BP neural network photovoltaic power generation system power prediction method based on similar day

A technology of BP neural network and photovoltaic power generation system, which is used in forecasting, data processing applications, instruments, etc., and can solve problems such as reduced forecasting accuracy and failure of forecasting models.

CN105631558AInactive Publication Date: 2016-06-01STATE GRID CORP OF CHINA +5
3 Cites 41 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2016-06-01
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a BP neural network photovoltaic power generation system power prediction method based on a similar day. After quantization coding of weather influence factors, a historical day, which has higher similarity with a prediction day, is selected according to a similar day selection principle; through power generation data and weather data of the similar historical day, and with meteorological data of the prediction day being combined, a training sample set is formed to carry out training on a BP neural network; and during training, a weight adjustment algorithm adopts a gradient correction method with additional momentum and variable learning rate being combined, thereby improving model convergence speed, reducing the probability that a model falls into locally optimal solution and ensuring prediction model precision and stability.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a similar day-based BP neural network power prediction method for a photovoltaic power generation system, which belongs to the technical field of photovoltaic power generation. Background technique

[0002] Energy is the foundation of modern social economy and development. The successive emergence of energy and environmental problems has prompted human beings to gradually realize the serious harm brought about by the excessive exploitation and unrestrained use of fossil fuels. Photovoltaic power generation has received widespread attention and rapid development due to its renewable, environmentally friendly and flexible characteristics. However, since the output of the photovoltaic power generation system is affected by the intensity of solar radiation and many weather factors, the change of its power generation is a non-stationary random process, and it is an uncontrollable source for the large power grid. Impact on the powe...

Examples

Embodiment Construction

[0054] like figure 1 Shown, is flow chart of the present invention, specifically comprises the following steps:

[0055] Step 1: Select meteorological influencing factors and code the weather type: According to the photovoltaic power generation power function, select solar radiation intensity and temperature as the influencing factors of photovoltaic power generation, use statistical laws to quantify the influence of weather factors, and numerically code the weather type, specifically as follows:

[0056] Photovoltaic system generating power per unit area P s Calculation formula:

[0057] P s =ηSI(1-0.005(T 0 +25))

[0058] In the formula, I is the light intensity, the unit is kW / m 2 ; η is the photovoltaic cell conversion efficiency; T 0 is the ambient temperature in °C; S is the area of ​​the photovoltaic array in m 2 .

[0059] The historical power generation data already includes parameters such as array conversion efficiency η and array area S, but solar radiatio...