, it is difficult to achieve consistent optimal energy production and reliable prediction of solar irradiance. In the study, a bagging-based ensemble learning system was used to predict solar irradiance based on weather patterns. Previous researches confirmed that ensemble learners produced unbiased and more accurate results compared to single learners. A pre-processed stacked long-short term memory model (stacked LSTM) was used as base learner in ensemble learning since it has good performance in handling time series sequences. A plot that compares the performance between single learner and ensemble learners was provided. From the plot, it shows that at some iteration, ensemble learners get consistent at providing more accurate predictions compared to single learners. Metrics used in the study include explained variance score, maximum residual error, mean absolute error, mean squared error, and regression score function. more

Topics: Solar irradiance (62%), Ensemble learning (58%), Photovoltaic system (54%) more

2 Citations

Proceedings ArticleDOI: 10.1109/IEECON48109.2020.229517
04 Mar 2020-
Abstract: Due to global warming issue and growing of energy demand, photovoltaic (PV) power plant is a desirable alternative to electrical power generations. An accurate PV power forecasting is essential to alleviate its negative impacts and to improve its performance. This paper proposed a short-term PV power forecasting technique based on Holt-Winters method. Its property and principle are presented. There are two main parameters, i.e. the number of days (N) and the weight index (α). The values of these two parameters affect the forecasting accuracy, and a set of optimal values for both parameters used for all season is proposed. A real PV generated power profile is collected from the eastern part of Thailand and used in this study. The performance of the proposed forecasting technique is carried out by MATLAB program. The simulation results indicate that the proposed method provides acceptable short-term forecasting results. The proposed technique can be applied in energy management and electrical power smoothing applications. more

Topics: Photovoltaic system (54%), Electric power (53%), Power station (53%) more

1 Citations


Journal ArticleDOI: 10.1109/TIA.2012.2190816
Jie Shi, Wei-Jen Lee1, Yongqian Liu, Yongping Yang  +1 moreInstitutions (1)
Abstract: Due to the growing demand on renewable energy, photovoltaic (PV) generation systems have increased considerably in recent years. However, the power output of PV systems is affected by different weather conditions. Accurate forecasting of PV power output is important for system reliability and promoting large-scale PV deployment. This paper proposes algorithms to forecast power output of PV systems based upon weather classification and support vector machines (SVM). In the process, the weather conditions are divided into four types which are clear sky, cloudy day, foggy day, and rainy day. In this paper, a one-day-ahead PV power output forecasting model for a single station is derived based on the weather forecasting data, actual historical power output data, and the principle of SVM. After applying it into a PV station in China (the capability is 20 kW), results show the proposed forecasting model for grid-connected PV systems is effective and promising. more

430 Citations

Journal ArticleDOI: 10.1109/TSTE.2014.2313600
Abstract: To improve real-time control performance and reduce possible negative impacts of photovoltaic (PV) systems, an accurate forecasting of PV output is required, which is an important function in the operation of an energy management system (EMS) for distributed energy resources. In this paper, a weather-based hybrid method for 1-day ahead hourly forecasting of PV power output is presented. The proposed approach comprises classification, training, and forecasting stages. In the classification stage, the self-organizing map (SOM) and learning vector quantization (LVQ) networks are used to classify the collected historical data of PV power output. The training stage employs the support vector regression (SVR) to train the input/output data sets for temperature, probability of precipitation, and solar irradiance of defined similar hours. In the forecasting stage, the fuzzy inference method is used to select an adequate trained model for accurate forecast, according to the weather information collected from Taiwan Central Weather Bureau (TCWB). The proposed approach is applied to a practical PV power generation system. Numerical results show that the proposed approach achieves better prediction accuracy than the simple SVR and traditional ANN methods. more

Topics: Probabilistic forecasting (62%), Probability of precipitation (52%), Photovoltaic system (52%) more

307 Citations

Proceedings ArticleDOI: 10.1109/IAS.2011.6074294
Jie Shi1, Wei-Jen Lee2, Yongqian Liu1, Yongping Yang1  +1 moreInstitutions (2)
10 Nov 2011-
Abstract: Due to the growing demand on renewable energy, photovoltaic (PV) generation systems have increased considerably in recent years. However, the power output of PV systems is affected by different weather conditions. Accurate forecasting of PV power output is important for the system reliability and promoting large scale PV deployment. This paper proposes algorithms to forecast power output of PV systems based upon weather classification and support vector machine. In the process, the weather conditions are firstly divided into four types which are clear sky, cloudy day, foggy and rainy day. One-day-ahead PV power output forecasting model for single station is derived based on the weather forecasting data and historically actual power output data as well as the principle of Support Vector Machine (SVM). After applying it into a PV station in China (the capability is 20 kW), results show the proposed forecasting model for grid-connected photovoltaic systems is effective and promising. more

295 Citations

Journal ArticleDOI: 10.1109/TSTE.2014.2381224
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. more

Topics: Photovoltaic system (60%), Electricity generation (52%), Wind speed (50%)

199 Citations

Open accessJournal ArticleDOI: 10.1109/TNNLS.2012.2216546
Abstract: Solar radiation prediction is an important challenge for the electrical engineer because it is used to estimate the power developed by commercial photovoltaic modules. This paper deals with the problem of solar radiation prediction based on observed meteorological data. A 2-day forecast is obtained by using novel wavelet recurrent neural networks (WRNNs). In fact, these WRNNS are used to exploit the correlation between solar radiation and timescale-related variations of wind speed, humidity, and temperature. The input to the selected WRNN is provided by timescale-related bands of wavelet coefficients obtained from meteorological time series. The experimental setup available at the University of Catania, Italy, provided this information. The novelty of this approach is that the proposed WRNN performs the prediction in the wavelet domain and, in addition, also performs the inverse wavelet transform, giving the predicted signal as output. The obtained simulation results show a very low root-mean-square error compared to the results of the solar radiation prediction approaches obtained by hybrid neural networks reported in the recent literature. more

Topics: Wavelet (59%), Wavelet transform (59%), Photovoltaic system (56%) more

140 Citations

No. of citations received by the Paper in previous years