Photovoltaic interval prediction method and system based on self-coding and extreme learning machine
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of extreme learning machine and prediction method, which is applied in prediction, system integration technology, information technology support system, etc. to achieve the effect of improving solution performance, ensuring accuracy, and reducing overfitting.
Inactive Publication Date: 2019-07-26
ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY +2
View PDF6 Cites 8 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, solar photovoltaic power generation is affected by the intensity of solar radiation, and its output has strong randomness and intermittency. After a large number of photovoltaics are connected
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0048] This embodiment provides a photovoltaic interval prediction method based on self-encoding and extreme learning machine. The interval prediction method includes the following steps:
[0049] Step 1), preprocess the historical data of photovoltaic output;
[0050] Step 2) Obtain the initial value of the photovoltaic prediction interval based on linear regression interval estimation;
[0051] Step 3), using self-encoding technology to initialize the input weight matrix of the dual-output extreme learning machine;
[0052] Step 4), establish a photovoltaic interval prediction model based on the dual-output extreme learning machine, and use the PSO heuristic algorithm to optimize and train the photovoltaic interval prediction model for the interval initial values and input weight matrix obtained in steps 2) and 3).
[0053] The accuracy metrics for the PV forecast interval include the average forecast interval width PI mean , Prediction interval coverage rate PICP and comprehensive ...
Embodiment 2
[0077] This embodiment provides a photovoltaic interval prediction system based on self-encoding and extreme learning machine, which includes:
[0078] Data preprocessing unit: preprocess historical data of photovoltaic output;
[0079] The unit for obtaining the initial value of the photovoltaic prediction interval: based on the linear regression interval estimation, obtain the initial value of the photovoltaic prediction interval;
[0080] Input weight matrix initialization unit: use self-encoding technology to initialize the input weight matrix of the dual-output extreme learning machine;
[0081] Prediction model establishment unit: establish a photovoltaic interval prediction model based on dual-output extreme learning machine;
[0082] Prediction model optimization training unit: According to the interval initial value and input weight matrix obtained by the foregoing unit, the PSO heuristic algorithm is used to optimize the training of the photovoltaic interval prediction model. ...
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 discloses a photovoltaic interval prediction method and system based on self-coding and an extreme learning machine. A dual-output extreme learning machine model is used for constructinga photovoltaic interval prediction model, dual outputs are the upper limit and the lower limit of a photovoltaic interval respectively, and due to lack of actual values of the photovoltaic interval,a traditional extreme learning machine training algorithm fails accordingly. According to the method, a heuristic algorithm is adopted to optimize a training extreme learning machine, a correspondinginitialization algorithm is provided for improving the calculation result and efficiency of the heuristic algorithm, and the method comprises: carrying out prediction interval initialization based onlinear regression interval estimation; carrying out inputting weight matrix initialization of an extreme learning machine based on self-coding; and carrying out optimization training of a particle swarm-based double-output extreme learning machine. The photovoltaic prediction interval obtained through the model replaces a traditional photovoltaic point prediction value, and more sufficient information can be provided for day-ahead robust scheduling and intra-day economic scheduling of a power system.
Description
Technical field [0001] The invention belongs to the field of distribution network scheduling optimization, and specifically is a photovoltaic interval prediction method and system based on a self-encoding and extreme learning machine. Background technique [0002] As a clean, renewable, and huge new energy source, solar photovoltaic power generation is gradually gaining popularity after wind power. However, solar photovoltaic power generation is affected by the intensity of solar radiation, and its output is highly random and intermittent. After a large number of photovoltaics are connected to the distribution network as distributed power sources, the peak regulation, frequency modulation, backup, power flow, and bus voltage of the grid Etc. have a greater impact. [0003] The interval forecast of photovoltaic power generation output is the basis for power system dispatch. Through accurate photovoltaic interval prediction, sufficient photovoltaic output forecast information can b...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more
IPC IPC(8): G06Q10/04G06Q50/06G06N3/00
CPCG06N3/006G06Q10/04G06Q50/06Y02E40/70Y04S10/50
Inventor 李鹏张雪松龙寰汪科葛晓慧马瑜涵
Owner ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY
Login to view more 
Login to view more