Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Distributed photovoltaic power station ultra-short-term power prediction method and system based on multiple tasks

A technology of distributed photovoltaic and photovoltaic power generation, which is applied in forecasting, neural learning methods, information technology support systems, etc., can solve the problems of a single photovoltaic power station, does not consider the correlation of photovoltaic power plants, and low efficiency of photovoltaic power plants, and achieves the goal of overcoming Inefficiency, the effect of improving accuracy

Inactive Publication Date: 2021-06-29
CHINA ELECTRIC POWER RES INST +1
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main problem of ultra-short-term photovoltaic power forecasting is that previous studies often only predict a single photovoltaic power station, without taking into account the correlation between multiple photovoltaic power stations in the region, and when predicting multiple photovoltaic power stations in the region low efficiency

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
  • Distributed photovoltaic power station ultra-short-term power prediction method and system based on multiple tasks
  • Distributed photovoltaic power station ultra-short-term power prediction method and system based on multiple tasks
  • Distributed photovoltaic power station ultra-short-term power prediction method and system based on multiple tasks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Since photovoltaic power generation has a strong correlation with light conditions, and the time of cloud movement is relatively lagging, comprehensive utilization of power generation data of multiple photovoltaic power plants can effectively improve prediction accuracy.

[0040] Based on this, in one or more implementations, a method for ultra-short-term power prediction of distributed photovoltaic power plants based on multi-task is disclosed, refer to figure 1 , including the following steps:

[0041] (1) Obtain T photovoltaic power generation data before the time to be predicted and the data of influencing factors at the time to be predicted; T is a natural number;

[0042] Influencing factors closely related to photovoltaic power generation considered in this embodiment include temperature, relative humidity, global horizontal radiation, diffuse horizontal radiation, wind direction and daily rainfall.

[0043] (2) Input the obtained data into the trained multi-tas...

Embodiment 2

[0071] In one or more embodiments, a multi-task-based ultra-short-term power prediction system for distributed photovoltaic power plants is disclosed, including:

[0072] The data acquisition module is used to obtain T photovoltaic power generation data before the time to be predicted and the data of influencing factors at the time to be predicted; T is a natural number;

[0073] The photovoltaic power generation power prediction module is used to input the obtained data into the trained multi-task learning neural network model to obtain the photovoltaic power generation power prediction data of multiple distributed photovoltaic power plants in the area at the moment to be predicted;

[0074] Wherein, the multi-task learning neural network model adopts a hard parameter sharing method, including two hard parameter sharing layers and a sub-task layer.

[0075] It should be noted that the specific implementation manners of the above modules have been described in the first embodi...

Embodiment 3

[0077] In some embodiments, an electronic device is disclosed, including a memory, a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, a method disclosed in Embodiment 1 is completed. The steps described in a multi-task-based ultra-short-term power forecasting method for distributed photovoltaic power plants.

[0078] In some other embodiments, a computer-readable storage medium is disclosed, which is used to store computer instructions. When the computer instructions are executed by a processor, the multi-task-based distributed photovoltaic power plant disclosed in Embodiment 1 is completed. The steps described in the ultra-short-term power forecasting method.

[0079] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the fo...

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

No PUM Login to View More

Abstract

The invention discloses a distributed photovoltaic power station ultra-short-term power prediction method and system based on multiple tasks, and the method comprises the steps: obtaining T pieces of photovoltaic power generation power data before a to-be-predicted moment and influence factor data at the to-be-predicted moment, and carrying out the normalization; inputting the obtained data into a trained multi-task learning neural network model to obtain photovoltaic power generation power prediction data of a plurality of distributed photovoltaic power stations in the region at a to-be-predicted moment, wherein the multi-task learning neural network model adopts a hard parameter sharing mode, and comprises two hard parameter sharing layers and a sub-task layer. The constructed multi-task learning network can realize multi-input and multi-output, overcomes the problem of low efficiency during prediction of the generated power of a plurality of photovoltaic power stations in a region, can realize prediction of the generated power of the plurality of photovoltaic power stations at the same time, and improves the precision of ultra-short-term photovoltaic generated power prediction.

Description

technical field [0001] The invention relates to the technical field of intelligent power distribution / utilization, in particular to a multi-task-based ultra-short-term power prediction method and system for distributed photovoltaic power plants. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] As one of the main renewable energy sources, distributed photovoltaic has the advantages of cleanness, safety and reliability, and has developed rapidly in recent years. However, the randomness and fluctuation of photovoltaic power generation also bring challenges to the stable operation of the power grid. Prediction of photovoltaic power generation will help the dispatching department to adjust the dispatch plan in time, thereby reducing the negative impact of photovoltaic grid connection on the system. Therefore, accurate and fast photovoltaic powe...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/06G06N3/04G06N3/08
CPCG06Q10/04G06Q50/06G06N3/08G06N3/044Y04S10/50
Inventor 王勃张菲徐航
Owner CHINA ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products