Self-adaptive solar photovoltaic power station grid-connected control method and system

Abstract

The invention relates to the technical field of solar photovoltaic power stations, in particular to a self-adaptive solar photovoltaic power station grid-connected control method and system, and the method comprises the steps: obtaining the weather forecast data of a first region, and the historical power generation data and real-time power generation data of a photovoltaic power station; training an output power prediction model based on the weather forecast data and the historical power generation data, and dynamically updating the output power prediction model by using the real-time power generation data; predicting future photovoltaic power generation output power in real time through the updated output power prediction model to obtain predicted photovoltaic power generation output power; analyzing the predicted photovoltaic power generation output power in combination with the load demand of the current power grid to obtain a current fluctuation trend and a load change trend; the current fluctuation state is judged through the load state and the current fluctuation state, and fault current is obtained; and based on the predicted photovoltaic power generation output power and the current fluctuation trend, constructing a fault current compensation model to dynamically compensate the fault current, and adjusting the fault current detection strategy of the relay protection device.

Description

Technical Field

[0001] The present invention relates to the technical field of solar photovoltaic power station, and in particular to an adaptive solar photovoltaic power station grid-connected control method and system. Background Art

[0002] With the growth of global energy demand and the development of renewable energy technology, solar photovoltaic power generation, as a clean and sustainable form of energy, is gradually becoming an important part of the power system. However, the access of large-scale photovoltaic power stations to the distribution network will have a certain impact on the operation of traditional power grids, especially under low-load or half-load operation, which may cause a series of technical problems. In the process of photovoltaic power generation grid connection, due to the intermittent and volatile nature of photovoltaic power generation, its output power will be significantly affected by weather changes. This volatility will cause significant changes in the current level of the power grid, especially under low-load conditions, the current level may drop significantly, making it impossible for the relay protection device to accurately detect the fault current, thereby affecting the safe operation of the power grid.

[0003] However, under low load or abnormal current fluctuation conditions, the existing fault current compensation model is difficult to respond to photovoltaic power generation fluctuations and current level changes in real time, and cannot effectively compensate for the errors in the fault current detection process. Therefore, there is an urgent need for a fault current detection method to accurately and efficiently detect fault currents under low load or abnormal current fluctuation conditions.

[0004] Therefore, an adaptive solar photovoltaic power station grid-connected control method and system are proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an adaptive solar photovoltaic power station grid-connected control method and system, which is suitable for accurate detection of fault current under low load or abnormal current fluctuation state. The method includes: obtaining weather forecast data of the first area, historical power generation data and real-time power generation data of the photovoltaic power station; training an output power prediction model based on weather forecast data and historical power generation data, and dynamically updating it using real-time power generation data; predicting the future photovoltaic power generation output power in real time through the updated output power prediction model to obtain the predicted photovoltaic power generation output power; analyzing the predicted photovoltaic power generation output power in combination with the current load demand of the power grid to obtain the current fluctuation trend and load change trend; determining the fault current through the load state and current fluctuation state; constructing a fault current compensation model based on the predicted photovoltaic power generation output power and current fluctuation trend to dynamically compensate for the fault current, and adjusting the fault current detection strategy of the relay protection device.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An adaptive solar photovoltaic power station grid-connected control method, comprising:

[0008] Obtain weather forecast data for the first area and historical power generation data of the photovoltaic power station; collect real-time power generation data of the photovoltaic power station through intelligent sensors;

[0009] Training an output power prediction model based on the weather forecast data and the historical power generation data; dynamically updating the output power prediction model using the real-time power generation data to obtain the updated output power prediction model; and predicting the future photovoltaic power generation output power in real time using the updated output power prediction model to obtain the predicted photovoltaic power generation output power;

[0010] In combination with the load demand of the current power grid, the predicted photovoltaic power generation output power is analyzed to obtain the current fluctuation trend and the load change trend;

[0011] The current fluctuation state is determined by the load change trend, the predicted photovoltaic power generation output power and the current fluctuation trend; the specific determination process is as follows:

[0012] The load state is determined according to the load change trend; if the load state is a low load and / or half load state, and the predicted photovoltaic power generation output power is higher than the expected output power, whether the current fluctuation state is an abnormal fluctuation state is detected according to the current fluctuation trend; if the current fluctuation state is the abnormal fluctuation state, it is determined to be a fault current;

[0013] Based on the predicted photovoltaic power generation output power and the current fluctuation trend, a fault current compensation model is constructed to dynamically compensate for the fault current, and the fault current detection strategy of the relay protection device is adjusted according to expert experience.

[0014] Preferably, the weather forecast data includes: temperature, humidity, solar radiation intensity, wind speed and cloud coverage of the first area;

[0015] The historical power generation data includes: historical output power data, historical current, historical voltage and historical environmental data of the photovoltaic power station within the specified time period that is the same as the weather forecast data;

[0016] The real-time power generation data includes: real-time output power, real-time grid load, real-time current and real-time voltage at the current time point.

[0017] Preferably, the output power prediction model comprises: a data preprocessing unit, a weather forecast data analysis unit and a photovoltaic power generation output power initial prediction unit;

[0018] The data preprocessing unit detects and removes abnormal values ​​in the weather forecast data and the historical power generation data by statistical analysis; aligns the weather forecast data and the historical power generation data in time series;

[0019] The weather forecast data analysis unit extracts features related to photovoltaic power generation output power from the weather forecast data to obtain weather features; the weather features include: cumulative solar radiation intensity, daily average temperature over the past N days, daily average cloud coverage and daily average humidity;

[0020] The photovoltaic power generation output power initial prediction unit predicts the photovoltaic power generation data power according to the weather characteristics and the historical power generation data through the LSTM model to obtain the initial predicted photovoltaic power generation output power.

[0021] Preferably, the output power prediction model is dynamically updated using the real-time power generation data to obtain the updated output power prediction model; the future photovoltaic power generation output power is predicted in real time using the updated output power prediction model to obtain the predicted photovoltaic power generation output power; the specific process includes:

[0022] Calculating a power generation error by comparing the real-time output power in the real-time power generation data with the initial predicted photovoltaic power generation output power;

[0023] The output power prediction model is updated using a sliding window method according to the power generation error; the updating frequency is once every two hours;

[0024] The updated output power prediction model calculates the future photovoltaic power generation output power in real time according to the weather forecast data at the current time point and the future time period to obtain the predicted photovoltaic power generation output power.

[0025] Preferably, the specific process of judging the load state according to the load change trend is: calculate the load deviation based on the current load demand of the power grid and the historical load average; perform a first-order differential on the load change trend to obtain the load change rate; and set a load state threshold to judge the load state according to the load deviation and the load change rate.

[0026] Preferably, the specific process of detecting whether the current fluctuation is in an abnormal fluctuation state according to the current fluctuation trend is: obtaining the real-time current fluctuation amplitude mean value by calculating the real-time current in the real-time power generation data; obtaining the historical current fluctuation amplitude mean value by calculating the historical current; determining whether the current fluctuation exceeds a preset normal range by comparing the real-time current fluctuation amplitude mean value with the historical current fluctuation amplitude mean value; if the current fluctuation exceeds the preset normal range, it is determined to be an abnormal fluctuation state.

[0027] Preferably, the fault current compensation model comprises: a fault current data input layer, a dynamic compensation layer and a relay protection strategy adjustment layer;

[0028] The fault current data input layer inputs the predicted photovoltaic power generation output power, the current fluctuation trend and the current deviation into the fault current compensation model; wherein the current deviation is obtained by calculating the difference between the real-time current and the predicted current;

[0029] The dynamic compensation layer calculates the fault current compensation amount according to the predicted photovoltaic power generation output power, the current fluctuation trend and the current deviation;

[0030] The relay protection strategy adjustment layer adjusts the sensitivity of the relay protection device and the fault current detection threshold according to the fault current compensation amount.

[0031] Preferably, the calculation formula of the fault current compensation amount is:

[0032] △I=k 1 f(P)+k 2 △I volatility +k 3 △I offset ;

[0033]

[0034] Where △I is the fault current compensation amount; k 1 is the output power difference equivalent current compensation coefficient; f(P) is the function of converting the output power difference into an equivalent circuit; P is the output power difference; k 2 is the current fluctuation amplitude compensation coefficient; △I volatility is the current fluctuation amplitude; k 3 is the current deviation compensation coefficient; △I offset is the current deviation; P forecast To predict the output power of photovoltaic power generation; P actual is the real-time photovoltaic power output power; V actual is the real-time voltage; α is the real-time voltage adjustment coefficient; I actual The real-time current.

[0035] An adaptive solar photovoltaic power station grid-connected control system, comprising:

[0036] A data acquisition module is used to acquire weather forecast data of the first area and historical power generation data of the photovoltaic power station; and collect real-time power generation data of the photovoltaic power station through intelligent sensors;

[0037] An output power prediction module is used to train an output power prediction model based on the weather forecast data and the historical power generation data; dynamically update the output power prediction model using the real-time power generation data to obtain the updated output power prediction model; and perform real-time prediction of future photovoltaic power generation output power using the updated output power prediction model to obtain the predicted photovoltaic power generation output power;

[0038] An output power analysis module is used to analyze the predicted photovoltaic power generation output power in combination with the load demand of the current power grid to obtain the current fluctuation trend and the load change trend;

[0039] The fault current determination module is used to determine the current fluctuation state according to the load change trend, the predicted photovoltaic power generation output power and the current fluctuation trend; the specific determination process is as follows:

[0040] The load state is determined according to the load change trend; if the load state is a low load and / or half load state, and the predicted photovoltaic power generation output power is higher than the expected output power, whether the current fluctuation state is an abnormal fluctuation state is detected according to the current fluctuation trend; if the current fluctuation state is the abnormal fluctuation state, it is determined to be a fault current;

[0041] The fault current detection strategy adjustment module is used to construct a fault current compensation model based on the predicted photovoltaic power generation output power and the current fluctuation trend to dynamically compensate for the fault current, and adjust the fault current detection strategy of the relay protection device according to expert experience.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention proposes an output power prediction model to predict the future photovoltaic power output power in real time. By acquiring weather forecast data, historical power generation data and real-time power generation data, the output power prediction model is dynamically constructed and updated, which can significantly improve the accuracy of photovoltaic power prediction and enable the system to quickly adapt to environmental changes; real-time prediction of future power output can assist the power grid in precise load management and optimized scheduling, and reduce the impact of grid-connected fluctuations on power grid operation; data support is provided for relay protection sensitivity adjustment, and the accuracy of fault detection under low load or abnormal current fluctuation conditions is improved, which effectively solves the problem of inaccurate power output prediction caused by the strong volatility of photovoltaic power generation, and provides more stable and reliable technical support for power grid operation.

[0044] 2. The present invention proposes a fault current detection method based on load change trend and photovoltaic power generation output power analysis. This method can accurately judge the load state of the power grid by real-time analysis of the load change trend and the predicted value of photovoltaic power generation output power, and judge whether the current is in an abnormal fluctuation state in combination with the current fluctuation trend. This analysis based on predicted power and load changes helps to accurately identify fault currents, avoid false alarms and missed alarms caused by load changes, improve the detection accuracy of fault currents and the system response speed, and provide efficient and reliable fault current detection support for the subsequent dynamic compensation of fault currents through fault current compensation models.

[0045] 3. The present invention proposes a method for constructing a fault current compensation model based on the predicted photovoltaic power generation output power and current fluctuation trend, and dynamically adjusting the fault current detection strategy of the relay protection device, which helps to achieve more accurate and intelligent fault current detection. This method can automatically adjust the sensitivity of the relay protection system according to the predicted value of the photovoltaic power generation output power and the current fluctuation trend to cope with the current changes caused by photovoltaic power generation fluctuations, and ensure that the fault current can be accurately detected under low or high load conditions. This dynamic compensation mechanism can reduce the risk of misoperation and leakage of the relay protection system of the photovoltaic power station, improve the reliability of the system, avoid unnecessary protection actions or faults that cannot be detected in time due to current fluctuations, thereby ensuring the stable grid-connected operation of the photovoltaic power station, while optimizing the overall safety and stability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flow chart of an adaptive solar photovoltaic power station grid-connected control method provided by an embodiment of the present invention;

[0047] Figure 2 A structural diagram of an adaptive solar photovoltaic power station grid-connected control system provided by an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of a flow chart of fault current determination provided by an embodiment of the present invention;

[0049] Figure 4 A schematic diagram of dynamic compensation of fault current provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] With the growth of global energy demand and the development of renewable energy technology, solar photovoltaic power generation, as a clean and sustainable form of energy, is gradually becoming an important part of the power system. However, the access of large-scale photovoltaic power stations to the distribution network will have a certain impact on the operation of traditional power grids, especially under low-load or half-load operation, which may cause a series of technical problems. In the process of photovoltaic power generation grid connection, due to the intermittent and volatile nature of photovoltaic power generation, its output power will be significantly affected by weather changes. This volatility will cause significant changes in the current level of the power grid, especially under low-load conditions, the current level may drop significantly, making it impossible for the relay protection device to accurately detect the fault current, thereby affecting the safe operation of the power grid.

[0052] The present invention proposes an adaptive solar photovoltaic power station grid-connected control method, which realizes efficient and accurate detection and dynamic compensation of fault current under low load conditions. This method is applied to an adaptive solar photovoltaic power station grid-connected control system. For specific method flow chart and system structure diagram, please refer to Figure 1 and Figure 2 In order to illustrate that the method and system of the present invention can play a role in efficient and accurate detection and dynamic compensation of fault current, the effectiveness of the present invention will be described from two embodiments below.

[0053] Embodiment 1

[0054] In the embodiment of the present application, the method and system proposed by the present invention are used to describe in detail the efficient and accurate detection and dynamic compensation process of the fault current. In the embodiment of the present application, the efficient and accurate detection and dynamic compensation of the fault current is aimed at the efficient and accurate detection and dynamic compensation of the fault current of the relay system of the solar photovoltaic power station A in a certain area. Figure 1 and Figure 2 The content describes in detail the efficient and accurate detection and dynamic compensation process of the fault current of the relay system of the solar photovoltaic power station; among them, Figure 1The specific process of the method proposed in the present invention includes: obtaining weather forecast data of a first area and historical power generation data of a photovoltaic power station; collecting real-time power generation data of a photovoltaic power station through an intelligent sensor; training an output power prediction model based on the weather forecast data and the historical power generation data; dynamically updating the output power prediction model using the real-time power generation data to obtain an updated output power prediction model; predicting future photovoltaic power generation output power in real time through the updated output power prediction model to obtain predicted photovoltaic power generation output power; analyzing the predicted photovoltaic power generation output power in combination with the current load demand of the power grid to obtain a current fluctuation trend and a load change trend; determining the fault current by combining the load change trend, the predicted photovoltaic power generation output power and the current fluctuation trend; constructing a fault current compensation model based on the predicted photovoltaic power generation output power and the current fluctuation trend to dynamically compensate for the fault current, and adjusting the fault current detection strategy of the relay protection device based on expert experience. Figure 2 The structure diagram of the system proposed by the present invention includes: a data acquisition module, an output power prediction module, an output power analysis module, a fault current determination module and a fault current detection strategy adjustment module; Figure 1 and Figure 2 The following is a description of the contents:

[0055] Obtain weather forecast data for the first area and historical power generation data of the photovoltaic power station; collect real-time power generation data of the photovoltaic power station through intelligent sensors;

[0056] The weather forecast data includes: temperature, humidity, solar radiation intensity, wind speed and cloud coverage of the first area;

[0057] The historical power generation data includes: historical output power data, historical current, historical voltage and historical environmental data of the photovoltaic power station within a specified time; in this embodiment, the historical power generation data of the photovoltaic power station from 2020 to 2022 is obtained;

[0058] The real-time power generation data includes: real-time output power, real-time grid load, real-time current and real-time voltage at the current time point;

[0059] In this embodiment, the weather forecast data, the historical power generation data and the real-time power generation data are obtained through the power company and the meteorological station in the first area.

[0060] In an embodiment of the present application, by acquiring weather forecast data of the first area, historical power generation data of the photovoltaic power station, and real-time power generation data, comprehensive data support is provided for accurate prediction of photovoltaic power generation output power and grid load management. Specifically, weather forecast data helps to predict changes in the external environment of photovoltaic power generation, thereby affecting the power generation efficiency of photovoltaic modules; historical power generation data provides a long-term reference basis for model training and power forecasting, which can improve the accuracy and reliability of forecasts; real-time power generation data can reflect the current operating status of the photovoltaic power station and changes in grid load, and support real-time monitoring and adjustment. By using these data in combination, a reliable data basis can be provided for the subsequent dynamic update of the output power prediction model to predict the future photovoltaic power generation output power.

[0061] Preferably, an output power prediction model is trained based on the weather forecast data and the historical power generation data;

[0062] The output power prediction model includes: a data preprocessing unit, a weather forecast data analysis unit and a photovoltaic power generation output power initial prediction unit;

[0063] The data preprocessing unit detects and removes abnormal values ​​in the weather forecast data and the historical power generation data by statistical analysis; aligns the weather forecast data and the historical power generation data in time series;

[0064] The weather forecast data analysis unit extracts features related to photovoltaic power generation output power from the weather forecast data to obtain weather features; the weather features include: cumulative solar radiation intensity, daily average temperature over the past N days, daily average cloud coverage and daily average humidity;

[0065] The photovoltaic power generation output power initial prediction unit predicts the photovoltaic power generation data power according to the weather characteristics and the historical power generation data through the LSTM model to obtain the initial predicted photovoltaic power generation output power.

[0066] In the embodiment of the present application, by combining weather forecast data and historical power generation data, the output power prediction model is trained using the LSTM model to achieve high-precision photovoltaic power generation output power prediction. By removing outliers and aligning time series through data preprocessing, weather characteristics related to power generation are extracted to further improve the prediction accuracy. This method can accurately predict future power generation, provide reliable support for power grid load management and scheduling, optimize photovoltaic power generation grid-connected control, and improve system stability and energy efficiency.

[0067] Preferably, the output power prediction model is dynamically updated using the real-time power generation data to obtain the updated output power prediction model; the future photovoltaic power generation output power is predicted in real time using the updated output power prediction model to obtain the predicted photovoltaic power generation output power; the specific process includes:

[0068] Calculating a power generation error by comparing the real-time output power in the real-time power generation data with the initial predicted photovoltaic power generation output power;

[0069] The output power prediction model is updated using a sliding window method according to the power generation error; the updating frequency is once every two hours;

[0070] The updated output power prediction model calculates the future photovoltaic power generation output power in real time according to the weather forecast data at the current time point and the future time period to obtain the predicted photovoltaic power generation output power.

[0071] To further illustrate the advantages of the above LSTM model in photovoltaic power generation output power prediction, the following Table 1 gives the comparison results of the present invention and other prediction methods in terms of prediction accuracy and computing performance.

[0072] Table 1 Comparison of performance indicators of photovoltaic power generation output power prediction results

[0073] method MAE RMSE Prediction time(s) The present invention 3.25 12.79 0.35 Regression analysis 5.32 15.20 1.20 CNN 5.71 18.37 0.83

[0074] In an embodiment of the present application, by dynamically updating the photovoltaic power generation output power prediction model, the accuracy and real-time performance of the model in predicting the photovoltaic power generation output power are improved. By comparing the real-time power generation data with the initial predicted power, the power generation error is calculated and the prediction model is updated using the sliding window method based on this error, so that the model can adapt to changes in the environment and the system in a timely manner. The output power prediction model is updated every two hours to ensure the real-time prediction of the photovoltaic power generation output power. The updated model combines weather forecast data to predict the future photovoltaic power generation output power in real time, providing accurate decision support for power grid dispatching and energy management, and effectively improving the regulation and control capabilities of photovoltaic power generation and the stability of grid connection.

[0075] Preferably, the predicted photovoltaic power generation output power is analyzed in combination with the load demand of the current power grid to obtain the current fluctuation trend and the load change trend;

[0076] The current fluctuation state is determined by combining the load change trend, the predicted photovoltaic power generation output power and the current fluctuation trend, referring to Figure 3 ; The specific judgment process is:

[0077] The load state is judged according to the load change trend; the specific process is: the load deviation is obtained by calculating the load demand of the current power grid and the historical load average; the load change trend is first differentiated to obtain the load change rate; according to the load deviation and the load change rate, the load state threshold is set to judge the load state.

[0078] In the embodiment of the present application, by combining the load deviation with the load change rate, the load state of the power grid can be accurately judged, avoiding misjudgment caused by a single real-time load value, and adapting to the load characteristics under different operating scenarios. By setting the load state threshold, normal fluctuations and abnormal fluctuations can be effectively distinguished, providing a reliable basis for subsequent current fluctuation analysis and fault detection.

[0079] Preferably, if the load state is a low load and / or half load state, and the predicted photovoltaic power generation output power is higher than the expected output power, whether the current fluctuation state is an abnormal fluctuation state is detected according to the current fluctuation trend; if the current fluctuation state is the abnormal fluctuation state, it is determined to be the fault current;

[0080] The specific process of detecting whether the current fluctuation is in an abnormal fluctuation state according to the current fluctuation trend is: obtaining the real-time current fluctuation amplitude mean value by calculating the real-time current in the real-time power generation data; obtaining the historical current fluctuation amplitude mean value by calculating the historical current; determining whether the current fluctuation exceeds the preset normal range by comparing the real-time current fluctuation amplitude mean value with the historical current fluctuation amplitude mean value; if the current fluctuation exceeds the preset normal range, it is determined to be an abnormal fluctuation state.

[0081] The embodiment of the present application accurately judges the abnormal state of current fluctuation by comparing and analyzing the real-time current fluctuation amplitude with the historical current fluctuation amplitude, ensuring the accurate identification of fault current. In combination with different load states and current fluctuation characteristics, the detection sensitivity is dynamically adjusted to effectively avoid misjudgment and missed judgment, and improve the system's response speed and adaptability to abnormal fluctuations. This method enhances the intelligent decision-making ability of the grid-connected control system of photovoltaic power stations and provides reliable support for the optimization of relay protection under low-load or half-load operation.

[0082] Preferably, based on the predicted photovoltaic power generation output power and the current fluctuation trend, a fault current compensation model is constructed to dynamically compensate for the fault current, and the fault current detection strategy of the relay protection device is adjusted according to expert experience, referring to Figure 4 ;

[0083] The fault current compensation model includes: a fault current data input layer, a dynamic compensation layer and a relay protection strategy adjustment layer;

[0084] The fault current data input layer inputs the predicted photovoltaic power generation output power, the current fluctuation trend and the current deviation; wherein the current deviation is obtained by calculating the difference between the real-time current and the predicted current;

[0085] The dynamic compensation layer calculates the fault current compensation amount according to the predicted photovoltaic power generation output power, the current fluctuation trend and the current deviation;

[0086] The relay protection strategy adjustment layer adjusts the sensitivity of the relay protection device and the fault current detection threshold according to the fault current compensation amount.

[0087] To further illustrate the advantages of the fault current determination method of the present invention in terms of accuracy and false alarm rate, Table 2 provides a comparison table of the performance of the fault current determination method of the present invention and methods with different parameters.

[0088] Table 2 Performance comparison of fault current determination methods

[0089]

[0090] The embodiment of the present application constructs a fault current compensation model that can dynamically compensate for possible fault currents in the power grid based on the predicted photovoltaic power output power and current fluctuation trend. The model receives and integrates the predicted photovoltaic power output power, current fluctuation trend and current deviation through the fault current data input layer; the dynamic compensation layer calculates the fault current compensation amount based on these inputs; the relay protection strategy adjustment layer adjusts the sensitivity of the relay protection device and the fault current detection threshold according to the compensation amount. This dynamic compensation mechanism can adjust the relay protection strategy in real time to avoid false operation or missed detection of the relay protection system due to current fluctuations, improve the stability and safety of the power grid, ensure the normal operation of the photovoltaic power station and protect the power system from faults.

[0091] Preferably, the calculation formula of the fault current compensation amount is:

[0092] △I=k 1 ·f(P)+k 2 △I volatility +k 3 △I offset ;

[0093]

[0094] Where △I is the fault current compensation amount; k 1 is the output power difference equivalent current compensation coefficient; f(P) is the function of converting the output power difference into an equivalent circuit; P is the output power difference; k 2 is the current fluctuation amplitude compensation coefficient; △I volatilityis the current fluctuation amplitude; k 3 is the current deviation compensation coefficient; △I offset is the current deviation; P forecast To predict the output power of photovoltaic power generation; P actual is the real-time photovoltaic power output power; V actual is the real-time voltage; α is the real-time voltage adjustment coefficient; I actual The real-time current.

[0095] The calculation formula for the fault current compensation amount provided in the embodiment of the present application ensures that the power grid remains stable when the load fluctuates and the photovoltaic power generation changes by dynamically adjusting the current based on the predicted photovoltaic power generation output power, current fluctuation trend and current deviation, and provides a scientific basis for the subsequent adjustment of the fault current detection strategy of the relay protection device; by weighting and dynamically adjusting different key parameters, the dynamic compensation process of the fault current has higher adaptability.

[0096] The embodiment of the present application constructs a dynamically updated output power prediction model based on weather forecast data, historical power generation data and real-time power generation data, and combines the load demand of the power grid to comprehensively analyze the current fluctuation trend and load change trend, thereby realizing accurate detection of abnormal current under low load or half load conditions. Further, by constructing a fault current compensation model, dynamically compensate for the current level changes caused by photovoltaic power generation fluctuations, and adjust the fault current detection strategy of the relay protection device, thereby significantly improving the accuracy and sensitivity of fault detection. The method can adapt to complex and changeable operating environments, especially under low load or half load operating conditions, and can effectively avoid the relay protection system from leaking or misdetecting fault currents caused by current level fluctuations, thereby improving the safety and stability of photovoltaic power station grid-connected operation. In addition, the method of the present invention relies on intelligent data-driven analysis, reduces human intervention, optimizes system automation performance, and demonstrates highly intelligent grid-connected control capabilities, ensuring that the impact of photovoltaic power stations on grid operation is minimized when connected to the power grid, and realizing accurate and efficient detection of fault currents under low load or abnormal current fluctuation conditions.

[0097] Embodiment 2

[0098] In Example 1, the method proposed in the present invention successfully realizes efficient and accurate detection and dynamic compensation of the fault current of the relay system of the solar photovoltaic power station in area A. To further verify the effectiveness of the present invention, the present application embodiment also proposes an adaptive solar photovoltaic power station grid-connected control system to detect and compensate for the fault current of the relay system of the solar photovoltaic power station in area B; the system includes: a data acquisition module, an output power prediction module, an output power prediction module, a fault current determination module and a fault current detection strategy adjustment module.

[0099] A data acquisition module is used to acquire weather forecast data of the first area and historical power generation data of the photovoltaic power station; and collect real-time power generation data of the photovoltaic power station through intelligent sensors;

[0100] The weather forecast data includes: temperature, humidity, solar radiation intensity, wind speed and cloud coverage of the first area;

[0101] The historical power generation data includes: historical output power data, historical current, historical voltage and historical environmental data of the photovoltaic power station within a specified time; in this embodiment, the historical power generation data of the photovoltaic power station from 2020 to 2022 is obtained;

[0102] The real-time power generation data includes: real-time output power, real-time grid load, real-time current and real-time voltage at the current time point.

[0103] Preferably, an output power prediction module is used to train an output power prediction model based on the weather forecast data and the historical power generation data;

[0104] The output power prediction model includes: a data preprocessing unit, a weather forecast data analysis unit and a photovoltaic power generation output power initial prediction unit;

[0105] The data preprocessing unit detects and removes abnormal values ​​in the weather forecast data and the historical power generation data by statistical analysis; aligns the weather forecast data and the historical power generation data in time series;

[0106] The weather forecast data analysis unit extracts features related to photovoltaic power generation output power from the weather forecast data to obtain weather features; the weather features include: cumulative solar radiation intensity, daily average temperature over the past N days, daily average cloud coverage and daily average humidity;

[0107] The photovoltaic power generation output power initial prediction unit predicts the photovoltaic power generation data power according to the weather characteristics and the historical power generation data through the LSTM model to obtain the initial predicted photovoltaic power generation output power.

[0108] Preferably, the output power prediction model is dynamically updated using the real-time power generation data to obtain the updated output power prediction model; the future photovoltaic power generation output power is predicted in real time using the updated output power prediction model to obtain the predicted photovoltaic power generation output power; the specific process includes:

[0109] Calculating a power generation error by comparing the real-time output power in the real-time power generation data with the initial predicted photovoltaic power generation output power;

[0110] The output power prediction model is updated using a sliding window method according to the power generation error; the updating frequency is once every two hours;

[0111] The updated output power prediction model calculates the future photovoltaic power generation output power in real time according to the weather forecast data at the current time point and the future time period to obtain the predicted photovoltaic power generation output power.

[0112] Preferably, the output power analysis module is used to analyze the predicted photovoltaic power generation output power in combination with the load demand of the current power grid to obtain the current fluctuation trend and the load change trend.

[0113] Preferably, the fault current determination module is used to determine the current fluctuation state according to the load change trend, the predicted photovoltaic power generation output power and the current fluctuation trend; the specific determination process is:

[0114] Determine the load state according to the load change trend;

[0115] If the load state is a low load and / or half load state, and the predicted photovoltaic power generation output power is higher than the expected output power, detecting whether the current fluctuation state is an abnormal fluctuation state according to the current fluctuation trend;

[0116] If the current fluctuation state is the abnormal fluctuation state, it is determined to be a fault current.

[0117] The specific process of judging the load status according to the load change trend is as follows:

[0118] The load deviation is calculated based on the current load demand of the power grid and the historical load average;

[0119] Performing a first-order differentiation on the load change trend to obtain a load change rate;

[0120] According to the load deviation and the load change rate, a load state threshold is set to perform load state judgment;

[0121] The specific process of detecting whether the current fluctuation state is in an abnormal fluctuation state according to the current fluctuation trend is as follows:

[0122] The real-time current fluctuation amplitude mean is obtained by calculating the real-time current in the real-time power generation data;

[0123] The mean value of historical current fluctuation amplitude is obtained based on historical current calculation;

[0124] By comparing the real-time current fluctuation amplitude mean value with the historical current fluctuation amplitude mean value, determining whether the current fluctuation exceeds a preset normal range;

[0125] If the current fluctuation exceeds the preset normal range, it is determined to be the abnormal fluctuation state.

[0126] Preferably, a fault current detection strategy adjustment module is used to construct a fault current compensation model to dynamically compensate for the fault current based on the predicted photovoltaic power generation output power and the current fluctuation trend, and adjust the fault current detection strategy of the relay protection device according to expert experience;

[0127] The fault current compensation model includes: a fault current data input layer, a dynamic compensation layer and a relay protection strategy adjustment layer;

[0128] The fault current data input layer inputs the predicted photovoltaic power generation output power, the current fluctuation trend and the current deviation; wherein the current deviation is obtained by calculating the difference between the real-time current and the predicted current;

[0129] The dynamic compensation layer calculates the fault current compensation amount according to the predicted photovoltaic power generation output power, the current fluctuation trend and the current deviation; the calculation formula of the fault current compensation amount is:

[0130] △I=k 1 f(P)+k 2 △I volatility +k 3 △I offset ;

[0131]

[0132] Where △I is the fault current compensation amount; k 1 is the output power difference equivalent current compensation coefficient; f(P) is the function of converting the output power difference into an equivalent circuit; P is the output power difference; k 2 is the current fluctuation amplitude compensation coefficient; △I volatility is the current fluctuation amplitude; k 3 is the current deviation compensation coefficient; △I offset is the current deviation; P forecast To predict the output power of photovoltaic power generation; P actual is the real-time photovoltaic power output power; V actual is the real-time voltage; α is the real-time voltage adjustment coefficient; I actual is the real-time current;

[0133] The relay protection strategy adjustment layer adjusts the sensitivity and the fault current detection threshold of the relay protection device according to the fault current compensation amount based on expert experience.

[0134] Table 3 shows the results of adjusting the sensitivity of the relay protection device and the fault current detection threshold according to the fault current compensation amount.

[0135] Table 3 Sensitivity of relay protection device and fault current detection threshold adjustment results

[0136]

[0137] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An adaptive solar photovoltaic power station grid-connected control method, characterized in that: include: Obtain weather forecast data for the first area and historical power generation data of the photovoltaic power station; collect real-time power generation data of the photovoltaic power station through intelligent sensors; Training an output power prediction model based on the weather forecast data and the historical power generation data; dynamically updating the output power prediction model using the real-time power generation data to obtain the updated output power prediction model; and predicting the future photovoltaic power generation output power in real time using the updated output power prediction model to obtain the predicted photovoltaic power generation output power; In combination with the load demand of the current power grid, the predicted photovoltaic power generation output power is analyzed to obtain the current fluctuation trend and the load change trend; The current fluctuation state is determined by the load change trend, the predicted photovoltaic power generation output power and the current fluctuation trend; the specific determination process is as follows: Determine the load state according to the load change trend; if the load state is a low load and / or half load state, and the predicted photovoltaic power generation output power is higher than the expected output power, detect whether the current fluctuation state is an abnormal fluctuation state according to the current fluctuation trend; If the current fluctuation state is the abnormal fluctuation state, it is determined to be a fault current; Based on the predicted photovoltaic power generation output power and the current fluctuation trend, a fault current compensation model is constructed to dynamically compensate for the fault current, and the fault current detection strategy of the relay protection device is adjusted according to expert experience.

2. The method for controlling the grid connection of an adaptive solar photovoltaic power station according to claim 1, characterized in that: The weather forecast data includes: temperature, humidity, solar radiation intensity, wind speed and cloud coverage of the first area; The historical power generation data includes: historical output power data, historical current, historical voltage and historical environmental data of the photovoltaic power station within a specified time; The real-time power generation data includes: real-time output power, real-time grid load, real-time current and real-time voltage at the current time point.

3. The method for controlling the grid connection of an adaptive solar photovoltaic power station according to claim 1, characterized in that: The output power prediction model includes: a data preprocessing unit, a weather forecast data analysis unit and a photovoltaic power generation output power initial prediction unit; The data preprocessing unit detects and removes abnormal values ​​in the weather forecast data and the historical power generation data by statistical analysis; aligns the weather forecast data and the historical power generation data in time series; The weather forecast data analysis unit extracts features related to photovoltaic power generation output power from the weather forecast data to obtain weather features; the weather features include: cumulative solar radiation intensity, daily average temperature over the past N days, daily average cloud coverage and daily average humidity; The photovoltaic power generation output power initial prediction unit predicts the photovoltaic power generation data power according to the weather characteristics and the historical power generation data through the LSTM model to obtain the initial predicted photovoltaic power generation output power.

4. The method for controlling the grid connection of an adaptive solar photovoltaic power station according to claim 1, characterized in that: The output power prediction model is dynamically updated by using the real-time power generation data to obtain the updated output power prediction model; the future photovoltaic power generation output power is predicted in real time by using the updated output power prediction model to obtain the predicted photovoltaic power generation output power; the specific process includes: Calculating a power generation error by comparing the real-time output power in the real-time power generation data with the initial predicted photovoltaic power generation output power; The output power prediction model is updated using a sliding window method according to the power generation error; the updating frequency is once every two hours; The updated output power prediction model calculates the future photovoltaic power generation output power in real time according to the weather forecast data at the current time point and the future time period to obtain the predicted photovoltaic power generation output power.

5. The method for controlling the grid connection of an adaptive solar photovoltaic power station according to claim 1, characterized in that: The specific process of judging the load status according to the load change trend is as follows: Compare the current load demand of the power grid with the historical load average and calculate the load deviation; Performing a first-order differentiation on the load change trend to obtain a load change rate; A load state threshold is set according to the load deviation and the load change rate to perform load state judgment.

6. The method for controlling the grid connection of an adaptive solar photovoltaic power station according to claim 1, characterized in that: The specific process of detecting whether the current fluctuation state is in an abnormal fluctuation state according to the current fluctuation trend is as follows: The real-time current fluctuation amplitude mean is obtained by calculating the real-time current in the real-time power generation data; The mean value of historical current fluctuation amplitude is obtained based on historical current calculation; By comparing the real-time current fluctuation amplitude mean value with the historical current fluctuation amplitude mean value, determining whether the current fluctuation exceeds a preset normal range; If the current fluctuation exceeds the preset normal range, it is determined to be the abnormal fluctuation state.

7. The method for controlling the grid connection of an adaptive solar photovoltaic power station according to claim 1, characterized in that: The fault current compensation model includes: a fault current data input layer, a dynamic compensation layer and a relay protection strategy adjustment layer; The fault current data input layer inputs the predicted photovoltaic power generation output power, the current fluctuation trend and the current deviation; wherein the current deviation is obtained by calculating the difference between the real-time current and the predicted current; The dynamic compensation layer calculates the fault current compensation amount according to the predicted photovoltaic power generation output power, the current fluctuation trend and the current deviation; The relay protection strategy adjustment layer adjusts the sensitivity of the relay protection device and the fault current detection threshold according to the fault current compensation amount.

8. The method for controlling the grid connection of an adaptive solar photovoltaic power station according to claim 7, characterized in that: The calculation formula of the fault current compensation amount is: △I=k1·f(P)+k2·△I volatility +k3·△I offset ; Wherein, △I is the fault current compensation amount; k1 is the output power difference equivalent current compensation coefficient; f(P) is the function that converts the output power difference into an equivalent circuit; P is the output power difference; k2 is the current fluctuation amplitude compensation coefficient; △I volatility is the current fluctuation amplitude; k3 is the current deviation compensation coefficient; △I offset is the current deviation; P forecast To predict the photovoltaic power output power; P actual is the real-time photovoltaic power output power; V actual is the real-time voltage; α is the real-time voltage adjustment coefficient; I actual The real-time current.

9. An adaptive solar photovoltaic power station grid-connected control system, characterized in that: include: A data acquisition module is used to acquire weather forecast data of the first area and historical power generation data of the photovoltaic power station; and collect real-time power generation data of the photovoltaic power station through intelligent sensors; An output power prediction module is used to train an output power prediction model based on the weather forecast data and the historical power generation data; dynamically update the output power prediction model using the real-time power generation data to obtain the updated output power prediction model; and perform real-time prediction of future photovoltaic power generation output power using the updated output power prediction model to obtain the predicted photovoltaic power generation output power; An output power analysis module is used to analyze the predicted photovoltaic power generation output power in combination with the load demand of the current power grid to obtain the current fluctuation trend and the load change trend; The fault current determination module is used to determine the current fluctuation state according to the load change trend, the predicted photovoltaic power generation output power and the current fluctuation trend; the specific determination process is as follows: The load state is determined according to the load change trend; if the load state is a low load and / or half load state, and the predicted photovoltaic power generation output power is higher than the expected output power, whether the current fluctuation state is an abnormal fluctuation state is detected according to the current fluctuation trend; if the current fluctuation state is the abnormal fluctuation state, it is determined to be a fault current; The fault current detection strategy adjustment module is used to construct a fault current compensation model based on the predicted photovoltaic power generation output power and the current fluctuation trend to dynamically compensate for the fault current, and adjust the fault current detection strategy of the relay protection device according to expert experience.

Images