Research on the Power Prediction of Photovoltaic Power Station Based on LMS Adaptive Filter

2013 ◽  
Vol 433-435 ◽  
pp. 464-468
Author(s):  
Hong Lu Zhu ◽  
Jian Xi Yao
Keyword(s):  
Adaptive Filter ◽  
Prediction Method ◽  
Energy Output ◽  
Power Prediction ◽  
Power Station ◽  
Stochastic Fluctuation ◽  
Continuous Increase ◽  
Power Stations ◽  
Photovoltaic Power ◽  
Lms Filter

Along with continuous increase of capacity of PV(photovoltaic) power station, techniques for power prediction of PV power station play an important role in reducing impact of stochastic fluctuation of PV power stations energy output on power system. The paper proposes a method for power prediction of PV power station based on LMS adaptive filter, a FIR approach model of PV station power prediction model based on LMS adaptive filter is established with history runtime value of PV station as the input value of filter and current value as the expected value. The advantage of using LMS filter to power prediction of PV power station is that a real-time, explicit identification result can be obtained as well as that the algorithm is simple. A test has been made with runtime data of one PV power station and the result showed that the prediction method in the paper has good accuracy in terms of super-short term power prediction.

scholarly journals Research on power prediction of photovoltaic power station based on similar hour and LM-BP neural network

2021 ◽  
Vol 252 ◽  
pp. 01056
Author(s):  
Qiang Zhang ◽  
Gang Liu ◽  
Xiangzhong Wei
Keyword(s):  
Neural Network ◽  
Output Power ◽  
Bp Neural Network ◽  
Prediction Method ◽  
Weather Conditions ◽  
Power Prediction ◽  
Power Station ◽  
Short Term ◽  
Factors Affecting ◽  
Photovoltaic Power

Aiming to solve the problem of low precision of traditional photovoltaic power forecast method under abrupt weather conditions. In this paper, a high-precision photovoltaic power prediction method based on similarity time and LM-BP neural network is proposed. Firstly, the factors affecting the output power of photovoltaic power station are analyzed, and the short-term output power model of photovoltaic power station is established based on similar day and LM-BP neural network. Then, from the perspective of model training efficiency and prediction accuracy, the deficiencies in the short-term power prediction of photovoltaic power stations based on similar days and LM-BP algorithm are analyzed. Secondly, the prediction model of LM-BP neural network based on similar hours is established. Finally, Jiaxing photovoltaic power station is taken as an example for simulation verification. The simulation results show that the proposed method has high accuracy in predicting photovoltaic power under abrupt weather conditions.

A Power Prediction Method for Photovoltaic Power Station Based on Neutral Network Using Numerical Weather Information

2013 ◽  
Vol 724-725 ◽  
pp. 3-9 ◽  
Author(s):  
Hong Lu Zhu ◽  
Jian Xi Yao
Keyword(s):  
Neural Network ◽  
Solar Radiation ◽  
Prediction Model ◽  
Prediction Method ◽  
Weather Forecast ◽  
Power Prediction ◽  
Power Station ◽  
Numerical Weather ◽  
Photovoltaic Power ◽  
Solar Radiation Intensity

As the installed capacity of photovoltaic power station is growing, the power prediction techonology is of great important to reduce the random damage to the power system. A prediction model using neural network is proposed in the paper, the solar radiation model is adopt to ensure the accuracy of the prediction results in clear sky contions.Through the analysis of photovoltaic power station output power influence factors, the the solar radiation intensity, humidity and temperature are chosen as the input of the neural network prediction model.At the same time, in order to improve accuracy the photovoltaic power station power prediction model, the power adopt numerical weather forecast information. And the prediction model is tested by the photovoltaic power station historical operation data, and the short-term power prediction has a good performance.

scholarly journals PVsyst Software for Better Energy Efficiency of a Grid-Connected Photovoltaic Power Station

2021 ◽  
Vol 21 (2) ◽  
pp. 85-93
Keyword(s):  
Weather Station ◽  
Tracking Systems ◽  
Power Station ◽  
Solar Insolation ◽  
Power Stations ◽  
Photovoltaic Power ◽  
Solar Tracking ◽  
Orenburg Oblast ◽  
Solar Tracker

The paper presents a classification of solar tracking systems used in photovoltaic power stations (PVS) and their operating principles. A simulation model of a grid-connected 5-kW PVS has been developed in PVsyst, to which end the researchers selected PVS equipment and optimized the PV cell tilt angles. The paper further analyzes a grid-connected PVS in Orenburg Oblast in PVsyst under the following configurations: static PV cells, not tilted vs seasonally varied tilts; single-axis solar trackers with vertical and horizontal axes of rotation vs a dual-axis solar tracker. The analysis is based on solar insolation data for 2019 obtained from the research team’s HP-2000 weather station. Dual-axis solar tracker and single-axis vertical trackers are shown to have the best year-round generation, providing an increase of 13.2% and 11.5%, respectively, against the static PV cells (no change in tilt).

scholarly journals Combined Multi-Layer Feature Fusion and Edge Detection Method for Distributed Photovoltaic Power Station Identification

Energies ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 6742
Author(s):  
Yongshi Jie ◽  
Xianhua Ji ◽  
Anzhi Yue ◽  
Jingbo Chen ◽  
Yupeng Deng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Edge Detection ◽  
Semantic Segmentation ◽  
Remote Sensing Images ◽  
Power Station ◽  
Data Set ◽  
Photovoltaic Panels ◽  
Power Stations ◽  
Photovoltaic Power

Distributed photovoltaic power stations are an effective way to develop and utilize solar energy resources. Using high-resolution remote sensing images to obtain the locations, distribution, and areas of distributed photovoltaic power stations over a large region is important to energy companies, government departments, and investors. In this paper, a deep convolutional neural network was used to extract distributed photovoltaic power stations from high-resolution remote sensing images automatically, accurately, and efficiently. Based on a semantic segmentation model with an encoder-decoder structure, a gated fusion module was introduced to address the problem that small photovoltaic panels are difficult to identify. Further, to solve the problems of blurred edges in the segmentation results and that adjacent photovoltaic panels can easily be adhered, this work combines an edge detection network and a semantic segmentation network for multi-task learning to extract the boundaries of photovoltaic panels in a refined manner. Comparative experiments conducted on the Duke California Solar Array data set and a self-constructed Shanghai Distributed Photovoltaic Power Station data set show that, compared with SegNet, LinkNet, UNet, and FPN, the proposed method obtained the highest identification accuracy on both data sets, and its F1-scores reached 84.79% and 94.03%, respectively. These results indicate that effectively combining multi-layer features with a gated fusion module and introducing an edge detection network to refine the segmentation improves the accuracy of distributed photovoltaic power station identification.

A Hybrid Model of Photovoltaic Power Stations for Model Ling Tasks of Large Power Systems

2021 ◽  
Vol 69 (4) ◽  
pp. 43-49
Author(s):  
Nikolay RUBAN ◽  
◽  
Vladimir RUDNIK ◽  
Igor RAZZHIVIN ◽  
Anton KIEVEC ◽  
...  
Keyword(s):  
Power Systems ◽  
Power System ◽  
Power Station ◽  
Partial Shading ◽  
Large Power ◽  
Photovoltaic Panels ◽  
Power Stations ◽  
Photovoltaic Power ◽  
Software And Hardware ◽  
The Impact

Renewable energy sources are being actively penetrated in the global energy sector, with the main growth being achieved by new photovoltaic power stations. At the same time, the influence of photovoltaic power stations on the operation of power systems is known. This is primarily due to the inconstancy of the weather, which leads to a decrease in the output of each specific photovoltaic panel and power station as a whole. To study the effect of partial shading of photovoltaic panels on the parameters of its operation, various models of the current-voltage characteristics of photovoltaic cells are used in the world, while detailed two-diode models show the best results. The use of detailed models allows to get complete information about the processes in a variety of photovoltaic panels of a power station, as well as other elements of it, such as a voltage converter. This makes it possible to assess the impact of these processes on the external power system. However, for detailed modelling of large photovoltaic power stations as part of power systems, it is necessary to use powerful software and hardware systems. Such systems include the Hybrid real-time power system simulator. This simulator is a multiprocessor installation that provides a solution to the aggregate model of the power system through the use of three approaches to modelling: digital, analogue and physical. The article presents the results of experimental studies of software and hardware tools for modelling a photovoltaic power station, developed on the basis of a hybrid approach to modelling electric power systems.

scholarly journals The Photovoltaic Output Prediction Based on Variational Mode Decomposition and Maximum Relevance Minimum Redundancy

2019 ◽  
Vol 9 (17) ◽  
pp. 3593 ◽  
Author(s):  
Peidong Du ◽  
Gang Zhang ◽  
Pingli Li ◽  
Meng Li ◽  
Hongchi Liu ◽  
...  
Keyword(s):  
Prediction Accuracy ◽  
Prediction Method ◽  
Great Difficulty ◽  
Variational Mode Decomposition ◽  
Power Station ◽  
Output Sequence ◽  
Photovoltaic Power ◽  
Mode Decomposition ◽  
Modal Component ◽  
Different Characteristics

Photovoltaic output is affected by solar irradiance, ambient temperature, instantaneous cloud cluster, etc., and the output sequence shows obvious intermittent and random features, which creates great difficulty for photovoltaic output prediction. Aiming at the problem of low predictability of photovoltaic power generation, a combined photovoltaic output prediction method based on variational mode decomposition (VMD), maximum relevance minimum redundancy (mRMR) and deep belief network (DBN) is proposed. The method uses VMD to decompose the photovoltaic output sequence into modal components of different characteristics, and determines the main characteristic factors of each modal component by mRMR, and the DBN model is used to fit the modal components and the corresponding characteristic factors, then the predicted results of each modal component is superimposed to obtain the predicted value of the photovoltaic output. By using the data of a certain photovoltaic power station in Yunnan for comparative experiments, it is found that the model proposed in this paper improves the prediction accuracy of photovoltaic output.

Sign in / Sign up

Export Citation Format

Share Document