Method and device for obtaining reactive power loss of new energy stations

Abstract

The present invention provides a method and device for obtaining reactive power loss of a new energy station, wherein the method comprises: obtaining one or more groups of reactive data samples based on the target reactive power of the grid connection point, the reactive data samples comprising the total reactive power data of the power generation unit and the reactive power data of the grid connection point; inputting the reactive data samples and the target reactive power of the grid connection point into a multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model, the multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid connection point, and the target total reactive power of the power generation unit is used to determine the reactive loss of the new energy station. The method and device for obtaining reactive power loss of a new energy station provided by the present invention obtain the reactive power loss of the new energy station through reactive data samples and a multivariate driving model, thereby improving the reliability of obtaining reactive power loss of the new energy station.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method and device for acquiring reactive power loss of a new energy station. Background Art

[0002] New energy plants connected to UHV DC lines need to adopt the island operation mode. The reactive power loss compensation control method of new energy plants in the island operation mode needs to take into account the reactive power loss of new energy plants. Accurately calculating the reactive power loss compensation of new energy plants is the core issue of the island operation mode.

[0003] The traditional method of calculating reactive power loss in new energy stations relies on the electrical parameters of the lines, transformers, and control units as well as the four remote control data. In addition, the pass rate of state estimation is low, so there are problems such as low reliability of the calculated reactive power loss. Summary of the invention

[0004] The present invention provides a method and device for acquiring reactive power loss of a new energy station, which are used to solve the defect of low reliability of reactive power loss calculation in the prior art and improve the accuracy of reactive power loss acquisition.

[0005] In a first aspect, the present invention provides a method for obtaining reactive power loss of a new energy station, comprising:

[0006] Acquire one or more groups of reactive data samples based on the target reactive power of the grid connection point, wherein the reactive data samples include total reactive power data of the power generation unit and reactive power data of the grid connection point;

[0007] The reactive data sample and the target reactive power of the grid-connected point are input into a multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model. The multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid-connected point. The target total reactive power of the power generation unit is used to determine the reactive loss of the new energy station.

[0008] Optionally, the multivariate driving model is:

[0009]

[0010]

[0011]

[0012] in, is the target reactive power of the grid-connected point; Q gentar is the target total reactive power of the generating unit; Q geni is the total reactive power of the generating unit of the i-th group of reactive data samples, is the grid-connected point reactive power of the i-th group of reactive data samples.

[0013] Optionally, acquiring one or more groups of reactive data samples based on the target reactive power of the grid connection point includes:

[0014] Determine the sample screening interval based on the target reactive power of the grid connection point and the preset accuracy;

[0015] The historical samples whose reactive power of the grid-connected point meets the sample screening interval are determined as the reactive data samples.

[0016] Optionally, before inputting the reactive data samples and the target reactive power of the grid-connected point into the multivariate driving model, the method further includes: determining that the number of the reactive data samples is greater than or equal to a preset number of samples.

[0017] Optionally, the method further comprises:

[0018] When it is determined that the number of reactive data samples is less than the preset number of samples, acquiring real-time reactive data of the new energy station;

[0019] Inputting the real-time reactive power data of the new energy station into an inductance equivalent model, and obtaining the equivalent inductance of the new energy station output by the inductance equivalent model;

[0020] The reactive loss of the new energy station and the target total reactive power of the power generation unit are obtained based on the equivalent inductance and the target reactive power of the grid connection point.

[0021] Optionally, the method further comprises:

[0022] Determine the reactive power adjustment amount of each of the power generation units based on the target total reactive power of the power generation units, the reactive rated capacity of each of the power generation units, and the total reactive rated capacity of the new energy station;

[0023] A reactive power adjustment instruction is sent to each of the power generation units based on the reactive power adjustment amount.

[0024] In a second aspect, the present invention further provides a device for acquiring reactive power loss of a new energy station, comprising:

[0025] An acquisition unit, used to acquire one or more groups of reactive data samples based on the target reactive power of the grid connection point, wherein the reactive data samples include total reactive power data of the power generation unit and reactive power data of the grid connection point;

[0026] A model unit is used to input the reactive data sample and the target reactive power of the grid-connected point into a multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model, wherein the multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid-connected point.

[0027] In a third aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for obtaining reactive power loss of a new energy station as described in the first aspect is implemented.

[0028] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for obtaining reactive power loss of a new energy station as described in the first aspect.

[0029] In a fifth aspect, the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for obtaining reactive power loss of a new energy station as described in the first aspect.

[0030] The method and device for obtaining reactive power loss of new energy stations provided by the present invention obtain reactive power loss of new energy stations through reactive power data samples and multivariate driving models, thereby improving the reliability of reactive power loss acquisition. In addition, the method for obtaining reactive power loss of new energy stations provided by the embodiments of the present invention comprehensively utilizes the linear regression relationship between historical data and variables, and reduces the reactive power loss of new energy plants from a complex function to a univariate function, thereby solving the problem of slow data uplinking and complex network loss calculation of traditional new energy power generation units. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 This is one of the flow charts of the method for obtaining reactive power loss of a new energy station provided in an embodiment of the present invention;

[0033] Figure 2 This is a second flow chart of a method for obtaining reactive power loss of a new energy station provided in an embodiment of the present invention;

[0034] Figure 3 It is a structural schematic diagram of a device for acquiring reactive power loss of a new energy station provided by an embodiment of the present invention;

[0035] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0037] The following is an introduction to the technical terms involved in the present invention:

[0038] AVC: AVC is the abbreviation of Automatic Voltage Control, commonly known as automatic voltage control. The control system deployed at the renewable energy station is used to receive the instructions of the AVC master station of the power grid and adjust the reactive equipment in the station to make the voltage / reactive power of the grid connection point meet the requirements of the master station. It is the main control method for the power grid to control the reactive power of renewable energy stations.

[0039] Active power: directly consumes electrical energy, converts it into mechanical energy, thermal energy, chemical energy or sound energy, and uses these energies to do work. This part of power is called active power;

[0040] Reactive power: consumes electrical energy, but only converts it into another form of energy. This energy is a necessary condition for electrical equipment to work, and this energy is periodically converted with electrical energy in the power grid. This part of power is called reactive power.

[0041] Power generation unit: The power generation unit of a new energy station mainly refers to the minimum active power control unit of the new energy station; for photovoltaic power stations, it mainly refers to photovoltaic inverters; for wind farms, it mainly refers to wind turbine clusters or wind turbine energy management platforms.

[0042] Grid connection point: The power output aggregation point of new energy stations. Usually, all assessments of new energy are conducted at the grid connection point.

[0043] Reactive loss: The reactive loss of new energy stations mainly comes from power generation units, power generation unit transformers, lines, main transformers and other equipment.

[0044] SVG: Dynamic reactive power compensation device, which can dynamically generate and absorb reactive power. It has the characteristics of fast response and precise regulation. Generally, the maximum SVG reactive capacity needs to be reserved in the AVC regulation of new energy stations.

[0045] Traditionally, new energy plants connected to the AC grid adopt the AC networking operation mode. The command value received by the new energy station in the AC networking operation mode is the voltage target value of the grid-connected bus. The cycle of issuing commands is 5 minutes, and the control cycle varies from 30s to 90s depending on the response of the equipment. However, the new energy plant connected to the DC UHV line adopts a fixed voltage control mode for the AC bus because the control system of the converter station adopts a fixed voltage control mode for the AC bus, and the reactive power regulation of the converter station DC system is faster and has a larger capacity than that of the new energy plant. The electrical distance between the new energy plant and the DC converter station is small and the electrical connection is close. These factors cause the reactive power regulation of the new energy plant to have little effect on the regional voltage. If the traditional voltage regulation command is still used, it will cause reactive power overregulation of the new energy plant and reactive power flow and frequent oscillation in the region. Therefore, the new energy plant connected to the DC UHV line needs to adopt the island operation mode. The command value of the reactive power target value received by the new energy plant in the island operation mode is 1min, and each round of control cycle is 15s. At present, there are two control modes for the island mode: 1. Prioritize SVG action to meet the command value of the reactive power target value faster. After meeting the reactive power target value of the master station, it is necessary to replace the reactive power of the power generation unit and SVG to increase reactive reserve. Since the reactive power loss of new energy plants cannot be accurately calculated, when the replacement step is large, the reactive power of the grid connection point frequently exceeds the assessment range, increasing the assessment cost; when the replacement step is small, the replacement effect is not obvious, and the reactive reserve is always insufficient; second, the power generation unit is prioritized, and there are high requirements for the performance of the power generation unit and the timeliness of communication. If the reactive power loss of the entire field cannot be accurately calculated, the reactive power target of the grid connection point cannot respond to the reactive power target value quickly and in a timely manner.

[0046] Both control methods need to consider the reactive power loss of new energy plants and stations. Therefore, accurately calculating the reactive power loss compensation of new energy plants and stations is the core issue of the island operation mode. If the reactive power loss of the plant is accurately calculated, when the SVG is prioritized, reactive power oscillation during reactive power replacement can be avoided; when the power generation unit is prioritized, the shortcomings of low performance and communication timeliness of the power generation unit can be compensated, and the purpose of quickly responding to the reactive power target of the grid connection point can be achieved.

[0047] Combine the following Figure 1-Figure 2 A method for acquiring reactive power loss of a new energy station provided by an embodiment of the present invention is described.

[0048] Figure 1 is one of the flow charts of the method for obtaining reactive power loss of a new energy station provided in an embodiment of the present invention, such as Figure 1 As shown, the method for obtaining reactive power loss of a new energy station provided by an embodiment of the present invention includes:

[0049] Step 110, acquiring one or more groups of reactive data samples based on the target reactive power of the grid connection point, wherein the reactive data samples include total reactive power data of the power generation unit and reactive power data of the grid connection point;

[0050] Specifically, the target reactive power of the grid connection point refers to the reactive power target value to be executed by the grid connection point of the new energy station at the next moment or the next control cycle. The reactive data sample refers to the data sample related to reactive power in the historical operation data of the new energy station, including the total reactive power data of the power generation unit and the reactive power data of the grid connection point. The total reactive power of the power generation unit refers to the sum of the reactive power of all power generation units.

[0051] Step 120, input the reactive data sample and the target reactive power of the grid connection point into the multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model, wherein the multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid connection point, and the target total reactive power of the power generation unit is used to determine the reactive loss of the new energy station.

[0052] Specifically, the multivariate driving model is a linear regression model of the reactive power at the grid connection point and the target total reactive power of the power generation unit. Since the change of the target total reactive power of the power generation unit has a significant impact on the reactive power at the grid connection point, based on the linear regression analysis, the reactive power at the grid connection point is determined as the independent variable and the target total reactive power of the power generation unit is determined as the dependent variable. The regression coefficient and the constant term are determined based on the historical data samples (i.e., the reactive data samples). The multivariate driving model can predict the value of the dependent variable (i.e., the target total reactive power of the power generation unit) according to the given value of the independent variable (i.e., the target reactive power of the grid connection point).

[0053] The method for obtaining reactive power loss of a new energy station provided by an embodiment of the present invention obtains reactive power loss of a new energy station through reactive data samples and a multivariate driving model. It does not need to build electrical parameter models of lines, transformers, and control units, and does not rely on electrical parameters of lines, transformers, and control units, current active power, reactive power, and voltage information. It solves the problem that the current AVC system has no accurate parameter model due to the lack of four remote data, the state estimation is difficult to converge, bad measurements cannot be filtered, and reactive power loss cannot be accurately calculated, so as to achieve precise control. In addition, the method for obtaining reactive power loss of a new energy station provided by an embodiment of the present invention comprehensively utilizes the linear regression relationship between historical data and variables, and reduces the reactive power loss of a new energy plant from a complex function to a univariate function, which solves the problems of slow uplink data of traditional new energy power generation units, complex network loss calculation, and low reliability, and can be applied to new energy electric fields operating in island mode.

[0054] Optionally, the multivariate driving model is:

[0055]

[0056]

[0057]

[0058] in, is the target reactive power of the grid-connected point; Q gentar is the target total reactive power of the generating unit; Q geni is the total reactive power of the generating unit of the i-th group of reactive data samples, is the grid-connected point reactive power of the i-th group of reactive data samples, n is the total number of reactive data samples, and n is a positive integer.

[0059] Optionally, acquiring one or more groups of reactive data samples based on the target reactive power of the grid connection point includes:

[0060] Determine the sample screening interval based on the target reactive power of the grid connection point and the preset accuracy;

[0061] The historical samples whose reactive power of the grid-connected point meets the sample screening interval are determined as the reactive data samples.

[0062] Exemplarily, the target reactive power of the grid connection point is 100Mvar, with 2% as the preset accuracy, 98% to 102% (i.e. 98Mvar to 102Mvar) of the target reactive power of the grid connection point is used as the sample screening interval, and the historical samples of new energy stations whose reactive power of the grid connection point falls within the sample screening interval are the reactive data samples.

[0063] Optionally, before inputting the reactive data samples and the target reactive power of the grid-connected point into the multivariate driving model, the method further includes: determining that the number of the reactive data samples is greater than or equal to a preset number of samples.

[0064] Due to the method for obtaining reactive loss of new energy stations provided by the embodiment of the present invention, the reactive loss of new energy stations is obtained through reactive data samples and a multivariate driving model. Therefore, when the number of reactive data samples is greater than or equal to the preset number of samples, it can ensure that historical data is sufficient and the accuracy of the regression coefficient and constant term of the linear regression model is guaranteed, thereby improving the accuracy of the reactive loss of new energy stations.

[0065] Optionally, the method further comprises:

[0066] Step 210: when it is determined that the number of reactive data samples is less than the preset number of samples, acquiring real-time reactive data of the new energy station;

[0067] Specifically, real-time reactive power data refers to real-time data related to reactive power of new energy sites, including the total reactive power of new energy electric field power generation units, the total active power of power generation units, the reactive power of the grid connection point and the rated voltage of the main transformer.

[0068] Step 220, inputting the real-time reactive power data of the new energy station into an inductance equivalent model, and obtaining the equivalent inductance of the new energy station output by the inductance equivalent model;

[0069] Specifically, the inductor equivalent model is:

[0070]

[0071] Where X is the equivalent inductance, Q gen is the total reactive power of the generating unit, is the reactive power at the grid connection point, U h is the rated voltage of the main transformer, P gen is the total active power of the generating unit.

[0072] Step 230: Obtain the reactive loss of the new energy station and the target total reactive power of the power generation unit based on the equivalent inductance and the target reactive power of the grid connection point.

[0073] Specifically, the equivalent inductance and the target reactive power of the grid connection point are input into the equivalent reactive loss model to obtain the reactive loss of the new energy station output by the equivalent reactive loss model. The equivalent reactive loss model is:

[0074]

[0075] Among them, ΔQ is the reactive power loss of the new energy station, is the target reactive power of the grid connection point, P pcc is the active power at the grid connection point, U pcc is the grid-connected point voltage, and X is the equivalent inductance.

[0076] Since the target total reactive power of the power generation unit is equal to the sum of the target reactive power and reactive loss of the grid connection point, the formula is as follows:

[0077]

[0078] Therefore, the target total reactive power of the power generation unit can be obtained based on the target reactive power of the grid connection point and the reactive power loss of the new energy station.

[0079] The method for obtaining reactive power loss of new energy stations provided in an embodiment of the present invention avoids the problem of output distortion of the multivariate driving model due to insufficient historical samples that may exist when reactive power data samples are insufficient, thereby improving the reliability of obtaining reactive power loss of new energy stations.

[0080] Optionally, the method further comprises:

[0081] Step 310, determining the reactive power adjustment amount of each of the power generation units based on the target total reactive power of the power generation units, the reactive rated capacity of each of the power generation units, and the total reactive rated capacity of the new energy station;

[0082] Specifically, the reactive rated capacity of a power generation unit refers to the installed capacity of the i-th power generation unit, the total reactive rated capacity of a new energy station refers to the total installed capacity of all power generation units, and the reactive power regulation amount of a power generation unit refers to the reactive power executed by the power generation unit.

[0083] The reactive power regulation amount of each power generation unit can be determined based on the reactive power regulation formula. The reactive power regulation formula is as follows:

[0084]

[0085] Among them, Q cmdi Reactive power regulation of generating unit i; Q ni is the installed capacity of power generation unit i, Q n is the total capacity of the power generation unit.

[0086] Step 320: Send a reactive power adjustment instruction to each of the power generation units based on the reactive power adjustment amount. Specifically, the reactive power adjustment instruction is used to instruct the power generation unit to perform reactive power.

[0087] The method for obtaining reactive power loss of a new energy station provided by an embodiment of the present invention obtains reactive power loss of a new energy station through reactive power data samples and a multivariate driving model when the number of samples meets a preset number, and obtains reactive power loss of a new energy station through real-time reactive power data and an equivalent model when the number of samples is less than a preset number. The model calculation is simple and the reactive power loss value has high reliability. This solves the problem that traditional reactive power loss depends on electrical parameters such as lines, box transformers, power generation units, and four-remote control data, the state estimation qualification rate is low, and the reliability of reactive power loss value is not high.

[0088] Figure 2 This is a second flow chart of a method for obtaining reactive power loss of a new energy station provided by an embodiment of the present invention, such as Figure 2 As shown, the method for obtaining reactive power loss of a new energy station provided by an embodiment of the present invention includes:

[0089] The multivariate driving model and inductance equivalent model are established respectively.

[0090] The corresponding model is selected for calculation according to the number of reactive data samples. For example, the preset number of samples is 10. When the number of reactive data samples is greater than or equal to 10, the target reactive power is obtained based on the multivariate driving model; when the number of reactive data samples is less than 10, the equivalent inductance is obtained based on the inductance equivalent model.

[0091] Based on the result obtained in the previous step and the target reactive power of the grid connection point, the total target reactive power of the power generation unit and / or the reactive loss of the new energy station is obtained.

[0092] Next, possible implementations of the above steps in specific embodiments are further described.

[0093] The inductor equivalent model formula is as follows:

[0094]

[0095] Among them, X is the equivalent inductance (i.e. the equivalent inductance of the entire field), Q gen is the total reactive power of the generating unit, is the reactive power at the grid connection point, U h is the rated voltage of the main transformer, P gen is the total active power of the generating unit.

[0096] The calculation formula of the multivariate driving model is as follows:

[0097]

[0098] The solution formulas for a and b are as follows:

[0099]

[0100] Known quantity: is the target reactive power of the grid-connected point; Q gentar is the target total reactive power of the generating unit; Q geni is the total reactive power of the generating unit of the i-th group of reactive data samples, is the grid-connected point reactive power of the i-th group of reactive data samples.

[0101] Step 1: According to the target reactive power of the grid connection point Determine reactive data samples to 97% to 103% is the sample screening interval. By default, N=0, and the historical samples that meet the sample screening interval are included in the reactive data samples, and the number of samples N is increased by 1. Finally, according to the number of N, it is divided into the following two cases:

[0102] N<10, it is considered that the reactive data samples are insufficient, and the inductance equivalent model needs to be referenced for calculation, and jump to step 3;

[0103] N≥10, use the multivariate driving model for calculation and jump to step 2;

[0104] Step 2: Introduce the successfully screened reactive data samples, calculate the values ​​of a and b, and substitute them into the current multivariate driving model formula. Calculated Skip to step 5;

[0105] Step 3: Calculate the full-field equivalent inductance X based on the current sampling data (real-time operation data of the new energy station);

[0106] Step 4: Calculate the total reactive power loss using equivalent inductance:

[0107]

[0108]

[0109] Step 5: If the reactive power control of the power generation unit is single-machine control or cluster control, use the capacity average allocation strategy to allocate reactive power regulation to each power generation unit:

[0110]

[0111] Among them, Q cmdi Reactive power regulation of generating unit i; Q ni is the installed capacity of power generation unit i, Q n is the total capacity of the power generation unit.

[0112] In one embodiment, a 150MW new energy station, P pcc =42.98MW, U h =115kV, grid connection point voltage U pcc =114.17kV, P gen =47.07MW, Q gen =20.34Mvar. Target reactive power

[0113] There are 60 wind turbines, divided into three clusters. Cluster 1 has 15 wind turbines, with a reactive rated capacity of 18.75Mvar, and the reactive power of cluster 1 is 2.34MVar; Cluster 2 has 20 wind turbines, with a reactive rated capacity of 25Mvar, and the reactive power of cluster 2 is 5Mvar; Cluster 3 has 25 wind turbines, with a reactive rated capacity of 31.25MVar, and the reactive power of cluster 3 is 6MVar, with a total capacity of 75MVar.

[0114] Step 1: As the goal, arrive The sample screening interval is screened, and the reactive data samples screened out are shown in Table 1, totaling 11 samples:

[0115] Table 1. Reactive power data sample

[0116]

[0117]

[0118] Step 2: At this time, N≥10, and the reactive sample data is substituted into the multivariate driving model to obtain a=18.194061 and b=0.166652 respectively;

[0119] Step 3: Exploitation Substitute a and b obtained in step 2 into the multivariate driving model to obtain

[0120] Step 4: Use the capacity averaging strategy to send reactive power regulation instructions to each cluster:

[0121] Cluster 1 reactive power command:

[0122]

[0123] Cluster 2 reactive command:

[0124]

[0125] Cluster 3 reactive command:

[0126]

[0127] The method for obtaining reactive power loss of new energy stations provided by the embodiment of the present invention utilizes a data-driven linear regression method, which is simple, easy to calculate, and highly reliable. It solves the problems that the current new energy stations rely on electrical parameters such as lines, box transformers, power generation units, and four remote data, the state estimation qualification rate is low, and the reliability of the calculated reactive power loss is not high. It can comprehensively utilize historical data and prior knowledge. Deep learning technology can mine effective information from historical data, directly analyze the implicit rules between input and output, and combine with data-driven regression methods. Under the premise of no external transformation, it can enhance the stability of the power grid to the new energy field, improve the accuracy of the reactive power control of the automatic voltage control, reduce the reactive power assessment costs of new energy plants and stations and the reactive power coordination pressure of the upper-level new energy collection area, and achieve stable and precise control.

[0128] The device for obtaining reactive power loss of a new energy station provided by the present invention is described below. The device for obtaining reactive power loss of a new energy station described below and the method for obtaining reactive power loss of a new energy station described above can be referred to each other.

[0129] Figure 3 is a schematic diagram of the structure of a device for acquiring reactive power loss of a new energy station provided by an embodiment of the present invention, such as Figure 3 As shown, the device for obtaining reactive power loss of a new energy station provided by an embodiment of the present invention includes:

[0130] An acquisition unit 310 is used to acquire one or more groups of reactive data samples based on the target reactive power of the grid connection point, wherein the reactive data samples include total reactive power data of the power generation unit and reactive power data of the grid connection point;

[0131] The model unit 320 is used to input the reactive data sample and the target reactive power of the grid-connected point into the multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model. The multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid-connected point.

[0132] It should be noted here that the above-mentioned device provided in the embodiment of the present invention can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects that are the same as the method embodiment in this embodiment will not be described in detail here.

[0133] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 complete mutual communication through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute a method for acquiring reactive power loss of a new energy station, the method comprising: acquiring one or more groups of reactive data samples based on the target reactive power of the grid connection point, the reactive data samples comprising the total reactive power data of the power generation unit and the reactive power data of the grid connection point; inputting the reactive data samples and the target reactive power of the grid connection point into a multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model, the multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid connection point, and the target total reactive power of the power generation unit is used to determine the reactive loss of the new energy station.

[0134] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0135] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for obtaining the reactive loss of a new energy station provided by the above-mentioned methods. The method includes: obtaining one or more groups of reactive data samples based on the target reactive power of the grid connection point, and the reactive data samples include the total reactive power data of the power generation unit and the reactive power data of the grid connection point; inputting the reactive data samples and the target reactive power of the grid connection point into a multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model, and the multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid connection point, and the target total reactive power of the power generation unit is used to determine the reactive loss of the new energy station.

[0136] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the method for obtaining the reactive loss of the new energy station provided by the above-mentioned methods. The method includes: obtaining one or more groups of reactive data samples based on the target reactive power of the grid connection point, and the reactive data samples include the total reactive power data of the power generation unit and the reactive power data of the grid connection point; inputting the reactive data samples and the target reactive power of the grid connection point into a multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model, and the multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid connection point, and the target total reactive power of the power generation unit is used to determine the reactive loss of the new energy station.

[0137] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for obtaining reactive power loss of a new energy station, characterized in that: include: Acquire one or more groups of reactive data samples based on the target reactive power of the grid connection point, wherein the reactive data samples include total reactive power data of the power generation unit and reactive power data of the grid connection point; Input the reactive data sample and the target reactive power of the grid connection point into a multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model, wherein the multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid connection point, and the target total reactive power of the power generation unit is used to determine the reactive loss of the new energy station; The multivariate driving model is: in, is the target reactive power of the grid-connected point; Q gentar is the target total reactive power of the generating unit; Q geni is the total reactive power of the generating unit of the i-th group of reactive data samples, is the grid-connected point reactive power of the i-th group of reactive data samples, and n is the total number of reactive data samples.

2. The method for obtaining reactive power loss of a new energy station according to claim 1, characterized in that: The obtaining of one or more groups of reactive data samples based on the target reactive power of the grid connection point comprises: Determine the sample screening interval based on the target reactive power of the grid connection point and the preset accuracy; The historical samples whose reactive power of the grid-connected point meets the sample screening interval are determined as the reactive data samples.

3. The method for obtaining reactive power loss of a new energy station according to claim 1, characterized in that: Before inputting the reactive data samples and the target reactive power of the grid connection point into the multivariate driving model, the method further includes: determining that the number of the reactive data samples is greater than or equal to a preset number of samples.

4. The method for obtaining reactive power loss of a new energy station according to claim 3 is characterized in that: The method further comprises: When it is determined that the number of reactive data samples is less than the preset number of samples, acquiring real-time reactive data of the new energy station; Inputting the real-time reactive power data of the new energy station into an inductance equivalent model, and obtaining the equivalent inductance of the new energy station output by the inductance equivalent model; Obtaining reactive power loss of the new energy station and target total reactive power of the power generation unit based on the equivalent inductance and the target reactive power of the grid connection point; Wherein, the inductance equivalent model is: Where X is the equivalent inductance, Q gen is the total reactive power of the generating unit, is the reactive power at the grid connection point, U h is the rated voltage of the main transformer, P gen is the total active power of the generating unit.

5. The method for obtaining reactive power loss of a new energy station according to any one of claims 1 to 4, characterized in that: The method further comprises: Determine the reactive power adjustment amount of each of the power generation units based on the target total reactive power of the power generation units, the reactive rated capacity of each of the power generation units, and the total reactive rated capacity of the new energy station; A reactive power adjustment instruction is sent to each of the power generation units based on the reactive power adjustment amount.

6. A device for acquiring reactive power loss of a new energy station, characterized in that: include: An acquisition unit, used to acquire one or more groups of reactive data samples based on the target reactive power of the grid connection point, wherein the reactive data samples include total reactive power data of the power generation unit and reactive power data of the grid connection point; A model unit, used for inputting the reactive data sample and the target reactive power of the grid connection point into a multivariate driving model to obtain the target total reactive power of the power generation unit output by the multivariate driving model, wherein the multivariate driving model is established based on the linear regression relationship between the total reactive power of the power generation unit and the reactive power of the grid connection point; The multivariate driving model is: in, is the target reactive power of the grid-connected point; Q gentar is the target total reactive power of the generating unit; Q geni is the total reactive power of the generating unit of the i-th group of reactive data samples, is the grid-connected point reactive power of the i-th group of reactive data samples.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for obtaining reactive power loss of a new energy station as described in any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for obtaining reactive power loss of a new energy station as described in any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for obtaining reactive power loss of a new energy station as described in any one of claims 1 to 5 is implemented.

Images