Photovoltaic power generation short-term power prediction method
A technology of power prediction and photovoltaic power generation, applied in prediction, neural learning methods, instruments, etc., can solve problems such as premature convergence, local optimization of particle swarm optimization algorithm, and failure to search for optimal solutions, etc., to overcome premature and realize Accuracy, the effect of avoiding the decline of particle search ability
Active Publication Date: 2021-02-05
HEBEI UNIV OF TECH
View PDF7 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Therefore, it is particularly important to choose an appropriate optimization method to optimize the neural network. Based on this, the literature "Zhang Jiawei, Zhang Zijia. Short-term photovoltaic system power generation prediction based on PSO-BP neural network [J]. Renewable Energy, 2012, 30(8 ):28-32.》Using the particle swarm optimization algorithm to optimize the BP neural network, although the result is more accurate, but the particle swarm optimization algorithm is easy to fall into the problem of local optimum and premature convergence, and may not be able to search for the optimal solution
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0087] Step 1: Obtain the historical data of the photovoltaic power station for the past two years. The historical data refers to meteorological factors, including irradiance, temperature, wind speed, humidity, and air pressure. The collection period is 10 minutes. Apply mutual information to extract the main influencing factors, such as formula (1);
[0088]
[0089] In the formula, p(x) and p(y) are the marginal probability density functions of two random variables x and y respectively, p(x, y) is the joint probability density function of x and y; I(x, y) is The mutual information value can be understood as the contribution to reducing the uncertainty of x after knowing y. The stronger the correlation between the two variables, the greater the mutual information value; if the two variables are independent of each other, the mutual information value is 0.
[0090] This embodiment assumes that each meteorological factor variable X i =(i=1,2,3,4,5) represent irradiance, tem...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a photovoltaic power generation short-term power prediction method, which comprises the following steps: obtaining historical data of a photovoltaic power station including various meteorological information influence factors, extracting corresponding main influence factors with mutual information values greater than 0.7 by applying mutual information, and forming trainingand testing data samples by using the extracted main influence factors; building an Elman neural network, initializing network parameters, using samples as input of the neural network, wherein the input vector dimension of the neural network is consistent with the number of the extracted main influence factors; and optimizing a connection weight of a network structure unit of the neural network by using an improved hybrid particle swarm tabu search hybrid algorithm, and inputting main influence factors of mutual information extraction into the optimized Elman neural network for final prediction to obtain photovoltaic power generation power. According to the method, the problem of easy prematurity is effectively solved, local convergence and reduction of particle search capability are avoided, falling into local optimum is prevented, and the accuracy of photovoltaic prediction is integrally realized.
Description
technical field [0001] The invention belongs to the field of photovoltaic power generation and specifically designs a short-term power prediction method for photovoltaic power generation. According to historical photovoltaic data, the power of photovoltaic power plants in the next few hours is accurately predicted by using an improved hybrid particle swarm-taboo search hybrid algorithm. Background technique [0002] Photovoltaic power generation has become an important part of China's energy system today. Today, photovoltaic power generation technology is mature enough. Accurate prediction of photovoltaic power is an important basis for grid security scheduling, and is of great significance to grid security scheduling. [0003] The power of photovoltaic power generation is affected by many factors and has instability and volatility. Therefore, it is difficult to predict photovoltaic power. For the prediction of photovoltaic power, traditional intelligent methods have the prob...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q50/06G06Q10/04G06N3/08G06N3/02G06N3/00
CPCG06Q50/06G06Q10/04G06N3/006G06N3/086G06N3/02
Inventor 张家安郝峰姜皓龄郭翔宇
Owner HEBEI UNIV OF TECH