Generator and main transformer coordinated regulation method and device, electronic equipment and storage medium

Abstract

The invention provides a generator and main transformer coordinated regulation method and device, electronic equipment and a storage medium, and relates to the technical field of power regulation. Power grid operation state data including generator output power, main transformer input voltage and power grid frequency are collected in real time, and power fluctuation of a new energy power generation system is predicted based on the data; and dynamically adjusting the reactive compensation amount at the main transformer side according to the prediction result to suppress the fluctuation of the input voltage of the main transformer, and synchronously adjusting the simulated inertial parameters of the generator to enhance the frequency recovery capability of the power grid, so that the problem that the new energy generation power has high uncertainty and volatility under the new energy architecture in the prior art can be solved. Therefore, the technical effects of effectively suppressing the fluctuation of the input voltage of the main transformer, improving the frequency recovery efficiency of the power grid, and ensuring the reliable and efficient operation of the power system under the novel energy architecture are achieved in the case that the main transformer is faced with voltage fluctuation, the power grid is faced with insufficient frequency recovery capability and the power generator and the main transformer lack cooperative control to deal with the problems.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of power regulation, in particular to a generator and main transformer coordinated regulation method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the continuous increase of the penetration rate of renewable energy such as wind and light storage, new energy architecture has become the core direction of power system transformation and is widely used in distributed power generation, microgrid control and smart grid construction. However, the traditional centralized control mode cannot meet the requirements of high proportion of new energy access to power grid dynamic stability, and the existing technology has significant limitations: no joint inertia support mechanism is established for generators and main transformers, the traditional synchronous generator inertia support and fixed main transformer voltage regulation strategy cannot match the millisecond level response demand of new energy power fluctuation, resulting in power frequency recovery timeout and main transformer input voltage fluctuation exceeding ± 15%. At the same time, the generator and the main transformer lack real-time state interaction, and the inertia support and reactive power compensation coordination are missing, which not only limits the new energy consumption (the existing penetration rate bottleneck is 35%), but also causes equipment loss increase, power transmission economic deterioration and cascading failure risk, and it is urgent to reconstruct the coordinated control technology framework. SUMMARY

[0003] The present disclosure provides a generator and main transformer coordinated regulation method and device, electronic equipment and storage medium. Its main purpose is to at least solve one of the technical problems in the related art to some extent.

[0004] According to a first aspect of the present disclosure, a generator and main transformer coordinated regulation method is provided, comprising: real-time acquisition of operation state data of the power grid, the operation state data at least including generator output power, main transformer input voltage and power grid frequency; based on the operation state data, predicting power fluctuation of a new energy power generation system; according to the prediction result of the power fluctuation, dynamically adjusting the reactive power compensation amount on the main transformer side to suppress the fluctuation of the main transformer input voltage; synchronously adjusting the analog inertia parameters of the generator to enhance the recovery ability of the power grid frequency.

[0005] Optionally, the real-time acquisition of the operation state data of the power grid comprises: acquiring real-time data of the generator output power, the main transformer input voltage and the power grid frequency at a preset sampling frequency through a phasor measurement device; using a data acquisition and monitoring system to perform multi-source data fusion processing on the real-time data and historical operation data to construct a correlation model of device state and power grid parameters.

[0006] Optionally, the power fluctuation of the new energy power generation system is predicted based on the operation state data, and the prediction comprises: The power generation of the new energy power generation system is predicted by using a time series prediction model, and training data of the prediction model comprises at least one characteristic parameter of light intensity, wind speed and state of charge of an energy storage device; A power change sequence in a future time interval is generated by using a sliding time window method, and the power fluctuation is generated, and a prediction accuracy of the prediction model meets a preset error constraint condition.

[0007] Optionally, the reactive power compensation amount on the side of the main transformer is dynamically adjusted according to the prediction result of the power fluctuation, and the adjustment comprises: According to the correlation between the power grid frequency deviation and the voltage fluctuation amplitude, the reactive power compensation amount is calculated by using a multi-objective optimization algorithm; The load rate of the main transformer is monitored in real time, and when the load rate exceeds a preset threshold, voltage regulation is preferentially performed by using the reactive power compensation device.

[0008] Optionally, the analog inertia parameter of the generator is synchronously adjusted, and the adjustment comprises: The analog inertia constant of the generator is dynamically adjusted based on real-time load demand, and an adjustment range of the analog inertia constant is constrained by a preset upper limit and a lower limit; The dynamic response of the analog inertia parameter is realized by adding an inertia simulation function module in a generator control loop, and an output response of the function module meets a preset dynamic function relationship.

[0009] Optionally, the method further comprises: A cooperative control mechanism of the main transformer tap adjusting device and the reactive power compensation device is established, and according to an optimization result of a main transformer on-load voltage regulation control logic, the operation frequency of the main transformer tap is reduced and the response time is shortened.

[0010] According to a second aspect of the present disclosure, a generator and main transformer cooperative adjustment device is provided, comprising: An acquisition unit is configured to acquire operation state data of a power grid in real time, and the operation state data at least comprises generator output power, main transformer input voltage and power grid frequency; A prediction unit is configured to predict a power fluctuation of a new energy power generation system based on the operation state data; A first adjustment unit is configured to dynamically adjust a reactive power compensation amount on the side of a main transformer according to a prediction result of the power fluctuation, so as to suppress a fluctuation of the main transformer input voltage; A second adjustment unit is configured to synchronously adjust an analog inertia parameter of a generator, so as to enhance the recovery capability of the power grid frequency.

[0011] Optionally, the acquisition unit is further configured to: acquire real-time data of the generator output power, the main transformer input voltage and the power grid frequency by a phasor measurement device at a preset sampling frequency; perform multi-source data fusion processing on the real-time data and historical operation data by a data acquisition and monitoring system, and construct a correlation model of device state and power grid parameters.

[0012] Optionally, the prediction unit is further configured to: predict the power generation of the new energy power generation system by using a time series prediction model, wherein training data of the prediction model comprises at least one characteristic parameter of illumination intensity, wind speed and state of charge of an energy storage device; generate a power change sequence in a future time interval by a sliding time window method, and generate the power fluctuation, wherein a prediction accuracy of the prediction model meets a preset error constraint condition.

[0013] Optionally, the first adjustment unit is further configured to: calculate the reactive power compensation amount by using a multi-objective optimization algorithm according to a correlation between the power grid frequency deviation and the voltage fluctuation amplitude; monitor a load rate of the main transformer in real time, and preferentially perform voltage regulation by the reactive power compensation device when the load rate exceeds a preset threshold.

[0014] Optionally, the second adjustment unit is further configured to: dynamically adjust the simulated inertia constant of the generator based on real-time load demand, wherein an adjustment range of the simulated inertia constant is constrained by preset upper and lower limits; add an inertia simulation function module in a generator control loop to realize dynamic response of the simulated inertia parameter, wherein an output response of the function module meets a preset dynamic function relationship.

[0015] Optionally, the method further comprises: a control unit configured to establish a cooperative control mechanism of the main transformer tap adjustment device and the reactive power compensation device, and reduce an operation frequency of the main transformer tap and shorten a response time according to an optimization result of a main transformer on-load voltage regulation control logic.

[0016] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the first aspect.

[0017] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform the method of the first aspect.

[0018] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of the first aspect.

[0019] The generator and main transformer coordinated regulation method and device, electronic equipment and storage medium provided by the present disclosure can solve the problem that the main transformer is subjected to voltage fluctuation and the power grid is subjected to insufficient frequency recovery capability due to the high uncertainty and volatility of new energy power generation under the new energy architecture, and the generator and the main transformer lack coordinated control to cope with the above problems, and achieve the technical effects of effectively suppressing the main transformer input voltage fluctuation, improving the power grid frequency recovery efficiency, and guaranteeing the reliable and efficient operation of the power system under the new energy architecture.

[0020] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings are used to better understand the present scheme and do not constitute a limitation on the present disclosure. Among them: Figure 1 A flowchart of a generator and main transformer coordinated regulation method provided by an embodiment of the present disclosure; Figure 2 A structural diagram of a generator and main transformer coordinated regulation device provided by an embodiment of the present disclosure; Figure 3 A schematic block diagram of an example electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, including various details in order to facilitate understanding. They should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to make the description clear and concise, the description of well-known functions and structures is omitted in the following description.

[0023] A generator and main transformer coordinated regulation method and device, electronic equipment and storage medium are described below with reference to the accompanying drawings.

[0024] Figure 1 A flowchart of a generator and main transformer coordinated regulation method provided by the embodiments of the present disclosure.

[0025] As Figure 1 shown, the method comprises the following steps: Step 101, real-time collection of operation state data of the power grid, the operation state data at least including generator output power, main transformer input voltage and power grid frequency.

[0026] In the embodiments of the present disclosure, under the new energy architecture, in view of the dispersion, diversity and high uncertainty of energy which will affect the flexibility of generator operation and the stability of main transformer voltage, in order to build the basic data support for subsequent power system regulation and control, real-time collection of operation state data of the power grid needs to be performed. The collection process needs to acquire key state parameters that can reflect the operating characteristics of the generator, the working condition of the main transformer and the overall operation stability of the power grid, at least including the generator output power, the main transformer input voltage and the power grid frequency. The generator output power can directly represent the current power output level of the generator, the main transformer input voltage is the core index reflecting the operating voltage condition of the main transformer, and the power grid frequency is related to the stability of the overall operation of the power grid. The three together constitute the basic data set for subsequent analysis of the operation state of the power grid and development of regulation strategies. As an implementation manner, a real-time data collection device suitable for the new energy architecture can be used to continuously and dynamically collect the above-mentioned generator output power, main transformer input voltage and power grid frequency, so as to ensure the timeliness and continuity of data acquisition, and to match the real-time requirement of power grid state monitoring under the fluctuation of new energy power generation.

[0027] By acquiring the key operation state data including the generator output power, the main transformer input voltage and the power grid frequency, accurate and timely basic information support is provided for subsequent data-based power fluctuation prediction and equipment regulation, which avoids the deviation of the judgment of the operation state of the power grid due to the lack or lag of key data, and further lays a data foundation for ensuring the pertinence and effectiveness of the operation regulation of the generator and the main transformer under the new energy architecture.

[0028] Step 102, prediction of power fluctuation of the new energy power generation system based on the operation state data.

[0029] In the embodiments of the present disclosure, under the new energy architecture, the high uncertainty and volatility of new energy power generation power easily causes power imbalance of the power grid, and further affects the operation flexibility of the generator and the voltage stability of the main transformer, so it is necessary to carry out power fluctuation prediction of the new energy power generation system based on the aforementioned real-time collected power grid operation state data (at least including generator output power, main transformer input voltage and power grid frequency). The prediction process constructs a power fluctuation prediction logic suitable for the characteristics of new energy by analyzing the internal correlation between the aforementioned operation state data and new energy power, such as that the real-time change of the generator output power can indirectly reflect the supply-demand difference of the new energy power, the main transformer input voltage fluctuation and the new energy power fluctuation have a coupling response relationship, and the power grid frequency change is related to the overall power balance state, to predict the future change trend of the new energy power generation power. As an implementation manner, the short-term power fluctuation of the new energy power generation system can be calculated by combining the historical new energy power generation data and the real-time collected generator output power, main transformer input voltage and power grid frequency data through a preset prediction model, so as to ensure that the prediction result can reserve a response time for subsequent adjustment operation.

[0030] By using the key operation state data to establish the correlation prediction mechanism with the new energy power, the change trend of the new energy power generation power is obtained in advance, the subsequent adjustment action is avoided to lag due to the inability to predict the fluctuation, and the prospective basis is provided for the subsequent dynamic adjustment of the main transformer reactive power compensation amount and the generator simulation inertia parameter, so as to effectively reduce the impact of new energy fluctuation on the stable operation of the power grid.

[0031] In step 103, the reactive power compensation amount on the main transformer side is dynamically adjusted according to the prediction result of the power fluctuation, so as to suppress the fluctuation of the main transformer input voltage.

[0032] In the embodiments of the present disclosure, under the new energy architecture, the high uncertainty and volatility of new energy power generation power easily causes the main transformer input voltage fluctuation, and further affects the voltage stability of the power grid, so it is necessary to dynamically adjust the reactive power compensation amount on the main transformer side according to the prediction result of the aforementioned power fluctuation of the new energy power generation system. The adjustment process is based on the power fluctuation prediction result, and the output amount of the reactive power compensation device on the main transformer side is adjusted in real time by adapting the current operation condition of the main transformer and the predicted power change trend, so that the reactive power compensation amount matches the new energy power fluctuation, thereby offsetting the influence of the power fluctuation on the main transformer input voltage, and realizing the suppression of the main transformer input voltage fluctuation; as an implementation manner, the static reactive power compensation device (SVC) or the static synchronous compensation device (STATCOM) and the like can be used, the switching state and the compensation amount of the compensation device are automatically adjusted in combination with the predicted power fluctuation amplitude and direction, and the dynamic adjustment of the main transformer tapping is linked, so as to further improve the suppression effect on the main transformer input voltage fluctuation, and meet the demand of the main transformer for voltage regulation ability under the new energy architecture.

[0033] By adapting the reactive power compensation amount on the side of the main transformer based on the power fluctuation prediction result, the problem of unstable input voltage of the main transformer caused by power fluctuation of new energy under the new energy architecture is effectively solved, the limitation of response lag of the traditional fixed voltage regulation strategy is avoided, and the stable operation of the main transformer under the power change scenario of new energy is ensured, which provides support at the voltage level for reliable grid connection of new energy.

[0034] In step 104, the analog inertia parameter of the generator is adjusted synchronously to enhance the recovery ability of the grid frequency.

[0035] In the embodiment of the present disclosure, under the new energy architecture, the high uncertainty and volatility of new energy power generation easily cause grid frequency fluctuation, and the traditional generator is difficult to respond to power change due to large inertia, resulting in insufficient recovery ability of the grid frequency. Therefore, the analog inertia parameter of the generator needs to be adjusted synchronously in combination with the aforementioned real-time collected grid operation state data and the prediction result of the power fluctuation of the new energy power generation system. The adjustment process adjusts the analog inertia parameter of the generator to simulate the inertia characteristics of the traditional synchronous generator by adapting the predicted power fluctuation trend and the current frequency state of the grid, so that the generator can provide effective inertia support when the power changes, thereby adapting the demand of new energy power fluctuation for the stability of the grid frequency and helping to improve the recovery ability of the grid frequency to respond to fluctuations. As an implementation manner, the virtual inertia control technology can be used in combination with advanced speed regulation algorithms (such as fuzzy control, neural network control algorithm) to dynamically adjust the analog inertia parameter of the generator according to the predicted power fluctuation amplitude and the grid frequency change trend, so as to ensure that the generator can quickly respond to the frequency instruction and meet the requirement of flexible operation of the generator under the new energy architecture.

[0036] By dynamically adapting the analog inertia parameter of the generator, the problem of weak recovery ability of the grid frequency caused by insufficient inertia support of the traditional generator and difficulty in responding to new energy power fluctuation under the new energy architecture is effectively solved, the situation of grid frequency recovery timeout is avoided, and the stable operation of the grid frequency under the new energy architecture is ensured, which provides support at the frequency level for large-scale reliable grid connection of new energy.

[0037] The power generator and main transformer coordinated regulation method provided by the present disclosure can solve the problem that the main transformer is faced with voltage fluctuation and the power grid is faced with insufficient frequency recovery capability, and the power generator and the main transformer lack coordinated control to cope with the above problems, and achieve the technical effects of effectively suppressing the main transformer input voltage fluctuation, improving the power grid frequency recovery efficiency, and ensuring the reliable and efficient operation of the power system under the new energy architecture.

[0038] As a specific embodiment of the present disclosure, on the basis of the basic scheme, the real-time acquisition of the operating state data of the power grid further includes: acquiring real-time data of the generator output power, the main transformer input voltage and the power grid frequency at a preset sampling frequency through a phasor measurement device; and performing multi-source data fusion processing on the real-time data and historical operating data by using a data acquisition and monitoring system to construct a correlation model of device state and power grid parameters.

[0039] Specifically, in this specific implementation form of the present disclosure, for the operation of collecting the power grid operation state data in real time, the phasor measurement device (PMU) is used in cooperation with the data acquisition and monitoring system (SCADA) to realize the operation: first, the phasor measurement device is connected with the current transformer, the voltage transformer of the generator and the input voltage transformer of the main transformer and the power grid frequency monitoring point, and the preset sampling frequency is set to 25Hz-50Hz (the frequency can be flexibly adjusted according to the response requirement of the new energy power fluctuation under the new energy architecture), the instantaneous value of the generator output power, the effective value of the main transformer input voltage and the real-time value of the power grid frequency are collected in real time by the phasor measurement device, so as to ensure that the collected data can accurately reflect the dynamic operation state of the power grid and the equipment; then, the real-time data collected by the phasor measurement device is transmitted to the data acquisition and monitoring system, the system calls the pre-stored historical operation data of the power grid (including the generator output power change curve, the main transformer input voltage fluctuation record and the power grid frequency stability data under different new energy output conditions at different time periods in the past 3 months), and the real-time data and the historical data are fused by using a weighted average fusion algorithm - the abnormal jump data (such as data exceeding 5% of the normal range at a time) in the real-time data caused by instantaneous interference of the sensor is removed, at the same time, the real-time data is calibrated by using the parameter mean value under the same working condition in the historical data, and finally the correlation model of the equipment state (such as the generator load rate and the main transformer winding temperature) and the power grid parameter (the generator output power, the main transformer input voltage and the power grid frequency) is constructed by using the linear regression analysis method, so as to clearly define the quantitative corresponding relationship between the change of each power grid parameter and the equipment state.

[0040] The high-frequency sampling of the phasor measurement device ensures the real-time and accuracy of the power grid operation state data, the multi-source data fusion processing of the data acquisition and monitoring system eliminates the data interference, the construction of the equipment state and power grid parameter correlation model realizes the deep utilization of the data, effectively avoids the prediction deviation of the subsequent power fluctuation caused by the data quality problem, and provides more reliable data support for the formulation of the power grid regulation strategy under the new energy architecture.

[0041] As a specific implementation form of the present disclosure, on the basis of the basic scheme, the power fluctuation of the new energy power generation system is further predicted based on the operation state data, including: using a time series prediction model to predict the power generation of the new energy power generation system, the training data of the prediction model including at least one characteristic parameter of light intensity, wind speed and state of charge of the energy storage device; the power change sequence in the future time interval is generated by using the sliding time window method, and the power fluctuation is generated, and the prediction accuracy of the prediction model meets the preset error constraint condition.

[0042] Specifically, in this specific implementation form of the present disclosure, the operation of predicting the power fluctuation of the new energy power generation system based on the operating state data is specifically realized through a time series prediction model and a sliding time window method: first, a time series prediction model (such as a long short-term memory network LSTM model or an autoregressive integrated moving average ARIMA model) that adapts to the time series characteristics of new energy power generation is selected, and in addition to the real-time collected power grid operating state data, at least one of the feature parameters of the light intensity, the wind speed and the state of charge of the energy storage device is also included in the training data required in the model training stage - wherein the light intensity is collected in real time by a high-precision light sensor arranged at the new energy station, the wind speed is obtained by a ultrasonic anemometer matched with the station, and the state of charge (SOC) of the energy storage device is extracted from the battery management unit (BMS) of the energy storage system. After aligning these feature parameters and historical power generation data in the time dimension, they are used for model training, verification and parameter optimization; then, the real-time data is processed by using a sliding time window method, the size of the sliding time window is set to 5-15 minutes, and the step is 1 minute, based on the real-time collected generator output power, main transformer input voltage and power grid frequency data, the time series change characteristics of the data are captured by the window in segments, the power change sequence of the new energy power generation system within 10-30 minutes in the future is generated, and then the amplitude, direction and duration of the power fluctuation are determined; at the same time, the preset error constraint condition of the prediction model is set to the mean absolute percentage error (MAPE) not exceeding 5%, the predicted value and the actual power generation value are compared in real time during the model running process, if the error exceeds the constraint range, the dynamic calibration of the model parameters is triggered to ensure that the prediction accuracy meets the subsequent adjustment requirements.

[0043] By including the core influencing factors of new energy power generation such as light and wind speed into the model training data, the pertinence and accuracy of power fluctuation prediction are improved; the sliding time window method can dynamically capture the short-term power change rule and adapt to the rapid fluctuation characteristics of new energy power; the preset error constraint ensures the reliability of the prediction results, provides accurate basis for the subsequent accurate adjustment of the main transformer reactive power compensation amount and the generator simulation inertia parameter, and effectively avoids the problem of power grid adjustment error caused by prediction deviation.

[0044] As a specific implementation form of the present disclosure, on the basis of the basic scheme, the dynamic adjustment of the reactive power compensation amount on the main transformer side according to the prediction result of the power fluctuation comprises: according to the correlation between the power grid frequency deviation and the voltage fluctuation amplitude, the reactive power compensation amount is calculated by using a multi-objective optimization algorithm; the load rate of the main transformer is monitored in real time, and when the load rate exceeds a preset threshold, voltage regulation is preferentially performed by the reactive power compensation device.

[0045] Specifically, in this specific implementation form of the present disclosure, the operation of dynamically adjusting the reactive power compensation amount of the main transformer side according to the power fluctuation prediction result needs to be combined with the operation characteristics of the main transformer under the new energy architecture: first, based on the coupling relationship between new energy power fluctuation and power grid frequency and voltage in the new energy architecture, the power grid frequency deviation data (such as the difference between the frequency and the rated value 50Hz) and the corresponding main transformer input voltage fluctuation amplitude data (such as the percentage deviation of the voltage from the rated value) of the main transformer under different new energy output conditions are collected, and the correlation model between the two is established through linear regression analysis, and the corresponding change amount of the voltage fluctuation amplitude when the frequency deviation changes by 0.1Hz is determined, which provides a correlation basis for subsequent reactive power compensation amount calculation; then, a multi-objective optimization algorithm (such as non-dominated sorting genetic algorithm NSGA-Ⅱ) is used to calculate the reactive power compensation amount, with "minimum power grid frequency deviation" and "minimum main transformer input voltage fluctuation amplitude" as the dual optimization objectives, and the rated capacity of the main transformer side reactive power compensation device (such as static synchronous compensator STATCOM) (referring to the reactive power demand configuration of the main transformer under the new energy architecture, usually 50Mvar-100Mvar) and the allowable voltage fluctuation range of the power grid (such as ±5% rated voltage) as the constraint conditions, the optimal reactive power compensation amount interval is obtained through algorithm iteration; at the same time, the main transformer winding temperature sensor and the current transformer are used to collect the main transformer load rate (i.e. the ratio of the actual load power to the rated capacity) in real time, and a preset threshold of 80% is set (adapted to the operation requirement of avoiding overload of the main transformer under the new energy architecture), when the load rate is monitored to exceed 80%, the mechanical adjustment action of the main transformer tap is suspended, and the power module switching of STATCOM or the thyristor trigger angle of static var compensator (SVC) is preferentially controlled to quickly adjust the reactive power compensation amount to stabilize the main transformer input voltage, and to avoid the frequent operation of the tap to aggravate the loss of the main transformer.

[0046] By establishing the correlation between the power grid frequency deviation and the voltage fluctuation amplitude, the reactive power compensation amount calculation takes into account the frequency and voltage stability, and meets the demand for coordinated regulation of multiple parameters of the power grid under the new energy architecture; the multi-objective optimization algorithm ensures the optimality of the compensation amount, and avoids the imbalance of other parameters caused by single target adjustment; when the load rate exceeds the threshold, the voltage is preferentially regulated by reactive power compensation, effectively avoiding the risk of overload of the main transformer, reducing the mechanical loss of the tap, and meeting the requirements of efficient and stable operation of the main transformer under the new energy architecture.

[0047] As a specific implementation form of the present disclosure, on the basis of the basic scheme, the analog inertia parameter of the synchronous regulation generator is further limited, including: dynamically adjusting the analog inertia constant of the generator based on the real-time load demand, and the adjustment range of the analog inertia constant is constrained by the preset upper and lower limits; by adding an inertia simulation function module in the generator control loop, the dynamic response of the analog inertia parameter is realized, and the output response of the function module conforms to the preset dynamic function relationship.

[0048] Specifically, in this specific implementation form of the present disclosure, the operation of synchronously adjusting the generator simulation inertia parameter needs to be combined with the load fluctuation characteristics of the power grid under the new energy architecture and the operation demand of the generator: first, the real-time load demand data (covering the real-time power value and change rate of various loads such as industrial and residential loads) of the current and short-term prediction is obtained through the real-time monitoring system of the power grid, and the simulation inertia constant of the generator is adjusted according to the dynamic change trend of the load demand - when the real-time load demand suddenly increases (such as a change rate exceeding 5% / s), the simulation inertia constant is increased to strengthen the inertia support capability of the generator and slow down the frequency drop rate of the power grid; when the load demand is stable or slightly fluctuates (the change rate is less than 1% / s), the simulation inertia constant is appropriately reduced to improve the response speed of the generator to the power instruction, and the preset lower limit of the simulation inertia constant is set to 0.5 s and the upper limit is set to 2.0 s (this range is determined based on the basic demand of the power grid for inertia support under the new energy architecture and the maximum response capability of the generator control loop, to avoid inertia deficiency caused by too low constant and restrict the regulation flexibility caused by too high constant); subsequently, an inertia simulation function module is added in the speed regulation control loop (such as the core control unit of the electro-hydraulic speed regulation system) of the generator, the input signals of the module include the real-time load change rate, the new energy power fluctuation prediction value and the power grid frequency deviation, the output signal is the simulation inertia compensation amount, and the output response strictly follows the preset dynamic function relationship (specifically, simulation inertia compensation amount = K x real-time load change rate + C x new energy power fluctuation prediction amplitude, wherein K is the load response coefficient, the value range is 0.02-0.05 s² / kW, C is the fluctuation compensation coefficient, the value range is 0.01-0.03 s² / kW, and the value is determined through offline simulation calibration), to ensure that the adjustment of the simulation inertia parameter can match the change of the power grid operation state in real time and realize accurate dynamic response.

[0049] By dynamically adjusting the simulation inertia constant based on the real-time load demand and limiting the preset upper and lower limits, the inertia support sufficiency when the load of the power grid fluctuates sharply is ensured, and the regulation flexibility caused by improper constant is avoided; the setting of the inertia simulation function module and the preset dynamic function relationship makes the response of the simulation inertia parameter more accurate and controllable, meets the demand of the generator for fast and stable inertia regulation under the new energy architecture, effectively improves the timeliness and stability of the power grid frequency recovery, and reduces the influence of frequency fluctuation on the operation of the power system.

[0050] As a specific implementation form of the present disclosure, on the basis of the basic scheme, it is further limited that the present disclosure further comprises: establishing a cooperative control mechanism of the main transformer tap changer adjustment device and the reactive power compensation device, reducing the operation frequency of the main transformer tap changer and shortening the response time according to the optimization result of the main transformer on-load voltage regulation control logic.

[0051] Specifically, in this specific implementation form of the present disclosure, in view of the demand for main transformer voltage regulation and device loss control under the new energy architecture, a cooperative control mechanism of the main transformer tap changer and the reactive power compensation device is constructed and the on-load voltage regulation control logic is optimized. First, a data interaction module is built in the control unit of the main transformer (such as the main transformer intelligent monitoring terminal) to realize real-time information sharing between the tap changer (such as the electric operating mechanism) and the reactive power compensation device (such as the static var compensator SVC and the static synchronous compensator STATCOM). The interaction data includes the current tap position, the regulation margin of the tap changer, the real-time output capacity of the reactive power compensation device, the remaining compensation capacity, and the real-time fluctuation value of the input voltage of the main transformer. Then, the on-load voltage regulation control logic of the main transformer is optimized based on the characteristics of the main transformer voltage fluctuation under the new energy architecture (such as the voltage change amplitude and frequency caused by new energy power fluctuation). The voltage regulation priority is set. When the input voltage fluctuation amplitude of the main transformer is within ±3% of the rated voltage, the reactive power compensation device is preferred to adjust the output capacity to realize voltage stability. Only when the voltage fluctuation exceeds the range and the reactive power compensation device reaches the upper limit of the rated capacity, the tap changer is triggered to act. At the same time, in order to shorten the response time of the tap changer, a pre-regulation judgment mechanism is introduced into the control logic. Combined with the prediction result of the new energy power fluctuation, if it is predicted that the future voltage fluctuation will exceed the regulation range of the reactive power compensation, the tap changer is switched to the “action-ready” state in advance to reduce the mechanical start-up delay. In addition, through statistical analysis of historical operation data, the optimization goal of the single-day operation frequency of the tap changer is set to not more than 15 times (referring to the reduction of 30% of the traditional tap changer operation frequency under the new energy architecture), and a frequency monitoring module is added to the control logic. When the single-day operation frequency approaches the threshold, the regulation range of the reactive power compensation device is further expanded to avoid frequent operation of the tap changer.

[0052] By establishing the cooperative control mechanism of the main transformer tap changer and the reactive power compensation device, the mechanical operation of the tap changer is reduced by taking advantage of the fast response of the reactive power compensation device, the operation frequency of the tap changer is effectively reduced, and the demand for reducing the device loss of the main transformer is met. The optimization of the on-load voltage regulation control logic and the introduction of the pre-regulation mechanism shorten the response time of the tap changer, solve the problem that the mechanical response speed of the traditional tap changer is difficult to match the new energy power fluctuation, and at the same time guarantee the stability of the input voltage of the main transformer, thereby improving the reliability and economy of the main transformer operation under the new energy architecture.

[0053] It should be noted that the embodiments of the present disclosure can include multiple steps, which are numbered for the convenience of description, but these numbers do not limit the execution time slots and execution order between the steps; the steps can be implemented in any order, and the embodiments of the present disclosure do not limit this.

[0054] Corresponding to the above-mentioned generator and main transformer coordinated regulation method, the disclosure also proposes a generator and main transformer coordinated regulation device. Since the device embodiment of the disclosure corresponds to the above-mentioned method embodiment, for the details not disclosed in the device embodiment, please refer to the above-mentioned method embodiment, which will not be described in detail in the disclosure.

[0055] Figure 2 A structural schematic diagram of a generator and main transformer coordinated regulation device provided by an embodiment of the disclosure is shown in Figure 2 As shown, it comprises: The acquisition unit 21 is configured to acquire the operating state data of the power grid in real time, wherein the operating state data at least includes the generator output power, the main transformer input voltage and the power grid frequency. The prediction unit 22 is configured to predict the power fluctuation of the new energy power generation system based on the operating state data. The first adjustment unit 23 is configured to dynamically adjust the reactive power compensation amount on the main transformer side according to the prediction result of the power fluctuation, so as to suppress the fluctuation of the main transformer input voltage. The second adjustment unit 24 is configured to synchronously adjust the analog inertia parameter of the generator, so as to enhance the recovery ability of the power grid frequency.

[0056] The generator and main transformer coordinated regulation device provided by the disclosure can acquire the operating state data of the power grid in real time, including the generator output power, the main transformer input voltage and the power grid frequency, predict the power fluctuation of the new energy power generation system based on the data, and dynamically adjust the reactive power compensation amount on the main transformer side according to the prediction result to suppress the fluctuation of the main transformer input voltage, while synchronously adjusting the analog inertia parameter of the generator to enhance the recovery ability of the power grid frequency. Therefore, the technical effect of effectively suppressing the fluctuation of the main transformer input voltage, improving the recovery efficiency of the power grid frequency, and guaranteeing the reliable and efficient operation of the power system under the new energy architecture can be achieved.

[0057] Further, in one possible implementation manner of the embodiment, the acquisition unit 21 is further configured to: acquire real-time data of the generator output power, the main transformer input voltage and the power grid frequency by a phasor measurement device at a preset sampling frequency; perform multi-source data fusion processing on the real-time data and historical operating data by a data acquisition and monitoring system, and construct a correlation model of device state and power grid parameters.

[0058] Further, in one possible implementation manner of the embodiment, the prediction unit 22 is further configured to: The time series prediction model is used to predict the power generation of the new energy power generation system, and training data of the prediction model includes at least one characteristic parameter of light intensity, wind speed and state of charge of an energy storage device. The power change sequence in the future time interval is generated by a sliding time window method, the power fluctuation is generated, and the prediction accuracy of the prediction model meets a preset error constraint condition.

[0059] Further, in a possible implementation of the embodiment, the first adjusting unit 23 is further configured to: According to the correlation between the grid frequency deviation and the voltage fluctuation amplitude, the multi-objective optimization algorithm is used to calculate the reactive power compensation amount. The load rate of the main transformer is monitored in real time, and when the load rate exceeds a preset threshold, the voltage is adjusted by the reactive power compensation device.

[0060] Further, in a possible implementation of the embodiment, the second adjusting unit 24 is further configured to: The simulated inertia constant of the generator is dynamically adjusted based on real-time load demand, and the adjustment range of the simulated inertia constant is constrained by preset upper and lower limits. The dynamic response of the simulated inertia parameter is realized by adding an inertia simulation function module in the generator control loop, and the output response of the function module meets a preset dynamic function relationship.

[0061] Further, in a possible implementation of the embodiment, as shown in Figure 2 Further, the embodiment also includes: The control unit 25 is configured to establish a cooperative control mechanism of the main transformer tap adjusting device and the reactive power compensation device, reduce the operation frequency of the main transformer tap, and shorten the response time according to the optimization result of the main transformer on-load voltage regulation control logic.

[0062] It should be noted that the foregoing explanation and description of the method embodiment are also applicable to the device of the present embodiment, and the principle is the same, which is not limited in the present embodiment.

[0063] According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0064] Figure 3A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0065] like Figure 3 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 302 or a computer program loaded from storage unit 308 into RAM (Random Access Memory) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O (Input / Output) interface 305 is also connected to the bus 304.

[0066] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0067] The computing unit 301 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 301 performs various methods and processes described above, such as the generator and main transformer coordinated regulation method. For example, in some embodiments, the generator and main transformer coordinated regulation method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded onto the RAM 303 and executed by the computing unit 301, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 301 can be configured to perform the aforementioned generator and main transformer coordinated regulation method by any other appropriate means, such as by means of firmware.

[0068] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a Field Programmable Gate Array (FPGA), an Application-Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a System on Chip (SoC), a Complex Programmable Logic Device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0069] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0070] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include one or more lines of electrical connections, portable computer disks, hard disk drives, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory cards, optical fibers, CD-ROMs (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0071] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0072] The systems and techniques described herein can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described herein), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, and a blockchain network.

[0073] The computer system can include clients and servers. The clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server is one of communication and distribution, with the server generally providing communication and distribution services to the clients. The servers can be cloud servers, also known as cloud computing servers or cloud hosts, which are a host product in the cloud computing service system to solve the defects of large management difficulty and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"). The servers can also be servers of a distributed system, or servers combined with a blockchain.

[0074] It should be noted that artificial intelligence is a discipline that studies enabling computers to simulate some thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.) of people, both hardware and software technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing, etc.; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, knowledge graph technology, etc. several major directions.

[0075] The first, second, and various other numerical designations involved in the present disclosure are only for the convenience of description and do not limit the scope of the embodiments of the present disclosure, nor do they represent a sequence.

[0076] At least one of the present disclosure can also be described as one or more, multiple can be two, three, four or more, the present disclosure does not make restrictions. In the embodiments of the present disclosure, for a technical feature, the technical features in the technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D" and the like. The technical features described by "first", "second", "third", "A", "B", "C" and "D" have no order or size order.

[0077] It should be understood that the steps shown above can be reordered, added or deleted. For example, the steps described in the present disclosure can be executed in parallel, sequentially or in different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, which is not limited herein.

[0078] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for coordinated regulation of a generator and a main transformer, characterized in that, include: Real-time acquisition of power grid operating status data, including at least generator output power, main transformer input voltage, and power grid frequency; Based on the aforementioned operating status data, predict the power fluctuations of the new energy power generation system; Based on the predicted power fluctuations, the reactive power compensation on the main transformer side is dynamically adjusted to suppress fluctuations in the main transformer input voltage. Synchronously adjust the simulated inertial parameters of the generator to enhance the grid frequency recovery capability.

2. The method according to claim 1, characterized in that, The real-time acquisition of power grid operation status data includes: Real-time data of the generator output power, the main transformer input voltage, and the grid frequency are collected using a phasor measurement device at a preset sampling frequency. The real-time data and historical operating data are fused using a data acquisition and monitoring system to construct a correlation model between equipment status and power grid parameters.

3. The method according to claim 1, characterized in that, The prediction of power fluctuations in the new energy power generation system based on the operational status data includes: The power generation of the new energy power generation system is predicted using a time series prediction model. The training data of the prediction model includes at least one characteristic parameter among solar intensity, wind speed, and the state of charge of the energy storage device. The power fluctuation is generated by generating a power change sequence within a future time interval using a sliding time window method, and the prediction accuracy of the prediction model meets the preset error constraint conditions.

4. The method according to claim 1, characterized in that, The step of dynamically adjusting the reactive power compensation on the main transformer side based on the predicted power fluctuations includes: Based on the correlation between grid frequency deviation and voltage fluctuation amplitude, a multi-objective optimization algorithm is used to calculate the reactive power compensation amount; The load rate of the main transformer is monitored in real time, and voltage regulation is preferentially performed through the reactive power compensation device when the load rate exceeds a preset threshold.

5. The method according to claim 1, characterized in that, The simulated inertial parameters of the synchronous regulating generator include: The simulated inertia constant of the generator is dynamically adjusted based on real-time load demand, and the adjustment range of the simulated inertia constant is constrained by preset upper and lower limits. By adding an inertia simulation function module to the generator control loop, the dynamic response of the simulated inertia parameters is realized, and the output response of the function module conforms to a preset dynamic function relationship.

6. The method according to claim 1, characterized in that, Also includes: Establish a collaborative control mechanism between the main transformer tap changer adjustment device and the reactive power compensation device. Based on the optimization results of the main transformer on-load tap changer control logic, reduce the operation frequency of the main transformer tap changer and shorten the response time.

7. A generator and main transformer coordinated regulation device, characterized in that, include: The data acquisition unit is used to acquire real-time power grid operating status data, which includes at least generator output power, main transformer input voltage, and power grid frequency. The prediction unit is used to predict the power fluctuation of the new energy power generation system based on the operating status data. The first adjustment unit is used to dynamically adjust the reactive power compensation amount on the main transformer side according to the predicted power fluctuation results, so as to suppress the fluctuation of the main transformer input voltage. The second regulating unit is used to synchronously regulate the simulated inertial parameters of the generator to enhance the recovery capability of the grid frequency.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images