Historical Power Data Research Articles

Research on Wind Power Short-Term Forecasting Method Based on Temporal Convolutional Neural Network and Variational Modal Decomposition.

Wind energy reserves are large worldwide, but their randomness and volatility hinder wind power development. To promote the utilization of wind energy and improve the accuracy of wind power prediction, we comprehensively consider the influence of wind farm environmental factors and historical power on wind power generation. This paper presents a short-term wind power prediction model based on time convolution neural network (TCN) and variational mode decomposition (VMD). First, due to the non-smooth characteristics of the wind farm environmental data, this paper uses VMD to decompose the data of each environmental variable to reduce the influence of the random noise of the data on the prediction model. Then, the modal components with rich feature information are extracted according to the Pearson correlation coefficient and Maximal information coefficient (MIC) between each modal component and the power. Thirdly, a prediction model based on TCN is trained according to the preferred modal components and historical power data to achieve accurate short-term wind power prediction. In this paper, the model is trained and tested with a public wind power dataset provided by the Spanish Power Company. The simulation results show that the model has higher prediction accuracy, with MAPE and R2 are 2.79% and 0.9985, respectively. Compared with the conventional long short-term neural network (LSTM) model, the model in this paper has good prediction accuracy and robustness.

Offshore Wind Power Forecasting—A New Hyperparameter Optimisation Algorithm for Deep Learning Models

The main obstacle against the penetration of wind power into the power grid is its high variability in terms of wind speed fluctuations. Accurate power forecasting, while making maintenance more efficient, leads to the profit maximisation of power traders, whether for a wind turbine or a wind farm. Machine learning (ML) models are recognised as an accurate and fast method of wind power prediction, but their accuracy depends on the selection of the correct hyperparameters. The incorrect choice of hyperparameters will make it impossible to extract the maximum performance of the ML models, which is attributed to the weakness of the forecasting models. This paper uses a novel optimisation algorithm to tune the long short-term memory (LSTM) model for short-term wind power forecasting. The proposed method improves the power prediction accuracy and accelerates the optimisation process. Historical power data of an offshore wind turbine in Scotland is utilised to validate the proposed method and compare its outcome with regular ML models tuned by grid search. The results revealed the significant effect of the optimisation algorithm on the forecasting models’ performance, with improvements of the RMSE of 7.89, 5.9, and 2.65 percent, compared to the persistence and conventional grid search-tuned Auto-Regressive Integrated Moving Average (ARIMA) and LSTM models.

Collaborative optimization of train timetable and speed trajectory considering stochastic photovoltaic power: A two-step approach

Faced with the integrated system composed of the train power system, the photovoltaic (PV) power system, and the energy storage system (ESS), this research studies the energy-efficient operation and energy management strategy from the perspective of both train optimal control and timetable optimization, aiming at achieving a long-term energy consumption reduction. A two-step approach for collaboratively optimizing the train timetable, speed trajectory, and energy management strategy considering the stochastic characteristics of PV power generation is proposed to solve this large-scale complex problem. Before the two-step approach, a mixed-integer linear programming (MILP) model is established to optimize the energy consumption of the inter-station operation. On this basis, explicit energy consumption expressions for all inter-stations of the entire line are obtained by the proposed data fitting method. The historical PV power data is clustered to generate scenarios with different probabilities to characterize the stochastic PV power. The first step of this two-step approach is to minimize the total energy consumption expectations of all inter-stations determined by the obtained explicit energy consumption expressions to optimize the timetable while ensuring the total time and time window constraints are met. The second step is to minimize the weighted sum of energy consumption under all possible scenarios to obtain the optimal speed trajectory and energy management strategy based on the optimized timetable obtained in the first step. The validity of the model is verified by case studies using the real data of Qingdao Metro Line 11 under both scenarios with and without PV power. This study provides a novel method for energy-efficient operation and energy management of the integrated system and demonstrates the prospect of the proposed two-step stochastic optimization in reducing the net grid-supplied energy for the long-term operation of urban rail transportation systems.

Intelligent voltage prediction of active distribution network with high proportion of distributed photovoltaics

The access of high proportion of zero carbon energy, such as distributed photovoltaics (DPVs), makes the voltage time series of the new active distribution network (ADN) show a high degree of volatility and randomness, which brings great difficulties to voltage prediction. Hence, a voltage prediction method named VMD-XGBTCN that combining variable modal decomposition (VMD), extreme gradient boosting (XGBoost) and temporal convolutional network (TCN) to achieve an accurate voltage prediction. Primarily, it uses three spline interpolation functions to fill the historical voltage and power data with missing values to obtain a reliable sample data set and breaks down the voltage time series into multiple sub-signal modes by VMD to reduce data non-stability. It also uses the XGBoost to extract multiple characteristic features affecting voltage, avoiding the limitations of single feature importance measurement. Finally, it improves overall prediction accuracy by using optimization of the data input of TCN and overlay of the prediction outputs. Simulation results show that the proposed voltage intelligent prediction method fully integrates data feature extraction, combined prediction and residual correction compared with the traditional methods, and has better application effect on the accuracy and efficiency of voltage prediction.

A Multi-step ahead photovoltaic power forecasting model based on TimeGAN, Soft DTW-based K-medoids clustering, and a CNN-GRU hybrid neural network

Accurate photovoltaic (PV) power generation forecasting is very important for making economic and reliable power dispatching plans. This study proposes a multi-step ahead PV power forecasting (PPF) model, which combines time-series generative adversarial networks (TimeGAN), soft dynamic time warping (DTW)-based K-medoids clustering algorithms, and a hybrid neural network model computed by a convolutional neural network (CNN) and gated recurrent units (GRU). First, a new PV power data augmentation method based on TimeGAN is proposed to realize the expansion of the historical PV power data. Second, the combination of soft-DTW and K-medoids clustering is developed to extract and distinguish the commonalities and differences between time series characteristics of PV power. Finally, a hybrid neural network model is developed to integrate CNN and GRU into a unified framework for an accurate PPF under different weather conditions. The performance of the proposed model was tested using real datasets of two PV power stations with an installed capacity of 50MW. The comparative analysis of the proposed model with five reference models confirms its superiority in terms of forecasting accuracy. For the sunny days and cloudy days, the range of root mean square error (RMSE) values are produced by the proposed model distributed in [0.927–2.523] MW and [1.781–6.173] MW respectively with respect to the multi-step ahead forecasting from 15-min up to 24-hour. The experimental results of the hybrid model proposed in this study indicate that data augmentation-based clustering method is very helpful for improving the accuracy of PV power forecasting.

Ultra-Short-Term Power Prediction of a Photovoltaic Power Station Based on the VMD-CEEMDAN-LSTM Model

The prediction of photovoltaic power generation is helpful to the overall allocation of power planning departments and improves the utilization rate of photovoltaic power generation. Therefore, this study puts forward an ultra-short-term power forecasting model of a photovoltaic power station based on modal decomposition and deep learning. The methodology involved taking the data of a 50 MW photovoltaic power generation system in the Inner Mongolia Autonomous Region as a sample. Furthermore, the weather conditions were classified, and the historical power data were decomposed into multiple VMF subcomponents and residual terms by the VMD method. Then, the residual term was decomposed twice by the CEEMDAN method. All subcomponents were sent to the LSTM network for prediction, and the predicted value of the photovoltaic power station was obtained by superimposing the subcomponent prediction results. ARIMA, SVM, LSTM, and VMD-LSTM models were built to compare the accuracy with the proposed models. The results revealed that the prediction accuracy of a non-combination forecasting model was limited when the weather suddenly changed. The VMD method was used to decompose the residual term twice, which could fully extract the complex data information in the residual term, and when compared with the VMD-LSTM model, the eRMSE, eMAPE, and eTIC of the VMD-CEEMDAN-LSTM model were reduced by 0.104, 16.596, and 0.038, respectively. The second decomposition technology has obvious prediction advantages. The proposed quadratic modal decomposition model effectively improves the precision of ultra-short-term prediction of photovoltaic power plants.

Short-Term PV Power Forecasting Using a Regression-Based Ensemble Method

One of the most critical aspects of integrating renewable energy sources into the smart grid is photovoltaic (PV) power generation forecasting. This ensemble forecasting technique combines several forecasting models to increase the forecasting accuracy of the individual models. This study proposes a regression-based ensemble method for day-ahead PV power forecasting. The general framework consists of three steps: model training, creating the optimal set of weights, and testing the model. In step 1, a Random forest (RF) with different parameters is used for a single forecasting method. Five RF models (RF1, RF2, RF3, RF4, and RF5) and a support vector machine (SVM) for classification are established. The hyperparameters for the regression-based method involve learners (linear regression (LR) or support vector regression (SVR)), regularization (least absolute shrinkage and selection operator (LASSO) or Ridge), and a penalty coefficient for regularization (λ). Bayesian optimization is performed to find the optimal value of these three hyperparameters based on the minimum function. The optimal set of weights is obtained in step 2 and each set of weights contains five weight coefficients and a bias. In the final step, the weather forecasting data for the target day is used as input for the five RF models and the average daily weather forecasting data is also used as input for the SVM classification model. The SVM output selects the weather conditions, and the corresponding set of weight coefficients from step 2 is combined with the output from each RF model to obtain the final forecasting results. The stacking recurrent neural network (RNN) is used as a benchmark ensemble method for comparison. Historical PV power data for a PV site in Zhangbin Industrial Area, Taiwan, with a 2000 kWp capacity is used to test the methodology. The results for the single best RF model, the stacking RNN, and the proposed method are compared in terms of the mean relative error (MRE), the mean absolute error (MAE), and the coefficient of determination (R2) to verify the proposed method. The results for the MRE show that the proposed method outperforms the best RF method by 20% and the benchmark method by 2%.

Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural Networks

In order to cope with the challenges of dispatching of power grids brought by large-scale distributed photovoltaic power generation related to production and consumers, a maximum expected sample weighted convolutional neural network (EM-WS-CNN) is proposed to forecast the distributed photovoltaic output. First, the distance correlation coefficient and the principal component analysis method are used to extract the comprehensive meteorological factors from the original meteorological data, and then the 6 statistical indexes of the comprehensive meteorological factors and historical power data are used as the clustering characteristics. The historical data are divided into different weather types by using the maximum expectation clustering, and the training samples are weighted based on the membership matrix. Finally, the weighted training data are used to construct the EM-WS-CNN model. In the experimental analysis, the above-mentioned method is compared with the CNN model, and the results show that the proposed method has higher accuracy and robustness.

Research on Ultra-Short-Term Prediction Model of Wind Power Based on Attention Mechanism and CNN-BiGRU Combined

With the rapid development of new energy technologies and aiming at the proposal of the “DOUBLE CARBON” goal, the proportion of wind energy and other new sustainable energy power solutions in the power industry continues to increase and occupy a more critical position. However, the instability of wind power output brings serious challenges to safe and stable power grid operations. Therefore, accurate ultra-short-term wind power prediction is of great significance in stabilizing power system operations. This paper presents an ACNN-BiGRU wind power ultra-short-term prediction model based on the Attention mechanism, the fusion of convolutional neural network (CNN), and bidirectional gated recurrent unit (BiGRU). The model takes a single wind turbine as the prediction unit and uses the real-time meteorological data in the wind farm, the historical power data of the wind turbine, and the real-time operation data for parallel training. Then, it extracts the key features of the input data through CNN and uses the BiGRU network to conduct bidirectional modeling learning on the dynamic changes of the features proposed by CNN. In addition, the Attention mechanism is introduced to give different weights to BiGRU implicit states through mapping, weighting, and learning parameter matrix to complete the ultra-short-term wind power prediction. Finally, the actual observation data of a wind farm in Northwest China is used to verify the feasibility and effectiveness of the proposed model. The model provides new ideas and methods for ultra-short-term high-precision prediction for wind power.

Novel data-driven energy management of a hybrid photovoltaic-reverse osmosis desalination system using deep reinforcement learning

This paper proposes a novel deep reinforcement learning-accelerated energy management system for a hybrid grid-connected photovoltaic-reverse osmosis-pressure retarded osmosis desalination plant. The energy management problem is formulated as a partially observable Markov decision process by using historical photovoltaic (PV) power data in order to cope with uncertainties related to the generation of solar power and provide more information regarding the true state of the system. The soft actor-critic (SAC) algorithm is employed as the core of the energy management system to maximize water production rate and contaminant removal efficiency while minimizing the supplied power from the external grid. We introduce 1-dimensional convolutional neural networks (1-D CNNs) to the actor, critic, and value function networks of the SAC algorithm to address the partial observability dilemma involved in PV-powered energy systems, extract essential features from the PV power time series, and achieve immensely improved performance ultimately. Furthermore, it is assumed that the proposed CNN-SAC algorithm does not have access to the current output power data of the PV system. The development of more practical energy management systems necessitates this assumption, and we demonstrate that the proposed method is capable of forecasting the current PV power data. The superiority of the CNN-SAC model is verified by comparing its learning performance and simulation results with those of four state-of-the-art deep reinforcement learning algorithms: Deep deterministic policy gradient (DDPG), proximal policy optimization (PPO), twin delayed DDPG (TD3), and vanilla SAC. The results show that the CNN-SAC model outperforms the benchmark methods in terms of effective solar energy exploitation and power scheduling, manifesting the necessity of exploiting historical PV power data and 1-D CNNs. Moreover, the CNN-SAC algorithm is benchmarked against a powerful energy management system we developed in our previous investigation by studying three scenarios, and it is demonstrated that considerable improvement in energy efficiency can be obtained without using any solar power generation forecasting algorithm. By conducting ablation studies, the critical contribution of the introduced 1-D CNN is demonstrated, and we highlight the significance of providing historical PV power data for substantial performance enhancement. The average and standard deviation of evaluation scores obtained during the last stages of training reveal that the 1-D CNN significantly improves the final performance and stability of the SAC algorithm. These results demonstrate that the modifications we detail in our investigation render deep reinforcement learning algorithms extremely powerful for the energy management of PV-powered microgrids, including PV-driven reverse osmosis desalination plants.

Modeling of solar photovoltaic power using a two-stage forecasting system with operation and weather parameters

ABSTRACT The integration of solar photovoltaic (SPV) system to the grid has introduced a new source of intermittency in the grid, and the grid has to react smartly to the changes that occur in the penetration of SPV power. Accurate modeling of weather-dependent SPV power will be helpful in forecasting the penetration of SPV power into the grid. An SPV power output forecasting model has been developed based on artificial neural network (ANN) approach. Two forecasters, namely ANN forecaster and two-stage hybrid-ANN forecaster, are developed with operational and weather parameters. The historical data of SPV power (P), hours of operation of SPV system (to), daily global solar radiation (H), and ambient temperature(T) are used as modeling parameters. The combination of modeling parameters {P, H, T, to} is identified as the best combination that influences the forecasting of day-ahead power output. A relative root mean square error (RRMSE) of 5.74% was obtained with the combination of {P, H, T, to}. An RRMSE of 6.04% was observed with the combination of {P, H, T} as inputs, and the hours of operation of the SPV plant could be ignored in the model. The historical power data of the SPV plant is identified as the crucial parameter in the SPV power forecast model and has given an RRMSE of 7.25%. The models developed with temperature and radiation as modeling parameters have resulted in good forecasting accuracy, which could be best suitable for feasibility studies of SPV plant at a particular location. Solar radiation prediction models are used in the development of hybrid-ANN forecaster. It has produced an RRMSE of 7.35% with four inputs. The hybrid-ANN forecaster with predicted radiations as modeling input will eliminate the need of a costly pyranometer. The models developed in the present study have utilized readily available parameters as modeling parameters, thereby cost of the forecasting system has been decreased. The developed models will be useful for energy scheduling and energy management in the smart grid. Abbreviations: GSR, Global Solar Radiation; ANN, Artificial Neural networks; SPV, Solar Photovoltaics; MAPE, Mean Absolute Percentage Error; RRMSE, Relative Root Mean Square Error; MSE, Mean Square Error.

Short-Term Wind Power Prediction Based on Wavelet Feature Arrangement and Convolutional Neural Networks Deep Learning

Wind power prediction (WPP) has an important impact on the security and reliability operation of power grid after a large amount of wind power integration into the system. There are two main challenges in WPP: 1) Both numerical weather prediction (NWP) and wind power contain abundant frequency information. If these data are directly input to the prediction model, the connection between different frequency bands is difficult to be mined. 2) Wind power has strong randomness and volatility, so the nonlinear relationship between input and output is difficult to be reflected by traditional prediction models. To overcome the challenge, a novel short-term WPP model based on wavelet feature arrangement and convolutional neural networks (CNN) is proposed in the article. First, wavelet transform is applied to split the original NWP data and historical power data into multiple sets of different frequency components. Then, the features of different frequencies are arranged in various ways, named feature arrangement (FA), which are input into the CNN model for WPP, and finally, the prediction results are obtained. Two case studies demonstrated the effectiveness of the proposed novel WT-FA-CNN deep learning model for short-term WPP.

Research on intelligent early warning system of rail transit line trip based on pscada

In this paper, an intelligent early warning scheme for rail transit line trip based on PSCADA system is proposed. The scheme takes into account the defects of low prediction accuracy and real-time prediction caused by the lack of power data in the traditional line trip prediction method. At the same time, a large number of power data generated by PSCADA system in the long-term application process are ignored in the field of rail transit[1]. Based on this situation, the prediction data set is constructed by combining the historical power data collected by PSCADA system in rail transit and the lightning weather data in traditional prediction methods. On this basis, the lightgbm machine learning intelligent algorithm is used to compare the similar support vector machine (SVM) and logistic regression algorithm to obtain a model with good prediction effect. In practical application, the real-time data set is constructed by using the real-time power data and real-time weather data collected by PSCADA system to predict, and an intelligent early warning system with the dual advantages of real-time and high accuracy is obtained.

SolarNet: A hybrid reliable model based on convolutional neural network and variational mode decomposition for hourly photovoltaic power forecasting

Photovoltaic (PV) power generation has high uncertainties due to the randomness and imbalance nature of solar energy and meteorological parameters. Hence, accurate PV power forecasts are essential in the operation of PV power plants (PVPP) for short-term dispatches and power generation schedules. In this study, a novel convolutional neural network (CNN) model, namely SolarNet, is proposed for short-term PV output power forecasting under different weather conditions and seasons. The proposed CNN model is designed as a parallel pooling structure to increase the forecasting performance. This structure consists of max-pooling and average-pooling blocks. The input parameters are the measured historical solar radiation, temperature, humidity, and active power data. The power data is decomposed into sub-components with the variational mode decomposition method and a data preprocessing and reconstruction process is utilized to obtain deep input feature maps. After input parameters are converted to hue-saturation-value (HSV) color space, the subsets feed to the input of the network. The experimental studies are performed with a case study using a 23.40 kW PVPP dataset from the Desert Knowledge Australia Solar Centre. The design CNN model is also compared with benchmark deep learning methods. In the experiments, the average correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE) of the proposed method for 1-h different weather conditions are achieved as 0.9871, 0.3090, and 0.1750, respectively. The experimental results show that the proposed deep forecasting method has higher accuracy and stability in short-term PV power forecasting and outperforms the other deep learning methods.

Novel application of adaptive swarm intelligence techniques coupled with adaptive network-based fuzzy inference system in predicting photovoltaic power

Accurate photovoltaic (PV) power prediction is necessary for future development of the micro-grids projects and the economic dispatch sector. This study investigates the potential of using a novel hybrid approach of adaptive swarm intelligence techniques and adaptive network-based fuzzy inference system (ANFIS) in estimating the PV power of a solar system at different time horizons, from 0 to 24 h. The developed approach is an integration of ANFIS and particle swarm optimization (PSO) with adaptive and time-varying acceleration coefficients, i.e., ANFIS-APSO (ANFIS-PSO with adaptive acceleration coefficients) and ANFIS-IPSO (ANFIS-PSO with time-varying acceleration coefficients), were developed. The performance of the proposed models was compared with other hybrid ANFIS models, namely ANFIS-PSO (ANFIS coupled with PSO), ANFIS-BBO (ANFIS coupled with biogeography-based optimization), ANFIS-GA (ANFIS coupled with genetic algorithm), and ANFIS-GWO (ANFIS coupled with grey wolf optimization). For this purpose, the climatic variables and historical PV power data of a 960 kWP grid-connected PV system in the south of Italy were used to design and evaluate the models. Several statistical analyses were implemented to evaluate the accuracy of the proposed models and assess the impact of variables that affects the PV power values. The experimental results show that the proposed ANFIS-APSO attained the most accurate prediction of the PV power with R2 = 0.835 and 0.657, RMSE = 0.088 kW and 0.081 kW, and MAE = 0.077 kW and 0.079 kW in the testing phase at time horizons 12 h and 24 h, respectively. Based on the obtained results, the newly constructed ANFIS-APSO outperformed the standard ANFIS-PSO model including other hybrid models, and hence very potential to be a new alternative to assist engineers for predicting the PV power of solar systems at short- and long-time horizons.

Hybrid Forecasting Methodology for Wind Power-Photovoltaic-Concentrating Solar Power Generation Clustered Renewable Energy Systems

Forecasting of large-scale renewable energy clusters composed of wind power generation, photovoltaic and concentrating solar power (CSP) generation encounters complex uncertainties due to spatial scale dispersion and time scale random fluctuation. In response to this, a short-term forecasting method is proposed to improve the hybrid forecasting accuracy of multiple generation types in the same region. It is formed through training the long short-term memory (LSTM) network using spatial panel data. Historical power data and meteorological data for CSP plant, wind farm and photovoltaic (PV) plant are included in the dataset. Based on the data set, the correlation between these three types of power generation is proved by Pearson coefficient, and the feasibility of improving the forecasting ability through the hybrid renewable energy clusters is analyzed. Moreover, cases study indicates that the uncertainty of renewable energy cluster power tends to weaken due to partial controllability of CSP generation. Compared with the traditional prediction method, the hybrid prediction method has better prediction accuracy in the real case of renewable energy cluster in Northwest China.

Short term solar power forecasting using hybrid minimum variance expanded RVFLN and Sine-Cosine Levy Flight PSO algorithm

With the increase in solar power integration, the necessity for accurate solar power forecasting is of paramount importance for various energy markets, grid management system, power dispatching and so on. This paper analyses a new and efficient hybrid forecasting approach consisting of empirical wavelet transform (EWT) and Robust minimum variance Random Vector Functional Link Network (RRVFLN) with random weight vector for the enhancement nodes along with a functionally expanded direct link to the output node from input nodes. The RRVFLN contains dual activation functions in each hidden neuron of the network and its parameters are optimized by an efficient Sine Cosine and levy flight based particle swarm optimization (PSOLVSC). The proposed RRVFLN has some similarity with recently proposed broad learning system that can replace neural networks with deep architecture for handling big and time varying data bases. For examining the solar power prediction accuracy of the proposed EWT-RRVFLN model, the historical solar power data for different seasons of Alabama, Ikitelli, and Berlin are taken into consideration which are divided into three time horizon intervals of 5min, 15min, 30min and 60 min, respectively.

A Novel Short-Term Photovoltaic Power Forecasting Approach based on Deep Convolutional Neural Network

ABSTRACT In this study, a novel photovoltaic power forecasting system that utilizes a deep Convolutional Neural Network (CNN) structure and an input signal decomposition algorithm is proposed. The proposed CNN architecture extracts deep features to forecast short-term power using transfer learning-based AlexNet. The historical power, solar radiation, wind speed, and temperature data are selected as the input. The signal decomposition algorithm called Empirical Mode Decomposition (EMD) is utilized to decompose the historical power signal into sub-components. In order to extract deep features, all input parameters are converted to 2D feature maps and feed to the input of the CNN. The experiments are realized on a grid-tied Photovoltaic Power Plant (PVPP) that has 1000 kW installed capacity located in Turkey. The experiments are performed under four weather conditions as partial cloudy, cloudy-rainy, heavy-rainy, and sunny days to show the effectiveness of the proposed method. The obtained results are compared with the benchmark regression algorithms. When the results are analyzed, the proposed method gives the highest Correlation Coefficient (R) and the lowest Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and SMAPE values under all horizons and weather conditions. For 1-h to 5-h ahead, the average R values of the proposed method are obtained as 97.28%, 95.77%, 94.49%, 93.61%, and 92.62%, respectively. The average RMSE values are observed as 4.90%, 6.30%, 7.50%, 8.00%, and 9.17% for 1-h to 5-h ahead. The experimental results confirm that the proposed method outperforms the conventional regression algorithms and reveals effective results with its competitive performance.

A Hybrid K-Means-GRA-SVR Model Based on Feature Selection for Day-Ahead Prediction of Photovoltaic Power Generation

In order to ensure that the large-scale application of photovoltaic power generation does not affect the stability of the grid, accurate photovoltaic (PV) power generation forecast is essential. A short-term PV power generation forecast method using the combination of K-means++, grey relational analysis (GRA) and support vector regression (SVR) based on feature selection (Hybrid Kmeans-GRA-SVR, HKGSVR) was proposed. The historical power data were clustered through the multi-index K-means++ algorithm and divided into ideal and non-ideal weather. The GRA algorithm was used to match the similar day and the nearest neighbor similar day of the prediction day. And selected appropriate input features for different weather types to train the SVR model. Under ideal weather, the average values of MAE, RMSE and R2 were 0.8101, 0.9608 kW and 99.66%, respectively. And this method reduced the average training time by 77.27% compared with the standard SVR model. Under non-ideal weather conditions, the average values of MAE, RMSE and R2 were 1.8337, 2.1379 kW and 98.47%, respectively. And this method reduced the average training time of the standard SVR model by 98.07%. The experimental results show that the prediction accuracy of the proposed model is significantly improved compared to the other five models, which verify the effectiveness of the method.

Short-term Photovoltaic Power Forecast Based on Greenhouse Energy Supply Requirements

In order to solve the problem of “disposal of light” in distributed photovoltaic power plants,this paper proposed that the energy supply of photovoltaic power plants could achieve local consumption in agricultural greenhouses, and predict the photovoltaic power generation in advance according to the load demand of greenhouses. The historical power data and meteorological data of the input variables were normalized, and the PV power prediction was performed at a time interval of 1 h for a time comparison. The prediction method based on the iterative improved BP neural network model was proposed. The prediction results showed that the prediction error was not More than 2%,could meet the energy supply stability requirements of greenhouse loads.