Virtual power plant power equipment control system and method thereof

Abstract

The invention relates to the field of power system management and control, and discloses a virtual power plant power equipment control system and method, and the system comprises a fault starting judgment module which is used for collecting the state monitoring information of the operation path of power equipment in a virtual power plant, analyzing the abnormal change type in the real-time operation index, and determining the abnormal change type; determining a fault starting condition of the power equipment; the operation stability calculation module is used for calculating an operation stability index of the power equipment; the power distribution calculation module is used for calculating a power distribution index of the power equipment when a fault occurs; the response fit analysis module is used for determining an adjustment mode corresponding to the power equipment, analyzing the load characteristics of the power equipment under the current power grid condition, and analyzing the response fit degree of the equipment in the adjustment mode and energy storage cooperation; and the adjustment management and control module is used for performing adjustment management and control processing on the equipment and energy storage in the adjustment mode to obtain a management and control result. The control stability of the power plant power equipment control system can be virtualized.

Description

TECHNICAL FIELD

[0001] The present application relates to a virtual power plant power equipment control system and method thereof, and belongs to the field of power system management and control. BACKGROUND

[0002] As a key carrier for integrating distributed energy and optimizing power resource allocation, the collaborative control capability of the power equipment of the virtual power plant is directly related to the operation efficiency of the power grid, the energy utilization rate and the power supply reliability, and has an important influence on new energy consumption and power system stability. At present, the mainstream power equipment control system adopts a fixed adjustment mode based on preset control logic. This method relies on established equipment operating parameters and historical static response models, but it is difficult to adapt to the dynamic fluctuations of the power grid load and the real-time changes of the equipment working conditions. In actual operation, due to the solidification of the equipment control strategy and the lack of real-time adaptation capability in fault state, local equipment abnormalities often associate with other equipment, and single equipment operating conditions may occur, which may lead to unbalanced operation, resulting in waste of energy resources and increase of operation and maintenance costs. In addition, the lack of emergency regulation mechanism may cause overall power distribution disorder risk, and the lack of equipment coordination flexibility may also cause power supply stability fluctuations, leading to poor power supply quality in the same area. SUMMARY

[0003] The present application provides a virtual power plant power equipment control system and method thereof, which mainly aims to improve the control stability of the virtual power plant power equipment control system.

[0004] To achieve the above purpose, the virtual power plant power equipment control system provided by the present application comprises: a fault start determination module, a running smoothness calculation module, a power distribution calculation module, a response fitting analysis module and an adaptation control module; The fault start determination module is used to collect the state monitoring information of the running path of the power equipment in the virtual power plant, the state monitoring information includes real-time running indicators and past fault information, and analyzes the types of abnormal changes in the real-time running indicators to determine the fault start condition of the power equipment. The running smoothness calculation module is used to calculate the running smoothness index of the power equipment based on the fault start condition. The power distribution calculation module is used to analyze the equipment conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs based on the past fault information, so as to calculate the power distribution index of the power equipment when a fault occurs. The response fit analysis module is configured to determine the adjustment mode corresponding to the power equipment, analyze the load characteristics of the power equipment under the current power grid condition, analyze the response fit degree of the equipment and energy storage in the adjustment mode based on the load characteristics, and determine the response fit degree of the equipment and energy storage in the adjustment mode based on the load characteristics. The adaptive control module is configured to perform adaptive control processing on the equipment and energy storage in the adjustment mode based on the response fit degree, and obtain a control result.

[0005] Optionally, the calculation of the fracture toughness coefficient corresponding to the casing sample comprises: querying a test function requirement corresponding to the casing sample, and positioning a casing test area corresponding to the casing sample based on the test function requirement; performing an indentation test on the casing test area according to a preset test load, and obtaining a test casing sample; acquiring a casing crack image of the test casing sample, and calculating the fracture toughness coefficient corresponding to the casing sample based on the test load and the casing crack image.

[0006] Optionally, the analysis of the abnormal variation type in the instant operation index comprises: performing abstract extraction processing on the instant operation index, and obtaining an operation index abstract; performing variation identification processing on the operation index abstract, and obtaining an abnormal index abstract; performing type matching processing on the abnormal index abstract, and obtaining a matching abnormal type; performing effective analysis processing on the matching abnormal type, and obtaining an effective variation type; analyzing the abnormal variation type in the instant operation index based on the effective variation type.

[0007] Optionally, the effective analysis processing on the matching variation type comprises: performing environment checking processing on the matching variation type, and obtaining an environment-related type; analyzing an abnormal evolution trend corresponding to the environment-related type, and determining a sustained abnormal type in the environment-related type based on the abnormal evolution trend; analyzing an influence area corresponding to the sustained abnormal type, and identifying a key abnormal type in the sustained abnormal type based on the influence area; calculating a system correlation degree corresponding to the key abnormal type, and determining an effective variation type in the key abnormal type based on the system correlation degree.

[0008] Optionally, the calculating the system correlation degree corresponding to the key abnormal type comprises: extracting a fault chain feature corresponding to the key abnormal type, and determining a fault severity level corresponding to the key abnormal type based on the fault chain feature; querying an abnormal device of the key abnormal type, analyzing a functional attribute of the abnormal device in the virtual power plant, and calculating a current power shortage ratio corresponding to the abnormal device; allocating a device function weight corresponding to the key abnormal type based on the functional attribute; detecting an operating condition of a current power grid of the virtual power plant, calculating a condition adjustment margin and an allowed shortage limit value of the key abnormal type based on the operating condition; combining the fault severity level, the device function weight, the condition adjustment margin, the current power shortage ratio, and the allowed shortage limit value, and calculating a system correlation degree corresponding to the key abnormal type by using the following formula: ; wherein A represents the system correlation degree corresponding to the key abnormal type, represents the fault severity level, represents the device function weight, represents the condition adjustment margin, represents the current power shortage ratio, represents the allowed shortage threshold.

[0009] Optionally, the calculating the operation stability index of the power equipment based on the fault starting condition comprises: performing stage label identification on the fault starting condition to obtain a fault development stage label; calculating a stage stability loss corresponding to the fault development stage label; determining a stage fluctuation duration corresponding to the fault development stage label based on the stage stability loss; calculating an operating state deviation degree corresponding to the power equipment based on the stage fluctuation duration; calculating the operation stability index of the power equipment based on the operating state deviation degree.

[0010] Optionally, the calculating the operating state deviation degree corresponding to the power equipment based on the stage fluctuation duration comprises: performing functional unit decomposition on the stage fluctuation duration to obtain a stage key unit; extracting a unit reference value and a unit real-time value corresponding to the stage key unit; scheduling a unit historical fault data corresponding to the stage key unit; determine a maximum fluctuation duration corresponding to the stage key unit based on the unit historical failure data; In combination with the unit reference value, the unit real-time value, the stage fluctuation duration and the maximum fluctuation duration, the running state deviation degree corresponding to the power equipment is calculated by using the following formula: ; wherein G represents the running state deviation degree corresponding to the power equipment, represents the unit real-time value corresponding to the kth unit in the stage key unit, represents the unit reference value corresponding to the kth unit in the stage key unit, and M represents the stage fluctuation duration, represents the maximum fluctuation duration, k represents the serial number corresponding to the stage key unit, and m represents the number corresponding to the stage key unit.

[0011] Optionally, the device conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs are analyzed based on the past failure information, including: hub clustering is performed on the past failure information to obtain a clustered hub archive; state transition feature extraction is performed on the clustered hub archive to obtain a device state transition feature; low-frequency filtering is performed on the device state transition feature to obtain a high-frequency state transition paradigm; energy storage behavior analysis is performed on the clustered hub archive to obtain an energy storage feature cluster; typical mode analysis is performed on the energy storage feature cluster to obtain a typical energy storage paradigm; In combination with the high-frequency state transition paradigm and the typical energy storage paradigm, the device conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs are analyzed.

[0012] Optionally, the device conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs are analyzed to calculate the power distribution index of the power equipment when a failure occurs, further including: mode encoding processing is performed on the device conversion characteristics to obtain a conversion encoding set; behavior quantization processing is performed on the energy storage characteristics to obtain a storage quantization set; the actual conversion sequence and the actual energy storage operation sequence corresponding to the current failure event of the power equipment are extracted; the sequence matching degree of the actual conversion sequence and the conversion encoding set is calculated; the execution fit degree of the actual energy storage operation sequence and the storage quantization set is calculated; In combination with the sequence matching degree and the execution fit degree, the power distribution index of the power equipment when a failure occurs is calculated.

[0013] Optionally, the response fit degree of the device in the regulation mode and the energy storage is analyzed based on the load characteristics, comprising: Resolving the power demand constraint element corresponding to the load characteristics; Analyzing the device regulation attribute corresponding to the device in the regulation mode; Analyzing the energy storage response attribute corresponding to the energy storage in the regulation mode; Calculating the fit degree between the device regulation attribute and the power demand constraint element to obtain a first fit degree; Calculating the fit degree between the energy storage response attribute and the power demand constraint element to obtain a second fit degree; Combining the first fit degree and the second fit degree, the response fit degree of the device in the regulation mode and the energy storage is analyzed.

[0014] In order to solve the above problems, the present application also provides a virtual power plant power equipment control method, the method comprises: Collecting the state monitoring information of the operation path of the power equipment in the virtual power plant, the state monitoring information contains the instant operation index and the past fault information, analyzing the abnormal change type in the instant operation index to determine the fault start condition of the power equipment; Based on the fault start condition, the operation stability index of the power equipment is calculated; Based on the past fault information, the device conversion characteristics and the energy storage characteristics of the power equipment under different power grid hubs are analyzed to calculate the power distribution index of the power equipment when the fault occurs; Combining the operation stability index and the power distribution index, the regulation mode corresponding to the power equipment is determined, the load characteristics of the power equipment under the current power grid condition are analyzed, and the response fit degree of the device in the regulation mode and the energy storage is analyzed based on the load characteristics; Based on the response fit degree, the device in the regulation mode and the energy storage are adjusted and controlled to obtain a control result.

[0015] Compared with the problems described in the background art, the present application can determine the specific operation parameter related factors causing equipment failure by analyzing the types of abnormal changes in the instant operation indicators, providing a judgment basis for subsequent fault start identification. Further, the present application can quantify the disturbance degree of the equipment failure initiation stage to the operation state by calculating the operation stability index of the power equipment based on the fault start condition, providing a core reference index for the state evaluation of the power system. Further, the present application can mine the adaptation influence law of the power grid hub to power distribution by analyzing the equipment conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs based on the past fault information, thereby providing data support for subsequent power distribution index calculation. Further, the present application can screen out equipment operation modes with stability and adaptability by determining the adjustment mode corresponding to the power equipment by combining the operation stability index and the power distribution index, analyzing the load characteristics of the power equipment under the current power grid condition, and mastering the change law and core influencing factors of the power grid load. Finally, the present application can make the adjustment mode more applicable and improve the control stability of the virtual power plant power equipment control system by adjusting and controlling the equipment and energy storage in the adjustment mode based on the response fit degree, thereby obtaining the control result. Therefore, the virtual power plant power equipment control system and the method thereof provided by the embodiments of the present application can improve the control stability of the virtual power plant power equipment control system. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 A functional module diagram of a virtual power plant power equipment control system is provided for an embodiment of the present application. Figure 2 An adjustment and control process diagram in a virtual power plant power equipment control system is provided for the present application. Figure 3 A flowchart for implementing the virtual power plant power equipment control method is provided for an embodiment of the present application.

[0017] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0018] In order to make the object, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0019] In addition, the step sequence in each of the following method embodiments is only an example and is not strictly limited.

[0020] In fact, the server device deployed by the virtual power plant power equipment control system can be composed of one or more devices. The virtual power plant power equipment control system can be implemented as a business instance, a virtual machine, or a hardware device. For example, the virtual power plant power equipment control system can be implemented as a business instance deployed on one or more devices in a cloud node. In short, the virtual power plant power equipment control system can be understood as a software deployed on a cloud node to provide portable stone removal services for each user end. Alternatively, the virtual power plant power equipment control system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. The virtual machine has application software for managing each user end. Alternatively, the virtual power plant power equipment control system can also be implemented as a server composed of a plurality of same or different types of hardware devices, and one or more hardware devices are provided to provide portable stone removal services for each user end.

[0021] In terms of implementation, the virtual power plant power equipment control system and the user end adapt to each other. That is, the virtual power plant power equipment control system is an application installed on a cloud service platform, and the user end is a client that establishes a communication connection with the application; or the virtual power plant power equipment control system is implemented as a website, and the user end is implemented as a webpage; or the virtual power plant power equipment control system is implemented as a cloud service platform, and the user end is implemented as an applet in an instant messaging application.

[0022] Referring to Figure 1 Fig. 1 shows a functional module diagram of a virtual power plant power equipment control system according to an embodiment of the present application.

[0023] The virtual power plant power equipment control system 100 can be set in a cloud server. In terms of implementation, it can be one or more service devices, or an application installed on a cloud (such as a portable stone removal server, a server cluster, etc.), or it can be developed as a website. According to the implemented functions, the virtual power plant power equipment control system 100 includes a fault start determination module 101, a running smoothness calculation module 102, a power distribution calculation module 103, a response matching analysis module 104, and an adaptive control module 105.

[0024] The fault start determination module 101 is used to collect the state monitoring information of the running path of the power equipment in the virtual power plant. The state monitoring information includes real-time running indicators and past fault information. The abnormal change types in the real-time running indicators are analyzed to determine the fault start condition of the power equipment.

[0025] The application can determine the specific operation parameter related factors causing the equipment failure by analyzing the abnormal variation types in the instant operation index, thereby providing a judgment basis for subsequent fault identification and start-up, wherein the state monitoring information is a collection of information reflecting various states of the power equipment in the operation path, and the abnormal variation types refer to the variation types in the instant operation index that do not conform to the normal operation range.

[0026] As an embodiment of the application, the analysis of the abnormal variation types in the instant operation index comprises: performing abstract extraction processing on the instant operation index to obtain an operation index abstract; performing variation identification processing on the operation index abstract to obtain an abnormal index abstract; performing type matching processing on the abnormal index abstract to obtain a matching abnormal type; performing effective analysis processing on the matching abnormal type to obtain an effective variation type; analyzing the abnormal variation types in the instant operation index based on the effective variation type.

[0027] The instant operation index refers to a collection of operation parameters of the power equipment (such as a generator, a transformer, an inverter, etc.) collected by the virtual power plant monitoring system in real time, for example, "#G12 generator real-time speed 1450 r / min (rated 1500 r / min), stator temperature 72℃ (threshold 70℃), output voltage 382V"; the operation index abstract refers to concise parameter variation information obtained after abstract extraction processing, for example, "photovoltaic inverter DC side current fluctuation ±12%, AC side frequency offset 0.8Hz"; the abnormal index abstract refers to specific abnormal variation items obtained after variation identification processing, for example, "battery pack voltage drop 15V within 1 hour" "breaker opening time extension 0.3 seconds"; the matching abnormal type refers to a standardized abnormal type obtained after type matching processing, for example, "electrical parameter type" "mechanical action type"; and the effective variation type refers to an accurate abnormal type confirmed after effective analysis processing, for example, "voltage drop type" "temperature rapid rise type".

[0028] Further, the summary extraction processing can be performed by signal noise reduction technology, for example, using a wavelet threshold denoising algorithm, automatically filtering transient interference signals and extracting core parameters related to abnormal changes, and generating a running index summary; the change recognition processing can be performed by dynamic threshold comparison combined with time series curve analysis, for example, setting dynamic standards such as "voltage change rate exceeding 5% / minute" and "temperature rise rate exceeding 2℃ / minute", and extracting change information exceeding the threshold; the type matching processing can be realized by establishing an abnormal change classification database of power equipment, for example, matching "abnormal speed, excessive vibration amplitude, and high bearing temperature" to "mechanical state class", and matching "voltage fluctuation, current mutation, and frequency deviation" to "electrical parameter class"; the effective analysis processing can be performed by a feature verification system, for example, setting a rule that "the matching type needs to contain specific parameters + change characteristics (such as 'voltage drop' and 'temperature rise')", and screening out effective change types meeting the requirements; the power equipment real-time running abnormal change type analysis report can be generated by frequency statistics and proportion analysis of the effective change types, for example, the statistics show that "the proportion of electrical parameter class abnormality is 41%, and the proportion of mechanical state class abnormality is 33%", and the analysis of abnormal change types is completed.

[0029] Further, as an optional embodiment of the present application, the effective analysis processing on the matching change type to obtain an effective change type comprises: checking the running environment of the matching change type to obtain an environment-related type; analyzing an abnormal evolution trend corresponding to the environment-related type, and determining a sustained abnormal type in the environment-related type based on the abnormal evolution trend; analyzing an influence area corresponding to the sustained abnormal type, and identifying a key abnormal type in the sustained abnormal type based on the influence area; calculating a system correlation degree corresponding to the key abnormal type, and determining an effective change type in the key abnormal type based on the system correlation degree.

[0030] The environment-related type refers to a matching variation type associated with environmental factors after running environment inspection, such as “motor speed fluctuation class affected by high temperature environment”; the abnormal evolution trend refers to the development and change characteristics of the environment-related type over time, including the increase and decrease of abnormal amplitude, the high and low of frequency, etc., for example, “temperature over-temperature class” presents a continuous deterioration trend of rising 2℃ per hour; the sustained abnormal type refers to an environment-related type whose abnormal state lasts for a preset threshold (such as 15 minutes) based on the abnormal evolution trend, for example, “insulation resistance decrease class caused by excessive humidity” lasts for 20 minutes; the influence area refers to the influence range of the sustained abnormal type on the power system, including single equipment, local line, regional power grid, etc., for example, “circuit breaker opening abnormal class” affects the coverage area of 10kV distribution line; the key abnormal type refers to a sustained abnormal type whose influence area contains core power facilities (such as main transformer, central controller), for example, “oil temperature abnormal class affecting the operation of main transformer”; the system correlation degree refers to the correlation between the key abnormal type and the stable operation of the entire power system (such as power supply reliability, load balancing, voltage stability, etc.), the value range is 0-1, the higher the value, the closer the correlation, for example, the correlation degree of “generator excitation current abnormal class” and system voltage stability is 0.9; the effective variation type refers to a key abnormal type with a system correlation degree higher than a preset threshold (such as 0.7), for example, “generator excitation current abnormal class” with a correlation degree of 0.9.

[0031] Further, the running environment inspection process can be performed by constructing a power equipment environment parameter database, for example, the environmental tolerance threshold of the equipment, the environmental factors and the abnormal association rules are entered into the database, and it is judged whether the matching variation type is related to the environment by comparison; the abnormal evolution trend analysis can be performed by time series data trend fitting, for example, the sliding window algorithm is used to track the variation amplitude of “voltage fluctuation class” every 5 minutes, and the evolution curve is fitted; the influence area can be determined by analyzing the power system topology graph, for example, based on the device connection relationship graph, the downstream distribution area range affected by “capacitor group switching abnormal class” is located; the system correlation degree can be calculated by training a gradient boosting model, the model input is the influence range, the duration, the parameter deviation degree and other characteristics of the key abnormal type, and the output is the correlation degree value of 0-1; the effective variation type can be determined by setting a dynamic threshold adjustment mechanism, for example, the system correlation degree threshold is increased from 0.7 to 0.8 during the peak electricity consumption period, and the abnormal type with greater influence on power supply reliability is preferentially identified.

[0032] Further, as an optional embodiment of the present application, the calculation of the system correlation degree corresponding to the key abnormal type comprises: extracting a fault chain feature corresponding to the key abnormal type, determining a fault severity level corresponding to the key abnormal type based on the fault chain feature; querying an abnormal device of the key abnormal type, analyzing a functional attribute of the abnormal device in the virtual power plant, and calculating a current power shortage ratio corresponding to the abnormal device; allocating a device function weight corresponding to the key abnormal type based on the functional attribute; detecting an operation condition of a current power grid of the virtual power plant, calculating a condition adjustment margin and an allowed shortage limit value of the key abnormal type based on the operation condition; combining the fault severity level, the device function weight, the condition adjustment margin, the current power shortage ratio, and the allowed shortage limit value, and calculating a system correlation degree corresponding to the key abnormal type by using the following formula.

[0033] The fault chain feature refers to a cascading fault propagation path and an influence degree caused by the key abnormal type, such as a chain of cascading reactions of “transformer oil temperature abnormality → insulation breakdown → regional power grid power failure → energy storage system overload protection”. The fault severity level is an index for quantifying the damage degree of the chain feature, and takes a value of 0-10 points (the higher the points, the more serious the influence), for example, an abnormality level directly leading to a main grid power failure is 9 points. The functional attribute refers to the core function positioning of the abnormal device in the virtual power plant, such as “peak shaving main equipment”, “voltage support equipment”, “backup power supply equipment”, etc. The current power shortage ratio refers to the ratio of power loss caused by the abnormality to the rated total power of the system, for example, a 20 MW power loss caused by a fault of a certain fan, and the system rated 1000 MW, so the ratio is 2%. The device function weight is a weighted value (0-1) given according to the functional attribute (the higher the core equipment weight, the higher the weight, such as the weight of the peak shaving main equipment is 0.8). The operation condition refers to the load state of the current power grid (such as peak load, valley frequency modulation, fault recovery, etc.). The condition adjustment margin is the remaining adjustment capability of the system to the abnormality (0-1.5), and the lower the margin, the weaker the risk resistance capability, such as the margin may be as low as 0.3 in the peak load. The allowed shortage limit value is the maximum power shortage ratio that the system can tolerate (0-20%), for example, the limit value is 10% in the peak period. The system correlation degree is an index for comprehensively measuring the influence of the key abnormality on the overall system (0-2), and the higher the value, the closer the abnormality is associated with the stable operation of the system.

[0034] Further, the fault chain characteristics can be extracted by fault tree analysis (FTA) and causal mapping technology, for example, a three-layer association model of "abnormal type-secondary fault-impact range" is constructed to automatically identify the chain path; the fault severity level can be determined by a gradient boosting model trained by historical fault data, the model input is the chain path length, the number of affected devices and other characteristics, and the output is a level value of 0-10; the function attribute can be queried by a virtual power plant device digital twin account, which pre-stores "function type" and "control priority" labels; the current power shortage ratio can be calculated by real-time collection of abnormal device power data from the SCADA system combined with the system rated power account, for example, the power of a certain photovoltaic array decreases from 50 MW to 10 MW after a fault, and the system rated power is 500 MW, then the ratio is (50-10) / 500=8%; the device function weight can be dynamically allocated by an expert system and a dispatching strategy, for example, in the frequency modulation working condition, the weight of energy storage device is temporarily increased from 0.7 to 0.9; the operating condition can be identified by analyzing real-time load rate, frequency deviation and other data through K-means clustering algorithm, for example, when the load rate is greater than 85%, it is determined as a peak load working condition; the working condition adjustment margin can be calculated by the ratio of system backup capacity to current load, for example, when the backup capacity is 200 MW and the current load is 1000 MW, the margin is 0.2; the allowed shortage limit value can be set according to the grid safety regulations and the working condition type, for example, the limit value is tightened from 15% to 8% in the fault recovery working condition; the system correlation degree can be calculated by coupling the above parameters, which provides a quantitative basis for priority ranking of abnormal disposal.

[0035] Further, as another embodiment of the application, the system correlation degree corresponding to the key abnormal type is calculated by the following formula based on the fault severity level, the device function weight, the working condition adjustment margin, the current power shortage ratio and the allowed shortage limit value, including: ; Wherein A represents the system correlation degree corresponding to the key abnormal type, represents the fault severity level, represents the device function weight, represents the working condition adjustment margin, represents the current power shortage ratio, represents the allowed shortage threshold.

[0036] The principle of the formula is: buffer the extreme value impact of fault level, quantify the core degree of the device, avoid the denominator distortion of low working condition margin, describe the power shortage pressure, and the core assumption is that the fault chain propagates independently and the device weight is compatible with dynamic and static correction.

[0037] The formula effect: In the virtual power plant scene, the abnormal risk can be accurately graded (high correlation degree triggers preferential treatment), the power grid frequency response time is shortened (such as 15 seconds to 8 seconds), the device implicit fault is identified 40 minutes in advance (the decoupling accuracy is improved by 40%), and the system "active defense" is supported.

[0038] The application can capture the potential germination state of device fault by analyzing the abnormal change type in the real-time operation index to determine the fault start condition of the power equipment, and provide a core judgment basis for power system fault pre-control, wherein the fault start condition is a state description that the power equipment operation parameter breaks through the safety threshold and meets the fault trigger logic, such as a fan pitch angle deviation of more than 20° within 3 minutes, a storage battery cell voltage drop of 15%, etc.; further, based on the abnormal change type, the abnormal change mode is matched with the preset fault judgment criterion (such as "parameter fluctuation frequency> 5 times / minute" corresponding to "secondary fault warning"), and the fault start condition of the power equipment is determined.

[0039] The running smoothness calculation module 102 is used for calculating the running smoothness index of the power equipment based on the fault start condition.

[0040] The application can quantify the interference degree of the device fault germination stage on the running state by calculating the running smoothness index of the power equipment based on the fault start condition, and provide a core reference index for the state evaluation of the power system, wherein the running smoothness index is a quantitative value for measuring the consistency between the actual running state of the power equipment and the normal steady state, and the closer the numerical value is to 1, the more stable the running is.

[0041] As an embodiment of the application, the calculation of the running smoothness index of the power equipment based on the fault start condition comprises: Phase label identification is performed on the fault start condition to obtain a fault development phase label; The phase smoothness loss corresponding to the fault development phase label is calculated; The phase fluctuation duration corresponding to the fault development phase label is determined based on the phase smoothness loss; The running state deviation degree corresponding to the power equipment is calculated based on the phase fluctuation duration; The running smoothness index of the power equipment is calculated based on the running state deviation degree.

[0042] The fault development stage label is a development stage classification mark based on the evolution characteristics (such as parameter change rate, fluctuation intensity) of the fault starting condition; the stage stable loss refers to the parameter fluctuation amount generated in the fault stage in addition to the normal operation state of the equipment, for example, the motor vibration amplitude is ≤0.1 mm in the normal operation, and reaches 0.3 mm in the abnormal stage, and the stage stable loss is 0.2 mm; the stage fluctuation duration refers to the actual fluctuation duration calculated in combination with the stage stable loss and the historical fluctuation probability of the stage, for example, the stage stable loss is 0.2 mm, and the historical fluctuation probability is 60%, and the stage fluctuation duration is 0.12 hours; the operation state deviation degree refers to the deviation proportion of the actual operation parameter of the equipment and the normal steady-state parameter, for example, the output voltage of the transformer is 380V in the normal steady state, and is 410V in the abnormal state, and the operation state deviation degree is (410-380) / 380≈7.9%; the operation stable index is an index (the value is 0-1) for measuring the degree of agreement between the equipment operation state and the normal steady state, and the closer the value is to 1, the more stable the operation is, for example, when the operation state deviation degree is 7.9%, the operation stable index is 0.921.

[0043] Further, the stage label identification can be performed by matching the fault feature map, for example, the matching rules of "temperature change rate <5℃ / min and duration over threshold→ parameter slow change stage" and "vibration frequency sudden increase over 20Hz→ sudden oscillation stage" are set; the stage stable loss can be calculated by comparing the actual parameter fluctuation of the fault stage with the historical operation baseline of the same type equipment, for example, the average insulation resistance of the "critical early warning stage" is reduced by 10%, and the current reduction is 30%, and the stage stable loss is 20%; the stage fluctuation duration can be determined by multiplying the stage stable loss by the fluctuation influence weight (for example, the parameter slow change stage weight is 0.8, and the sudden oscillation stage weight is 1.5), for example, 20%*1.5=0.3 hours; the stable index can be calculated by the formula "operation stable index=1-operation state deviation degree / maximum allowed deviation degree" (the maximum allowed deviation degree is preset according to the type of the equipment, for example, the transformer is set to 20%), for example, when the operation state deviation degree is 7.9%, the operation stable index=1-7.9% / 20%≈0.605.

[0044] Further, as an optional embodiment of the present application, the operation state deviation degree corresponding to the power equipment is calculated based on the stage fluctuation duration, which comprises: The stage key unit is obtained by function unit decomposition of the stage fluctuation duration; The unit reference value and the unit real-time value corresponding to the stage key unit are extracted; The unit historical fault data corresponding to the stage key unit is dispatched; The maximum fluctuation duration corresponding to the stage key unit is determined based on the unit historical fault data; The running state deviation degree corresponding to the power equipment is calculated by using the following formula in combination with the unit reference value, the unit real-time value, the stage fluctuation duration and the maximum fluctuation duration.

[0045] The stage key unit is a segmented unit which is decomposed according to function modules in the whole running process of the power equipment (for example, "power generation unit→power transmission unit→power transformation unit→power distribution unit", and each segment can be subdivided into secondary units, for example, the "power transmission unit" includes "line transmission", "voltage monitoring" and "fault protection"); the unit reference value is a standard running parameter preset for each key unit (for example, the reference value of the "power generation unit" is 50 MW rated power); the unit real-time value is a parameter actually running in the unit (for example, the real-time power of the power generation unit is 42 MW); the stage fluctuation duration is the duration that the parameter of the key unit deviates from the reference value (for example, the voltage fluctuation duration of the power transmission unit is 15 minutes); and the maximum fluctuation duration is the longest parameter deviation time in the historical fault of the unit (for example, the maximum fluctuation duration of the power distribution unit in history is 40 minutes).

[0046] Further, the stage fluctuation duration can be functionally decomposed by the equipment running log, for example, the stage key units such as "power generation unit→power transmission unit" are automatically divided according to the power generation start time and the power transmission switching time recorded by the power monitoring system; the unit reference value and the unit real-time value of the stage key unit can be extracted from the power equipment management system, for example, the records of the reference voltage 10 kV and the real-time voltage 9.2 kV of the "power transformation unit" are called; the historical fault data of the unit is scheduled by the database query interface, for example, the fluctuation records of the power distribution unit in the past 3 years are accessed from the equipment fault archives; and the maximum fluctuation duration is determined by statistical analysis of the historical fault data of the unit, for example, the maximum value of the duration of 100 fluctuation events of the power transmission unit is taken.

[0047] Further, as another embodiment of the present application, the running state deviation degree corresponding to the power equipment is calculated by using the following formula in combination with the unit reference value, the unit real-time value, the stage fluctuation duration and the maximum fluctuation duration: ; Wherein G represents the running state deviation degree corresponding to the power equipment, represents the unit real-time value corresponding to the kth unit in the stage key unit, represents the unit reference value corresponding to the kth unit in the stage key unit, M represents the stage fluctuation duration, represents the maximum fluctuation duration, k represents the serial number of the stage key unit, and m represents the number of the stage key unit.

[0048] It should be noted that the operation state deviation calculation formula integrates and quantizes the operation deviation of each stage key unit of the power equipment, and the absolute deviation proportion of the real-time value and the reference value of each stage key unit is calculated , combined with the ratio of stage fluctuation time length and maximum fluctuation time length , and the calculation results of all units are averaged to realize mathematical modeling of the overall operation deviation state of the equipment, and the core is to assume that the operation deviation and fluctuation of each key unit have independent superposition, and the state deviation degree of the global power equipment is reflected by weighted aggregation.

[0049] In specific applications, for example, in the energy storage-photovoltaic collaborative unit monitoring scene of the virtual power plant, the formula can quantize the deviation contribution of the photovoltaic power generation unit, the energy storage converter unit and other stage key units: assuming that the photovoltaic unit reference power L1=500kW, the real-time power H1=450kW, and the stage fluctuation time length M1=10min (the historical maximum fluctuation time length Mmax1=60min; the energy storage unit reference voltage L2=380V, the real-time voltage H2=375V, and the stage fluctuation time length M2=8min (the historical maximum fluctuation time length M2=40min), the contribution of the two units to the overall deviation degree can be accurately split by formula calculation, in addition, by adjusting the unit weight to adapt to the high-frequency fluctuation characteristics of power electronic equipment (such as inverters), the calculation accuracy is provided, and the continuous small operation deviation is effectively identified, which provides more accurate state basis for real-time regulation of the virtual power plant.

[0050] The power distribution calculation module 103 is configured to analyze equipment switching characteristics and energy storage characteristics of the power equipment under different power grid hubs based on the past fault information, so as to calculate a power distribution index of the power equipment when a fault occurs.

[0051] The present application can mine the adaptation influence law of the power grid hub on the power distribution by analyzing the equipment switching characteristics and energy storage characteristics of the power equipment under different power grid hubs based on the past fault information, thereby providing data support for subsequent power distribution index calculation, wherein the equipment switching characteristics are the performance of the power equipment in switching the operating state between different power grid hubs, including switching type (such as converter switching, generator set start-stop), switching time, and connection stability; and the energy storage characteristics are the processing performance of the power equipment associated energy storage unit in the power grid hub, including charging and discharging response delay, capacity utilization rate, and energy storage deployment frequency.

[0052] As an embodiment of the present application, the analysis of the equipment switching characteristics and energy storage characteristics of the power equipment under different power grid hubs based on the past fault information comprises: clustering the past fault information according to hubs to obtain a clustered hub archive; State transition feature extraction is performed on the cluster hub archive to obtain device state transition features; Low-frequency filtering is performed on the device state transition features to obtain high-frequency state transition norms; Energy storage behavior analysis is performed on the cluster hub archive to obtain energy storage feature clusters; Typical mode analysis is performed on the energy storage feature clusters to obtain typical energy storage norms; The high-frequency state transition norms and the typical energy storage norms are combined to analyze the device switching features and energy storage features of the power equipment under different power grid hubs.

[0053] The hub clustering is the aggregation of past fault information according to the power dispatching range of the power grid hub (such as provincial power transmission hubs, municipal power distribution hubs, etc.), and the cluster hub archive contains information such as the occurrence date, device fault location, and fault impact range of all fault cases under this hub, for example, "provincial power transmission hub clustering" contains 85 fault records caused by device switching in this hub in 2022; the device state transition features are the details of the device operating state transition extracted from the cluster hub archive, including the original operating device (such as a high-voltage circuit breaker), the target switching device (such as a standby transformer), and the switching trigger factors (such as device overload and line short circuit), for example, "municipal power distribution hub → high-voltage circuit breaker to standby transformer, due to current overrun"; the high-frequency state transition norms are the state transition forms that account for more than 35% of the device state transition features after low-frequency filtering, for example, "provincial power transmission hub → electric reactor to capacitor bank" accounts for 45% of the fault cases in this hub, which is a high-frequency norm; the energy storage feature cluster is a set of features that reflect the operation process of energy storage devices in the power grid hub, including energy storage device charging and discharging power, energy storage duration, and device maintenance cycle; the typical energy storage norm is a regular performance summarized from the energy storage feature cluster, for example, "municipal power distribution hub → energy storage device charging and discharging power is stable at 60%-80% of the rated power, and the maintenance cycle can be extended to 3 months". Further, the past fault information can be hub clustered by grid hub dispatching code, for example, records marked with "dispatching code SD-05" (provincial power transmission hub) are aggregated into a category to form a clustered hub archive; the state transition feature can be extracted from the "operation state change record" of the power equipment, for example, the item "2022-07-10 municipal distribution hub: high-voltage circuit breaker → standby transformer, trigger factor: equipment overheating" is filtered from the record to obtain the equipment state transition feature; low-frequency state transitions can be filtered by setting a frequency ratio lower limit, for example, state transition modes with a ratio lower than 15% are removed, and high-frequency state transition modes are retained; the energy storage behavior can be analyzed by the operation log of the energy storage equipment, for example, records such as "energy storage equipment D charging and discharging power 50kW, energy storage time 4 hours, last maintenance time 2022-05-01" are retrieved to form an energy storage feature cluster; typical mode analysis can be performed by analyzing the operation data of similar energy storage equipment, for example, the relationship between the charging and discharging power and the maintenance period of 30 energy storage equipment in a hub is counted to determine the typical energy storage mode; the high-frequency state transition mode and the typical energy storage mode can be associated through a feature correlation diagram, for example, in the "provincial power transmission hub" cluster, the "reactor to capacitor bank" high-frequency mode is associated with the "energy storage equipment charging and discharging power 60%-70%" typical mode to determine the device conversion and energy storage linkage characteristics of this type of hub.

[0054] The application analyzes the device conversion characteristics and energy storage characteristics of the power equipment under different grid hubs to calculate the power distribution index of the power equipment when a fault occurs, which can determine the adaptation degree of different grid hubs to the power distribution path and provide a quantitative basis for subsequent determination of the adjustment mode corresponding to the power equipment, wherein the power distribution index represents the adaptation degree quantitative value of the current power transmission path of the power equipment when a fault occurs to the device conversion characteristics and energy storage characteristics of the corresponding grid hub.

[0055] As an embodiment of the application, the analysis of the device conversion characteristics and energy storage characteristics of the power equipment under different grid hubs to calculate the power distribution index of the power equipment when a fault occurs further comprises: performing mode encoding processing on the device conversion characteristics to obtain a conversion encoding set; performing behavior quantization processing on the energy storage characteristics to obtain a storage quantization set; extracting the actual conversion sequence and the actual energy storage operation sequence corresponding to the current fault event of the power equipment; calculating the sequence matching degree of the actual conversion sequence and the conversion encoding set; calculating the execution fit degree of the actual energy storage operation sequence and the storage quantization set; The power distribution index of the power equipment when the fault occurs is calculated in combination with the sequence matching degree and the execution fitting degree.

[0056] The conversion code set is a standardized code set of typical equipment conversion characteristics under different power grid hubs, for example, "BD-TQ" represents "substation→unit start-stop", "HL-BL" represents "converter station→converter switching", each code corresponds to the average conversion time, convergence stability and other characteristics of the corresponding mode; the storage quantization set is a numerical expression of energy storage characteristics, for example, "5-0.65" represents "charge-discharge response delay 5 milliseconds, capacity utilization rate 65%", and the closer the numerical value is to the historical optimal value, the more suitable the energy storage is; the actual conversion sequence is the actual sequence record of equipment conversion in the current fault event, such as the step chain of "converter station→converter switching→unit start-stop"; the actual energy storage operation sequence is the actual processing flow of the energy storage unit in the current fault event, such as the link chain of "charge trigger→response delay→discharge adjustment"; the sequence matching degree is the matching degree of the actual conversion sequence and the optimal mode in the conversion code set, represented by a numerical value between 0 and 1, and 1 represents complete consistency; the execution fitting degree is the fitting degree of the actual energy storage operation sequence and the standard flow in the storage quantization set, and the higher the numerical value, the more in line with the optimal specification.

[0057] Further, the equipment conversion characteristics can be processed by mode coding according to feature mapping rules, for example, "converter station F→converter switching, average time consumption 400 milliseconds" is coded as "HLF-BLTQ-400" to form the conversion code set; the energy storage characteristics can be quantitatively processed by grade assignment, for example, scoring according to response delay (≤5 milliseconds for 3 points, 5-10 milliseconds for 2 points, and >10 milliseconds for 1 point) and capacity utilization rate (≥70% for 3 points, 60-70% for 2 points, and <60% for 1 point) to form the storage quantization set; the actual conversion sequence and the actual energy storage operation sequence can be extracted by the power fault tracing system, for example, the record of "2024-03-05 converter station F: converter switching start" is filtered from the fault report; the sequence matching degree can be calculated by sequence alignment algorithm, for example, the actual conversion sequence is compared with the steps of "optimal conversion mode" in the code set one by one, and 0.25 points are added for each matched step, and the full score is 1; the execution fitting degree can be calculated by the coincidence proportion of operation links, for example, the actual energy storage operation coincides with the standard flow by 75%, and the fitting degree is 0.75; the sequence matching degree and the execution fitting degree can be combined by weighted average, for example, the matching degree is 0.8 and the fitting degree is 0.75, and the power distribution index is 0.8×0.6+0.75×0.4=0.78, which can be directly used to judge whether the current power distribution path needs to be adjusted (for example, the index <0.6 triggers the adjustment mode optimization).

[0058] The response fitting analysis module 104 is used to determine the adjustment mode corresponding to the power equipment in combination with the operation stability index and the power distribution index, analyze the load characteristics of the power equipment under the current power grid condition, and analyze the response fitting degree of the equipment and energy storage in the adjustment mode based on the load characteristics.

[0059] The application can screen the device operation mode with stability and adaptability by determining the adjustment mode corresponding to the power equipment in combination with the operation stability index and the power distribution index, and can master the change rule and core influencing factors of the power grid load by analyzing the load characteristics of the power equipment under the current power grid condition, wherein the adjustment mode is a device operation adjustment mode (including device start-stop combination, power adjustment amplitude, etc.) determined in combination with the operation stability index and the power distribution index, and the load characteristics are inherent load characteristics (including load peak period, fluctuation frequency, capacity upper limit, etc.) of the current power grid condition of the power equipment. Further, the operation stability index and the power distribution index are normalized and weighted summed, and the mode corresponding to the highest summation result is selected to determine the adjustment mode corresponding to the power equipment. The load monitoring data of the current power grid can be collected and the characteristics can be extracted to analyze the load characteristics of the power equipment under the current power grid condition.

[0060] The application can determine the coordination level of the equipment and energy storage resources by analyzing the response fitting degree of the equipment and energy storage in the adjustment mode based on the load characteristics, which provides a basis for subsequent optimization processing of the adjustment mode, wherein the response fitting degree represents the efficient coordination degree of the equipment and energy storage in the adjustment mode and the adaptation ability to the load characteristics.

[0061] As an embodiment of the application, the analysis of the response fitting degree of the equipment and energy storage in the adjustment mode based on the load characteristics comprises: Analyzing the power demand constraint element corresponding to the load characteristics; Analyzing the device adjustment attribute corresponding to the equipment in the adjustment mode; Analyzing the energy storage response attribute corresponding to the energy storage in the adjustment mode; Calculating the fitting degree between the device adjustment attribute and the power demand constraint element to obtain a first fitting degree; Calculating the fitting degree between the energy storage response attribute and the power demand constraint element to obtain a second fitting degree; Combining the first fitting degree and the second fitting degree to analyze the response fitting degree of the equipment and energy storage in the adjustment mode.

[0062] The electric energy demand constraint element is a set of electric energy demand limit conditions extracted from load characteristics, such as "time constraint (power consumption peak is 19:00-23:00 every day), fluctuation constraint (grid frequency fluctuation is less than or equal to ±0.2 Hz), capacity constraint (single power adjustment is less than or equal to 8 MW)", etc.; the equipment adjustment attribute is a specific performance of the electric power equipment adapting to the electric energy demand constraint, including "equipment power adjustment speed, matching ratio of maximum adjustment capacity and demand capacity, continuous operation stability during peak period", etc.; the energy storage response attribute is a specific performance of the energy storage adapting to the electric energy demand constraint, such as "energy storage charge and discharge response time, frequency fluctuation compensation accuracy, continuous power supply time length during peak period", etc.; the first fitting degree is a degree quantitative value of the equipment adjustment attribute meeting the electric energy demand constraint element, for example, when the equipment power adjustment speed reaches 92%, the fitting degree is 0.92; the second fitting degree is a degree quantitative value of the energy storage response attribute meeting the electric energy demand constraint element, for example, when the energy storage frequency fluctuation compensation accuracy is 90%, the fitting degree is 0.9; the response fitting degree is a comprehensive result of the first fitting degree and the second fitting degree, and the value is 0-1, and the higher the value, the better the cooperation of the equipment and the energy storage meets the current electric energy demand constraint. Further, the electric energy demand constraint element can be analyzed by demand dimension decomposition of the load characteristics, for example, the constraint types of time, fluctuation and capacity are decomposed from the "industrial park grid load characteristics" to form the electric energy demand constraint element; the equipment adjustment attribute can be analyzed by equipment operation log statistical analysis, for example, the power adjustment record of the gas turbine in the past one month is called to calculate the adjustment speed compliance rate; the energy storage response attribute can be analyzed by energy storage monitoring system data report, for example, the proportion of the compensation deviation of the energy storage within the allowed range during the frequency fluctuation is calculated; the first fitting degree can be calculated by the compliance rate, for example, when the maximum adjustment capacity of the equipment is 95% of the demand capacity, the fitting degree is 0.95; the second fitting degree can be calculated by the accuracy conversion, for example, when the energy storage charge and discharge response time compliance rate is 88%, the fitting degree is 0.88; the two fitting degrees can be combined by weighted summation, for example, the first fitting degree accounts for 60%, and the second fitting degree accounts for 40%, and when the two are 0.9 and 0.85 respectively, the response fitting degree = 0.9*0.6+0.85*0.4 = 0.88, which can be used to judge whether the cooperation of the equipment and the energy storage meets the current electric energy demand constraint requirement.

[0063] The adjustment control module 105 is configured to perform adjustment and control processing on the equipment and the energy storage in the adjustment mode based on the response fitting degree, and obtain a control result.

[0064] The adjustment control module 105 is configured to perform adjustment and control processing on the equipment and the energy storage in the adjustment mode based on the response fitting degree, and obtain a control result.

[0065] Further, based on the response fit degree, the equipment and energy storage in the adjustment mode are adapted and controlled to obtain a control result, for example, replacing an originally running ordinary generator set with a gas generator set with stronger peak shaving capacity, and adjusting the charging and discharging strategy of the energy storage to real-time adjustment according to load fluctuation, so as to improve the adaptability to the load fluctuation and capacity requirement of the power grid; or reducing the power output of the equipment to 80% of the load peak value, and optimizing the power supply sequence of the energy storage to preferentially guarantee critical loads, thereby reducing the fluctuation risk of the power grid operation. Specifically, for further intuitive understanding of the adaptation control process of the virtual power plant power equipment control system in the present application, reference can be made to Figure 3 The figure shows the adaptation control process of the virtual power plant power equipment control system provided by the present application. It should be noted that in the present application, Figure 3 The process diagram presented is only for the adaptation control of the virtual power plant power equipment control system, and is not limited to the adaptation control of the virtual power plant power equipment control system in actual different application scenarios.

[0066] As Figure 3 The figure shows the process diagram of the virtual power plant power equipment control method provided by an embodiment of the present application. In this embodiment, the method comprises: Collecting state monitoring information of the running path of the power equipment in the virtual power plant, the state monitoring information including instant running indicators and past fault information, analyzing the types of abnormal changes in the instant running indicators to determine the fault start condition of the power equipment; Based on the fault start condition, calculating the running stability index of the power equipment; Based on the past fault information, analyzing the equipment conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs to calculate the power distribution index of the power equipment when a fault occurs; Combining the running stability index and the power distribution index, determining the corresponding adjustment mode of the power equipment, analyzing the load characteristics of the power equipment under the current power grid condition, based on the load characteristics, analyzing the response fit degree of the equipment and energy storage in the adjustment mode; Based on the response fit degree, the equipment and energy storage in the adjustment mode are adapted and controlled to obtain a control result.

[0067] In several embodiments provided by the present application, it should be understood that the provided system and method can be implemented by other manners. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and another division manner can be used in actual implementation.

[0068] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0069] Finally, it should be noted that in the above multiple embodiments, each embodiment can be combined with or independent of each other, and the deletion of any one embodiment does not affect the technical implementation of other embodiments. The above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application.

Claims

1. A virtual power plant power equipment control system, characterized in that, The system includes: a fault start determination module, a stable operation calculation module, a power distribution calculation module, a response matching analysis module, and an adjustment and control module; The fault initiation determination module is used to collect status monitoring information of the operating path of power equipment in the virtual power plant. The status monitoring information includes real-time operating indicators and past fault information. The module analyzes the types of abnormal changes in the real-time operating indicators to determine the fault initiation conditions of the power equipment. The stable operation calculation module is used to calculate the stable operation index of the power equipment based on the fault initiation conditions. The power distribution calculation module is used to analyze the equipment conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs based on the past fault information, so as to calculate the power distribution index of the power equipment when a fault occurs. The response matching analysis module is used to combine the operation stability index and the power distribution index to determine the corresponding adjustment mode of the power equipment, analyze the load characteristics of the power equipment under the current power grid conditions, and analyze the response matching degree of the equipment and energy storage in the adjustment mode based on the load characteristics. The adjustment and control module is used to perform adjustment and control processing on the equipment and energy storage in the adjustment mode based on the response fit, and obtain the control result.

2. The virtual power plant power equipment control system as described in claim 1, characterized in that, The analysis of abnormal changes in the real-time operational indicators includes: The real-time operational metrics are processed to extract a summary of the operational metrics. The operational indicator summary is subjected to change identification processing to obtain an abnormal indicator summary; The anomaly index summary is subjected to type matching processing to obtain the matching anomaly type; Effective analysis and processing of the matching anomaly types yield valid variation types; Based on the valid change types, analyze the types of abnormal changes in the real-time operating indicators.

3. The virtual power plant power equipment control system as described in claim 2, characterized in that, The effective analysis and processing of the matched variation types to obtain effective variation types includes: The matching variation type is then checked and processed for the operating environment to obtain the environment-related type; Analyze the abnormal evolution trends corresponding to the aforementioned environmental types, and based on these abnormal evolution trends, determine the persistent abnormal types among the aforementioned environmental types; Analyze the affected area corresponding to the persistent anomaly type, and based on the affected area, identify the key anomaly type in the persistent anomaly type; Calculate the system correlation degree corresponding to the key anomaly type, and based on the system correlation degree, determine the effective variation type among the key anomaly types.

4. The virtual power plant power equipment control system as described in claim 3, characterized in that, The calculation of the system correlation degree corresponding to the key anomaly type includes: Extract the fault chain features corresponding to the key anomaly types, and determine the fault severity level corresponding to the key anomaly types based on the fault chain features. Query the abnormal devices of the key anomaly types, analyze the functional attributes of the abnormal devices in the virtual power plant, and calculate the current power deficit ratio corresponding to the abnormal devices; Based on the aforementioned functional attributes, assign device functional weights corresponding to the key anomaly types; The operating conditions of the current power grid for the virtual power plant are detected, and based on the operating conditions, the operating condition adjustment margin and allowable deficit limit for the key anomaly type are calculated. Combining the fault severity level, the equipment functional weight, the operating condition adjustment margin, the current power deficit ratio, and the allowable deficit limit, the system correlation degree corresponding to the key anomaly type is calculated using the following formula: ； Where A represents the system correlation degree corresponding to the key anomaly type, Indicates the severity level of the fault. Indicates the weight of device functions. Indicates the operating condition adjustment margin. Indicates the current power deficit ratio. This indicates the allowable shortfall threshold.

5. A virtual power plant power equipment control system as described in claim 1, characterized in that, The calculation of the operational stability index of the power equipment based on the fault initiation conditions includes: The fault initiation conditions are identified by stage marking to obtain fault development stage labels; Calculate the stage steady loss corresponding to the fault development stage label; Based on the stage steady loss, determine the stage fluctuation duration corresponding to the fault development stage label; Based on the duration of the aforementioned stage fluctuations, the deviation of the operating state corresponding to the power equipment is calculated. Based on the deviation of the operating state, the operating stability index of the power equipment is calculated.

6. A virtual power plant power equipment control system as described in claim 5, characterized in that, The calculation of the operating state deviation of the power equipment based on the duration of the stage fluctuation includes: The duration of the stage fluctuations is decomposed into functional units to obtain the key units of the stage; Extract the unit baseline value and unit real-time value corresponding to the key unit of the stage; Schedule the historical fault data of the units corresponding to the key units in the aforementioned stage; Based on the historical fault data of the unit, the maximum fluctuation duration corresponding to the key unit of the stage is determined; Combining the unit baseline value, the unit real-time value, the stage fluctuation duration, and the maximum fluctuation duration, the operating state deviation of the power equipment is calculated using the following formula: ； Wherein, G represents the deviation of the operating state of the power equipment. This represents the real-time value of the k-th unit in the key unit of the stage. This represents the base value of the k-th unit in the key unit of the stage, and M represents the stage fluctuation duration. This represents the maximum fluctuation duration, k represents the sequence number corresponding to the key unit of the stage, and m represents the quantity corresponding to the key unit of the stage.

7. A virtual power plant power equipment control system as described in claim 1, characterized in that, The analysis of the equipment switching characteristics and energy storage characteristics of the power equipment under different power grid hubs based on the past fault information includes: The past fault information is clustered into hubs to obtain clustered hub files; Transition features are extracted from the clustered hub files to obtain equipment transition features; Low-frequency filtering of the device transition characteristics yields a high-frequency transition paradigm; The energy storage behavior of the clustered hub files is analyzed to obtain energy storage feature clusters; Typical pattern analysis was performed on the energy storage feature cluster to obtain typical energy storage paradigms; Combining the high-frequency transition paradigm and the typical energy storage paradigm, the equipment conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs are analyzed.

8. A virtual power plant power equipment control system as described in claim 1, characterized in that, The analysis of the equipment conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs, in order to calculate the power distribution index of the power equipment during a fault, further includes: The device conversion features are subjected to pattern encoding processing to obtain a conversion encoding set; The energy storage characteristics are subjected to behavioral quantization processing to obtain a storage quantization set; Extract the actual conversion sequence and actual energy storage operation sequence corresponding to the current fault event of the power equipment; Calculate the sequence matching degree between the actual transformed sequence and the transformed encoding set; Calculate the execution fit between the actual energy storage operation sequence and the storage quantization set; By combining the sequence matching degree and the execution fit degree, the power distribution index of the power equipment when a fault occurs is calculated.

9. A virtual power plant power equipment control system as described in claim 1, characterized in that, The analysis of the response compatibility between the equipment and energy storage in the regulation mode based on the load characteristics includes: Analyze the power demand constraints corresponding to the load characteristics; Analyze the device adjustment attributes corresponding to the devices in the aforementioned adjustment mode; Analyze the energy storage response attributes corresponding to the energy storage in the aforementioned regulation mode; Calculate the degree of fit between the equipment regulation attributes and the power demand constraints to obtain a first degree of fit; Calculate the degree of fit between the energy storage response attribute and the power demand constraint element to obtain the second degree of fit; By combining the first degree of fit and the second degree of fit, the response fit of the device and energy storage in the regulation mode is analyzed.

10. A method for controlling power equipment in a virtual power plant, characterized in that, The method includes: Collect status monitoring information of the operation path of power equipment in the virtual power plant. The status monitoring information includes real-time operation indicators and past fault information. Analyze the types of abnormal changes in the real-time operation indicators to determine the fault initiation conditions of the power equipment. Based on the aforementioned fault initiation conditions, calculate the operational stability index of the power equipment; Based on the past fault information, the equipment conversion characteristics and energy storage characteristics of the power equipment under different power grid hubs are analyzed to calculate the power distribution index of the power equipment when a fault occurs. By combining the operational stability index and the power distribution index, the regulation mode corresponding to the power equipment is determined, the load characteristics of the power equipment under the current power grid conditions are analyzed, and based on the load characteristics, the response fit between the equipment and energy storage in the regulation mode is analyzed. Based on the response fit, the equipment and energy storage in the regulation mode are adjusted and controlled to obtain the control results.

Images