Hydropower station AGC intelligent optimization control method and system based on multi-unit dynamic load distribution and prediction and early warning

Abstract

The invention discloses a hydropower station AGC intelligent optimization control method and system based on multi-unit dynamic load distribution and prediction and early warning, and relates to the technical field of AGC control, and the method comprises the steps: initializing system parameters, including a unit power range and upper and lower limits of a vibration region, and designing a dynamic vibration region crossing control algorithm, a prediction model and a multi-unit intelligent load distribution algorithm; acquiring real-time load and operation data, inputting the real-time load and operation data into the prediction model to obtain a prediction result, and triggering a load adjustment or early warning mechanism according to the prediction result; calling a vibration area crossing algorithm, and adjusting the unit power to a safe range; and a multi-unit intelligent load distribution algorithm is used, multi-unit loads are dynamically distributed, a control instruction is output, and real-time adjustment is completed. The method reduces manual intervention, improves the operation efficiency, prolongs the service life of equipment, reduces the operation cost through the optimization model, improves the economic benefits of a power plant, adapts to various working conditions, is short in response time, and adapts to complex scheduling scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment inspection, and particularly to an intelligent optimization control method and system for AGC of a hydropower station based on multi-unit dynamic load distribution and prediction and early warning. Background Art

[0002] In modern power systems, the automatic generation control (AGC) system is an important part of frequency modulation ancillary services, which is used to maintain the stability of the power grid frequency and the economy of load distribution. As an important power source for flexible regulation, hydropower stations need to take into account vibration zone crossing, load distribution optimization, and equipment operation stability while meeting the frequency modulation requirements of the power grid. However, the existing AGC systems have the following deficiencies:

[0003] Low vibration zone crossing efficiency: The manual adjustment process is complex, the response speed is slow, which easily leads to fluctuations in the unit operating conditions and increases equipment wear.

[0004] Lack of load distribution optimization: When multiple units operate simultaneously, the load distribution often adopts an average distribution method, without fully considering the rated power and economy of each unit.

[0005] Lack of load prediction and early warning functions: Traditional AGC systems lack the ability to accurately predict future load changes and are difficult to respond to sudden startup and shutdown demands in a timely manner.

[0006] In view of the above problems, the present invention proposes an intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning, providing an efficient, stable, and intelligent solution for the AGC system of hydropower stations. Summary of the Invention

[0007] In view of the existing problems above, the present invention is proposed.

[0008] Therefore, the problems to be solved by the present invention are: how to solve the problems that the existing AGC system has low vibration zone crossing efficiency: the manual adjustment process is complex, the response speed is slow, which easily leads to fluctuations in the unit operating conditions and increases equipment wear; lack of load distribution optimization: when multiple units operate simultaneously, the load distribution often adopts an average distribution method, without fully considering the rated power and economy of each unit; lack of load prediction and early warning functions: traditional AGC systems lack the ability to accurately predict future load changes and are difficult to respond to sudden startup and shutdown demands in a timely manner.

[0009] To solve the above technical problems, the present invention provides the following technical solutions: A hydroelectric power station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning, including initializing system parameters, including unit power range, upper and lower limits of the vibration area, designing a dynamic vibration area crossing control algorithm, a prediction model, and a multi-unit intelligent load distribution algorithm; collecting real-time load and operation data, inputting it into the prediction model to obtain a prediction result, and triggering a load adjustment or early warning mechanism according to the prediction result; calling the vibration area crossing algorithm to adjust the unit power to a safe range; using the multi-unit intelligent load distribution algorithm to dynamically distribute the multi-unit load, outputting a control command, and completing real-time regulation.

[0010] As a preferred solution of the hydroelectric power station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning described in the present invention, wherein: the load and operation data include unit power, vibration area range, AGC adjustment command, and grid load data.

[0011] As a preferred solution of the hydroelectric power station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning described in the present invention, wherein: the dynamic vibration area crossing control algorithm includes recording the current output power of unit i as P i , the vibration area range is [P v,lower , P v,upper , the power increment is ΔP i , and the vibration area crossing strategy is divided into automatic upward crossing and automatic downward crossing; the automatic upward crossing includes when P i > P v,upper + ΔP safe , automatically adjusting the unit power to a safe range, expressed as:

[0012] P i ← P i + k·ΔP adj

[0013] The automatic downward crossing includes when P i < P v,lower + ΔP safe , automatically adjusting the unit power to a safe range, expressed as:

[0014] P i ← P i - k·ΔP adj

[0015] Wherein, k is the adjustment step coefficient, and ΔP adj is the dynamic power increment; during the crossing process, the vibration signal and output stability of the unit are monitored in real time.

[0016] As a preferred solution of the AGC intelligent optimization control method for hydropower stations based on multi-unit dynamic load distribution and prediction and early warning of the present invention, wherein: the prediction model includes an ARIMA model based on time series analysis, combined with short-term machine learning, to predict the future power grid load demand, expressed as:

[0017]

[0018] wherein, P t+k is the predicted future load, ΔP t+j is the load increment at the future moment, is the model error.

[0019] As a preferred solution of the AGC intelligent optimization control method for hydropower stations based on multi-unit dynamic load distribution and prediction and early warning of the present invention, wherein: the trigger load adjustment or early warning mechanism includes that if the predicted load exceeds the sum of the rated powers of all units, the start-up reminder is triggered in advance; if the predicted load is lower than the sum of the powers of the current minimum operating units, the shutdown reminder is triggered in advance.

[0020] As a preferred solution of the AGC intelligent optimization control method for hydropower stations based on multi-unit dynamic load distribution and prediction and early warning of the present invention, wherein: the trigger load adjustment or early warning mechanism further includes that if the power is within the vibration zone range, the vibration zone crossing algorithm is called to adjust the unit power to the safe range.

[0021] As a preferred solution of the AGC intelligent optimization control method for hydropower stations based on multi-unit dynamic load distribution and prediction and early warning of the present invention, wherein: the multi-unit intelligent load distribution algorithm includes establishing a load distribution optimization function with the operating economy of each unit as the goal, expressed as:

[0022]

[0023] wherein, P i is the unit output power, P i,rated is the unit rated power, C i is the unit operating cost, λ is the weight factor; the constraint conditions include the unit power range and the total load balance; a smart optimization algorithm based on gradient descent is adopted, combined with a genetic algorithm to improve the solution speed and global convergence.

[0024] Another object of the present invention is to provide a system for the AGC intelligent optimization control method for hydropower stations based on multi-unit dynamic load distribution and prediction and early warning, which can solve the AGC intelligent optimization control problem for hydropower stations based on multi-unit dynamic load distribution and prediction and early warning by constructing an AGC intelligent optimization control system for hydropower stations based on multi-unit dynamic load distribution and prediction and early warning.

[0025] To solve the above technical problems, the present invention provides the following technical solutions: A hydropower station AGC intelligent optimization control system based on multi-unit dynamic load distribution and prediction and early warning, including a data acquisition module, a dynamic vibration zone crossing module, a load prediction and early warning module, an intelligent load distribution module, and a control output module; the data acquisition module is used to collect real-time unit power, vibration zone range, AGC adjustment instructions, and grid load data; the dynamic vibration zone crossing module is used to achieve automatic up and down crossing of the vibration zone by adjusting power; the load prediction and early warning module is used to predict future load changes and provide startup and shutdown early warnings based on a prediction model; the intelligent load distribution module is used to dynamically adjust the operating power of multiple units based on a multi-unit intelligent load distribution algorithm; the control output module is used to send the optimized power distribution instructions to each unit for execution.

[0026] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning are implemented.

[0027] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning are implemented.

[0028] The beneficial effects of the present invention are as follows: The hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning provided by the present invention realizes automatic crossing of the vibration zone, reduces manual intervention, improves operation efficiency, and extends the service life of equipment. The load prediction is accurate, combining historical data and machine learning to perceive changes in grid demand in advance. The intelligent distribution has high economy, reduces operating costs through an optimization model, and improves the economic benefits of the power plant. Real-time performance and compatibility, adapting to various working conditions, with a short response time, and adapting to complex scheduling scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0030] Figure 1 It is a flowchart of a hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning provided by the first embodiment of the present invention.

[0031] Figure 2 Structural diagram of a hydropower station AGC intelligent optimization control system based on multi - unit dynamic load distribution and prediction and early warning provided for the second embodiment of the present invention. Specific implementation manners

[0032] To make the above - mentioned objects, features and advantages of the present invention more obvious and understandable, the specific implementation manners of the present invention will be described in detail below with reference to the accompanying drawings of the specification.

[0033] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0034] Embodiment 1, referring to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a hydropower station AGC intelligent optimization control method based on multi - unit dynamic load distribution and prediction and early warning, including: initializing system parameters, including unit power range, upper and lower limits of the vibration area, designing a dynamic vibration area crossing control algorithm, a prediction model and a multi - unit intelligent load distribution algorithm; collecting real - time load and operation data, inputting it into the prediction model to obtain a prediction result, and triggering a load adjustment or early warning mechanism according to the prediction result; calling the vibration area crossing algorithm to adjust the unit power to the safe range; using the multi - unit intelligent load distribution algorithm to dynamically distribute the loads of multiple units, outputting control instructions, and completing real - time adjustment.

[0035] S1. Initialize system parameters, including unit power range, upper and lower limits of the vibration area, and design a dynamic vibration area crossing control algorithm, a prediction model and a multi - unit intelligent load distribution algorithm.

[0036] The load and operation data include unit power, vibration area range, AGC adjustment instructions and grid load data.

[0037] The dynamic vibration area crossing control algorithm includes that the current output power of unit i is denoted as P i , the vibration area range is [P v,lower , P v,upper , the power increment is ΔP i , and the vibration area crossing strategy is divided into automatic upward crossing and automatic downward crossing.

[0038] The automatic upward crossing includes that when P i >P v,upper +ΔP safe , automatically adjust the unit power to the safe range, which is expressed as:

[0039] P i ←P i +k·ΔPadj

[0040] Automatic under-crossing includes when P i <P v,lower +ΔP safe , automatically adjust the unit power to the safe range, expressed as:

[0041] P i ←P i -k·ΔP adj

[0042] where k is the adjustment step coefficient and ΔP adj is the dynamic power increment.

[0043] During the crossing process, it is necessary to monitor the vibration signal and output stability of the unit in real time to prevent equipment fatigue damage caused by frequent crossing.

[0044] S2. Collect real-time load and operation data, input it into the prediction model to obtain the prediction result, and trigger the load adjustment or warning mechanism according to the prediction result.

[0045] Adopt the ARIMA model based on time series analysis, combined with short-term machine learning (such as LSTM), to predict the power grid load demand in the next 15 minutes. In the South China Power Grid area, a point is issued every 15 minutes, so it continues for 15 minutes. The prediction formula is as follows:

[0046]

[0047] where P t+k is the predicted future load, ΔP t+j is the load increment at the future moment, is the model error.

[0048] Adopt the combination of the ARIMA model of time series analysis and machine learning algorithms (such as LSTM). The ARIMA model is responsible for capturing the trend and periodic characteristics of load changes, while the LSTM neural network processes short-term fluctuations and non-linear relationships through its memory unit structure. Based on the time series characteristics of historical load data (such as daily load curve, weekly load cycle) and real-time power grid operation data, establish the mapping relationship between load increment and factors such as time and working conditions through model training. In the prediction formula, ΔP t+1 represents the load change amount from time t to t + 1, and ΔP t+j is jointly determined by the regression analysis of historical data and the extrapolation of real-time data by the above hybrid model.

[0049] Startup warning condition: If the predicted load exceeds the sum of the rated powers of all units, trigger a startup reminder 15 minutes in advance.

[0050] Shutdown warning condition: If the predicted load is lower than the total power of the current minimum operating units, a shutdown reminder is triggered 15 minutes in advance.

[0051] S3. Invoke the vibration zone crossing algorithm to adjust the unit power to the safe range.

[0052] If the power is within the vibration zone range, the vibration zone crossing algorithm is invoked to adjust the unit power to the safe range.

[0053] S4. Use the multi-unit intelligent load distribution algorithm to dynamically distribute the multi-unit load, output control instructions, and complete real-time adjustment.

[0054] The multi-unit intelligent load distribution algorithm includes establishing a load distribution optimization function with the operating economy of each unit as the goal, expressed as:

[0055]

[0056] Among them, P i is the unit output power, P i,rated is the unit rated power, C i is the unit operating cost, and λ is the weight factor.

[0057] The constraint conditions include the unit power range and the total load balance.

[0058] Unit power range:

[0059] P i,min ≤P i ≤P i,max

[0060] Total load balance:

[0061]

[0062] An intelligent optimization algorithm based on gradient descent is adopted, combined with the genetic algorithm (GA) to improve the solution speed and global convergence.

[0063] When the load prediction module detects that a unit needs to be added or reduced in the next 15 minutes. For example, when the predicted load exceeds the total capacity of the current units, the system may add new units and adjust the power of the original units. At this time, if the power adjustment needs to enter the vibration zone range, the vibration zone crossing will be triggered.

[0064] During the power adjustment process, when the intelligent load distribution module (retrieval segment 15) dynamically distributes the power of each unit, if the target power of a certain unit is within the vibration zone range. For example: when a certain unit needs to be increased from 70MW (outside the vibration zone) to 85MW (inside the vibration zone), the system will automatically calculate the power increment and quickly cross the vibration zone to a safe point (such as 90MW).

[0065] During the traversal process, if abnormal equipment conditions (such as excessive vibration) are detected in the vibration zone monitoring data (retrieval segment 24), the system will suspend load adjustment and reallocate the loads of other units to form a closed-loop control.

[0066] The relationship between the two is not a simple alarm corresponding to traversal, but rather realizes dynamic coordination through the process of load demand prediction → power adjustment trigger → automatic vibration zone traversal → safety feedback. Early warning is the trigger condition for adjustment demand, and traversal is the safety execution means during the power adjustment process.

[0067] Example 2, referring to Figure 2 , is the second embodiment of the present invention. Different from the previous embodiment, it provides a hydropower station AGC intelligent optimization control system based on multi-unit dynamic load distribution and prediction and early warning, including: a data acquisition module, a dynamic vibration zone traversal module, a load prediction and early warning module, an intelligent load distribution module, and a control output module.

[0068] The data acquisition module is used to collect in real time the unit power, vibration zone range, AGC adjustment instruction, and grid load data.

[0069] The dynamic vibration zone traversal module is used to achieve automatic up and down traversal of the vibration zone by adjusting the power.

[0070] The load prediction and early warning module is used to predict future load changes and provide start-up and shutdown early warnings based on a prediction model.

[0071] The intelligent load distribution module is used to dynamically adjust the operating power of multiple units based on a multi-unit intelligent load distribution algorithm.

[0072] The control output module is used to send the optimized power distribution instruction to each unit for execution.

[0073] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., which can store program codes.

[0074] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0075] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, a computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise appropriately processing it when necessary, and then storing it in a computer memory.

[0076] It should be understood that the various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0077] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning, characterized by: include, Initialize system parameters, including unit power range, upper and lower limits of vibration zone, design dynamic vibration zone crossing control algorithm, prediction model and multi-unit intelligent load distribution algorithm; Collect real-time load and operation data, input them into the prediction model to obtain prediction results, and trigger load adjustment or early warning mechanisms based on the prediction results; Call the vibration zone crossing algorithm to adjust the unit power to a safe range; Use multi-unit intelligent load distribution algorithm to dynamically distribute multi-unit loads, output control instructions, and complete real-time adjustment.

2. A hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning as claimed in claim 1, characterized in that: The load and operation data include unit power, vibration zone range, AGC adjustment instructions and power grid load data.

3. A hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning as claimed in claim 2, characterized in that: The dynamic vibration zone crossing control algorithm includes the current output power of unit i, denoted as P i , the vibration range is The power increment is ΔP i ,The vibration zone crossing strategy is divided into automatic up-crossing and automatic down-crossing; The automatic up-wearing includes when P i >P v,upper +ΔP safe , automatically adjust the unit power to a safe range, expressed as, P i ←P i +k·ΔP adj The automatic down-penetration includes when P i <P v,lower +ΔP safe , automatically adjust the unit power to a safe range, expressed as, P i ←P i -k·ΔP adj Where k is the adjustment step coefficient, ΔP adj is the dynamic power increment; During the crossing process, the vibration signal and output stability of the unit are monitored in real time.

4. A hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning as claimed in claim 3, characterized in that: The prediction model includes using the ARIMA model based on time series analysis combined with short-term machine learning to predict future power grid load demand, expressed as: Among them, P t+k is the predicted future load, ΔP t+j is the load increment at the future time, is the model error.

5. A hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning as claimed in claim 4, characterized in that: The triggering load adjustment or early warning mechanism includes triggering a startup reminder in advance if the predicted load exceeds the sum of the rated powers of all units; If the predicted load is lower than the total power of the current smallest operating unit, a shutdown reminder will be triggered in advance.

6. A hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning as claimed in claim 5, characterized in that: The triggering load adjustment or early warning mechanism also includes calling the vibration zone crossing algorithm to adjust the unit power to a safe range if the power is within the vibration zone.

7. A hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning as claimed in claim 6, characterized in that: The multi-unit intelligent load distribution algorithm includes establishing a load distribution optimization function with the operation economy of each unit as the goal, which is expressed as: Among them, P i is the unit output power, P i,rated is the rated power of the unit, C i is the unit operating cost, λ is the weight factor; Constraints include unit power range and total load balance; An intelligent optimization algorithm based on gradient descent is used in combination with a genetic algorithm to improve the solution speed and global convergence.

8. A system using a hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning as claimed in any one of claims 1 to 7, characterized in that: Including data acquisition module, dynamic vibration zone crossing module, load prediction and early warning module, intelligent load distribution module and control output module; The data acquisition module is used to collect unit power, vibration zone range, AGC adjustment instructions and power grid load data in real time; The dynamic vibration zone crossing module is used to achieve automatic up and down crossing of the vibration zone by adjusting the power; The load prediction and warning module is used to predict future load changes and provide startup and shutdown warnings based on the prediction model; The intelligent load distribution module is used to dynamically adjust the operating power of multiple units based on the multi-unit intelligent load distribution algorithm; The control output module is used to send the optimized power distribution instructions to each unit for execution.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of a hydropower station AGC intelligent optimization control method based on multi-unit dynamic load distribution and prediction and early warning according to any one of claims 1 to 7 are implemented.

Images