Wind power plant power optimization control system and method
Through the wind farm power optimization control system, combined with data collection, analysis and meteorological forecasting, wind power plants can achieve the improvement of power generation efficiency and operational stability while meeting the assessment standards, and solve the problem of maximizing the benefits of wind power plants under the restrictions of wind speed fluctuations and assessment policies.
Patent Information
- Application Number
- CN202411893192.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-20
- Publication Date
- 2025-03-28
AI Technical Summary
It is difficult for wind power plants to maximize their power generation benefits while meeting assessment standards, especially in the face of wind speed fluctuations and assessment policies.
A wind farm power optimization control system is designed, including a power control unit, a power prediction unit, a control switching unit and an AGC instruction processing unit. Through data acquisition, data analysis and model construction, meteorological data fusion processing and control mode optimization, accurate power control and optimized power generation strategies are achieved.
Under the same meteorological conditions and assessment policies, the power change assessment fee will be reduced by 35%-45%, the annual power generation will be increased by 12%-18%, economic benefits, and the operational stability and reliability of wind farms in complex environments.
Smart Images
Figure CN119726915A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of wind power generation, and in particular relates to a wind farm power optimization control system and method. Background Art
[0002] In the operation of wind power plants, there are strict "two detailed rules" assessments, among which the assessment of active power change value is the most critical part. For example, when the installed capacity exceeds 1 million kW, the active power change value accounts for 50%-60% of the total assessment cost. This is mainly due to two aspects: First, the assessment policy sets clear active power change limits for wind power plants with installed capacity greater than 150 megawatts, that is, the maximum limit of active power change in 10 minutes is 50 megawatts, and the maximum limit of active power change in 1 minute is 15 megawatts; second, the special geographical location of some sea areas leads to frequent convective weather, and the wind speed is prone to sudden rise and fall, which in turn leads to large fluctuations in the output power of wind power plants, causing more assessment events. If power restriction measures are taken for a long time, the occurrence of assessment events can be reduced, but if power restriction measures are taken for a long time, the power transmission of power plants will be low and the income of power plants will decrease.
[0003] The current traditional active power control methods of wind power plants are difficult to maximize power generation benefits while meeting assessment standards. Summary of the invention
[0004] The present invention provides a wind farm power optimization control system and method to solve the problem that active power control means of a wind power plant is difficult to achieve maximum power generation benefits while meeting assessment standards.
[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: On the one hand, the present application provides a wind farm power optimization control system and method, including: The power control unit includes a data acquisition subunit, a data analysis and model building subunit, and a control mode setting subunit. The data acquisition subunit is used to obtain historical operation data and real-time monitoring data from the wind farm's wind turbine power output sensors, meteorological monitoring equipment, and grid access point monitoring devices. The data analysis and model building subunit uses data mining algorithms and machine learning algorithms to process data to build a power control model. The control mode setting subunit sets the optimal control limit mode based on the "two rules" and data analysis results, and adjusts the control parameters by calculating the difference between the power change assessment power and the lower limit power of the control mode to balance the relationship between the two; The power prediction unit includes a meteorological data acquisition module, a fan operation parameter acquisition module and a fusion processing module. The meteorological data acquisition module acquires meteorological forecast data from a professional meteorological forecasting agency. The fan operation parameter acquisition module acquires key fan operation parameters. The fusion processing module uses a deep learning algorithm to fuse meteorological data and fan operation parameters for power prediction. A control switching unit is connected in communication with the power prediction unit and the power control unit, selects a power control or free power generation state according to the power prediction result and transmits instructions; The AGC instruction processing unit is connected to the power control unit for communication. After receiving the AGC instruction, the power control model is suspended, the instruction is parsed and a power re-planning strategy is formulated. After the execution is completed, the power control model is resumed.
[0006] Furthermore, the data acquisition subunit adopts wireless communication technology to connect with the data source, and the communication frequency is not less than once per second.
[0007] Furthermore, the data analysis and model building subunit uses a cluster analysis algorithm to classify the power change data in different wind speed intervals and establish sub-models when building the model, and the weights of the sub-models are dynamically adjusted.
[0008] Furthermore, the meteorological forecast data acquired by the meteorological data acquisition module has high timeliness and high resolution, and is transmitted through a dedicated data link, which has encryption and verification functions.
[0009] Furthermore, the parameters collected by the fan operation parameter collection module include blade angle, rotation speed, torque, cabin temperature, and vibration amplitude. The data is transmitted at high speed through the optical fiber communication network, and the transmission rate is not less than 100Mbps.
[0010] Furthermore, the power prediction unit pre-processes the data before power prediction, including data cleaning, outlier processing and data normalization operations.
[0011] Furthermore, when the control switching unit selects the power control state, the fan parameters are adjusted through the PID controller, and the PID controller parameters are adaptively adjusted, and the cycle does not exceed 1 minute.
[0012] Furthermore, the AGC instruction processing unit considers the wind turbine climbing rate, power upper limit, operating status and power prediction results when formulating the power adjustment strategy, and uses piecewise linear interpolation to smooth the power output.
[0013] Furthermore, the control mode lower limit power determined by the control mode setting subunit comprehensively considers the wind turbine equipment characteristics and grid compatibility requirements.
[0014] On the other hand, the present application provides a wind farm power optimization control method, comprising the following steps: Data collection and initialization: The data collection subunit of the power control unit collects and transmits data from various data sources at a frequency of not less than once per second through wireless communication. The meteorological data acquisition module of the power prediction unit obtains meteorological forecast data. The fan operation parameter acquisition module collects and transmits fan operation parameters. The fusion processing module predicts power after preprocessing and fusion data. Power prediction: The fusion processing module of the power prediction unit uses deep learning algorithms to fuse meteorological data and wind turbine operating parameters, predict power change trends and transmit the results; Power control model construction and optimization: The data analysis and model construction subunit processes the collected data to build the model and transmit it, and the control mode setting subunit sets the control limit optimal mode to balance the power relationship; Control state switching and execution: The control switching unit selects the state according to the prediction results. If it is the power control state, it instructs to adjust the fan parameters; AGC instruction processing: The AGC instruction processing unit monitors received instructions, parses and obtains information to formulate strategies, and resumes model operation after execution.
[0015] The present invention can achieve the following beneficial effects: By utilizing the wind farm power optimization control system and method of the present application, on the one hand, under the same meteorological conditions and assessment policies, the power change assessment fee can be reduced by 35%-45%, effectively reducing the assessment burden of the wind farm; on the other hand, through precise power control and optimized power generation strategy, the annual power generation of the wind farm can be increased by 12%-18% on the basis of meeting the assessment requirements, significantly improving the economic benefits of the wind farm; on the third hand, the system of the present application can adjust the active power output in real time according to different working conditions, effectively reducing the impact on the power grid caused by large fluctuations in active power, improving the operating stability and reliability of the wind farm in complex environments, and reducing the losses of equipment such as wind turbines due to frequent active power fluctuations, thereby extending the service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 A schematic diagram of a wind farm power optimization control system according to the present invention; Figure 2 The figure is a flow chart of a wind farm power optimization control method according to the present invention. DETAILED DESCRIPTION
[0017] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.
[0018] like Figure 1 As shown, a wind farm power optimization control system includes a power control unit, a power prediction unit, a control switching unit and an AGC instruction processing unit.
[0019] Among them, the power control unit includes a data acquisition subunit, a data analysis and model building subunit and a control mode setting subunit.
[0020] The data acquisition subunit, as the front end of the system to obtain data, establishes connections with various data sources such as wind turbine power output sensors, meteorological monitoring equipment, and monitoring devices at grid access points in the wind farm through wireless communication technology. This wireless communication technology ensures the flexibility and efficiency of data transmission, with a communication frequency of no less than once per second, and can timely capture information such as the operating status of wind turbines, changes in meteorological conditions, and grid access conditions, providing comprehensive and real-time data support for subsequent power control. For example, in a wind farm, the power output sensors distributed on each wind turbine can monitor the power generation of the wind turbine in real time, and the meteorological monitoring equipment can accurately measure meteorological parameters such as wind speed, wind direction, air pressure, and temperature. The monitoring device at the grid access point is used to obtain information such as voltage, current, and frequency on the grid side. These data together constitute the input source of the data acquisition subunit.
[0021] The data analysis and model building subunit is used to receive massive data from the data acquisition subunit and then use advanced data mining algorithms and machine learning algorithms for in-depth processing. Among them, the data mining algorithm can be used to discover potential power change patterns and laws from a large amount of historical data. For example, the association rule mining algorithm can find the correlation between different meteorological conditions and wind turbine power output; the machine learning algorithm builds a model that can accurately predict the power change trend by learning historical operation data. In the model building process, the cluster analysis algorithm is used to classify the power change data in different wind speed ranges. For example, the wind speed is divided into low wind speed, i.e. 0-5m / s, medium wind speed, i.e. 5-15m / s and high wind speed, i.e. 15m / s and above, and a sub-model is established for each range. The weight of each sub-model is dynamically adjusted according to the actual operation data and simulation analysis results. In this way, in actual power control, the appropriate sub-model can be selected for prediction and control decision-making according to the range to which the current wind speed belongs, thereby improving the accuracy of control. For example, in the low wind speed range, the power output characteristics of the wind turbine are significantly different from those in the high wind speed range. By dynamically adjusting the sub-model weights, it can better adapt to the power control requirements under different working conditions.
[0022] The control mode setting subunit sets the optimal control limit mode according to the control requirements for active power rate in the "two detailed rules" and the power change law analysis results provided by the data analysis and model building subunit. The core of this mode is to calculate the difference between the power change assessment power and the lower limit power of the control mode in real time, and dynamically adjust the control parameters based on this. The lower limit power of the control mode here is determined by comprehensively considering multiple factors such as wind turbine equipment characteristics and grid compatibility requirements. The wind turbine equipment characteristics specifically include the starting wind speed, rated power, and minimum stable operating power of the wind turbine. The grid compatibility requirements specifically include the grid's requirements for reactive power compensation and harmonic control, as well as the power fluctuation range that the grid can withstand. For example, when the wind turbine is running at a low wind speed and the grid load is low, the power control limit is appropriately relaxed to allow the wind turbine to increase the power generation within a certain range to improve the power generation efficiency; when the wind speed changes drastically or the grid load is close to the upper limit, the power change is strictly controlled to ensure that it does not exceed the assessment limit and avoid the loss of assessment power. Through this dynamic adjustment mechanism, a fine balance is achieved between the power change assessment power and the lower limit power of the control mode, so that the wind farm can generate as much power as possible while meeting the assessment standards.
[0023] The power prediction unit includes a meteorological data acquisition module, a wind turbine operation parameter acquisition module and a fusion processing module.
[0024] The meteorological data acquisition module establishes a close data cooperation relationship with professional meteorological forecasting agencies and obtains meteorological forecast data through a dedicated data link. The data link has data encryption and verification functions to ensure the security and integrity of meteorological data during transmission and prevent data from being stolen or tampered with. The acquired meteorological forecast data has high timeliness, that is, it is updated once an hour and high resolution, that is, the spatial resolution reaches the level of several kilometers, which can provide timely and accurate meteorological information support for wind farm power forecasting. For example, the meteorological forecasting agency predicts the changing trends of meteorological parameters such as wind speed, wind direction, air pressure, and temperature in the area where the wind farm is located in the future. These data are transmitted to the power forecast unit of the wind farm through a dedicated data link.
[0025] The wind turbine operation parameter acquisition module includes a high-precision sensor system installed on each wind turbine. The sensor system is used to collect key parameters during the operation of the wind turbine, such as blade angle, speed, torque, cabin temperature, vibration amplitude and other parameters. The data collected by the sensor system is transmitted to the central control system at high speed through the optical fiber communication network, and the data transmission rate is not less than 100Mbps to ensure the timeliness and accuracy of data transmission. For example, the blade angle sensor monitors the pitch angle changes of the wind turbine blades in real time, the speed sensor accurately measures the rotation speed of the wind turbine main shaft, the torque sensor reflects the power output of the wind turbine, the cabin temperature sensor is used to monitor the temperature changes inside the wind turbine, and the vibration amplitude sensor can detect the vibration state during the operation of the wind turbine. These parameters together reflect the real-time operation status of the wind turbine and provide an important basis for power prediction.
[0026] The fusion processing module uses a model that combines the convolutional neural network and the long short-term memory network in the deep learning algorithm to fuse the meteorological forecast data and the wind turbine operating parameters to achieve power prediction. The convolutional neural network is mainly used to extract spatial features from meteorological data, such as mining the spatial distribution and correlation of meteorological factors such as wind speed and wind direction through the convolution layer and the pooling layer; the long short-term memory network is good at processing time series data, and can learn the historical power output data, the trend of wind turbine operating parameters, and the time change law of meteorological data, so as to accurately predict the future power change trend. Before power prediction, the meteorological forecast data and wind turbine operating parameters are preprocessed, including data cleaning, outlier processing and data normalization operations to improve the accuracy of power prediction. Among them, data cleaning is to remove obviously wrong or abnormal data points, such as outliers caused by sensor failure; outlier processing is to use a reasonable algorithm to correct or replace outliers, such as the mean replacement method or interpolation method based on statistical principles; data normalization operation is to map data of different magnitudes to a specific interval, such as [0,1] or [-1,1], to facilitate model processing.
[0027] The control switching unit is used to realize communication connection and data reception, state switching decision and control instruction transmission and execution.
[0028] Specifically, the control switching unit maintains real-time communication connection with the power prediction unit and the power control unit, and receives the power change trend data predicted by the power prediction unit. The data contains the expected change of wind farm power in the future period, such as 10 minutes, 30 minutes or 1 hour, including information such as the rate and amplitude of power increase or decrease.
[0029] The control switching unit then automatically determines and selects the power control or free power generation state in real time based on the received power forecast trend data. When it is predicted that the power change will exceed the assessment limit range, in one embodiment, when the active power change may exceed 50 MW within 10 minutes or exceed 15 MW within 1 minute, it switches to the power control state; if it is predicted that the power change is relatively stable and in a safe range, the free power generation state is selected. In the switching process, the balance between assessment requirements and power generation benefits is fully considered to ensure the optimization of wind farm operation.
[0030] If the power control state is selected, the control instruction is transmitted to the control mode setting subunit. The control mode setting subunit adjusts the pitch angle, speed and other parameters of the wind turbine through the PID controller according to the control instruction, so that the power output is stable within the assessment range. The parameters of the PID controller are adaptively adjusted according to the characteristics of the wind turbine, such as the inertia and damping coefficient of the wind turbine and the actual operating conditions, such as the current wind speed, the deviation of the power output from the assessment requirements, etc., and the adjustment cycle does not exceed 1 minute. In one specific embodiment, when the power output is higher than the assessment upper limit, the PID controller reduces the power output by reducing the pitch angle or reducing the speed; when the power output is lower than the assessment lower limit, the pitch angle is increased or the speed is increased to ensure that the power is stable within a reasonable range and meets the assessment requirements.
[0031] The AGC instruction processing unit is used to realize instruction monitoring and reception, instruction parsing and information acquisition, as well as power re-planning and execution.
[0032] The AGC instruction processing unit monitors in real time whether an AGC instruction is received. The AGC instruction is usually issued by the power grid dispatching center according to the requirements of power grid load balance, frequency stability, etc. Once the AGC instruction is received, the corresponding processing flow is immediately started.
[0033] When receiving the AGC command, the power control model in the power control unit is suspended, and the AGC command content is parsed, including the power adjustment range required by the command, such as how many megawatts of power to increase or decrease, the adjustment time node, such as how long it will take to complete the power adjustment, and other key information. At the same time, the current wind turbine operating status information is obtained from the power control unit, and the power forecast trend information is obtained from the power forecast unit, providing comprehensive data support for formulating power re-planning strategies.
[0034] Formulate a power re-planning strategy based on the AGC instructions and the current wind farm operation status. When formulating the strategy, fully consider the wind turbine's ramp rate, power upper limit, operating status, and power prediction results of the power prediction unit. Calculate the power adjustment amount and adjustment time node for each wind turbine to ensure that while meeting the AGC instruction requirements, the impact on the wind turbine equipment and the impact on power generation efficiency are minimized.
[0035] During the power adjustment process, the piecewise linear interpolation method is used to smoothly transition the power output of the wind turbine to avoid sudden power changes. For example, when the power output needs to be increased, the power output of each wind turbine is gradually increased according to the climbing rate and current operating status of the wind turbine, so that the power change shows a linear growth trend instead of a sudden jump increase, thereby ensuring the stability of the wind farm power output and meeting the power grid's requirements for power regulation. After the AGC instruction is executed, according to the power prediction trend and assessment requirements of the power prediction unit, the normal power control model in the power control unit is restored to ensure that the wind farm continues to operate stably.
[0036] like Figure 2 As shown, the present application also provides a wind farm power optimization control method based on the above wind farm power optimization control system, comprising the following steps: Data collection and initialization: The data collection subunit of the power control unit starts the wireless communication module and establishes connections with wind turbine power output sensors, meteorological monitoring equipment, and monitoring devices at grid access points distributed throughout the wind farm at a communication frequency of no less than once per second to collect historical operation data and real-time monitoring data. After preliminary processing, the collected data is transmitted to the data analysis and model building subunit through the internal communication bus.
[0037] At the same time, the meteorological data acquisition module of the power prediction unit sends data requests to professional meteorological forecasting agencies through a dedicated data link to receive meteorological forecast data. The fan operation parameter acquisition module obtains real-time operation parameters from the high-precision sensor system installed on the fan. The collected fan operation parameters are transmitted to the fusion processing module of the power prediction unit through the optical fiber communication network at a data transmission rate of not less than 100Mbps. After receiving the meteorological data and fan operation parameters, the fusion processing module pre-processes the data to prepare for subsequent power prediction.
[0038] Power prediction: The fusion processing module of the power prediction unit fuses the pre-processed meteorological prediction data and wind turbine operating parameters. After further processing, the prediction results are transmitted to the control switching unit through the communication interface in a specific data format.
[0039] Power control model construction and optimization: After receiving the historical operation data and real-time monitoring data from the data acquisition subunit, the data analysis and model construction subunit uses data mining algorithms and machine learning algorithms to deeply process the data. By analyzing a large amount of historical data, the inherent laws between power changes and wind turbine operating parameters, meteorological conditions, and power grid status are explored.
[0040] When constructing the power control model, the appropriate model structure and algorithm parameters are selected according to the rules and patterns discovered. At the same time, the cluster analysis algorithm is used to classify the power change data in different wind speed ranges, and a sub-model is established for each type of data. The weight of each sub-model is dynamically adjusted according to the actual operation data and simulation analysis results. The constructed power control model is transmitted to the control mode setting sub-unit. The control mode setting sub-unit sets the optimal control limit mode based on the control requirements for active power rate in the "two detailed rules" and combined with the data analysis results.
[0041] Control state switching and execution: After receiving the power prediction results from the power prediction unit, the control switching unit automatically selects the power control or free power generation state in real time according to the preset decision rules. The decision rules are formulated based on the power prediction trend, assessment requirements and the operation objectives of the wind farm. For example, when the predicted power change rate exceeds 15 MW in the next minute, or exceeds 50 MW in the next 10 minutes, switch to the power control state; otherwise, select the free power generation state.
[0042] If the power control state is selected, the control switching unit sends the control command to the control mode setting subunit of the power control unit. The control mode setting subunit adjusts the pitch angle, speed and other parameters of the wind turbine through the PID controller according to the control command. If the free power generation state is selected, the wind turbine is allowed to operate in the maximum power tracking mode to make full use of wind energy resources and improve power generation efficiency.
[0043] AGC instruction processing: The AGC instruction processing unit monitors in real time whether the AGC instruction is received. Once the AGC instruction is received, the power control model in the power control unit is immediately suspended to avoid conflicts between the current power control strategy and the AGC instruction. At the same time, the AGC instruction content is parsed to obtain key information such as the power adjustment range and adjustment time node required by the instruction. Then, the current wind turbine operating status information is obtained from the power control unit, and the power forecast trend information is obtained from the power forecast unit. Based on this information, a power re-planning strategy is formulated.
[0044] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A wind farm power optimization control system, characterized in that: include: The power control unit includes a data acquisition subunit, a data analysis and model building subunit, and a control mode setting subunit. The data acquisition subunit is used to obtain historical operation data and real-time monitoring data from the wind farm's wind turbine power output sensors, meteorological monitoring equipment, and grid access point monitoring devices. The data analysis and model building subunit uses data mining algorithms and machine learning algorithms to process data to build a power control model. The control mode setting subunit sets the optimal control limit mode based on the "two rules" and data analysis results, and adjusts the control parameters by calculating the difference between the power change assessment power and the lower limit power of the control mode to balance the relationship between the two; The power prediction unit includes a meteorological data acquisition module, a fan operation parameter acquisition module and a fusion processing module. The meteorological data acquisition module acquires meteorological forecast data from a professional meteorological forecasting agency. The fan operation parameter acquisition module acquires key fan operation parameters. The fusion processing module uses a deep learning algorithm to fuse meteorological data and fan operation parameters for power prediction. A control switching unit is connected in communication with the power prediction unit and the power control unit, and selects a power control or free power generation state according to a power prediction result and transmits instructions; The AGC instruction processing unit is connected to the power control unit for communication. After receiving the AGC instruction, the power control model is suspended, the instruction is parsed and a power re-planning strategy is formulated. After the execution is completed, the power control model is resumed.
2. The wind farm power optimization control system according to claim 1, characterized in that: The data acquisition subunit adopts wireless communication technology to connect with the data source, and the communication frequency is not less than once per second.
3. The wind farm power optimization control system according to claim 2, characterized in that: The data analysis and model building subunit uses a cluster analysis algorithm to classify the power change data in different wind speed ranges and establish sub-models when building the model, and the sub-model weights are dynamically adjusted.
4. The wind farm power optimization control system according to claim 1, characterized in that: The meteorological forecast data acquired by the meteorological data acquisition module has high timeliness and high resolution, and is transmitted through a dedicated data link with encryption and verification functions.
5. The wind farm power optimization control system according to claim 4, characterized in that: The parameters collected by the fan operation parameter collection module include blade angle, speed, torque, cabin temperature, and vibration amplitude. The data is transmitted at high speed through the optical fiber communication network, and the transmission rate is not less than 100Mbps.
6. The wind farm power optimization control system according to claim 1, characterized in that: The power prediction unit preprocesses the data before power prediction, including data cleaning, outlier processing and data normalization operations.
7. The wind farm power optimization control system according to claim 1, characterized in that: When the control switching unit selects the power control state, the fan parameters are adjusted through the PID controller, and the PID controller parameters are adaptively adjusted with a cycle of no more than 1 minute.
8. The wind farm power optimization control system according to claim 1, characterized in that: The AGC instruction processing unit considers the wind turbine climbing rate, power upper limit, operating status and power prediction results when formulating the power adjustment strategy, and uses piecewise linear interpolation to smooth the power output.
9. The wind farm power optimization control system according to claim 1, characterized in that: The control mode lower limit power determined by the control mode setting subunit comprehensively considers the wind turbine equipment characteristics and grid compatibility requirements.
10. A wind farm power optimization control method, characterized in that: The following steps are involved: Data collection and initialization: The data collection subunit of the power control unit collects and transmits data from various data sources at a frequency of not less than once per second through wireless communication. The meteorological data acquisition module of the power prediction unit obtains meteorological forecast data. The fan operation parameter acquisition module collects and transmits fan operation parameters. The fusion processing module predicts power after preprocessing and fusion data. Power prediction: The fusion processing module of the power prediction unit uses deep learning algorithms to fuse meteorological data and wind turbine operating parameters, predict power change trends and transmit the results; Power control model construction and optimization: The data analysis and model construction subunit processes the collected data to build the model and transmit it, and the control mode setting subunit sets the control limit optimal mode to balance the power relationship; Control state switching and execution: The control switching unit selects the state according to the prediction results. If it is the power control state, it instructs to adjust the fan parameters; AGC instruction processing: The AGC instruction processing unit monitors received instructions, parses and obtains information to formulate strategies, and resumes model operation after execution.