Method for predicting optical power of centralized photovoltaic power station

Abstract

The invention discloses a centralized photovoltaic power station optical power prediction method. The method comprises the following steps: S1, data acquisition and processing; s2, predicting optical power; s3, error feedback; and S4, continuously monitoring and optimizing. According to the optical power prediction method, the prediction precision can be effectively improved and errors can be reduced by constructing the optical power prediction model and combining the data collected in real time, and the photovoltaic power station can be kept in the optimal operation state for a long time through a feedback mechanism which is adjusted in real time and continuously optimized; and power grid load fluctuation and equipment loss caused by prediction errors are avoided. And meanwhile, the system has intelligent, self-adaptive and self-optimization functions, so that the system can stably and efficiently operate under various environmental conditions, and the economic benefit and the energy utilization efficiency of the photovoltaic power station are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to a method for predicting optical power of a centralized photovoltaic power station. Background Art

[0002] As the world's attention to renewable energy continues to increase, photovoltaic power generation has been widely used as a clean and environmentally friendly form of energy. In modern centralized photovoltaic power stations, how to accurately predict the optical power output has become a key issue in improving the efficiency and economy of photovoltaic power stations. The power output of photovoltaic power stations is affected by many factors, including environmental conditions such as light intensity, temperature, humidity, wind speed, cloud density, and the status and performance of photovoltaic modules. Therefore, accurate optical power prediction can not only help power stations optimize operation and reduce maintenance costs, but also provide accurate load prediction for power grid dispatching, improving the stability and reliability of the power grid.

[0003] At present, researchers mainly focus on model construction based on weather forecast data, historical power generation data and environmental sensor data for photovoltaic power station optical power prediction methods. However, most existing prediction methods rely on static models that are trained once. When the environment changes or the state of photovoltaic components changes, their prediction accuracy is prone to decrease, especially under climate conditions with large dynamic changes. In addition, the gap between the prediction error and the actual optical power output may cause grid scheduling errors, affecting the operating efficiency and stability of the grid. Therefore, its prediction method needs to be improved. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a method for predicting optical power of a centralized photovoltaic power station, comprising:

[0007] S1. Data collection and processing: collect data in real time through sensors; standardize the collected data;

[0008] S2. Optical power prediction: The optical power output in the future is predicted by the optical power prediction model;

[0009] S3, error feedback: after the prediction is completed, the error between the real-time optical power and the predicted value is calculated, and the model parameters are adjusted according to the error feedback. The adjustment of the model parameters is calculated and adjusted according to the corresponding adjustment formula;

[0010] S4. Continuous monitoring and optimization: Continuously monitor the prediction results of the model, record the difference between the predicted power and the actual success rate, and perform periodic model optimization.

[0011] As a preferred solution of the optical power prediction method of a centralized photovoltaic power station described in the present invention, the optical power prediction model algorithm is as follows:

[0012]

[0013] Where: A(t) is the impact of weather factors and component status at time t; B(t) is the weighted impact of historical optical power data; C(t) is the normalized adjustment term, which takes into account the weighted effects of weather and component status; It is a correction term used to correct other influencing factors in the model.

[0014] As a preferred solution of the method for predicting the optical power of a centralized photovoltaic power station described in the present invention, the specific algorithm of A(t) is as follows:

[0015]

[0016] Where: W(τ) is the weather factor at time τ; S(τ) is the state of the photovoltaic module at time τ; α is the attenuation factor.

[0017] As a preferred solution of the optical power prediction method of a centralized photovoltaic power station described in the present invention, the specific algorithm of B(t) is as follows:

[0018]

[0019] Where: β i is the weighting coefficient of historical optical power data; H(t-Δt i ) is the time t-Δt i The historical optical power data at the time of ; N is the number of historical data points considered.

[0020] As a preferred solution of the optical power prediction method of a centralized photovoltaic power station described in the present invention, the specific algorithm of C(t) is as follows:

[0021]

[0022] Where: i is the weighting coefficient of weather factors; γ is the weighting coefficient of the PV module status.

[0023] As a preferred solution of the optical power prediction method of a centralized photovoltaic power station described in the present invention, the error calculation formula between the real-time optical power and the predicted value is as follows:

[0024] ε(t)=P actual (t)-P pred (t)

[0025] Where: ε(t) is the error value; P actual (t) is the actual power.

[0026] As a preferred solution of the method for predicting the optical power of a centralized photovoltaic power station described in the present invention, the adjustment formula is as follows:

[0027]

[0028] Among them: α(t) is the decay factor at the current moment; η is the learning rate; β i (t) is the weighting coefficient of historical data; γ(t) is the weighting coefficient of the PV module status.

[0029] In a second aspect, an embodiment of the present invention further provides a centralized photovoltaic power station optical power prediction system, comprising:

[0030] Data acquisition preprocessing module: including data acquisition unit: collects environmental and photovoltaic system status data in real time through sensors installed at different locations of the photovoltaic power station; data processing unit: standardizes the collected data;

[0031] Optical power prediction model module: including an optical power prediction unit: predicting the optical power output in a future period of time through a prediction model;

[0032] Error feedback and parameter adjustment module: including error detection unit: comparing the error between actual optical power and predicted optical power; feedback mechanism unit: adjusting the prediction model parameters when the error exceeds a certain range;

[0033] Continuous monitoring and optimization module: including model monitoring unit: real-time monitoring of the error between the prediction results of the optical power prediction model and the actual optical power output, and evaluation of the accuracy of the model; model optimization unit: regular automatic model optimization, retraining the model or adjusting parameters to improve prediction accuracy.

[0034] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of a centralized photovoltaic power station optical power prediction method as described in the first aspect of the present invention is implemented.

[0035] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of a centralized photovoltaic power station optical power prediction method as described in the first aspect of the present invention is implemented.

[0036] Beneficial effects of the present invention:

[0037] The optical power prediction method of the present invention can not only effectively improve the prediction accuracy and reduce the error by constructing an optical power prediction model and combining the real-time collected data, but also can enable the photovoltaic power station to maintain the best operating state for a long time through real-time adjustment and continuous optimization feedback mechanism, avoiding grid load fluctuations and equipment losses caused by prediction errors. At the same time, the system has intelligent, adaptive and self-optimization functions, so that it can operate stably and efficiently under various environmental conditions, improving the economic benefits and energy utilization efficiency of the photovoltaic power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0039] Figure 1 A method flow chart of a centralized photovoltaic power station optical power prediction method proposed by the present invention;

[0040] Figure 2 This is a system architecture diagram of a centralized photovoltaic power station optical power prediction system proposed by the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] Reference Figure 1-2 The present invention provides a method for predicting the optical power of a centralized photovoltaic power station, comprising:

[0045] S1. Data collection and processing: collect data in real time through sensors, including temperature, humidity, radiation intensity and cloud density, etc.; standardize the collected data;

[0046] S2. Optical power prediction: The optical power output in the future is predicted by the optical power prediction model;

[0047] S3, error feedback: after the prediction is completed, the error between the real-time optical power and the predicted value is calculated, and the model parameters are adjusted according to the error feedback. The adjustment of the model parameters is calculated and adjusted according to the corresponding adjustment formula;

[0048] S4. Continuous monitoring and optimization: Continuously monitor the prediction results of the model, record the difference between the predicted power and the actual success rate, and perform periodic model optimization.

[0049] The optical power prediction model algorithm is as follows:

[0050]

[0051] Where: A(t) is the impact of weather factors and component status at time t; B(t) is the weighted impact of historical optical power data; C(t) is the normalized adjustment term, which takes into account the weighted effects of weather and component status; This algorithm helps photovoltaic power plants to accurately predict the optical power according to the actual environment and operating conditions.

[0052] Furthermore, the specific algorithm of A(t) is as follows:

[0053]

[0054] Where: W(τ) is the weather factor at time τ; S(τ) is the state of the photovoltaic module at time τ; α is the attenuation factor, considering that the influence of weather and modules decays over time. (The integral term represents the cumulative effect of weather and module status from the past to the current moment.

[0055] Furthermore, the specific algorithm of B(t) is as follows:

[0056]

[0057] Where: β i is the weighting coefficient of historical optical power data, which indicates the influence weight of historical data at different time points on the current prediction; H(t-Δt i ) is the time t-Δti The historical optical power data at the time of

[0058] Furthermore, the specific algorithm of C(t) is as follows:

[0059]

[0060] Where: i is the weighted coefficient of weather factors, which indicates the impact of weather data at different time points on the current forecast; γ is the weighted coefficient of the PV module status, which indicates the impact of the module health status on the forecast

[0061] Furthermore, the error calculation formula between the real-time optical power and the predicted value is as follows:

[0062] ε(t)=P actual (t)-P pred (t)

[0063] Where: ε(t) is the error value; P actual (t) is the actual power. (When the error value is greater than the preset threshold, the feedback mechanism is activated to adjust the parameters

[0064] Furthermore, the adjustment formula is as follows:

[0065]

[0066] Where: α(t) is the attenuation factor at the current moment; η is the learning rate, which is used to control the speed of adjustment and determines the amplitude of model parameter update. When the learning rate is large, the update is faster, but it may be unstable; when it is small, the update is smoother, but the convergence is slower; β i (t) is the weighting coefficient of historical data; γ(t) is the weighting coefficient of the PV module status

[0067] This embodiment also provides a centralized photovoltaic power station optical power prediction system, including:

[0068] Data acquisition preprocessing module: including data acquisition unit: collects environmental and photovoltaic system status data in real time through sensors installed at different locations of the photovoltaic power station; data processing unit: standardizes the collected data;

[0069] Optical power prediction model module: including an optical power prediction unit: predicting the optical power output in a future period of time through a prediction model;

[0070] Error feedback and parameter adjustment module: including error detection unit: comparing the error between actual optical power and predicted optical power; feedback mechanism unit: adjusting the prediction model parameters when the error exceeds a certain range;

[0071] Continuous monitoring and optimization module: including model monitoring unit: real-time monitoring of the error between the prediction results of the optical power prediction model and the actual optical power output, and evaluation of the accuracy of the model; model optimization unit: regular automatic model optimization, retraining the model or adjusting parameters to improve the prediction accuracy

[0072] This embodiment also provides a computer device, which is applicable to a method for predicting optical power of a centralized photovoltaic power station, and includes: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a method for predicting optical power of a centralized photovoltaic power station as proposed in the above embodiment.

[0073] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0074] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a method for predicting the optical power of a centralized photovoltaic power station as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0075] In summary, the optical power prediction method of the present invention can not only effectively improve the prediction accuracy and reduce the error by constructing an optical power prediction model and combining the real-time collected data, but also can enable the photovoltaic power station to maintain the best operating state for a long time through real-time adjustment and continuous optimization feedback mechanism, avoiding grid load fluctuations and equipment losses caused by prediction errors. At the same time, the system has intelligent, adaptive and self-optimization functions, so that it can operate stably and efficiently under various environmental conditions, improving the economic benefits and energy efficiency of the photovoltaic power station.

[0076] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for predicting the optical power of a centralized photovoltaic power station, characterized in that: include: S1. Data collection and processing: collect data in real time through sensors; standardize the collected data; S2. Optical power prediction: The optical power output in the future is predicted by the optical power prediction model; S3, error feedback: after the prediction is completed, the error between the real-time optical power and the predicted value is calculated, and the model parameters are adjusted according to the error feedback. The adjustment of the model parameters is calculated and adjusted according to the corresponding adjustment formula; S4. Continuous monitoring and optimization: Continuously monitor the prediction results of the model, record the difference between the predicted power and the actual success rate, and perform periodic model optimization.

2. The method for predicting optical power of a centralized photovoltaic power station according to claim 1, characterized in that: The optical power prediction model algorithm is as follows: Where: A(t) is the impact of weather factors and component status at time t; B(t) is the weighted impact of historical optical power data; C(t) is the normalized adjustment term, which takes into account the weighted effects of weather and component status; It is a correction term used to correct other influencing factors in the model.

3. The method for predicting optical power of a centralized photovoltaic power station according to claim 2, characterized in that: The specific algorithm of A(t) is as follows: Where: W(τ) is the weather factor at time τ; S(τ) is the state of the photovoltaic module at time τ; α is the attenuation factor.

4. The method for predicting optical power of a centralized photovoltaic power station according to claim 3, characterized in that: The specific algorithm of B(t) is as follows: Where: β i is the weighting coefficient of historical optical power data; H(t-Δt i ) is the time t-Δt i The historical optical power data at the time of ; N is the number of historical data points considered.

5. The method for predicting optical power of a centralized photovoltaic power station according to claim 4, characterized in that: The specific algorithm of C(t) is as follows: Where: i is the weighting coefficient of weather factors; γ is the weighting coefficient of the PV module status.

6. A method for predicting optical power of a centralized photovoltaic power station according to claim 5, characterized in that: The error calculation formula between the real-time optical power and the predicted value is as follows: ε(t)=P actual (t)-P pred (t) Where: ε(t) is the error value; P actual (t) is the actual power.

7. A method for predicting optical power of a centralized photovoltaic power station according to claim 6, characterized in that: The adjustment formula is as follows: Among them: α(t) is the decay factor at the current moment; η is the learning rate; β i (t) is the weighting coefficient of historical data; γ(t) is the weighting coefficient of the PV module status.

8. A centralized photovoltaic power station optical power prediction system, based on a centralized photovoltaic power station optical power prediction method according to any one of claims 1 to 7, characterized in that: include: Data acquisition preprocessing module: including data acquisition unit: real-time collection of environmental and photovoltaic system status data through sensors installed at different locations of the photovoltaic power station; Data processing unit: standardize the collected data; Optical power prediction model module: including an optical power prediction unit: predicting the optical power output in a future period of time through a prediction model; Error feedback and parameter adjustment module: including error detection unit: comparing the error between actual optical power and predicted optical power; feedback mechanism unit: adjusting the prediction model parameters when the error exceeds a certain range; Continuous monitoring and optimization module: including model monitoring unit: real-time monitoring of the error between the prediction results of the optical power prediction model and the actual optical power output, and evaluation of the accuracy of the model; model optimization unit: regular automatic model optimization, retraining the model or adjusting parameters to improve prediction accuracy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a centralized photovoltaic power station optical power prediction method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for predicting optical power of a centralized photovoltaic power station as described in any one of claims 1 to 7 are implemented.

Images