Automatic power generation control method and system

Abstract

The invention discloses an automatic power generation control method and system, and relates to the technical field of power control, and the automatic power generation control method comprises the following steps: obtaining the operation characteristic data of a generator set; key factors influencing automatic frequency modulation and load distribution performance of the generator set are identified; the regional load prediction model is used to predict the frequency and load demand of the generator set at the future moment to obtain a frequency deviation and a load change trend; and the AGC closed-loop control logic is utilized to monitor the frequency deviation and the load change in real time and dynamically optimize the output distribution of the generator set. According to the method, through factor analysis, key factors influencing automatic frequency modulation and load distribution performance can be accurately identified, dependence on secondary factors is reduced, frequency modulation and load distribution are more targeted, and therefore it is ensured that load requirements are met in time, and meanwhile operation risks caused by frequency fluctuation are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power control, and more specifically, to an automatic generation control method and system. Background Art

[0002] Automatic Generation Control is abbreviated as AGC (Automatic Generation Control). It is an important part of the Energy Management System (EMS). It sends commands to relevant power plants or units according to the control objectives of the power grid dispatching center, and realizes the automatic control of the generator power through the automatic control and adjustment devices of the power plant or unit. In an interconnected power system, each regional power grid maintains the frequency stability within the system through AGC. Generally speaking, frequency regulation incurs costs, so regional power grids always hope to minimize their regulation costs, and generally require optimal economy during automatic generation control. When each region cooperates with each other, economic optimization can be achieved.

[0003] In the prior art, it is not convenient to accurately identify the key factors affecting the performance of automatic frequency regulation and load distribution, making the frequency regulation and load distribution lack pertinence. Moreover, it is not convenient to accurately predict the frequency deviation and load change trend at future moments, thus making it inconvenient to realize the early warning of possible future load fluctuations and frequency changes. At the same time, it is not convenient to use the AGC closed-loop control logic to optimize the output distribution in real time, and the output of the generator set cannot be made closer to the actual demand, thereby reducing the operating efficiency of the generator set and increasing the energy consumption and operating costs.

[0004] Regarding the problems in the related art, no effective solutions have been proposed yet. Summary of the Invention

[0005] Regarding the problems in the related art, the present invention proposes an automatic generation control method and system to overcome the above technical problems existing in the prior related art.

[0006] To this end, the specific technical solutions adopted by the present invention are as follows: According to one aspect of the present invention, an automatic generation control method is provided. The automatic generation control method includes the following steps: S1. Obtain the real-time operation data of the generator set, and preprocess the real-time operation data to obtain the operation characteristic data of the generator set; S2. Analyze the obtained operation characteristic data by using a factor analysis algorithm to identify the key factors affecting the automatic frequency regulation and load distribution performance of the generator set; S3. Based on the identified key factors, construct a regional load prediction model, and use the regional load prediction model to predict the frequency and load demand of the generator set at future moments to obtain the frequency deviation and load change trend; S4. Based on the frequency deviation and the load change trend, combined with the real-time operating status of the generating units, dynamically adjust the operating parameters of the generating units through the AGC control strategy, and use the AGC closed-loop control logic to monitor the frequency deviation and load change in real time, and dynamically optimize the output distribution of the generating units.

[0007] Further, analyze the obtained operating characteristic data by using the factor analysis algorithm, and identify the key factors affecting the automatic frequency regulation and load distribution performance of the generating units, including the following steps: S21. Obtain the historical operating data of the generating units, count the occurrence times of various key factors affecting the automatic frequency regulation and load distribution performance, and calculate the distribution ratio of the key factors; S22. Based on the rule analysis algorithm, deeply analyze the distribution of influencing factors in the operating characteristic data of the generating units, and generate the distribution rule of the influencing factor ratio; S23. Based on the generated distribution rule of the influencing factor ratio, construct an influencing factor identification model for the automatic frequency regulation and load distribution performance of the generating units; S24. If the action degree of the influencing factors detected in the operating status exceeds the set threshold, then use the influencing factor identification model to analyze the current operating status of the generating units, and identify the key factors that have a significant impact on the automatic frequency regulation and load distribution performance.

[0008] Further, based on the rule analysis algorithm, deeply analyze the distribution of influencing factors in the operating characteristic data of the generating units, and generate the distribution rule of the influencing factor ratio, including the following steps: S221. Set the initial parameters and the maximum number of iterations of the rule analysis algorithm; S222. In the feasible feature space of the operating characteristic data of the generating units, randomly generate an initial combination of influencing factors based on the historical data and statistical features, and calculate the distribution rule and fitness value of each combination through the rule analysis algorithm; S223. According to the fitness value, incorporate the combination of influencing factors with the best operating performance into the best group, and the worst-performing one into the optimization group; S224. Use the feature cross-analysis method to perform combination crossover between the best group and the optimization group to generate new candidate combinations of influencing factors; S225. For the new candidate combinations of influencing factors, calculate their distribution rules and fitness values; if the fitness of the new combination of influencing factors in terms of the influencing factor distribution rule is greater than that of the original combination of influencing factors, then use the new combination of influencing factors to replace the original combination of influencing factors; S226. Check whether the maximum number of iterations has been reached. If so, output the final distribution rule of the influencing factor ratio. Otherwise, return to step S223 to continue the optimization analysis.

[0009] Further, using the feature cross - analysis method, performing combinatorial crossover between the optimal group and the optimization group to generate new candidate combinations of influencing factors includes the following steps: S2241. Select the influencing factor combination with the highest fitness value from the optimal group as the parental candidate, and randomly select influencing factor combinations from the optimization group for pairing to form the basic influencing factor combination pairs for cross - analysis; S2242. According to the crossover formula, perform horizontal crossover operations on each pair of influencing factor combinations in the optimal group and the optimization group to generate new candidate combinations of influencing factors.

[0010] Further, based on the identified key factors, construct a regional load forecasting model, and use the regional load forecasting model to predict the frequency and load demand of the generator set at future moments, obtaining the frequency deviation and load change trend includes the following steps: S31. Taking the minimization of the regional load forecasting error as the objective function, combined with the operating characteristics of the generator set, establish the constraint conditions for frequency and load forecasting; S32. Using the deviation amount between the frequency deviation and the load change distribution, and adopting relative entropy to measure the distance between the actual distribution and the reference distribution, construct an uncertain set for load forecasting; S33. Based on the distributed robust optimization algorithm, construct a chance - constrained optimization model for the uncertain set, and use a mathematical solver to solve the chance - constrained model, outputting the predicted planned values of the frequency change and load demand of the generator set at future moments; S34. Combining the predicted planned value of the load, based on the current state, output increment and disturbance amount of the generator set, construct a regional load forecasting model to obtain the frequency deviation and load change trend.

[0011] Further, using the deviation amount between the frequency deviation and the load change distribution, and adopting relative entropy to measure the distance between the actual distribution and the reference distribution, constructing an uncertain set for load forecasting includes the following steps: S321. Set the relative entropy limit value of the frequency deviation and the load change distribution, use relative entropy to measure the deviation amount between the actual distribution and the reference distribution, and define the distance between the actual distribution and the reference distribution; S322. Based on the deviation amount between the actual distribution and the reference distribution, construct an uncertain set of the frequency deviation and the load change distribution.

[0012] According to another aspect of the present invention, an automatic generation control system is also provided. The automatic generation control system includes: A data acquisition module, configured to acquire the real - time operation data of the generator set, and pre - process the real - time operation data to obtain the operation characteristic data of the generator set; A factor analysis module, which is used to analyze the obtained operation characteristic data by using a factor analysis algorithm to identify the key factors affecting the automatic frequency regulation and load distribution performance of the generator set; A model construction module, which is used to construct a regional load prediction model based on the identified key factors, and use the regional load prediction model to predict the frequency and load demand of the generator set at future moments to obtain the frequency deviation and load change trend; A power generation control module, which is used to dynamically adjust the operation parameters of the generator set through an AGC control strategy based on the frequency deviation and load change trend, combined with the real-time operation state of the generator set, and use the AGC closed-loop control logic to monitor the frequency deviation and load change in real time and dynamically optimize the output distribution of the generator set.

[0013] The beneficial effects of the present invention are as follows: 1. Through factor analysis, the present invention can accurately identify the key factors affecting the automatic frequency regulation and load distribution performance, reduce the dependence on secondary factors, make the frequency regulation and load distribution more targeted, construct a regional load prediction model based on the key factors, can accurately predict the frequency deviation and load change trend at future moments, realize the early warning of possible future load fluctuations and frequency changes, use the AGC closed-loop control logic to optimize the output distribution in real time, make the output of the generator set closer to the actual demand, improve the operation efficiency of the generator set, reduce energy consumption and operation costs, ensure that the load demand is met in time, and at the same time reduce the operation risks caused by frequency fluctuations.

[0014] 2. Based on the factor analysis algorithm, the present invention constructs a scientific key factor identification model, makes the automatic frequency regulation and load distribution more accurate, significantly improves the utilization efficiency of power generation resources, reduces operation costs, quickly responds to abnormal states, enhances the stability and adaptability of the generator set under complex working conditions, thereby improving the accuracy of frequency regulation, reducing frequency deviation, and enhancing the stability of power grid operation.

[0015] 3. Through error minimization and constraint conditions, the load prediction model is more accurate, reduces frequency deviation and load fluctuations. The introduction of relative entropy and uncertainty sets can cope with complex working conditions and prediction errors, improve robustness, dynamically adjust the output plan of the generator set, reduce losses in frequency regulation and load distribution, reduce operation costs, dynamically update the prediction model and frequency deviation trend, improve the adaptability to the real-time operation state, dynamically update the prediction model and frequency deviation trend, improve the adaptability to the real-time operation state, and further avoid frequency instability caused by prediction errors and external disturbances, ensuring the safe operation of the power grid. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 is a flowchart of an automatic generation control method according to an embodiment of the present invention; Figure 2 is a schematic block diagram of an automatic generation control system according to an embodiment of the present invention.

[0018] In the figure: 1. Data acquisition module; 2. Factor analysis module; 3. Model construction module; 4. Generation control module. Detailed implementation manners

[0019] To further illustrate the embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be combined with the relevant descriptions in the specification to explain the operation principle of the embodiments. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention.

[0020] According to an embodiment of the present invention, an automatic generation control method and system are provided.

[0021] Now, the present invention will be further described in combination with the drawings and specific implementation manners. As Figure 1 shown, the automatic generation control method according to an embodiment of the present invention includes the following steps: S1. Obtain the real-time operation data of the generator set, and preprocess the real-time operation data to obtain the operation characteristic data of the generator set; Specifically, the real-time operation data includes electrical characteristic-related data, mechanical characteristic-related data, thermal characteristic-related data, status monitoring data, external condition-related data, etc.

[0022] Specifically, the operation characteristic data includes status characteristics, performance characteristics, health status characteristics, dynamic characteristics, environmental impact characteristics, etc.

[0023] S2. Analyze the obtained operation characteristic data by using a factor analysis algorithm to identify the key factors affecting the automatic frequency regulation and load distribution performance of the generator set; Specifically, the key factors include electrical characteristic factors, mechanical characteristic factors, thermal characteristic factors, operation status factors, load characteristic factors, environmental factors, etc.

[0024] S3. Based on the identified key factors, construct a regional load forecasting model, and use the regional load forecasting model to predict the frequency and load demand of the generating units at future moments, so as to obtain the frequency deviation and the load change trend; S4. Based on the frequency deviation and the load change trend, combined with the real-time operating state of the generating units, dynamically adjust the operating parameters of the generating units through the AGC control strategy, and use the AGC closed-loop control logic to monitor the frequency deviation and the load change in real time, and dynamically optimize the output distribution of the generating units.

[0025] It should be noted that the deviation between the current grid frequency and the target frequency (such as 50 Hz or 60 Hz) is monitored; the load change trend is monitored in real time through a load forecasting model or actual demand; the active power, reactive power, rotational speed, fuel consumption rate, and unit health status of the generator sets are collected, and the deviation between the real-time grid frequency and the target frequency is calculated; the increase and decrease rate of the load demand is predicted through trend analysis to determine the future change amount of the load demand; according to the current operating state of the generator sets, their response capabilities to frequency adjustment and load changes are evaluated; the frequency deviation value and load change trend data; according to the dynamic response capabilities, operating states, and health conditions of the generator sets, adjustment priorities are assigned to different units; the adjustment target is decomposed into multiple subtasks, including adjusting the active power according to the frequency deviation; the load balancing task; adjusting the unit output according to the load demand; using an optimal load distribution algorithm (such as the economic load distribution algorithm) to reduce fuel consumption and power generation costs while meeting the adjustment requirements, and outputting the adjustment targets (such as power increase or decrease, output distribution) of each generator set; adjusting the active power output of the generator sets to restore the frequency deviation; adjusting the reactive power output to ensure voltage stability; adjusting the main shaft speed of the generator sets according to the load demand; adjusting the fuel input to meet the power generation demand and optimize fuel consumption; with the adjusted operating parameters, the generator sets enter a new state; continuously collect the adjusted operating states, including frequency changes, load changes, and power output; if the adjusted frequency deviation and load demand do not reach the target, trigger further adjustment; automatically calculate new adjustment instructions according to the logic of the AGC controller; the closed-loop control logic iteratively optimizes the operating parameters of the generator sets based on real-time data until the target frequency and load distribution are reached; coordinate the output distribution of multiple units according to the dynamic adjustment capabilities of the generator sets and the grid load demand; while meeting frequency regulation and load distribution, use the economic load distribution (ELD) algorithm to reduce the total power generation cost; reserve the redundant capabilities of some generator sets to cope with sudden load increases or emergencies; monitor the operating states of the generator sets (such as overload, abnormal vibration, and over-temperature rise); enable standby units or fast-start units to make up for the output loss caused by abnormalities; if the AGC system cannot complete automatic adjustment, send an alarm signal and switch to manual intervention; save the real-time operating data, adjustment process data, and output distribution results; evaluate the frequency modulation performance, load distribution accuracy, and economy; optimize the AGC algorithm and load forecasting model according to the evaluation results.

[0026] In this alternative embodiment, obtaining the real-time operating data of the generator sets and preprocessing the real-time operating data to obtain the operating characteristic data of the generator sets includes the following steps: S11. Construct an operating characteristic curve based on the real-time data, calculate the difference in the change amplitude of the characteristic curve at adjacent moments, and extract the characteristic indicators of the operating state change; S12. A preset amplitude threshold. If the difference in the change amplitude exceeds the threshold, a new key operation moment is added; otherwise, the existing set of key moments is retained. S13. Check the distribution of key operation moments. If the distribution is too dense, adjacent moments are merged; otherwise, the current set of key moments is retained as the operation characteristic data of the generator set.

[0027] In this alternative embodiment, the factor analysis algorithm is used to analyze the obtained operation characteristic data, and the steps for identifying the key factors affecting the automatic frequency regulation and load distribution performance of the generator set are as follows: S21. Obtain the historical operation data of the generator set, count the occurrence times of various key factors affecting the automatic frequency regulation and load distribution performance, and calculate the distribution ratio of the key factors. S22. Based on the rule analysis algorithm, deeply analyze the distribution of influencing factors in the operation characteristic data of the generator set to generate the distribution rule of the influencing factor ratio. S23. Based on the generated distribution rule of the influencing factor ratio, construct an influencing factor identification model for the automatic frequency regulation and load distribution performance of the generator set. S24. If the action degree of the influencing factor detected in the operation state exceeds the set threshold, use the influencing factor identification model to analyze the operation state of the current generator set to identify the key factors that have a significant impact on the automatic frequency regulation and load distribution performance.

[0028] Specifically, the factor analysis algorithm is an improved NSGA-II algorithm, which is a classic multi-objective optimization algorithm. When dealing with multi-objective optimization problems, it can effectively find the solution set that meets the multi-objective requirements. The present invention improves the basic NSGA-II algorithm, designs an effective integer coding method, and introduces a duplicate removal operation.

[0029] In this alternative embodiment, based on the rule analysis algorithm, the steps for deeply analyzing the distribution of influencing factors in the operation characteristic data of the generator set to generate the distribution rule of the influencing factor ratio are as follows: S221. Set the initial parameters and the maximum number of iterations of the rule analysis algorithm. S222. In the feasible characteristic space of the operation characteristic data of the generator set, randomly generate an initial combination of influencing factors based on historical data and statistical characteristics, and calculate the distribution rule and fitness value of each combination through the rule analysis algorithm. S223. According to the fitness value, incorporate the combination of influencing factors with the best operation performance into the best group, and the combination with the worst performance into the optimization group. S224. Use the feature cross-analysis method to perform combination crossing between the best group and the optimization group to generate new candidate combinations of influencing factors. S225. Calculate the distribution law and fitness value of the new candidate combination of influencing factors; if the fitness of the new combination of influencing factors in terms of the distribution law of influencing factors is greater than that of the original combination of influencing factors, then use the new combination of influencing factors to replace the original combination of influencing factors. S226. Check whether the maximum number of iterations is reached. If so, output the distribution law of the final proportion of influencing factors; otherwise, return to step S223 to continue the optimization analysis.

[0030] Specifically, the law analysis algorithm is the sorting crossover optimization algorithm, which is an optimization algorithm based on the crossover and sorting mechanisms and is usually used to solve complex combinatorial optimization problems, such as scheduling problems, path planning problems, etc. It operates on the permutation order of solutions and combines mechanisms such as crossover, mutation, and selection to continuously search for the global optimal solution in the search space.

[0031] In this alternative embodiment, using the feature crossover analysis method, the combination crossover between the best group and the optimization group to generate new candidate combinations of influencing factors includes the following steps: S2241. Select the combination of influencing factors with the highest fitness value from the best group as the parent candidate, and randomly select combinations of influencing factors from the optimization group for pairing to form the basic combination pair of influencing factors for crossover analysis. S2242. According to the crossover formula, perform a horizontal crossover operation on each pair of combinations of influencing factors in the best group and the optimization group to generate new candidate combinations of influencing factors.

[0032] In this alternative embodiment, the crossover formula is: ; In the formula, Z new represents the newly generated candidate combination of influencing factors; Z best represents the combination of influencing factors selected from the best group; Z opt represents the combination of influencing factors selected from the optimization group; δ represents the weight coefficient; ε represents the random perturbation.

[0033] In this alternative embodiment, based on the identified key factors, a regional load forecasting model is constructed, and the regional load forecasting model is used to predict the frequency and load demand of the generator set at future moments, and the frequency deviation and load change trend are obtained, including the following steps: S31. Taking the minimization of the regional load forecasting error as the objective function, combined with the operating characteristics of the generator set, establish the constraint conditions for frequency and load forecasting. S32. Use the deviation between the frequency deviation and the load change distribution, adopt relative entropy to measure the distance between the actual distribution and the reference distribution, and construct a load forecasting uncertainty set; S33. Based on the distributed robust optimization algorithm, construct an opportunity-constrained optimization model for the uncertainty set, and use a mathematical solver to solve the opportunity-constrained model, and output the forecasted planned values of the frequency change and load demand of the generator set at future moments; Specifically, the distributed robust optimization algorithm is an optimization method used to solve problems under uncertainty conditions. Especially in the presence of an uncertainty set, it provides a robust solution to the constraint conditions. Its core goal is to ensure that the constraint conditions and optimization objectives can meet a certain confidence level under the influence of uncertainty.

[0034] Specifically, the mathematical solver includes gurobi (an efficient solver) or other mathematical solvers.

[0035] S34. Combine the forecasted planned value of the load, and based on the current state, output increment and disturbance amount of the generator set, construct a regional load forecasting model, and obtain the frequency deviation and load change trend.

[0036] In this alternative embodiment, using the deviation between the frequency deviation and the load change distribution, adopting relative entropy to measure the distance between the actual distribution and the reference distribution, and constructing a load forecasting uncertainty set includes the following steps: S321. Set the relative entropy limit of the frequency deviation and the load change distribution, use relative entropy to measure the deviation between the actual distribution and the reference distribution, and define the distance between the actual distribution and the reference distribution; Specifically, relative entropy, also known as Kullback-Leibler (KL) divergence, is an important concept in information theory used to measure the degree of difference between two probability distributions. It represents the amount of information lost by one distribution (usually the actual distribution) given another distribution (usually the reference distribution).

[0037] S322. Based on the deviation between the actual distribution and the reference distribution, construct an uncertainty set for the frequency deviation and the load change distribution.

[0038] In this alternative embodiment, the formula for defining the distance between the actual distribution and the reference distribution is: ; In the formula, represents using relative entropy to measure the distance between the actual distribution M and the reference distribution N ; M ( x ) represents the actual distribution of the frequency deviation and the load change; N ([[]] xrepresents the reference distribution of frequency deviation and load change; x represents the combined variable of frequency deviation and load change; d x represents the infinitesimal change of the combined variable; KL represents relative entropy.

[0039] According to another embodiment of the present invention, as Figure 2 shown, an automatic generation control system is further provided. The automatic generation control system includes: A data acquisition module 1, configured to acquire the real-time operation data of the generator set, and preprocess the real-time operation data to obtain the operation characteristic data of the generator set; A factor analysis module 2, configured to analyze the obtained operation characteristic data by using a factor analysis algorithm to identify the key factors affecting the automatic frequency regulation and load distribution performance of the generator set; A model construction module 3, configured to construct a regional load prediction model based on the identified key factors, and use the regional load prediction model to predict the frequency and load demand of the generator set at a future moment to obtain the frequency deviation and load change trend; A power generation control module 4, configured to dynamically adjust the operation parameters of the generator set through an AGC control strategy based on the frequency deviation and load change trend, in combination with the real-time operation state of the generator set, and use the AGC closed-loop control logic to monitor the frequency deviation and load change in real time and dynamically optimize the output power distribution of the generator set.

[0040] The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An automatic power generation control method, characterized in that: The automatic power generation control method comprises the following steps: S1. Acquire real-time operating data of the generator set, and pre-process the real-time operating data to obtain operating characteristic data of the generator set; S2. Analyze the obtained operation characteristic data using factor analysis algorithm to identify key factors affecting the automatic frequency regulation and load distribution performance of the generator set; S3. Based on the identified key factors, a regional load forecasting model is constructed, and the frequency and load demand of the generator sets at future moments are predicted using the regional load forecasting model to obtain the frequency deviation and load change trend; S4. Based on the frequency deviation and load change trend, combined with the real-time operating status of the generator set, the operating parameters of the generator set are dynamically adjusted through the AGC control strategy, and the AGC closed-loop control logic is used to monitor the frequency deviation and load changes in real time to dynamically optimize the output distribution of the generator set.

2. The automatic power generation control method according to claim 1, characterized in that: The method of acquiring the real-time operating data of the generator set and preprocessing the real-time operating data to obtain the operating characteristic data of the generator set comprises the following steps: S11. Construct an operation characteristic curve based on real-time data, calculate the difference in the change amplitude of the characteristic curve at adjacent moments, and extract characteristic indicators of the change in the operation state; S12, preset amplitude threshold, if the change amplitude difference exceeds the threshold, then add a new key running moment; otherwise, retain the existing key moment set; S13. Check the distribution of key operating moments. If the distribution is too dense, merge adjacent moments. Otherwise, retain the current key moment set as the operating characteristic data of the generator set.

3. The automatic power generation control method according to claim 1, characterized in that: The method of analyzing the obtained operating characteristic data by using a factor analysis algorithm to identify key factors affecting the automatic frequency regulation and load distribution performance of the generator set includes the following steps: S21. Obtain historical operating data of the generator set, count the number of occurrences of various key factors that affect automatic frequency regulation and load distribution performance, and calculate the distribution ratio of the key factors; S22. Based on the law analysis algorithm, the distribution of influencing factors in the operating characteristic data of the generator set is deeply analyzed to generate the distribution law of the proportion of influencing factors; S23, based on the distribution law of the generated influencing factor ratios, construct an influencing factor identification model for automatic frequency regulation and load distribution performance of the generator set; S24. If the degree of the influencing factors detected in the operating state exceeds the set threshold, the operating state of the current generator set is analyzed using the influencing factor identification model to identify key factors that have a significant impact on the automatic frequency regulation and load distribution performance.

4. The automatic power generation control method according to claim 3, characterized in that: The method of deeply analyzing the distribution of influencing factors in the operating characteristic data of the generator set based on the law analysis algorithm and generating the distribution law of the proportion of influencing factors includes the following steps: S221, setting initial parameters and maximum number of iterations of the regularity analysis algorithm; S222. In the feasible feature space of the operating characteristic data of the generator set, based on historical data and statistical characteristics, randomly generate an initial combination of influencing factors, and calculate the distribution law and fitness value of each combination through a law analysis algorithm; S223. According to the fitness value, the influencing factor combination with the best running performance is included in the best group, and the one with the worst performance is included in the optimization group; S224, using a feature crossover analysis method, performing a combination crossover between the best group and the optimized group to generate a new candidate influencing factor combination; S225, calculating the distribution law and fitness value of the new candidate influencing factor combination; if the fitness of the new influencing factor combination in the influencing factor distribution law is greater than that of the original influencing factor combination, replacing the original influencing factor combination with the new influencing factor combination; S226, check whether the maximum number of iterations has been reached, if so, output the final distribution law of the influencing factor ratio, otherwise, return to step S223 to continue the optimization analysis.

5. The automatic power generation control method according to claim 4, characterized in that: The method of using the feature crossover analysis method to perform a combination crossover between the best group and the optimized group to generate a new candidate influencing factor combination includes the following steps: S2241. Select the influencing factor combination with the highest fitness value from the best group as the parent candidate, randomly select the influencing factor combination from the optimization group for pairing, and form a basic influencing factor combination pair for cross analysis; S2242. According to the crossover formula, a horizontal crossover operation is performed on each pair of influencing factor combinations in the best group and the optimized group to generate a new candidate influencing factor combination.

6. An automatic power generation control method according to claim 5, characterized in that: The crossover formula is: ； In the formula, Z new Represents the newly generated candidate influencing factor combination; Z best represents the combination of influencing factors selected from the best group; Z opt represents the combination of influencing factors selected from the optimization group; δ represents the weight coefficient; ε represents a random disturbance.

7. The automatic power generation control method according to claim 1, characterized in that: The method of constructing a regional load forecasting model based on the identified key factors, and using the regional load forecasting model to forecast the frequency and load demand of the generator set at a future moment, and obtaining the frequency deviation and load change trend includes the following steps: S31. Taking the minimization of regional load forecast error as the objective function and combining the operating characteristics of the generator sets, establish the constraints for frequency and load forecasting; S32, using the deviation between the frequency deviation and the load change distribution, using relative entropy to measure the distance between the actual distribution and the reference distribution, and constructing a load forecast uncertainty set; S33. Based on the distributed robust optimization algorithm, a chance-constrained optimization model for the uncertain set is constructed, and a mathematical solver is used to solve the chance-constrained model, and the frequency change and load demand forecast plan values ​​of the generator set at future moments are output; S34. Combined with the load forecasting plan value, based on the current state of the generator set, output increment and disturbance, a regional load forecasting model is constructed to obtain the frequency deviation and load change trend.

8. An automatic power generation control method according to claim 7, characterized in that: The method of using the deviation between the frequency deviation and the load change distribution and using relative entropy to measure the distance between the actual distribution and the reference distribution to construct the load forecast uncertainty set includes the following steps: S321, setting the relative entropy limit of the frequency deviation and the load change distribution, using the relative entropy to measure the deviation between the actual distribution and the reference distribution, and defining the distance between the actual distribution and the reference distribution; S322. Based on the deviation between the actual distribution and the reference distribution, construct an uncertain set of frequency deviation and load change distribution.

9. An automatic power generation control method according to claim 8, characterized in that: The formula defining the distance between the actual distribution and the reference distribution is: ； In the formula, Indicates that the actual distribution is measured using relative entropy M With reference distribution N The distance between M ( x ) represents the actual distribution of frequency deviation and load change; N ( x ) represents the reference distribution of frequency deviation and load variation; x A combined variable representing frequency deviation and load change; d x Indicates a small change in a combined variable; KL Represents relative entropy.

10. An automatic power generation control system, used to implement the automatic power generation control method according to any one of claims 1 to 9, characterized in that: The automatic power generation control system includes: A data acquisition module is used to acquire the real-time operating data of the generator set and pre-process the real-time operating data to obtain the operating characteristic data of the generator set; A factor analysis module is used to analyze the obtained operation characteristic data using a factor analysis algorithm to identify key factors affecting the automatic frequency regulation and load distribution performance of the generator set; A model building module is used to build a regional load forecasting model based on the identified key factors, and use the regional load forecasting model to predict the frequency and load demand of the generator set at future moments, and obtain the frequency deviation and load change trend; The power generation control module is used to dynamically adjust the operating parameters of the generator set through the AGC control strategy based on the frequency deviation and load change trend, combined with the real-time operating status of the generator set, and use the AGC closed-loop control logic to monitor the frequency deviation and load changes in real time and dynamically optimize the output distribution of the generator set.

Images