Power grid auxiliary service data prediction method, device and equipment and readable storage medium

Abstract

The invention discloses a power grid auxiliary service data prediction method, device and equipment and a readable storage medium, and the method comprises the steps: obtaining power grid power generation data, power grid operation data, power grid auxiliary service data and equipment state data in a preset time period, and enabling the power grid power generation data, the power grid operation data, the power grid auxiliary service data and the equipment state data to be subjected to prediction; and inputting the prediction model, and predicting to obtain the power grid auxiliary service data and the power grid power generation data in the next preset time period. The power grid power generation data, the power grid operation data, the power grid auxiliary service data and the equipment state data in the preset time period are input into the pre-created prediction model, the input data are processed by the prediction model to obtain the data association relationship characteristics, and the data association relationship characteristics are combined to obtain the prediction result. And the power grid auxiliary service data and the power grid power generation data in the next preset time period are predicted, so that the power station can use the predicted data to carry out debugging optimization in advance, and normal operation of the system is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of power system management, and particularly relates to a method, device, equipment and readable storage medium for predicting grid auxiliary service data. Background Art

[0002] In recent years, the world economy has been booming. In the process of economic development, power supply plays a very important role. Under the traditional power production mode, power production is uniformly dispatched and managed, which can better ensure the safety of power production. However, under the current power production mode, in order to adapt to economic development and ensure that users obtain high-quality and inexpensive electric energy, the power market introduces a competition mechanism, which enhances the autonomy of power producers. The opening of the power grid and the use of new technologies by power producers have led to a substantial increase in the complexity of power grid operation and control, bringing huge challenges to the safe and reliable operation of the power grid.

[0003] On this basis, in order to ensure the safe and reliable operation of the power grid, corresponding auxiliary service measures need to be taken to adjust the power grid. Grid auxiliary services determine the operation of the power grid. If the grid auxiliary service data can be predicted in advance, the power grid can be adjusted in advance based on the prediction results to ensure the normal operation of the power system. Therefore, how to realize the prediction of grid auxiliary service data is the research direction of people. Summary of the Invention

[0004] In view of this, the present application provides a method, device, equipment and readable storage medium for predicting grid auxiliary service data, so as to facilitate the prediction of grid auxiliary service data.

[0005] In order to achieve the above object, the following solutions are proposed:

[0006] A method for predicting grid auxiliary service data, comprising:

[0007] Obtain grid power generation data, grid operation data, grid auxiliary service data and equipment status data within a preset time period, where the grid auxiliary service data includes: primary frequency modulation contribution rate, Automatic Generation Control (AGC) data, and Automatic Voltage Control (AVC) data;

[0008] Input the grid power generation data, grid operation data, grid auxiliary service data and equipment status data into a pre-created prediction model, and predict the grid auxiliary service data and grid power generation data within the next preset time period;

[0009] The prediction model is configured to process grid power generation data, grid operation data, grid auxiliary service data, and equipment status data within a preset time period of the input to obtain data correlation relationship features, and determine the grid auxiliary service data and grid power generation data within the next preset time period based on the grid power generation data, grid operation data, grid auxiliary service data, equipment status data, and the data correlation relationship features within the preset time period;

[0010] The prediction model includes: an input layer, a data correlation relationship analysis layer, and a data prediction layer cascaded in sequence;

[0011] The training process of the prediction model includes:

[0012] Through the input layer, obtain grid power generation training data, grid operation training data, auxiliary service training data, and equipment status training data within a preset time period;

[0013] Through the data correlation relationship analysis layer, process the grid power generation data, grid operation data, grid auxiliary service data, and equipment status data within the preset time period of the input to obtain data correlation relationship features;

[0014] Through the data prediction layer, determine the grid auxiliary service data and grid power generation data within the next preset time period based on the grid power generation data, grid operation data, grid auxiliary service data, equipment status data, and the data correlation relationship features;

[0015] Taking the determined grid auxiliary service data to approach the grid auxiliary service data label within the next preset time period, and taking the determined grid power generation data to approach the grid power generation data within the next preset time period as the training objective, update the parameters of the prediction model.

[0016] Optionally, the prediction model is pre-trained with grid power generation training data, grid operation training data, auxiliary service training data, and equipment status training data within a preset time period as training samples, and the grid auxiliary service data and grid power generation data within the next preset time period as training labels.

[0017] Optionally, after inputting the grid power generation data, grid operation data, grid auxiliary service data, and equipment status data into a pre-created prediction model to predict the grid auxiliary service data and grid power generation data within the next preset time period, it further includes:

[0018] Obtain the pre-set grid auxiliary service data assessment criteria;

[0019] Judge whether the predicted grid auxiliary service data meets the grid auxiliary service data assessment criteria;

[0020] If not, obtain the data association relationship characteristics;

[0021] Based on the grid auxiliary service data assessment criteria, the data association relationship characteristics, and the predicted grid auxiliary service data, determine a grid auxiliary service data adjustment plan.

[0022] Optionally, the determining a grid auxiliary service data adjustment plan based on the grid auxiliary service data assessment criteria, the data association relationship characteristics, and the predicted grid auxiliary service data includes:

[0023] Based on the grid auxiliary service data assessment criteria and the predicted grid auxiliary service data, determine unqualified data;

[0024] Based on the unqualified data and the data association relationship characteristics, determine the key factors affecting the unqualified data;

[0025] Based on the key factors, determine a grid auxiliary service data adjustment plan.

[0026] Optionally, after inputting the grid power generation data, grid operation data, grid auxiliary service data, and equipment status data into a pre-created prediction model to predict the grid auxiliary service data and grid power generation data within the next preset time period, it further includes:

[0027] Obtain the pre-set grid power generation data assessment criteria;

[0028] Determine whether the predicted grid power generation data meets the grid power generation data assessment criteria;

[0029] If not, obtain the data association relationship characteristics;

[0030] Based on the grid power generation data assessment criteria, the data association relationship characteristics, and the predicted grid power generation data, determine a grid power generation data adjustment plan.

[0031] Optionally, obtaining the primary frequency modulation contribution rate within a preset time period includes:

[0032] Obtain the actual primary frequency modulation contribution amount and the theoretical primary frequency modulation contribution amount within a preset time period;

[0033] Based on the actual primary frequency modulation contribution amount and the theoretical primary frequency modulation contribution amount, calculate the primary frequency modulation contribution rate within a preset time period.

[0034] Optionally, obtaining the AGC data within a preset time period includes:

[0035] Obtain the response speed performance index and the accuracy performance index within a preset time period;

[0036] Based on the response speed performance index and the accuracy performance index, calculate the AGC data within a preset time period.

[0037] A power grid auxiliary service data prediction device, comprising:

[0038] A data acquisition module, configured to acquire power grid generation data, power grid operation data, power grid auxiliary service data, and equipment status data within a preset time period, where the power grid auxiliary service data includes: primary frequency modulation contribution rate, AGC data, and AVC data;

[0039] A data prediction module, configured to input the power grid generation data, power grid operation data, power grid auxiliary service data, and equipment status data into a pre-created prediction model, and predict the power grid auxiliary service data and the power grid generation data within the next preset time period; the prediction model is configured to have the ability to process the input power grid generation data, power grid operation data, power grid auxiliary service data, and equipment status data within a preset time period to obtain data correlation relationship features, and based on the power grid generation data, power grid operation data, power grid auxiliary service data, equipment status data within a preset time period, and the data correlation relationship features, determine the power grid auxiliary service data and the power grid generation data within the next preset time period.

[0040] A model training module, configured to train the prediction model, where the prediction model includes: an input layer, a data correlation relationship analysis layer, and a data prediction layer connected in series; the training process of the prediction model includes: through the input layer, acquiring power grid generation training data, power grid operation training data, auxiliary service training data, and equipment status training data within a preset time period; through the data correlation relationship analysis layer, processing the input power grid generation data, power grid operation data, power grid auxiliary service data, and equipment status data within a preset time period to obtain data correlation relationship features; through the data prediction layer, based on the power grid generation data, power grid operation data, power grid auxiliary service data, equipment status data within a preset time period, and the data correlation relationship features, determine the power grid auxiliary service data and the power grid generation data within the next preset time period; taking the determined power grid auxiliary service data to approach the power grid auxiliary service data label within the next preset time period, and taking the determined power grid generation data to approach the power grid generation data within the next preset time period as the training objective, and updating the parameters of the prediction model.

[0041] A power grid auxiliary service data prediction device, comprising: a memory and a processor; the memory is used for storing programs;

[0042] A processor for executing a program to implement the steps of the power grid auxiliary service data prediction method according to any one of the foregoing.

[0043] A readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the power grid auxiliary service data prediction method according to any one of the foregoing are implemented.

[0044] As can be seen from the above technical solutions, a power grid auxiliary service data prediction method, device, equipment and readable storage medium provided by an embodiment of the present application include: obtaining power grid power generation data, power grid operation data, power grid auxiliary service data and equipment status data within a preset time period, where the power grid auxiliary service data includes: primary frequency modulation contribution rate, AGC data and AVC data; inputting the power grid power generation data, power grid operation data, power grid auxiliary service data and equipment status data into a pre-created prediction model to predict the power grid auxiliary service data and power grid power generation data within the next preset time period; the prediction model is configured to have the ability to process the input power grid power generation data, power grid operation data, power grid auxiliary service data and equipment status data within the preset time period to obtain data correlation relationship characteristics, and based on the power grid power generation data, power grid operation data, power grid auxiliary service data, equipment status data and data correlation relationship characteristics within the preset time period, determine the power grid auxiliary service data and power grid power generation data within the next preset time period; the prediction model includes: an input layer, a data correlation relationship analysis layer and a data prediction layer connected in series in sequence; the training process of the prediction model includes: obtaining power grid power generation training data, power grid operation training data, auxiliary service training data and equipment status training data within a preset time period through the input layer; processing the input power grid power generation data, power grid operation data, power grid auxiliary service data and equipment status data within the preset time period through the data correlation relationship analysis layer to obtain data correlation relationship characteristics; based on the power grid power generation data, power grid operation data, power grid auxiliary service data, equipment status data and data correlation relationship characteristics within the preset time period, determining the power grid auxiliary service data and power grid power generation data within the next preset time period through the data prediction layer; taking the determined power grid auxiliary service data to approach the power grid auxiliary service data label within the next preset time period, and taking the determined power grid power generation data to approach the power grid power generation data within the next preset time period as the training objective, and updating the parameters of the prediction model. By inputting the power grid power generation data, power grid operation data, power grid auxiliary service data and equipment status data within the preset time period into the pre-created prediction model, the present application processes the input data by the prediction model to obtain data correlation relationship characteristics, and then combines the data correlation relationship characteristics to predict the power grid auxiliary service data and power grid power generation data within the next preset time period, further enabling the power station to perform debugging and optimization in advance according to the predicted data, so as to ensure the normal operation of the system. Description of the Drawings

[0045] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on the provided drawings.

[0046] Figure 1 Flowchart of a method for predicting grid auxiliary service data provided by an embodiment of the present application;

[0047] Figure 2 Schematic structural diagram of a device for predicting grid auxiliary service data provided by an embodiment of the present application;

[0048] Figure 3 Hardware structure block diagram of a device for predicting grid auxiliary service data disclosed by an embodiment of the present application. Detailed implementation manners

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0050] Figure 1 Flowchart of a method for predicting grid auxiliary service data provided by an embodiment of the present application. The method may include the following steps:

[0051] Step S100: Obtain grid power generation data, grid operation data, grid auxiliary service data, and equipment status data within a preset time period.

[0052] Specifically, the grid power generation data may include: planned power generation data, actual power generation data, etc., which can reflect the production and operation conditions of power stations. The grid operation data may include: grid frequency, bus voltage, tie-line exchange power, etc. The equipment status data may include: operating parameters such as the temperature, pressure, and vibration of unit equipment, as well as equipment failure information, maintenance records, etc., which are helpful for judging the operating conditions of the equipment.

[0053] The above data can be collected in real time by a collection device from systems such as the power dispatching energy management system, the generator set regulation system, the operating condition upload system, and the wide area measurement system. After collection, data cleaning algorithms can be used to denoise and deduplicate the collected data. By setting data thresholds and rationality verification rules, the accuracy and validity of the data can be checked. For example, for active power output data, upper and lower limit thresholds can be set according to the rated capacity of the unit, and data outside the range is marked and processed as abnormal data to ensure the accuracy of subsequent analysis and assessment.

[0054] At the same time, the status of the data transmission channel can be monitored in real time. Network monitoring technologies and fault diagnosis algorithms are used to monitor the operating rates of communication devices such as carrier equipment, optical fiber equipment, and dispatching program-controlled switches. When the data channel is interrupted or abnormal, warning messages are sent in a timely manner, and the continuity of data transmission is ensured through backup channel switching technology.

[0055] Grid auxiliary service data can include: primary frequency modulation contribution rate, AGC data, AVC data, etc. As the key to ensuring the safe, stable, and efficient operation of power stations, grid auxiliary service data needs to be accurately calculated and evaluated using a unified and efficient system in combination with existing calculation rules to meet the refined management requirements of the power system and ensure the safety and economy of power system operation.

[0056] Step S101: Input grid power generation data, grid operation data, grid auxiliary service data, and equipment status data into a pre-created prediction model to predict the grid auxiliary service data and grid power generation data within the next preset time period.

[0057] Specifically, the prediction model can be configured to process the grid power generation data, grid operation data, grid auxiliary service data, and equipment status data within the input preset time period to obtain data correlation relationship features, and based on the grid power generation data, grid operation data, grid auxiliary service data, equipment status data, and data correlation relationship features within the preset time period, determine the grid auxiliary service data and grid power generation data within the next preset time period. Among them, the data correlation relationship features include the correlation and dependence relationships between various data.

[0058] The prediction model can include: an input layer, a data correlation relationship analysis layer, and a data prediction layer connected in series. The training process of the prediction model can include:

[0059] S11: Through the input layer, obtain the grid power generation training data, grid operation training data, auxiliary service training data, and equipment status training data within the preset time period.

[0060] Specifically, different types of data can be normalized and then input into the prediction model.

[0061] S12. Through the data correlation relationship analysis layer, process the grid power generation data, grid operation data, grid auxiliary service data, and equipment status data within the preset time period of the input to obtain the data correlation relationship characteristics.

[0062] S13. Through the data prediction layer, based on the grid power generation data, grid operation data, grid auxiliary service data, equipment status data, and data correlation relationship characteristics within the preset time period, determine the grid auxiliary service data and grid power generation data within the next preset time period.

[0063] S14. Using the determined grid auxiliary service data approaching the grid auxiliary service data label within the next preset time period, and the determined grid power generation data approaching the grid power generation data within the next preset time period as the training objectives, update the parameters of the prediction model.

[0064] As can be seen from the above technical solution, a method for predicting power grid auxiliary service data provided by an embodiment of the present application includes: obtaining power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data within a preset time period, where the power grid auxiliary service data includes: primary frequency modulation contribution rate, AGC data, and AVC data; inputting the power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data into a pre-created prediction model to predict the power grid auxiliary service data and power grid power generation data within the next preset time period; the prediction model is configured to have the ability to process the input power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data within the preset time period to obtain data association relationship features, and determine the power grid auxiliary service data and power grid power generation data within the next preset time period based on the power grid power generation data, power grid operation data, power grid auxiliary service data, equipment status data, and data association relationship features within the preset time period; the prediction model includes: an input layer, a data association relationship analysis layer, and a data prediction layer connected in series in sequence; the training process of the prediction model includes: obtaining power grid power generation training data, power grid operation training data, auxiliary service training data, and equipment status training data within a preset time period through the input layer; processing the input power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data within the preset time period through the data association relationship analysis layer to obtain data association relationship features; determining the power grid auxiliary service data and power grid power generation data within the next preset time period through the data prediction layer based on the power grid power generation data, power grid operation data, power grid auxiliary service data, equipment status data, and data association relationship features within the preset time period; using the determined power grid auxiliary service data to approach the power grid auxiliary service data label within the next preset time period, and using the determined power grid power generation data to approach the power grid power generation data within the next preset time period as the training objective to update the parameters of the prediction model. Through the present application, by inputting the power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data within the preset time period into a pre-created prediction model, the prediction model processes the input data to obtain data association relationship features, and then combines the data association relationship features to predict the power grid auxiliary service data and power grid power generation data within the next preset time period, further enabling the power station to perform debugging and optimization in advance according to the predicted data, thereby ensuring the normal operation of the system.

[0065] In addition, for new energy power stations such as wind power plants and photovoltaic power stations, corresponding meteorological data can be obtained, such as wind speed, light intensity, temperature, etc. The meteorological data and other data are input into the prediction model. Based on this, the prediction model can also be configured to process the grid power generation data, grid operation data, grid auxiliary service data, equipment status data, and meteorological data within a preset time period of the input, obtain data correlation relationship characteristics, and determine the grid auxiliary service data and grid power generation data in the next preset time period based on the grid power generation data, grid operation data, grid auxiliary service data, equipment status data, meteorological data, and data correlation relationship characteristics within the preset time period.

[0066] The prediction model can be pre-trained with the grid power generation training data, grid operation training data, auxiliary service training data, and equipment status training data within a preset time period as training samples, and the grid auxiliary service data and grid power generation data in the next preset time period as training labels. Historical data can be used as training samples during training, and the historical data is divided according to a preset time window to form multiple samples.

[0067] In some embodiments of the present application, the predicted grid auxiliary service data can also be evaluated to determine whether it meets the requirements. If it does not meet the evaluation requirements, optimization and adjustment can be carried out in advance. Based on this, after step S101, where the grid power generation data, grid operation data, grid auxiliary service data, and equipment status data are input into a pre-created prediction model to predict the grid auxiliary service data and grid power generation data in the next preset time period, the following steps can also be included:

[0068] S21. Obtain the pre-set grid auxiliary service data evaluation criteria.

[0069] Specifically, the relevant grid auxiliary service data evaluation criteria can be pre-set according to relevant regulations, which can be consistent with the relevant regulations or higher than the relevant regulations to ensure that the evaluation results meet the management requirements.

[0070] S22. Determine whether the predicted grid auxiliary service data in the next preset time period meets the grid auxiliary service data evaluation criteria.

[0071] Specifically, if it meets the criteria, no optimization and adjustment are required. If it does not meet the criteria, execute S23.

[0072] S23. Obtain the data correlation relationship characteristics.

[0073] Specifically, the data correlation relationship characteristics can reflect the correlation relationship between the grid auxiliary service data and other data, and the acquisition method can be the data correlation relationship characteristics obtained from the prediction model.

[0074] S24. Based on the characteristics of data correlation relationships, the grid auxiliary service data assessment criteria, and the predicted grid auxiliary service data for the next preset time period, determine the grid auxiliary service data adjustment plan.

[0075] Specifically, determining the adjustment plan for the grid auxiliary service data can optimize and adjust the power grid, avoid the situation where the grid auxiliary service data does not meet the assessment criteria, and ensure the safe and stable operation of the power grid.

[0076] Furthermore, based on the grid auxiliary service data assessment criteria and the predicted grid auxiliary service data for the next preset time period, if it is determined that the grid auxiliary service data does not meet the requirements, the possible assessment fees and the compliance situation of the assessment indicators can be estimated in combination with relevant assessment regulations, and an emergency plan can be formulated in advance, such as increasing standby equipment and optimizing the operation mode, to ensure that the assessment requirements can be met.

[0077] In some embodiments of the present application, S24. Based on the characteristics of data correlation relationships, the grid auxiliary service data assessment criteria, and the predicted grid auxiliary service data for the next preset time period, determine the grid auxiliary service data adjustment plan, which may include the following steps:

[0078] S31. Based on the grid auxiliary service data assessment criteria and the predicted grid auxiliary service data for the next preset time period, determine the unqualified data.

[0079] Specifically, compare the grid auxiliary service data assessment criteria with the predicted grid auxiliary service data for the next preset time period to determine the unqualified data, such as the non-compliance of the primary frequency modulation contribution rate.

[0080] S32. Based on the unqualified data and the characteristics of data correlation relationships, determine the key factors affecting the unqualified data.

[0081] Specifically, after determining the unqualified data, the key factors affecting the unqualified data can be determined in combination with the characteristics of data correlation relationships.

[0082] S33. Based on the key factors, determine the grid auxiliary service data adjustment plan.

[0083] Specifically, after determining the key factors affecting the unqualified data, optimization and adjustment can be carried out for the key factors to make the data meet the assessment requirements. For example, if the primary frequency modulation performance is related to the governor parameters and the power generation plan of the unit, the governor parameters can be adjusted and the power generation plan can be optimized to improve the contribution rate and response speed of the primary frequency modulation.

[0084] In some embodiments of the present application, the predicted grid power generation data can also be evaluated to determine whether it meets the requirements. If it does not meet the evaluation requirements, optimization and adjustment can be carried out in advance. Based on this, after step S101: inputting the grid power generation data, grid operation data, grid ancillary service data, and equipment status data into a pre-created prediction model to predict the grid ancillary service data and grid power generation data within the next preset time period, the following steps can also be included:

[0085] S41. Obtain the pre-set evaluation criteria for grid power generation data.

[0086] Specifically, the grid power generation data can include planned power generation data and actual power generation data, and the evaluation criteria for the grid power generation data can be evaluated according to the following formula.

[0087] In the case where the frequency is higher than 49.90 Hz and lower than 50.10 Hz, if: |P s -P a |-max{P s ×2%, 2 (MW)} > 0, then it is evaluated. That is, the allowable deviation range of the actual active power output is ±2% of the daily power generation dispatch plan curve. When the daily power generation plan is less than 100 MW, the allowable deviation range is 2 MW. Wherein, P s is the planned active power output, and P a is the actual active power output.

[0088] S42. Determine whether the predicted grid power generation data within the next preset time period meets the evaluation criteria for grid power generation data.

[0089] Specifically, if it meets the requirements, no optimization and adjustment are required. If it does not meet the requirements, then execute S43.

[0090] S43. Obtain the data correlation relationship characteristics.

[0091] S44. Based on the data correlation relationship characteristics, the evaluation criteria for grid power generation data, and the predicted grid power generation data within the next preset time period, determine the grid power generation data adjustment plan.

[0092] Specifically, the power generation plan can be reasonably adjusted according to the actual needs of the grid to improve the power generation efficiency and the stability of the grid. For example, during the peak load period of the grid, the power generation output of the units can be reasonably arranged.

[0093] In some embodiments of the present application, step S100 of obtaining the primary frequency regulation contribution rate within the preset time period can include the following steps:

[0094] S51. Obtain the actual primary frequency regulation contribution amount and the theoretical primary frequency regulation contribution amount within the preset time period.

[0095] Specifically, the actual contribution H of the primary frequency regulation i can be calculated by the following formula:

[0096]

[0097] where t0 is the moment when the system frequency exceeds the dead band of the primary frequency regulation of the unit; t t is the moment when the system frequency enters the dead band of the primary frequency regulation of the unit; P0 is the actual active power generated by the unit at the moment t0 (taking the average value of the previous 5 seconds before the moment t0); P t is the actual active power generated by the unit at the moment t.

[0098] The theoretical contribution H of the primary frequency regulation e can be calculated by the following formula:

[0099]

[0100] where t0 is the moment when the system frequency exceeds the dead band of the primary frequency regulation of the unit; t t is the moment when the system frequency enters the dead band of the primary frequency regulation of the unit; Δf(t) is the value by which the grid frequency exceeds 50 ± Δfsq (frequency modulation artificial dead band) at the corresponding moment t, positive for high frequency and negative for low frequency; MCR is the rated active power output of the unit; f n is the grid rated frequency of 50 Hz; f t is the grid frequency (Hz) at the corresponding moment t; K c is the speed regulation rate or the permanent speed droop coefficient of the unit.

[0101] S52. Calculate the primary frequency regulation contribution rate within a preset time period based on the actual contribution of the primary frequency regulation and the theoretical contribution of the primary frequency regulation.

[0102] Specifically, after calculating the actual contribution H of the primary frequency regulation i and the theoretical contribution H of the primary frequency regulation e , the primary frequency regulation contribution rate K can be calculated by the following formula:

[0103]

[0104] In some embodiments of the present application, AGC is used to monitor in real time the gap between the load and the power generation capacity of the power system and maintain the frequency stability of the power system by adjusting the power output of the generator set. AGC mainly focuses on the power balance of the power system to ensure the matching between the actual load and the power generation capacity. Obtaining the AGC data within the preset time period in step S100 may include the following steps:

[0105] S61. Obtain the response speed performance index and the accuracy performance index within the preset time period.

[0106] Specifically, the response speed performance index k1 can be calculated by the following formula:

[0107]

[0108] where ΔP is the adjustment amplitude (MW) during the actual adjustment process; P z is the command at any point during the adjustment process; P is the actual output (MW) corresponding to this point during the adjustment process; ΔP z is the initial output (MW) of the final command during the adjustment process; ΔT is the adjustment time (s) of the actual adjustment process; T1 is the adjustment compensation time, for thermal power: 0 - 30 seconds for subcritical units, 0 - 20 seconds for ultra (ultra-supercritical) units, for hydropower: 0 - 5 seconds; V0 is the unit's lifting and lowering rate.

[0109] The accuracy performance index k2 can be obtained by the following formula:

[0110]

[0111] where e is the adjustment accuracy during the adjustment process; when the control mode is the single - machine mode, P n is the rated capacity of the motor to be controlled, when the control mode is the whole - plant mode, P n is the rated capacity of the whole - plant units.

[0112] S62. Calculate the AGC data within the preset time period based on the response speed performance index and the accuracy performance index k2.

[0113] Specifically, after obtaining the response speed performance index k1 and the accuracy performance index, the AGC data k can be calculated by the following formula:

[0114] k = β × k1 × k2

[0115] where β is 1 for hydropower and 1.4 for thermal power.

[0116] In some embodiments of the present application, AVC is used to monitor the voltage level of the power system in real - time and maintain the voltage stability of the power system by adjusting transformers and reactive power compensation devices. AVC mainly focuses on the voltage stability of the power system to ensure that the voltage is within an appropriate range. The AVC data may include: AVC operation rate and AVC adjustment qualification rate. The AVC operation rate includes: AVC sub - station operation rate and unit AVC operation rate. Among them, the calculation formula of the AVC operation rate is as follows:

[0117] AVC operation rate = (AVC closed - loop operation time / AVC should - be - closed - loop operation time) × 100%

[0118] The qualified rate of AVC adjustment can be calculated according to the following formula:

[0119] Qualified rate of AVC adjustment = Number of qualified points executed by the substation / Number of adjustment instructions issued by the master station × 100%

[0120] Based on the above AVC data, the commissioning rate and qualified rate of AVC adjustment of grid-connected power plants equipped with AVC devices can be evaluated. The evaluation criteria can be set as follows: the commissioning rate of the AVC substation shall not be lower than 90%, the commissioning rate of each unit's AVC shall not be lower than 85%. For those with a monthly commissioning rate lower than the standard, for each percentage point reduction, the evaluation shall be carried out according to the standard of the rated capacity of the corresponding unit of the AVC device × 0.2 hours. The qualified rate of AVC substation adjustment of the power plant shall not be lower than 90%. For those with a qualified rate lower than the standard, for each percentage point reduction, the evaluation shall be carried out according to the standard of the rated capacity of the corresponding unit of the AVC device × 0.2 hours.

[0121] In some embodiments of the present application, the grid auxiliary service data may further include: bus voltage data. For the evaluation of the bus voltage, the voltage curve issued by the power dispatching agency can be used as the reactive power evaluation basis. When the bus voltage of the power plant exceeds the upper or lower limit of the voltage curve limit value, the reactive power output and power factor of the power plant unit shall be evaluated.

[0122] Each unit can calculate the evaluation points and qualified points at one point every 5 minutes. When the bus voltage of the power plant is less than the lower limit of the voltage curve and the reactive power output of the unit is less than or equal to 0, it is counted as one evaluation point; when the bus voltage of the power plant where the unit belongs is greater than the upper limit of the voltage curve and the generator set is in leading phase operation, and the absolute value of the reactive power output of the unit is less than the leading phase depth requirement, it is counted as one evaluation point, etc.

[0123] At the same time, the qualified rate of the bus voltage can be statistically calculated. The monthly qualified rate of the bus voltage shall be greater than or equal to 99.9%. For each 0.05 percentage point reduction, the evaluation shall be carried out according to the standard of the rated capacity of the whole plant × 0.25 hours.

[0124] In some embodiments of the present application, after comparing the obtained data with the pre-set evaluation criteria, the evaluation comparison results can be separately balanced and calculated according to different types of power stations, and the evaluation refund fees and evaluation fees of each power plant can be statistically calculated to obtain the monthly evaluation settlement fees of grid-connected power plants. Through big data analysis technology, the evaluation situations of different types of power plants can also be horizontally compared and vertically analyzed to evaluate the performance of each power plant in terms of auxiliary services and grid connection operation, providing a reference for the optimized operation of the power plant.

[0125] In some embodiments of the present application, when problems such as the data of the unit not meeting the pre-set evaluation criteria, data anomalies, system failures, etc. occur, warning messages can be sent through text messages, emails, system pop-ups, etc.

[0126] Specifically, hierarchical alarms can be issued according to the severity of abnormal situations. For example, a level-1 alarm indicates a situation that seriously affects the safe operation of the power system and needs to be processed immediately; a level-2 alarm indicates a certain impact on the system operation and needs to be processed as soon as possible, etc.

[0127] Next, a power grid auxiliary service data prediction device provided by an embodiment of the present application will be described. The power grid auxiliary service data prediction device described below can be correspondingly referred to the power grid auxiliary service data prediction method described above.

[0128] Reference Figure 2 shown in Figure 2 is a schematic structural diagram of a power grid auxiliary service data prediction device provided by an embodiment of the present application. The device may include:

[0129] A data acquisition module 10, configured to acquire power grid generation data, power grid operation data, power grid auxiliary service data, and equipment status data within a preset time period. The power grid auxiliary service data includes: primary frequency modulation contribution rate, AGC data, and AVC data;

[0130] A data prediction module 20, configured to input the power grid generation data, power grid operation data, power grid auxiliary service data, and equipment status data into a pre-created prediction model, and predict the power grid auxiliary service data and power grid generation data within the next preset time period; the prediction model is configured to have the ability to process the input power grid generation data, power grid operation data, power grid auxiliary service data, and equipment status data within the preset time period to obtain data correlation relationship features, and determine the power grid auxiliary service data and power grid generation data within the next preset time period based on the power grid generation data, power grid operation data, power grid auxiliary service data, equipment status data, and data correlation relationship features within the preset time period;

[0131] The model training module 30 is used to train a prediction model. The prediction model includes an input layer, a data association relationship analysis layer, and a data prediction layer that are cascaded in sequence. The training process of the prediction model includes: obtaining grid power generation training data, grid operation training data, ancillary service training data, and equipment status training data within a preset time period through the input layer; processing the input grid power generation data, grid operation data, grid ancillary service data, and equipment status data within the preset time period through the data association relationship analysis layer to obtain data association relationship features; determining the grid ancillary service data and grid power generation data within the next preset time period based on the grid power generation data, grid operation data, grid ancillary service data, equipment status data, and data association relationship features within the preset time period through the data prediction layer; and updating the parameters of the prediction model with the determined grid ancillary service data approaching the grid ancillary service data label within the next preset time period and the determined grid power generation data approaching the grid power generation data within the next preset time period as the training objectives.

[0132] As can be seen from the above technical solution, a power grid auxiliary service data prediction device provided by an embodiment of the present application includes: a data acquisition module 10 that acquires power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data within a preset time period, where the power grid auxiliary service data includes: primary frequency modulation contribution rate, AGC data, and AVC data; a data prediction module 20 inputs the power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data into a pre-created prediction model to predict the power grid auxiliary service data and power grid power generation data within the next preset time period; the prediction model is configured to have the ability to process the input power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data within a preset time period to obtain data correlation relationship characteristics, and based on the power grid power generation data, power grid operation data, power grid auxiliary service data, equipment status data, and data correlation relationship characteristics within a preset time period, determine the power grid auxiliary service data and power grid power generation data within the next preset time period; a model training module 30 is used to train the prediction model, and the prediction model includes: an input layer, a data correlation relationship analysis layer, and a data prediction layer connected in series in sequence; the training process of the prediction model includes: through the input layer, acquiring power grid power generation training data, power grid operation training data, auxiliary service training data, and equipment status training data within a preset time period; through the data correlation relationship analysis layer, processing the input power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data within a preset time period to obtain data correlation relationship characteristics; through the data prediction layer, based on the power grid power generation data, power grid operation data, power grid auxiliary service data, equipment status data, and data correlation relationship characteristics within a preset time period, determine the power grid auxiliary service data and power grid power generation data within the next preset time period; with the determined power grid auxiliary service data approaching the power grid auxiliary service data label within the next preset time period, and with the determined power grid power generation data approaching the power grid power generation data within the next preset time period as the training objective, update the parameters of the prediction model. Through the present application, the power grid power generation data, power grid operation data, power grid auxiliary service data, and equipment status data within a preset time period are input into a pre-created prediction model, the prediction model processes the input data to obtain data correlation relationship characteristics, and then combines the data correlation relationship characteristics to predict the power grid auxiliary service data and power grid power generation data within the next preset time period, further enabling the power station to perform debugging and optimization in advance according to the predicted data, thereby ensuring the normal operation of the system.

[0133] An embodiment of the present application further provides a power grid auxiliary service data prediction device, Figure 3 which shows the hardware structure block diagram of the power grid auxiliary service data prediction device. Refer to Figure 3, the hardware structure of the power grid auxiliary service data prediction device may include: at least one processor 1, at least one communication interface 2, at least one memory 3, and at least one communication bus 4;

[0134] In the embodiments of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 complete mutual communication through the communication bus 4;

[0135] The processor 1 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0136] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory, etc., such as at least one disk memory;

[0137] Wherein, the memory stores a program, and the processor can call the program stored in the memory, and the program is used to: implement each processing flow in the aforementioned power grid auxiliary service data prediction method.

[0138] The embodiments of the present application also provide a storage medium, which can store a program suitable for the processor to execute, and the program is used to: implement each processing flow in the aforementioned power grid auxiliary service data prediction method.

[0139] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0140] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined with each other, and the same or similar parts can be referred to each other.

[0141] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting power grid auxiliary service data, characterized in that: include: Acquire power generation data, power operation data, power auxiliary service data and equipment status data of the power grid within a preset time period, wherein the power auxiliary service data includes: primary frequency regulation contribution rate, automatic generation control (AGC) data and automatic voltage control (AVC) data; Inputting the power grid generation data, power grid operation data, power grid ancillary service data and equipment status data into a pre-created prediction model to predict the power grid ancillary service data and power grid generation data within the next preset time period; The prediction model is configured to process the power grid power generation data, power grid operation data, power grid ancillary service data and equipment status data input within a preset time period to obtain data association characteristics, and determine the power grid ancillary service data and power grid power generation data within the next preset time period based on the power grid power generation data, power grid operation data, power grid ancillary service data, equipment status data and the data association characteristics within the preset time period; The prediction model includes: an input layer, a data association relationship analysis layer and a data prediction layer which are cascaded in sequence; The training process of the prediction model includes: Obtaining power grid generation training data, power grid operation training data, auxiliary service training data and equipment status training data within a preset time period through the input layer; The data association relationship analysis layer processes the input power grid power generation data, power grid operation data, power grid auxiliary service data and equipment status data within a preset time period to obtain data association relationship characteristics; Through the data prediction layer, based on the power grid power generation data, power grid operation data, power grid auxiliary service data, equipment status data and the data association relationship characteristics within the preset time period, the power grid auxiliary service data and power grid power generation data within the next preset time period are determined; The parameters of the prediction model are updated by taking the determined grid ancillary service data approaching the grid ancillary service data label within the next preset time period and taking the determined grid power generation data approaching the grid power generation data within the next preset time period as training targets.

2. The method according to claim 1, characterized in that The prediction model is obtained by pre-training with power generation training data, power operation training data, auxiliary service training data and equipment status training data within a preset time period as training samples, and with power auxiliary service data and power generation data within the next preset time period as training labels.

3. The method according to claim 1, characterized in that After inputting the power grid generation data, power grid operation data, power grid ancillary service data and equipment status data into a pre-created prediction model to predict the power grid ancillary service data and power grid generation data within the next preset time period, the method further includes: Obtain pre-set grid ancillary service data assessment standards; Determining whether the predicted power grid auxiliary service data meets the power grid auxiliary service data assessment standard; If not, obtaining the data association relationship feature; Based on the grid ancillary service data assessment standard, the data association characteristics and the predicted grid ancillary service data, a grid ancillary service data adjustment plan is determined.

4. The method according to claim 3, characterized in that The determining of a grid ancillary service data adjustment plan based on the grid ancillary service data assessment standard, the data association relationship characteristics and the predicted grid ancillary service data includes: Determining unqualified data based on the grid ancillary service data assessment standard and the predicted grid ancillary service data; Determining key factors affecting the unqualified data based on the unqualified data and the data association relationship characteristics; Based on the key factors, a grid ancillary service data adjustment plan is determined.

5. The method according to claim 1, characterized in that After inputting the power grid generation data, power grid operation data, power grid ancillary service data and equipment status data into a pre-created prediction model to predict the power grid ancillary service data and power grid generation data within the next preset time period, the method further includes: Obtain pre-set grid power generation data assessment standards; Determining whether the predicted power grid power generation data meets the power grid power generation data assessment standard; If not, obtaining the data association relationship feature; Based on the power grid power generation data assessment standard, the data association relationship characteristics and the predicted power grid power generation data, a power grid power generation data adjustment plan is determined.

6. The method according to any one of claims 1 to 5, characterized in that: Get the primary frequency modulation contribution rate within the preset time period, including: Obtain the actual contribution of primary frequency modulation and the theoretical contribution of primary frequency modulation within a preset time period; Based on the actual contribution of the primary frequency modulation and the theoretical contribution of the primary frequency modulation, a contribution rate of the primary frequency modulation within a preset time period is calculated.

7. The method according to any one of claims 1 to 5, characterized in that: Get AGC data within a preset time period, including: Obtain response speed performance indicators and accuracy performance indicators within a preset time period; Based on the response speed performance index and the accuracy performance index, AGC data within a preset time period is calculated.

8. A power grid auxiliary service data prediction device, characterized in that: include: A data acquisition module is used to acquire power generation data, power operation data, power auxiliary service data and equipment status data within a preset time period, wherein the power auxiliary service data includes: primary frequency regulation contribution rate, AGC data and AVC data; A data prediction module, used for inputting the power grid power generation data, power grid operation data, power grid auxiliary service data and equipment status data into a pre-created prediction model, and predicting the power grid auxiliary service data and power grid power generation data within the next preset time period; the prediction model is configured to process the input power grid power generation data, power grid operation data, power grid auxiliary service data and equipment status data within the preset time period, obtain data association characteristics, and determine the power grid auxiliary service data and power grid power generation data within the next preset time period based on the power grid power generation data, power grid operation data, power grid auxiliary service data, equipment status data within the preset time period and the data association characteristics; A model training module is used to train and obtain the prediction model, wherein the prediction model includes: an input layer, a data association analysis layer and a data prediction layer cascaded in sequence; the training process of the prediction model includes: obtaining power grid power generation training data, power grid operation training data, auxiliary service training data and equipment status training data within a preset time period through the input layer; processing the input power grid power generation data, power grid operation data, power grid auxiliary service data and equipment status data within the preset time period through the data association analysis layer to obtain data association characteristics; determining the power grid auxiliary service data and power grid power generation data within the next preset time period based on the power grid power generation data, power grid operation data, power grid auxiliary service data, equipment status data and the data association characteristics within the preset time period through the data prediction layer; updating the parameters of the prediction model with the determined power grid auxiliary service data approaching the power grid auxiliary service data label within the next preset time period and with the determined power grid power generation data approaching the power grid power generation data within the next preset time period as training targets.

9. A power grid auxiliary service data prediction device, characterized in that: Comprising: a memory and a processor; the memory is used to store a program; The processor is used to execute the program to implement each step of the grid ancillary service data prediction method as claimed in any one of claims 1 to 7.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for predicting power grid auxiliary service data according to any one of claims 1 to 7 is implemented.

Images