Wind power plant reactive voltage control method and system

Abstract

The invention provides a wind power plant reactive voltage control method and system, and relates to the technical field of wind power plant reactive voltage intelligent control. Firstly, historical voltage, current and power factor data are collected at key positions at the bottom of a generator, a converter and a tower of a fan, and then the data are preprocessed; and the reactive power, the power loss and the voltage deviation of each fan are calculated. And then, generating a fitness value based on the power loss and the voltage deviation, and obtaining an optimal voltage, current and power factor combination through genetic algorithm optimization, thereby calculating optimal reactive power and obtaining a target value of the reactive power. And finally, collecting the current voltage, current and power factor of each fan in real time, obtaining the deviation between the optimal reactive power and the current reactive power, and analyzing the deviation, thereby adjusting the reactive voltage of each fan in real time, and ensuring the efficient, safe and stable operation of the wind power plant in a dynamic environment.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent reactive power voltage control for wind farms, and specifically to a method and system for controlling reactive power voltage in wind farms. Background Art

[0002] The reactive power voltage control technology for wind farms is an important part of modern power system management. With the rapid development of renewable energy, especially the wide application of wind energy, the proportion of wind farms in the power grid is increasing continuously. This trend brings new challenges, especially in terms of voltage stability and the safe operation of the system. The output of wind turbines is greatly affected by changes in wind speed, and their ability to regulate reactive power is usually limited. This makes it an urgent problem to effectively control the reactive power of wind farms to maintain the grid voltage within a reasonable range.

[0003] Reactive power plays a crucial role in the power system. It not only supports voltage stability but also affects the overall performance of the system and the safe operation of equipment. The lack of reactive power in the power grid may lead to voltage fluctuations, equipment overload, and even the collapse of the power system. Therefore, it is particularly important to implement effective reactive power voltage control strategies. Traditional voltage control methods mainly rely on equipment such as synchronous generators, transformers, and static var compensators to regulate the reactive power output of the system, but these methods are often restricted by the characteristics of wind turbines and operating conditions in wind farms.

[0004] The existing technologies have the following deficiencies:

[0005] Although the existing reactive power voltage control methods for wind farms have achieved certain results in improving system efficiency and stability, there are still some deficiencies, mainly reflected in the adaptability to dynamic changing environments and the real-time response speed. Traditional control strategies often rely on fixed parameters and models and cannot flexibly cope with complex situations of voltage and current data fluctuations, resulting in a reduction in the effectiveness of voltage control in extreme cases. In addition, the existing technologies also have limitations in the real-time nature of data collection and processing, which may lead to a slow response to instantaneous voltage fluctuations, thus affecting the safety and reliability of the overall power system. These deficiencies make it difficult for wind farms to achieve optimal reactive power regulation and voltage stability when facing changing grid demands.

[0006] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the present invention is to provide a method and system for controlling reactive power voltage in wind farms to solve the problems raised in the above background art.

[0008] To achieve the above object, the present invention provides a reactive voltage control method for a wind farm, and the specific steps include:

[0009] Step 1: Mark the generator at the top of each wind turbine tower, the converter inside the wind turbine, and the bottom of the wind turbine tower in the wind farm as the key nodes of the wind turbine, obtain the historical voltage, current, and power factor data at the key nodes, and calculate the historical voltage, current, and power factor data of the wind turbine based on this;

[0010] Step 2: Perform data preprocessing on the collected voltage, current, and power factor, analyze the preprocessed data, and calculate the reactive power, power loss, and voltage deviation of each wind turbine;

[0011] Step 3: Generate a fitness value reflecting the working state of the wind turbine based on the power loss and voltage deviation, determine the maximization of the fitness value as the optimization goal, use the genetic algorithm for optimization, obtain the optimal combination of voltage, current, and power factor, and calculate the optimal reactive power based on this combination;

[0012] Step 4: Collect the current voltage, current, and power factor at the key nodes of each wind turbine in the wind farm, and calculate the current voltage, current, power factor, and reactive power of the corresponding wind turbine based on this. Adjust the reactive voltage of each wind turbine based on the deviation between the optimal reactive power and the current reactive power of each wind turbine.

[0013] Further, the specific logic for calculating the voltage, current, and power factor data of the wind turbine is:

[0014] Install a voltage sensor, a current sensor, and a power analyzer at the key nodes of each wind turbine to obtain the voltage, current, and power factor data of each wind turbine. The formula for obtaining the voltage data of the wind turbine is:

[0015]

[0016] where V a is the voltage value of the a-th key node in the wind turbine, V′ is the voltage value of the wind turbine, n is the number of key nodes on the wind turbine, a is the index of the key node on the wind turbine, and a ∈ [1, n];

[0017] Similarly, the current I′ and power factor pf′ of the wind turbine are obtained.

[0018] Further, the specific logic for calculating the reactive power, power loss, and voltage deviation of each wind turbine is:

[0019] Perform preprocessing on the collected voltage, current, and power factor. The preprocessing includes detecting and removing abnormal data based on the Z-score method, and filling in missing data using the mean filling method;

[0020] The formula for calculating reactive power is as follows:

[0021]

[0022] Where Q is the reactive power of the fan, and V, I, and pf are the voltage, current, and power factor after preprocessing, respectively;

[0023] The formula for calculating power loss is as follows:

[0024] P = I 2 × R

[0025] Where P is the power loss of the fan and R is the circuit resistance of the fan;

[0026] The formula for calculating voltage deviation is as follows:

[0027]

[0028] Where v is the voltage deviation of the fan, is the target voltage of the fan.

[0029] Furthermore, the logic for obtaining the optimal reactive power is as follows:

[0030] Taking the combinations of voltage, current, and power factor of each fan in the wind farm as an individual respectively to form an initial population, calculate the fitness value of each individual. The calculation formula is as follows:

[0031] F = -(λ1 * P + λ2 * v)

[0032] Where F is the fitness value of the individual, and λ1 and λ2 respectively represent the power loss weight and voltage deviation weight corresponding to this individual. 0 < λ2 < λ1 < 1, and λ1 + λ2 = 1;

[0033] Sort the fitness values from large to small, select the individuals in the front row as parents, randomly select two parents for crossover to generate new individuals, then perform mutation operations on the newly generated individuals, integrate the newly generated individuals and the parent individuals into a new population, and repeat the operations of calculating fitness values, selection, crossover, and mutation until the preset fitness threshold is reached. Select the individual with the highest fitness as the optimal combination of voltage, current, and power factor, and calculate the optimal reactive power based on this combination.

[0034] Furthermore, the logic for adjusting the reactive power setting value of each fan is as follows:

[0035] The formula for obtaining the deviation between the reactive power of the current fan and the optimal reactive power is as follows:

[0036]

[0037] Among them, ΔQ is the power deviation between the current reactive power of the fan and the optimal reactive power, Q is the current reactive power of the fan, and

[0038] is the optimal reactive power;

[0039] Compare the deviation between the current reactive power of the fan and the optimal reactive power with a preset deviation threshold. If the deviation between the current reactive power of the fan and the optimal reactive power is lower than the preset deviation threshold, no adjustment is made temporarily. If the deviation between the current reactive power of the fan and the optimal reactive power is higher than the preset deviation threshold, obtain an adjustment factor to adjust the reactive voltage of the corresponding fan;

[0040]

[0041] Among them, α pf is the adjustment factor of the fan's reactive power, γ pf is the non-linear adjustment coefficient of the reactive power adjustment factor, k pf is the basic adjustment coefficient of the reactive power adjustment factor, ω pf is the dynamic weight of the reactive power adjustment factor;

[0042] The formula for obtaining the dynamic weight is:

[0043]

[0044] Among them, ω pf is the dynamic weight of the reactive power adjustment factor, β is the importance coefficient of the historical deviation, and its value range is [0, 1]. ∈ is the threshold of the deviation. Obtain the reactive power of the fan at a total of T acquisition times in the previous time period before the current time, and calibrate the reactive power at the t-th acquisition time in the previous time period before the current time as Q(t), where t is the index of the acquisition time and t ∈ [1, T]. ΔQ(t) represents the deviation between the reactive power of the fan at the t-th acquisition time in the previous time period before the current time and the optimal reactive power;

[0045] The formula for updating the set value of the reactive power is:

[0046] Q new = Q - α pf ·ΔQ + μ pf ·(ΔQ) 2

[0047] Among them, Q new is the target reactive power of the updated fan, and μ is the square error weight;

[0048] The formula for obtaining the deviation between the reactive power of the current wind turbine and the optimized target reactive power is as follows:

[0049] Δq = Q new -Q

[0050] Where, Δq is the deviation between the reactive power of the current wind turbine and the optimized target reactive power;

[0051] Judge the deviation between the reactive power of the current wind turbine and the optimized target reactive power. If Δq > 0, it means that reactive power needs to be increased, that is, reactive voltage needs to be increased, then the capacitor bank is enabled; if Δq < 0, it means that reactive power needs to be reduced, that is, reactive voltage needs to be reduced, then the inductor is enabled.

[0052] The present invention also provides a reactive voltage control system for a wind farm. The reactive voltage control system for a wind farm is used to implement the above-mentioned reactive voltage control method for a wind farm, and includes:

[0053] A data acquisition module, which is used to mark the generator at the top of each wind turbine tower, the converter inside the wind turbine, and the bottom of the wind turbine tower in the wind farm as the key nodes of the wind turbine, obtain the historical voltage, current, and power factor data at the key nodes, and calculate the historical voltage, current, and power factor data of the wind turbine based on this;

[0054] A data preprocessing and analysis module, which is used to perform data preprocessing on the collected voltage, current, and power factor, analyze the preprocessed data, and calculate the reactive power, power loss, and voltage deviation of each wind turbine;

[0055] An optimal parameter combination determination module, which is used to generate a fitness value reflecting the working state of the wind turbine based on the power loss and voltage deviation, determine the maximization of the fitness value as the optimization goal, use the genetic algorithm for optimization, obtain the best combination of voltage, current, and power factor, and calculate the best reactive power based on this combination;

[0056] A real-time monitoring and control module, which is used to collect the current voltage, current, and power factor at the key nodes of each wind turbine in the wind farm, and calculate the current voltage, current, power factor, and reactive power of the corresponding wind turbine based on this, and adjust the reactive voltage of each wind turbine based on the deviation between the best reactive power and the current reactive power of each wind turbine.

[0057] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0058] This reactive power voltage control method for wind farms significantly improves the operating efficiency of wind farms and the stability of power systems by real-time monitoring and dynamic adjustment of the reactive power voltage of each wind turbine. Through historical data analysis and genetic algorithm optimization, it can accurately calculate the optimal combination of voltage, current, and power factor, making the adjustment of reactive power more scientific and reasonable, thus effectively reducing power losses, reducing voltage fluctuations, and improving power quality. Through this intelligent management method, wind farms can flexibly adapt to environmental changes, enhance their support for the power grid, and ultimately achieve higher economic benefits and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0060] Figure 2 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0062] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meaning understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not denote any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0063] Embodiment:

[0064] Please refer to Figure 1 , the present invention provides a reactive power voltage control method for wind farms, and the specific steps include:

[0065] Step 1: Mark the generator at the top of each wind turbine tower, the converter inside the wind turbine, and the bottom of the wind turbine tower in the wind farm as the key nodes of the wind turbine, obtain the historical voltage, current, and power factor data at the key nodes, and calculate the historical voltage, current, and power factor data of the wind turbine based on this;

[0066] In this embodiment, the specific logic for calculating the voltage, current, and power factor data of the fan is as follows:

[0067] Install voltage sensors, current sensors, and power analyzers at the key nodes of each fan to obtain the voltage, current, and power factor data of each fan. The formula for obtaining the voltage data of the fan is:

[0068]

[0069] where V a is the voltage value of the ath key node in the fan, V′ is the voltage value of the fan, n is the number of key nodes on the fan, a is the index of the key node on the fan, and a ∈ [1, n];

[0070] Similarly, the current I′ and power factor pf′ of the fan are obtained.

[0071] By installing voltage sensors, current sensors, and power analyzers at the key nodes of the fan (such as the generator, converter, and bottom of the tower), the voltage, current, and power factor data of the fan can be obtained in real time and accurately. This provides a reliable data basis for subsequent reactive power control. Calculating the overall voltage value of the fan ensures that the electrical characteristics of each key node are fully considered in the overall power management. This comprehensive characteristic evaluation helps to improve the operating efficiency of the fan. Through real-time monitoring and historical data analysis, electrical anomalies of the fan, such as voltage fluctuations or power factor deviations, can be detected in a timely manner, thereby preventing possible failures and improving the overall reliability of the system.

[0072] Step 2: Preprocess the collected voltage, current, and power factor, analyze the preprocessed data, and calculate the reactive power, power loss, and voltage deviation of each fan;

[0073] In this embodiment, the specific logic for calculating the reactive power, power loss, and voltage deviation of each fan is as follows:

[0074] Preprocess the collected voltage, current, and power factor. The preprocessing includes detecting and removing abnormal data based on the Z-score method and filling in missing data using the mean filling method;

[0075] The formula for calculating the reactive power is:

[0076]

[0077] where Q is the reactive power of the fan, and V, I, and pf are the preprocessed voltage, current, and power factor respectively;

[0078] The formula for calculating the power loss is:

[0079] P=I 2 ×R

[0080] Where P is the power loss of the fan, and R is the circuit resistance of the fan;

[0081] The voltage deviation is calculated based on the formula:

[0082]

[0083] Where, v is the voltage deviation of the fan, is the target voltage of the fan.

[0084] The use of the Z-score method to detect and remove abnormal data can effectively improve the quality of data and ensure the accuracy of subsequent analysis. At the same time, the application of the mean filling method can handle missing data and avoid the deviation of analysis results caused by missing data. Calculating reactive power based on preprocessed data can more realistically reflect the power characteristics of the wind turbine during operation, thereby providing an accurate quantitative basis for reactive voltage control.

[0085] Step 3: Generate a fitness value reflecting the working state of the wind turbine based on power loss and voltage deviation, and determine the maximization of the fitness value as the optimization goal. Use genetic algorithm for optimization to obtain the best combination of voltage, current and power factor, and calculate the best reactive power based on this combination.

[0086] In this embodiment, the logic for obtaining the optimal reactive power is:

[0087] The voltage, current and power factor combination of each wind turbine in the wind farm is taken as an individual to form the initial population, and the fitness value of each individual is calculated. The calculation formula is as follows:

[0088] F=-(λ1*P+λ2*v)

[0089] Where F is the fitness value of the individual, λ1 and λ2 represent the power loss weight and voltage deviation weight corresponding to the individual, respectively, 0<λ2<λ1<1, and λ1+λ2=1;

[0090] Sort the fitness values ​​from large to small, select the individuals in the front row as the parents, randomly select two parents to cross over to generate new individuals, then perform mutation operations on the newly generated individuals, integrate the newly generated individuals and the parent individuals into a new population, repeat the calculation of fitness values, selection, crossover and mutation operations until the preset fitness threshold is reached, select the individual with the highest fitness as the optimal voltage, current and power factor combination, and calculate the optimal reactive power based on this combination.

[0091] The genetic algorithm optimizes the combination of voltage, current, and power factor of the wind turbines, which can dynamically adapt to the operating state of the wind farm and ensure that the wind turbines can still maintain the best working state under variable environmental and load conditions. Through repeated selection, crossover, and mutation operations, the genetic algorithm can efficiently explore the solution space and finally find the individual with the highest fitness, ensuring that the selected combination of voltage, current, and power factor is optimal. By defining the fitness value, the two key performance indicators of power loss and voltage deviation can be integrated, making the optimization process more targeted and directly reflecting the working state of the wind turbines. Based on the optimized combination of voltage, current, and power factor, the calculated optimal reactive power can better respond to the operating requirements of the wind farm in a timely manner, improving the power quality and system stability. Power loss directly affects the economic benefits of the wind farm and is an important consideration in the operation of the power system. Therefore, assigning a higher weight to power loss can prompt the optimization algorithm to give priority to reducing power loss, which is crucial for improving the overall economy of the wind farm. Although the weight of voltage deviation is relatively low, it is still important. Excessive voltage deviation may cause damage to electrical equipment or system instability, so it also needs to be considered in the optimization to ensure the stable operation of the system. By setting the relative relationship between these two weights, a reasonable balance can be found between pursuing economic benefits and system stability, ensuring that the wind farm will not sacrifice one goal for the other when optimizing the operating state. By restricting the sum of λ1 and λ2 to 1, it can be ensured that these two weight coefficients are within a standardized range.

[0092] Step 4: Collect the current voltage, current, and power factor at the key nodes of each wind turbine in the wind farm, and calculate the current voltage, current, power factor, and reactive power of the corresponding wind turbine. Based on the deviation between the optimal reactive power and the current reactive power of each wind turbine, adjust the reactive voltage of each wind turbine.

[0093] In this embodiment, the logic for adjusting the reactive power setting value of each wind turbine is as follows:

[0094] The formula for obtaining the deviation between the reactive power of the current wind turbine and the optimal reactive power is:

[0095]

[0096] where ΔQ is the power deviation between the current reactive power and the optimal reactive power of the wind turbine, Q is the current reactive power of the wind turbine, is the optimal reactive power;

[0097] Compare the deviation between the reactive power of the current wind turbine and the optimal reactive power with a preset deviation threshold. If the deviation between the reactive power of the current wind turbine and the optimal reactive power is lower than the preset deviation threshold, no adjustment is made temporarily. If the deviation between the reactive power of the current wind turbine and the optimal reactive power is higher than the preset deviation threshold, obtain an adjustment factor to regulate the reactive voltage of the corresponding wind turbine;

[0098] The formula for obtaining the adjustment factor is:

[0099]

[0100] where, α pf is the adjustment factor of the wind turbine reactive power, γ pf is the non-linear adjustment coefficient of the reactive power adjustment factor, k pf is the basic adjustment coefficient of the reactive power adjustment factor, ω pf is the dynamic weight of the reactive power adjustment factor;

[0101] The formula for obtaining the dynamic weight is:

[0102]

[0103] where, ω pf is the dynamic weight of the reactive power adjustment factor, β is the importance coefficient of the historical deviation, and its value range is [0, 1]. ∈ is the deviation threshold. Obtain the reactive power of the wind turbine at a total of T acquisition times in the previous time period before the current moment, and calibrate the reactive power at the t-th acquisition time in the previous time period before the current moment as Q(t), where t is the index of the acquisition time, and t ∈ [1, T]. ΔQ(t) represents the deviation between the reactive power of the wind turbine at the t-th acquisition time in the previous time period before the current moment and the optimal reactive power;

[0104] The formula for updating the set value of the reactive power is:

[0105] Q new = Q - α pf ·ΔQ + μ pf ·(ΔQ) 2

[0106] where, Q new is the target reactive power of the updated wind turbine, μ pf is the squared error weight;

[0107] The formula for obtaining the deviation between the reactive power of the current wind turbine and the optimized target reactive power is:

[0108] Δq = Q new - Q

[0109] Among them, Δq is the deviation between the reactive power of the current wind turbine and the optimized target reactive power, that is, Δq is the reactive power adjustment amount; judge the deviation between the reactive power of the current wind turbine and the optimized target reactive power. If Δq>0, it means that reactive power needs to be increased, that is, reactive voltage is increased, and the capacitor bank is enabled; if Δq<0, it means that reactive power needs to be reduced, that is, reactive voltage is reduced, and the inductor is enabled.

[0110] Collect the voltage, current, and power factor of each wind turbine every five minutes, which can monitor the operating status of the wind turbine in real time and adjust the reactive power in a timely manner to ensure that the wind turbine is in the best working state. This process improves the flexibility and adaptability of the wind farm. Using the deviation between the current reactive power and the optimal reactive power and the preset deviation threshold, it is possible to scientifically and effectively judge whether power adjustment is needed, avoiding unnecessary frequent adjustments and reducing the system burden. The formula for the deviation between the reactive power of the current wind turbine and the optimal reactive power calculates the deviation between the reactive power of the current wind turbine and the optimal reactive power. The absolute value of the deviation reflects the gap between the current state and the ideal state of the wind turbine and is the basis for adjustment.

[0111] Adjustment factor formula Aims to dynamically adjust the reactive power output of the wind turbine according to the deviation of the reactive power through a non-linear adjustment mechanism. Here, using an exponential function can effectively limit the change range of the factor when the deviation is large, preventing over-adjustment from causing system instability, especially when the wind speed changes greatly. Parameter k pf Is the basic adjustment coefficient, which sets the basic adjustment range, while γ pf Provides flexibility to the system response through the non-linear adjustment coefficient, making the adjustment more gentle when the deviation is small and being able to respond quickly when the deviation is large, thus ensuring the dynamic stability of the system. In calculating the adjustment factor, the larger ΔQ is, the larger the adjustment factor α pf Is also, which means that the reactive power deviation is more obvious and the system requires a greater adjustment force. This relationship is reasonable because a large deviation indicates the gap between the current state and the target state, and stronger adjustment is needed to correct this gap. Dynamic weight formula Embodies the comprehensive consideration of historical data and the current state. By introducing the accumulation of historical deviations, the past operation data can be effectively used to evaluate the current system's reactive power demand and enhance the accuracy of adjustment. The weight coefficient β adjusts the importance of the current deviation and the historical deviation, balancing real-time performance and stability. Using the maximum value and the threshold ∈ ensures that the dynamic weight does not fluctuate excessively when the deviation is very small, thus making the adjustment process smoother. Update formula Q new = Q - α pf ·ΔQ + μ pf ·(ΔQ) 2Combines the influence of the adjustment factor and the square term of the deviation. By introducing μ pf ·(ΔQ) 2 term, the system can take into account the non-linear characteristics of the adjustment, that is, when the deviation is large, the adjustment strength will increase, enhancing the response ability to large fluctuations. Such a design can effectively suppress voltage fluctuations caused by insufficient reactive power adjustment and ensure the stable operation of the wind farm under different environmental conditions. The updated reactive power takes into account the current power, the role of the adjustment factor, and the square error term of the deviation. Here, α pf directly affects the adjustment amplitude, while μ pf is to prevent excessive adjustment, ensure a smooth adjustment process, and reduce oscillations. The reactive voltage adjustment amount is proportional to the reactive power deviation and the sensitivity coefficient, indicating that the adjustment amount of reactive voltage depends on the state feedback of the current wind turbine, thus effectively reflecting how to adjust the voltage to achieve the target power. Through refined adjustment calculations, the power loss can be significantly reduced, the power generation efficiency can be improved, and the economic benefits of the wind farm can be enhanced. It strengthens the voltage control ability of the wind farm, ensures the stability and reliability of wind power output, and helps to improve the support performance for the power grid. Timely reactive voltage adjustment can reduce the failure rate of equipment, thereby reducing the maintenance cost and downtime of the wind farm. Through real-time monitoring and feedback mechanisms, it can better adapt to changes in the operating environment of the wind farm and ensure the efficient and stable operation of the system.

[0112] Please refer to Figure 2 for a wind farm reactive voltage control system provided by the present invention. The wind farm reactive voltage control system is used to implement the above-mentioned wind farm reactive voltage control method, including:

[0113] A data acquisition module, which marks the generator at the top of each wind turbine tower, the converter inside the wind turbine, and the bottom of the wind turbine tower in the wind farm as the key nodes of the wind turbine, obtains the historical voltage, current, and power factor data at the key nodes, and calculates the historical voltage, current, and power factor data of the wind turbine based on this;

[0114] A data preprocessing and analysis module, which preprocesses the acquired voltage, current, and power factor, analyzes the preprocessed data, and calculates the reactive power, power loss, and voltage deviation of each wind turbine;

[0115] An optimal parameter combination determination module, which generates a fitness value reflecting the working state of the wind turbine based on the power loss and voltage deviation, determines the maximization of the fitness value as the optimization goal, uses a genetic algorithm for optimization, obtains the best combination of voltage, current, and power factor, and calculates the best reactive power based on this combination;

[0116] The real-time monitoring and control module is used to collect the current voltage, current and power factor at the key nodes of each wind turbine in the wind farm, and calculate the current voltage, current, power factor and reactive power of the corresponding wind turbine based on this. Based on the deviation between the optimal reactive power and the current reactive power of each wind turbine, the reactive voltage of each wind turbine is adjusted.

[0117] The above formulas are all calculated by taking the numerical values without considering the dimensions. The formulas are obtained by software simulation of a large amount of collected data to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0118] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0119] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application.

Claims

1. A method for controlling reactive voltage in a wind farm, characterized in that: The specific steps include: Step 1: Mark the generator at the top of each wind turbine tower in the wind farm, the converter inside the wind turbine, and the bottom of the wind turbine tower as the key nodes of the wind turbine, obtain the historical voltage, current, and power factor data at the key nodes, and use them to calculate the historical voltage, current, and power factor data of the wind turbine; Step 2: Preprocess the collected voltage, current and power factor, analyze the preprocessed data, and calculate the reactive power, power loss and voltage deviation of each wind turbine; Step 3: Generate a fitness value reflecting the working state of the wind turbine based on power loss and voltage deviation, and determine the maximization of the fitness value as the optimization goal. Use genetic algorithm for optimization to obtain the best combination of voltage, current and power factor, and calculate the best reactive power based on this combination. Step 4: Collect the current voltage, current and power factor at the key nodes of each wind turbine in the wind farm, and use them to calculate the current voltage, current, power factor and reactive power of the corresponding wind turbine. Adjust the reactive voltage of each wind turbine based on the deviation between the optimal reactive power and the current reactive power of each wind turbine.

2. A wind farm reactive voltage control method according to claim 1, characterized in that: The specific logic for calculating the voltage, current and power factor data of the fan is: Voltage sensors, current sensors and power analyzers are installed at the key nodes of each wind turbine to obtain the voltage, current and power factor data of each wind turbine. The formula for obtaining the voltage data of the wind turbine is: Among them, V a is the voltage value of the ath key node in the wind turbine, V′ is the voltage value of the wind turbine, n is the number of key nodes on the wind turbine, a is the index of the key node on the wind turbine, and a∈[1,n]; Similarly, the current I′ and power factor pf′ of the fan are obtained.

3. A wind farm reactive voltage control method according to claim 2, characterized in that: The specific logic for calculating reactive power, power loss and voltage deviation of each wind turbine is as follows: The collected voltage, current and power factor are preprocessed. The preprocessing includes detecting and eliminating abnormal data based on the Z-score method and filling missing data with the mean filling method. The reactive power calculation is based on the formula: Among them, Q is the reactive power of the fan, V, I, and pf are the pre-processed voltage, current, and power factor, respectively; The power loss is calculated based on the formula: P=I 2 ×R Where P is the power loss of the fan, and R is the circuit resistance of the fan; The voltage deviation is calculated based on the formula: Where, v is the voltage deviation of the fan, is the target voltage of the fan.

4. A wind farm reactive voltage control method according to claim 3, characterized in that: The logic for obtaining the optimal reactive power is: The voltage, current and power factor combination of each wind turbine in the wind farm is taken as an individual to form the initial population, and the fitness value of each individual is calculated. The calculation formula is as follows: F=-(λ1*P+λ2*v) Where F is the fitness value of the individual, λ1 and λ2 represent the power loss weight and voltage deviation weight corresponding to the individual, respectively, 0<λ2<λ1<1, and λ1+λ2=1; Sort the fitness values ​​from large to small, select the individuals in the front row as the parents, randomly select two parents to cross over to generate new individuals, then perform mutation operations on the newly generated individuals, integrate the newly generated individuals and the parent individuals into a new population, repeat the calculation of fitness values, selection, crossover and mutation operations until the preset fitness threshold is reached, select the individual with the highest fitness as the optimal voltage, current and power factor combination, and calculate the optimal reactive power based on this combination.

5. A wind farm reactive voltage control method according to claim 4, characterized in that: The logic for adjusting the reactive power setpoint of each fan is based on: The formula for obtaining the deviation between the current wind turbine reactive power and the optimal reactive power is: Among them, ΔQ is the power deviation between the current reactive power of the wind turbine and the optimal reactive power, Q is the current reactive power of the wind turbine, is the optimal reactive power; Compare the deviation between the reactive power of the current wind turbine and the optimal reactive power with the preset deviation threshold; if the deviation between the reactive power of the current wind turbine and the optimal reactive power is lower than the preset deviation threshold, no adjustment is made temporarily; if the deviation between the reactive power of the current wind turbine and the optimal reactive power is higher than the preset deviation threshold, obtain an adjustment factor to adjust the reactive voltage of the corresponding wind turbine; The formula used to obtain the adjustment factor is: Among them, α pf is the adjustment factor of wind turbine reactive power, γ pf is the nonlinear adjustment coefficient of reactive power adjustment factor, k pf is the basic adjustment coefficient of reactive power adjustment factor, ω pf is the dynamic weight of the reactive power adjustment factor; The formula for obtaining dynamic weight is: Among them, ω pg is the dynamic weight of the reactive power adjustment factor, β is the importance coefficient of the historical deviation, and its value range is [0,1]. ∈ is the threshold of the deviation. The reactive power of the wind turbine at T collection moments in the time period before the current moment is obtained, and the reactive power at the tth collection moment in the time period before the current moment is calibrated as Q(t), where t is the index of the collection moment, and t∈[1,T]. ΔQ(t) represents the deviation between the reactive power of the wind turbine at the tth collection moment in the time period before the current moment and the optimal reactive power. The formula for updating the reactive power setpoint is: Q new =Q-α pf ·ΔQ+μ pf ·(ΔQ) 2 Among them, Q new is the target reactive power of the wind turbine after update, μ pf is the square error weight; The formula for obtaining the deviation between the reactive power of the current wind turbine and the optimized target reactive power is: Δq=Q new -Q Among them, Δq is the deviation between the current wind turbine reactive power and the optimized target reactive power; The deviation between the reactive power of the current wind turbine and the optimized target reactive power is judged. If Δq>0, it means that the reactive power needs to be increased, that is, the reactive voltage needs to be increased, and the capacitor group is enabled; if Δq<0, it means that the reactive power needs to be reduced, that is, the reactive voltage needs to be reduced, and the inductor is enabled.

6. A wind farm reactive voltage control system, characterized in that: The wind farm reactive voltage control system is used to implement the wind farm reactive voltage control method according to any one of claims 1 to 5, comprising: The data acquisition module is used to mark the generator at the top of each wind turbine tower in the wind farm, the converter inside the wind turbine and the bottom of the wind turbine tower as the key nodes of the wind turbine, obtain the historical voltage, current and power factor data at the key nodes, and calculate the historical voltage, current and power factor data of the wind turbine based on this; The data preprocessing and analysis module is used to preprocess the collected voltage, current and power factor, analyze the preprocessed data, and calculate the reactive power, power loss and voltage deviation of each wind turbine; The optimal parameter combination determination module is used to generate a fitness value reflecting the working state of the wind turbine based on power loss and voltage deviation, and determine the maximization of the fitness value as the optimization goal, use genetic algorithm for optimization, obtain the best combination of voltage, current and power factor, and calculate the best reactive power based on this combination; The real-time monitoring and control module is used to collect the current voltage, current and power factor at the key nodes of each wind turbine in the wind farm, and use this to calculate the current voltage, current, power factor and reactive power of the corresponding wind turbine, and adjust the reactive voltage of each wind turbine based on the deviation between the optimal reactive power and the current reactive power of each wind turbine.

Images