Electric energy quality voltage regulation control method and control device for intelligent power station

Abstract

The invention relates to the technical field of electric energy quality control, in particular to an electric energy quality voltage regulation control method and device for an intelligent power station. The method comprises the following steps: collecting corresponding data at each moment; determining the hardware state of the device according to the action times and the reactive compensation amount, and determining a correction coefficient according to the hardware state of the device; predicting the load value and the voltage value at the future moment according to the historical load value and the historical voltage value, and correcting the load value at the current moment according to the difference between the past load value and the predicted load value and a correction coefficient; and constructing an objective function based on the voltage deviation, the reactive compensation amount, the number of actions and the future load trend, and solving the objective function by using a dynamic inertia weight to realize accurate voltage regulation. According to the invention, the voltage stability is improved, and device conflicts are avoided.

Description

Technical Field

[0001] This application relates to the technical field of power quality control, and particularly to a power quality voltage regulation control method and a control device for intelligent power stations. Background Art

[0002] With the large-scale access of distributed energy and the rapid development of smart grids, power quality problems have become a key factor restricting the stable operation of the power grid. Reactive power voltage control is an important link in the operation of power systems. Its purpose is to maintain the stability of voltage in the power system by adjusting the distribution and magnitude of reactive power, ensuring the normal operation of power equipment and power quality.

[0003] Existing technologies often use a single voltage regulation control device for control. In the patent "CN118316135A Real-time Voltage Control Method for Active Distribution Networks Based on Reactive Power Regulation of Photovoltaic Inverters", the reactive power regulation ability of photovoltaic inverters is utilized, combined with a multi-agent deep reinforcement learning algorithm (MATD3PG) to achieve real-time voltage control of active distribution networks. Although this method does not require additional equipment, it may not be able to handle some complex situations. For example, when the photovoltaic output is insufficient or the inverter capacity is limited, it may not be able to provide sufficient reactive power compensation; controlling different devices for voltage regulation may lead to adjustment conflicts resulting in insufficient voltage regulation, or simultaneous adjustment may cause overcompensation. Summary of the Invention

[0004] To solve the technical problems of conflicts in adjustment of different devices and overcompensation, this application provides a power quality voltage regulation control method and a control device for intelligent power stations. The specific technical solutions adopted are as follows: In the first aspect, this application proposes a power quality voltage regulation control method for intelligent power stations. The method includes the following steps: Collect the reactive power, active power, voltage, the action times of OLTC, and the capacity utilization rate of SVG at each moment; Calculate the reactive power compensation capacity, and obtain the reactive power compensation amount at the current moment in combination with the capacity utilization rate; obtain the device hardware state at the current moment according to the difference between the reactive power compensation amount and the reactive power compensation capacity at the current moment, and the difference between the action times at the current moment and the maximum action times; combine the device hardware state with a preset initial correction coefficient to obtain the correction coefficient at the current moment; Obtain the predicted load value and the predicted voltage value at a future preset moment respectively through the historical load value and the historical voltage value before the current moment; correct the load value at the current moment based on the difference between the load value at the past moment and the predicted load value and the correction coefficient at the current moment to obtain the corrected load value at the current moment; Construct an objective function based on the voltage deviation, reactive power compensation amount, number of operations at the current moment, as well as the future load trend and voltage deviation; adjust the preset inertia weight based on the load change rate to obtain a dynamic inertia weight; and solve the objective function through the dynamic inertia weight to obtain the target compensation amount, and achieve precise voltage regulation through the target compensation amount.

[0005] In the above solution, this application triggers reactive power compensation and tap adjustment in advance based on load trend prediction, eliminates voltage overshoot of traditional lag control, and corrects errors according to real-time load and voltage regulating device status. When predicting load growth, multi-objective optimization triggers SVG pre-charging reactive power and OLTC pre-adjusting taps in advance, effectively reducing voltage fluctuations during load growth and improving power quality. At the same time, due to the combination of feedforward and feedback collaborative regulation, it avoids frequent OLTC operations and extends the equipment life; the adaptive strategy adapts to load fluctuation scenarios in real time, significantly improving voltage stability, enabling different devices to adjust successively and avoiding conflicts.

[0006] In one embodiment, the load value is the sum of the reactive power and active power at each moment.

[0007] In one embodiment, the method for obtaining the predicted load value is as follows: Extract the load values of the previous 24 hours before the current moment at a 5-minute step, and obtain the load values of the next 5 minutes, next 10 minutes, and next 15 minutes at the current moment through time series analysis; Extract the voltage values of the previous 24 hours before the current moment at a 5-minute step, and obtain the voltage values of the next 5 minutes, next 10 minutes, and next 15 minutes at the current moment through time series analysis.

[0008] In one embodiment, the corrected load value is positively correlated with the differences between the load values at past moments and the predicted load value, the correction coefficient at the current moment, and the load value at the current moment.

[0009] In one embodiment, the reactive power compensation amount at the current moment is the product of the reactive power compensation capacity and the capacity utilization rate of the SVG at the current moment.

[0010] In one embodiment, the method for obtaining the device hardware status at the current moment according to the difference between the reactive power compensation amount and the reactive power compensation capacity at the current moment, and the difference between the number of operations at the current moment and the maximum number of operations is as follows: , represents the reactive power compensation amount at the current moment, represents the reactive power compensation capacity, represents the number of operations at the current moment, represents the maximum number of operations per day, , respectively represent preset weight coefficients represents the hardware state of the device

[0011] In one embodiment, the expression of the objective function is: , represents the voltage deviation at time t represents the reactive power compensation amount of the SVG at time t represents the number of actions at time t represents the corrected load value at the i-th moment in the future after time t represents the voltage deviation at the i-th moment in the future at time t , , represent the preset weight values of the three

[0012] In one embodiment, the voltage deviation is the absolute value of the difference between the voltage at the current moment and the rated voltage

[0013] In one embodiment, the method for adjusting the preset inertia weight based on the load change rate to obtain the dynamic inertia weight is: , represents the preset initial inertia weight represents the preset inertia weight adjustment amplitude represents the load change rate at the current moment represents the preset change threshold is the sign function represents the dynamic inertia weight

[0014] Second, the embodiments of the present application also provide a power quality voltage regulation control device for an intelligent power station, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the power quality voltage regulation control method for an intelligent power station described in any one of the above

[0015] The beneficial effects of the present application are: This application triggers reactive power compensation and tap changer adjustment in advance based on load trend prediction, eliminates the voltage overshoot of traditional lag control, and corrects errors according to real-time load and voltage regulating device status. When predicting load growth, multi-objective optimization triggers SVG to pre-charge reactive power and OLTC to pre-adjust the tap in advance, effectively reducing voltage fluctuations during load growth and improving power quality. At the same time, due to the combination of feedforward and feedback co-regulation, it avoids frequent OLTC operations and extends the equipment life; the adaptive strategy adapts to load fluctuation scenarios in real time, significantly improving voltage stability, enabling different devices to adjust successively and avoiding conflicts. Description of the Drawings

[0016] To more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of the power quality voltage regulation control method for an intelligent power station provided by an embodiment of the present application. Detailed Embodiments

[0018] To further elaborate on the technical means and effects adopted by the present application to achieve the intended invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific embodiments, structures, features, and effects of the power quality voltage regulation control method and control device for an intelligent power station proposed according to the present application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs.

[0020] Embodiments of the power quality voltage regulation control method and control device for an intelligent power station: The following specifically describes the specific solutions of the power quality voltage regulation control method and control device for an intelligent power station provided by the present application in combination with the drawings.

[0021] Please refer to Figure 1 , which shows the flowchart of the power quality voltage regulation control method for an intelligent power station provided by an embodiment of the present application. The method includes the following steps: The voltage regulation device for the intelligent power station in this application consists of an on-load tap-changer (OLTC) and a static var generator (SVG). The OLTC realizes the coarse adjustment of voltage by adjusting the tap position of the transformer, has a large adjustment range, and is suitable for handling long-term and stable voltage deviations; the SVG has a fast dynamic response ability and can accurately adjust reactive power in a short time, and is suitable for coping with rapidly changing voltage fluctuations.

[0022] The OLTC is a device that can change the tap position when the transformer is under load. Its working principle is to adjust the output voltage by changing the turns ratio of the transformer winding. When the grid voltage changes, the OLTC switches the tap position according to the control signal, thereby changing the transformation ratio of the transformer and keeping the output voltage within the specified range.

[0023] The SVG converts the DC electrical energy on the DC side into AC electrical energy and injects it into the grid by controlling the on-off of turn-off power electronic devices (such as IGBTs). Its basic principle is to quickly adjust the magnitude and phase of the output current according to the reactive power demand of the grid, so as to realize the dynamic compensation of reactive power. Specifically, the SVG detects the voltage and current signals of the grid, calculates the magnitude and direction of the reactive power, and then controls the IGBT module to generate the corresponding compensation current, which is injected into the grid to balance the reactive power, and then adjusts the grid voltage.

[0024] In this application, the OLTC and the SVG are connected in parallel, and the SVG and the OLTC are integrated and designed as a whole. According to the real-time working conditions of the grid and the characteristics of voltage fluctuations, the action priorities of the SVG and the OLTC are dynamically adjusted. For example, when the voltage fluctuates rapidly, the SVG is preferentially started for rapid reactive power compensation to suppress voltage fluctuations; when the voltage deviation is large and relatively stable, the OLTC is then started to adjust the tap to achieve long-term voltage stability. This dynamic priority allocation strategy can give full play to the respective advantages of the SVG and the OLTC and improve the efficiency and accuracy of voltage regulation.

[0025] Step S001, collect the corresponding data at each moment.

[0026] First, collect data based on the data acquisition device, and set the acquisition frequency. In this embodiment, the acquisition frequency is 1 s, that is, data is collected every 1 s.

[0027] The data to be collected includes the active power, reactive power, and voltage collected by the wattmeter and the voltmeter. And an OLTC action counter and an SVG capacity monitoring device are respectively installed on the OLTC and the SVG to collect the action times of the OLTC and the capacity utilization rate of the SVG. The OLTC action counter only counts the action times of the current day and starts counting from 0 every new day.

[0028] So far, the active power, reactive power, voltage, the number of operations of the OLTC, and the capacity utilization rate of the SVG collected each time have been obtained.

[0029] Step S002: Determine the hardware state of the device according to the number of operations and the reactive power compensation amount, and determine the correction coefficient according to the quality of the device hardware state.

[0030] Receive the above-mentioned collected data through the edge control device, and analyze the above-mentioned collected data to complete the voltage regulation control of power quality.

[0031] When performing voltage regulation control, the state of the current voltage regulation device also needs to be considered. When the SVG is close to the maximum reactive power compensation capacity or the number of operations of the OLTC is close to the upper limit, the hardware is in a high-voltage or high-risk state. At this time, if relying on the historical load trend, the result may be disconnected from the actual demand. That is, the risk of SVG overload. Historical data may not reflect the current capacity limit of the SVG. The predicted high-load demand may require the SVG to output reactive power beyond its capacity, resulting in equipment damage. Or the OLTC operates frequently. Trend prediction may ignore the remaining life margin of the OLTC and continuously trigger tap adjustments, accelerating contact wear. The reactive power compensation capacity is calculated based on the "Reactive Power Compensation Capacity Calculation Coefficient Table". The reactive power compensation capacity is the maximum reactive power capacity. Multiply the capacity utilization rate of the SVG at the current moment by the reactive power compensation capacity to obtain the reactive power compensation amount at the current moment.

[0032] Based on the reactive power compensation amount and the difference between the number of operations and their upper limits at the current moment, correct the state of the voltage regulation device to obtain the hardware state of the device.

[0033] The hardware state of the device is negatively correlated with the difference between the reactive power compensation amount and its upper limit, and the difference between the number of operations and its upper limit, respectively.

[0034] It should be noted that negative correlation means that when one variable increases, the other variable decreases accordingly. The change directions of the two variables are opposite. When one variable changes from large to small or from small to large, the other variable also changes from small to large or from large to small; the specific relationship is determined by the actual application, and this application does not make special restrictions.

[0035] Preferably, in this embodiment, the expression of the hardware state of the device is: , represents the reactive power compensation amount at the current moment, represents the reactive power compensation capacity, represents the number of operations at the current moment, represents the maximum number of operations per day, , represent the weight coefficients respectively, represents the hardware state of the device. , The values of

[0036] are 0.6 and 0.4 respectively. Since SVG is responsible for quick response, and when the reactive power compensation amount of SVG exceeds the maximum, the damage to the device is greater than that when the action times of OLTC exceed the maximum, so its corresponding weight coefficient is larger.

[0037] The value range of is

[0038] , and the larger it is, the better the hardware state. When the SVG capacity utilization rate is low and the OLTC action times are small, HHI approaches 1; otherwise it approaches 0. Then the formula for dynamically adjusting the correction coefficient is where represents the correction coefficient at the current moment, norm() represents the normalization function,

[0039]

[0040]

[0041]

[0042] Step S003, predict the load value and voltage value at the future moment according to the historical load value and historical voltage value, and correct the load value at the current moment according to the difference between the past load value and the predicted load value and the correction coefficient.

[0042] Since the load change directly affects the voltage level, and voltage regulation is the key means to maintain the power supply quality. When the load increases, the line current increases, resulting in an increase in voltage loss, which may cause a local voltage drop; on the contrary, a sudden decrease in load may cause the voltage to rise. By adjusting the voltage tap or reactive power compensation capacity of the voltage regulating device, compensating for the voltage deviation caused by load fluctuations, the stable operation of the power grid under different load scenarios can be ensured. The reactive power compensation capacity is the reactive power supplementary capacity.

[0043] This application analyzes the load trend through time series analysis to capture the load change trend in advance, providing a basis for forward-looking decision-making for the control device. Specifically, load forecasting can help the system predict the voltage fluctuation risk, optimize the reactive power compensation strategy (such as injecting reactive power in advance by SVG) and the OLTC tap adjustment timing, so as to complete the control action before the load mutation and reduce the voltage deviation. At the same time, the trend data can be used to dynamically adjust the action priority of the equipment, reduce the mechanical wear of the OLTC, and extend the equipment life.

[0044] Since the electric power load has significant time periodicity and exhibits non-linear and non-stationary characteristics, it is necessary to use time series analysis method to extract the key information of the electric power load to predict future data.

[0045] Specifically, for each moment, several historical load values are extracted. Through the ARM processor integrated floating-point operation unit (FPU), the historical load values are input, and the time series analysis method is used to output several future load values. In this embodiment, the historical load values extracted are the load values of 24 hours, the extraction step is 5 minutes, and the output load values are the load values of the current moment in the next 5 minutes, the next 10 minutes, and the next 15 minutes. The load value of each moment is the sum of the reactive power and the active power at each moment. Based on the same operation above, several future voltage values are output through the historical voltage values.

[0046] It should be noted that the load value is mainly based on the latest input. That is, if the predicted values at the same future moment for time t and time t + 1 are different, the value at time t + 1 shall prevail. For example, if the predicted value for 10 minutes in the future at time t is different from the predicted value for 5 minutes in the future at time t + 1, the predicted value for 5 minutes in the future at time t + 1 shall be used as the predicted value at this time.

[0047] Since the time series analysis method depends on the periodic law of historical load data, when extreme weather or equipment failures occur in the power grid, the predicted value may deviate from the actual load. By introducing a real-time feedback correction mechanism, the prediction result can be dynamically calibrated, reducing the control strategy deviation caused by the lag of trend analysis, ensuring the accuracy of the actions of SVG and OLTC actuators, and thus improving the stability of voltage regulation and the equipment service life.

[0048] Therefore, based on the difference between the load value at the past moment and the predicted load value and the correction coefficient at the current moment, the load value at the current moment is corrected to obtain the corrected load value at the current moment.

[0049] The corrected load value is positively correlated with the difference between the load value at the past moment and the predicted load value, the correction coefficient at the current moment, and the load value at the current moment.

[0050] It should be noted that positive correlation means that when one variable increases, the other variable also increases, and the change directions of the two variables are the same. When one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large. The specific relationship is determined by the actual application, and no special restrictions are made in this application.

[0051] Preferably, in this embodiment, the expression of the corrected load value is: , represents the corrected load value at time t - 1, represents the predicted load value at time t - 1, represents the predicted load value at time t, represents the correction coefficient at the current moment, represents the corrected load value at time t.

[0052] Among them, The value range of is [0, 1]; the larger its value, the stronger the correction effect, and the smaller its value, the more the load change trend is retained to avoid excessive correction.

[0053] When the load changes smoothly, the load value obtained by trend analysis should be closer to the actual value. Therefore, it is necessary to increase the correction coefficient so that the corrected load value will be closer to the recent actual value. When the load fluctuates greatly, it is necessary to reduce the correction coefficient to retain the load change trend and avoid excessive correction.

[0054] So far, the correction of the load value at each moment has been completed.

[0055] Step S004, construct an objective function based on voltage deviation, reactive power compensation amount, number of operations, and future load trend, and solve the objective function using dynamic inertia weight to achieve precise voltage regulation.

[0056] In the voltage regulation of intelligent power stations, a single - target control strategy often cannot meet complex actual requirements. For example, only focusing on voltage stability may cause frequent device actions and shorten the service life of the device; while only considering the device life may not be able to effectively maintain voltage quality. Therefore, multi - objective optimization is adopted to balance multiple conflicting objectives to achieve the comprehensive optimal performance of the system. The main goal of this algorithm is to minimize the number of device actions, reduce active power losses while ensuring voltage quality, and at the same time combine the forward - looking information provided by load trend analysis to formulate a more reasonable control strategy in advance.

[0057] Based on the above analysis, construct an objective function through the current - moment voltage deviation, reactive power compensation amount, number of operations, and future load trend.

[0058] Preferably, in this embodiment, the objective function is: , represents the voltage deviation at time t, represents the reactive power compensation amount of the SVG at time t, represents the number of operation times at time t, represents the corrected load value at the i-th moment in the future after time t, represents the voltage deviation at the i-th moment in the future after time t, , , represent the weight values of the three.

[0059] Among them, the voltage deviation is the absolute value of the difference between the voltage at the current moment and the rated voltage, which reflects the degree of deviation of the grid voltage from the rated value; too large voltage deviation will affect the normal operation of electrical equipment and may even cause equipment damage. Each operation of the OLTC will cause a certain amount of wear on its contacts, and frequent operations will shorten its service life; by restricting the number of operations of the OLTC, the maintenance cost and replacement frequency of the equipment can be reduced. Among them, combining the predicted load value is to make the control strategy more forward-looking and respond to load changes in advance.

[0060] In this embodiment, the weight values are respectively taken as 0.5, 0.3 and 0.2, and the weight of the voltage deviation is relatively high because ensuring voltage quality is the primary task of grid operation. The equipment life is also relatively important. Appropriately reducing the number of operations of the OLTC can extend the service life of the equipment and reduce the operation and maintenance cost. The weights of considering future load and voltage deviation are relatively small, but they are of great significance for formulating a reasonable control strategy in advance.

[0061] After determining the objective function, in order to ensure the feasibility and safety of the finally output control strategy, it is also necessary to meet the constraint conditions. The constraint adjustment of this application is as follows: , represents the rated voltage, represents the reactive power compensation capacity of the SVG, which is 30 in this embodiment , exceeding the reactive power compensation capacity may cause damage to the SVG equipment and affect its normal operation. The number of operations of the OLTC is limited to no more than 200 times per day to ensure the service life of the equipment. Frequent tap adjustments will accelerate the wear of the contacts and increase the risk of equipment failure. The voltage deviation is controlled within 1% to meet the grid voltage quality standard and ensure the normal operation of electrical equipment.

[0062] This application solves the objective function through an improved particle swarm algorithm. The inertia weight controls the global and local search capabilities of the particles. The larger its value, the more inclined to perform global search, and vice versa, it is inclined to local search. The traditional particle swarm algorithm uses a fixed inertia weight, which has a significant impact on load fluctuations in the intelligent power station voltage regulation scenario. During load fluctuations, such as during the evening peak, the load changes greatly, and the traditional fixed inertia weight may not be able to adapt in time, resulting in falling into a local optimum. In a stable scenario, such as at night, the load changes little, and the traditional fixed inertia weight may cause oscillations and reduce the convergence accuracy.

[0063] Therefore, it is necessary to dynamically adjust the inertia weight, and adjust the inertia weight based on the load change rate at the current moment. In this embodiment, the expression of the dynamic inertia weight is: , represents the initial inertia weight, represents the inertia weight adjustment amplitude, represents the load change rate at the current moment, represents the change threshold, is the sign function, represents the dynamic inertia weight. The initial inertia weight is set to 0.8, and the inertia weight adjustment amplitude is 0.3; the value of the change threshold is 0.1. The load change rate is the difference between the corrected load value at the current moment and the corrected load value at the previous moment.

[0064] After updating the particle positions through the dynamic inertia weight, it is necessary to check whether the position of each particle satisfies the constraint conditions. If the position of a certain particle does not satisfy the constraint conditions, it is adjusted to make it satisfy the constraints. For example, if exceeds its maximum capacity , then it is adjusted to .

[0065] The final output is the optimal control sequence, which clarifies the action priorities of each actuator and the corresponding target compensation amounts. Specifically, the actuator action priorities determine the order of actions of different actuators in the current situation. The target compensation amount specifies the specific reactive power for each actuator. For example, the SVG may need to inject 10 Mvar of reactive power, or the OLTC needs to adjust the tap to a certain specific position to achieve precise voltage regulation.

[0066] Thus, the voltage regulation of power quality is achieved.

[0067] Based on the same inventive concept as the above method, an embodiment of the present invention further provides a power quality voltage regulation control device for an intelligent power station, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above methods for power quality voltage regulation control of an intelligent power station are implemented.

[0068] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0069] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A method for regulating and controlling power quality in an intelligent power station, characterized in that, The method includes the following steps: Collect the reactive power, active power, voltage, the action times of the OLTC, and the capacity utilization rate of the SVG at each moment; Calculate the reactive power compensation capacity, and obtain the reactive power compensation amount at the current moment in combination with the capacity utilization rate; obtain the device hardware state at the current moment according to the difference between the reactive power compensation amount and the reactive power compensation capacity at the current moment, and the difference between the action times at the current moment and the maximum action times; combine the device hardware state with the preset initial correction coefficient to obtain the correction coefficient at the current moment; Obtain the predicted load value and the predicted voltage value at a future preset moment respectively through the historical load value and the historical voltage value before the current moment; correct the load value at the current moment based on the difference between the load value in the past moment and the predicted load value and the correction coefficient at the current moment to obtain the corrected load value at the current moment; Construct an objective function based on the voltage deviation, reactive power compensation amount, action times at the current moment, and the future load trend and voltage deviation; adjust the preset inertia weight based on the load change rate to obtain a dynamic inertia weight; and solve the objective function through the dynamic inertia weight to obtain the target compensation amount, and achieve precise voltage regulation through the target compensation amount.

2. The power quality voltage regulation control method for an intelligent power station according to claim 1, characterized in that The load value is the sum of the reactive power and the active power at each moment.

3. A power quality voltage regulation control method for an intelligent power station according to claim 1, characterized in that, The method for obtaining the predicted load value and the predicted voltage value is as follows: Extract the load values in the 24 hours before the current moment at a step of 5 minutes, and obtain the load values at 5 minutes, 10 minutes, and 15 minutes in the future of the current moment through the time series analysis method; Extract the voltage values in the 24 hours before the current moment at a step of 5 minutes, and obtain the voltage values at 5 minutes, 10 minutes, and 15 minutes in the future of the current moment through the time series analysis method.

4. A power quality voltage regulation control method for an intelligent power station according to claim 1, characterized in that, The corrected load value is positively correlated with the differences between the load value in the past moment and the predicted load value, the correction coefficient at the current moment, and the load value at the current moment respectively.

5. A power quality voltage regulation control method for an intelligent power station according to claim 1, characterized in that, The reactive power compensation amount at the current moment is the product of the reactive power compensation capacity and the capacity utilization rate of the SVG at the current moment.

6. A power quality voltage regulation control method for an intelligent power station according to claim 1, characterized in that The method for obtaining the device hardware state at the current moment according to the difference between the reactive power compensation amount and the reactive power compensation capacity at the current moment, and the difference between the action times at the current moment and the maximum action times is as follows: , represents the reactive power compensation amount at the current moment, represents the reactive power compensation capacity, represents the number of operation times at the current moment, represents the maximum value of the number of operation times per day, , respectively represent the preset weight coefficients, represents the hardware state of the device.

7. A power quality voltage regulation control method for an intelligent power station according to claim 1, characterized in that, The expression of the objective function is: , represents the voltage deviation at time t, represents the reactive power compensation of the SVG at time t, represents the number of operation times at time t, represents the corrected load value at the i-th moment in the future after time t, represents the voltage deviation at the i-th moment in the future after time t, , , represent the preset weight values of the three.

8. A power quality voltage regulation control method for an intelligent power station according to claim 7, characterized in that The voltage deviation is the absolute value of the difference between the voltage at the current moment and the rated voltage.

9. The power quality voltage regulation control method for an intelligent power station according to claim 1, characterized in that, The method for adjusting the preset inertia weight based on the load change rate to obtain a dynamic inertia weight is as follows: , represents a preset initial inertia weight, represents a preset inertia weight adjustment range, represents the load change rate at the current moment, represents a preset change threshold, is a sign function, represents a dynamic inertia weight.

10. A power quality voltage regulation control device for an intelligent power station, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a method for regulating the power quality voltage of an intelligent power station as described in any one of claims 1-9.

Images