Reactor load regulation method and system based on electrical performance optimization

Abstract

The application discloses an electric reactor load adjusting method and system based on electrical performance optimization, and relates to the technical field of power equipment control and optimization. The method comprises the following steps: real-time monitoring of an electric reactor, acquisition of monitoring data and load data; obtaining an evaluation result through electrical performance evaluation of three channels, and judging whether the electrical performance evaluation constraint is met. If not, a first optimization strategy is generated according to the load data and the evaluation constraint. If yes, a trend is predicted based on the load data, and a second optimization strategy is generated in combination with the evaluation constraint. Finally, the electric reactor is adaptively adjusted according to the first and second optimization strategies. The technical problem that the adjustment of the electric reactor in the prior art cannot adapt to complex load changes, resulting in low adjustment accuracy of the electric reactor and poor electrical performance, is solved, and the technical effects of improving the adjustment accuracy of the electric reactor and optimizing the electrical performance are achieved.

Description

Technical Field

[0001] This application relates to the field of power equipment control and optimization technology, and in particular to a reactor load regulation method and system based on electrical performance optimization. Background Technology

[0002] With the rapid development of power systems, reactors, as crucial devices for regulating reactive power, limiting short-circuit current, and improving grid stability, have a significant impact on the overall system performance due to their operating efficiency and regulation accuracy. However, existing technologies suffer from insufficient regulation accuracy, limited electrical performance, poor dynamic adaptability, and uncontrollable operating conditions when facing complex load changes and diverse operating conditions. Traditional methods rely on fixed control strategies or simple feedback mechanisms, making it difficult to achieve fine-grained regulation. Furthermore, they lack the ability to predict load change trends and comprehensively evaluate operational efficiency, energy efficiency, and safety, leading to equipment lag, high energy consumption, low operating efficiency, and even regulation failure or equipment malfunction under extreme conditions. Therefore, achieving real-time monitoring, comprehensive performance evaluation, and dynamic adaptive regulation of reactors to improve regulation accuracy and electrical performance has become an urgent technical problem to be solved in the field of power system equipment control.

[0003] At present, there is a technical problem in the related technologies that the adjustment of reactors cannot adapt to complex load changes, resulting in low adjustment accuracy and poor electrical performance of reactors. Summary of the Invention

[0004] This application provides a reactor load regulation method and system based on electrical performance optimization, which solves the technical problem in the prior art that the regulation of reactors cannot adapt to complex load changes, resulting in low regulation accuracy and poor electrical performance of reactors.

[0005] This application provides a reactor load regulation method based on electrical performance optimization, including:

[0006] The reactor is monitored in real time to obtain reactor monitoring data and reactor load data. The reactor monitoring data is input into the three-channel electrical performance evaluation system to obtain electrical performance evaluation results. It is determined whether the electrical performance evaluation results meet the electrical performance evaluation constraints. If the electrical performance evaluation results do not meet the electrical performance evaluation constraints, the reactor is adjusted and optimized according to the reactor load data and the electrical performance evaluation constraints to generate a first optimization strategy for reactor adjustment. If the electrical performance evaluation results meet the electrical performance evaluation constraints, trend prediction is performed according to the reactor load data to obtain load trend prediction results. Combined with the electrical performance evaluation constraints, the reactor is adjusted and optimized to generate a second optimization strategy for reactor adjustment. Adaptive load adjustment of the reactor is performed according to the first optimization strategy and the second optimization strategy for reactor adjustment.

[0007] This application provides a reactor load regulation system based on electrical performance optimization, including:

[0008] A real-time monitoring module is used to monitor the reactor in real time and obtain reactor monitoring data and reactor load data; an evaluation result acquisition module is used to input the reactor monitoring data into the three-channel electrical performance evaluation to obtain electrical performance evaluation results; an evaluation result judgment module is used to determine whether the electrical performance evaluation results meet the electrical performance evaluation constraints; and an adjustment and optimization module is used to adjust the reactor load data and the electrical performance evaluation constraints if the electrical performance evaluation results do not meet the electrical performance evaluation constraints. The reactor undergoes adjustment optimization to generate a first reactor adjustment optimization strategy; a load trend prediction result acquisition module is used to perform trend prediction based on the reactor load data if the electrical performance evaluation result meets the electrical performance evaluation constraints, obtain a load trend prediction result, and combine it with the electrical performance evaluation constraints to perform adjustment optimization on the reactor to generate a second reactor adjustment optimization strategy; an adaptive load adjustment module is used to perform adaptive load adjustment on the reactor based on the first reactor adjustment optimization strategy and the second reactor adjustment optimization strategy.

[0009] The proposed reactor load regulation method and system based on electrical performance optimization firstly involves real-time monitoring of the reactor to acquire monitoring and load data. Then, evaluation results are obtained through three channels of electrical performance evaluation, determining whether the electrical performance evaluation constraints are met. If not, a first optimization strategy is generated based on the load data and evaluation constraints; if met, a second optimization strategy is generated based on load data trend prediction and combined with the evaluation constraints. Finally, adaptive load regulation of the reactor is performed according to the first and second optimization strategies, achieving the technical effects of improving reactor regulation accuracy and optimizing electrical performance. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0011] Figure 1A flowchart illustrating the reactor load regulation method based on electrical performance optimization provided in this application embodiment;

[0012] Figure 2 A schematic diagram of the structure of a reactor load regulation system based on electrical performance optimization provided in an embodiment of this application.

[0013] Figure labeling: Real-time monitoring module 10, evaluation result acquisition module 20, evaluation result judgment module 30, adjustment and optimization module 40, load trend prediction result acquisition module 50, adaptive load adjustment module 60. Detailed Implementation

[0014] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0017] This application provides a reactor load regulation method based on electrical performance optimization, such as... Figure 1 As shown, the method includes:

[0018] Step S100 involves real-time monitoring of the reactor to obtain reactor monitoring data and reactor load data. Specifically, based on the reactor's model, specifications, rated parameters, and the complexity of the power system, the system automatically selects and configures suitable monitoring equipment. For electrical parameter monitoring, the system uses a voltage transformer with an accuracy of ±0.1%, automatically installed on an insulating bracket at the reactor winding output to measure voltage. Simultaneously, a current transformer with an accuracy of ±0.2% is automatically fitted onto the incoming conductor and its stability is ensured by a fixing device to measure current. For load data acquisition, the system employs an intelligent load sensor, which integrates a strain gauge pressure sensor and an electromagnetic induction current sensor: the strain gauge sensor is automatically fixed to the connecting cable clamp, while the electromagnetic induction current sensor is automatically wrapped around the cable and covered with electromagnetic shielding material to reduce external interference, thereby accurately acquiring load data. After the equipment is installed and debugged, the monitoring system automatically collects data every 5 milliseconds. The analog signals from the sensors are transmitted to the data acquisition terminal via shielded cables or wireless communication modules (such as Bluetooth 5.0 or ZigBee professional band modules). The data acquisition terminal automatically runs a finite impulse response filtering algorithm to denoise the voltage and current data, and combines it with an outlier detection algorithm to correct and filter the collected data.

[0019] Step S200: Input the reactor monitoring data into the three-channel electrical performance evaluation system to obtain the electrical performance evaluation results. Specifically, based on the reactor design standards, operating specifications, and power system requirements, the system automatically constructs a three-channel electrical performance evaluation system and clarifies the functional pre-evaluation indicators for each channel. The reactor efficiency evaluation channel automatically constructs an efficiency evaluation model library; the energy efficiency evaluation channel has a built-in energy loss algorithm; and the operational safety evaluation channel presets risk warning indicators. The collected reactor monitoring data undergoes format standardization processing in the data processing module, and an automatic integrity check is performed. After repairing a small amount of missing data, the processed data is input into each channel in an orderly manner. Then, each channel independently completes the evaluation calculation: the efficiency evaluation channel inputs the data into multiple models in the model library in sequence and calculates the reactor efficiency coefficient through weighted average; the energy efficiency evaluation channel automatically calculates copper loss and iron loss based on the energy loss algorithm, combined with data such as voltage, current, and temperature, thereby obtaining the energy efficiency coefficient; and the operational safety evaluation channel compares the monitoring data with the preset risk warning indicators and outputs the operational safety coefficient based on the anomaly detection algorithm. Finally, the system integrates the three coefficients and adds metadata in a structured format to output electrical performance evaluation results, providing a basis for subsequent automated adjustment and optimization operations. In actual operation, the entire process is dynamically adjusted and optimized according to changes in system status to ensure stable operation of the power system and improve overall efficiency.

[0020] In one possible implementation, the reactor monitoring data is input into the three-channel electrical performance evaluation system to obtain the electrical performance evaluation results. Step S200 further includes step S210, whereby the three-channel electrical performance evaluation system includes a reactor efficiency evaluation channel, a reactor energy efficiency evaluation channel, and a reactor operation safety evaluation channel. Specifically, based on the role of the reactor in the power system, the system automatically analyzes its design data, historical operating data, and industry standards to construct the three-channel electrical performance evaluation system from three key dimensions: efficiency, energy efficiency, and operation safety. Through built-in data mining and feature extraction algorithms, the system automatically extracts key characteristic parameters such as reactive power output, power factor optimization, and harmonic suppression effect. Based on electromagnetic theory and power system analysis principles, it builds multiple efficiency evaluation models (such as models based on equivalent circuits and magnetic saturation characteristics) and collaboratively calculates and generates the reactor efficiency coefficient. Meanwhile, guided by the law of conservation of energy, the system utilizes high-precision current transformers to monitor winding current and calculates copper losses based on known resistance values. It also calculates iron losses using hysteresis and eddy current loss formulas and estimates stray losses using a spectrum analysis algorithm. These three values ​​are summed and divided by the total input electrical energy to generate the energy efficiency coefficient. Regarding operational safety, the system extracts key safety monitoring indicators through fault tree analysis and failure mode analysis. Combined with real-time data acquisition from high-sensitivity sensors, it compares data with safety thresholds, triggering alarms when exceeding limits. Simultaneously, it uses machine learning anomaly detection algorithms to model based on historical data, identifying potential anomalies in advance and outputting an operational safety coefficient. Finally, the system integrates the efficiency coefficient, energy efficiency coefficient, and operational safety coefficient to generate a comprehensive electrical performance evaluation result, providing a scientific basis for the automatic adjustment and optimization of the reactor.

[0021] Step S220: Input the reactor monitoring data into the reactor efficiency evaluation channel to obtain the reactor efficiency coefficient. Specifically, after the reactor monitoring system collects data, the raw data needs to be preprocessed. Data cleaning algorithms are used to remove erroneous data caused by sensor failures, electromagnetic interference, etc. Outliers are identified and removed by comparing and verifying with historical data and data from surrounding sensors. For a small number of missing data, linear interpolation or filling based on the average of data from adjacent time periods is used to ensure continuity and integrity. Then, the data format is standardized and unified to the International System of Units (SI) standard format to prepare for entering the evaluation channel. Next, the reactor efficiency evaluation channel presets multiple sub-models based on different theoretical algorithms. Based on the reactor type, operating conditions, and past model performance, a set of models suitable for the current situation is accurately selected. For example, for iron-core reactors with frequent voltage fluctuations, a model considering magnetic saturation characteristics and voltage sensitivity is selected; when the load is mostly resistive, a model based on the equivalent circuit principle that is good at handling resistive loads is selected. At the same time, some parameters are dynamically adjusted according to the characteristics of real-time monitoring data. Finally, the preprocessed and model-adapted data is input into the sub-models. Each sub-model calculates its local efficiency evaluation coefficients according to its own algorithm, such as the reactive power contribution coefficient based on the equivalent circuit model and the power factor improvement coefficient considering the magnetic saturation effect. Then, the weighted average method is used to integrate them, and the weights are determined by comprehensively weighing the accuracy and applicability of each sub-model to calculate the reactor efficiency coefficient, providing a basis for subsequent operations.

[0022] Step S230: Input the reactor monitoring data into the reactor energy efficiency evaluation channel to obtain the reactor energy efficiency coefficient. Specifically, after obtaining the raw monitoring data from the reactor's real-time monitoring system, comprehensive data preparation and preprocessing are first performed. Professional data verification algorithms are used to check the completeness of data such as voltage, current, and temperature, marking any possible missing or erroneous values. Scientific methods such as linear interpolation are used to supplement any missing data, and filtering algorithms are used to remove high-frequency noise caused by electromagnetic interference. All data is converted to a unified standard format and dimensioned. Next, the preprocessed monitoring data enters the reactor energy efficiency evaluation channel. The analysis program within the channel first extracts key parameters closely related to energy loss. Using a high-precision current transformer combined with known winding resistance values, copper losses are accurately calculated according to Joule's law. Based on voltage, current data, and core characteristic parameters, hysteresis and eddy current loss formulas are used to accurately estimate iron losses. Stray losses are evaluated using spectrum analysis technology combined with an empirical stray loss estimation model. Finally, the total energy loss is obtained by adding copper loss, iron loss, and stray loss. The total input electrical energy is calculated by integrating the voltage and current over a specific time period. Based on the energy efficiency calculation formula, the total energy loss is divided by the total electrical energy to obtain the reactor's energy efficiency coefficient. This coefficient can serve as a key basis for judging the reactor's operating status and formulating optimization strategies, thus helping the power system to save energy and reduce emissions, and promoting the development of the industry.

[0023] Step S240: Input the reactor monitoring data into the reactor operation safety evaluation channel and output the reactor operation safety factor. Specifically, real-time data from various monitoring points of the reactor, such as winding temperature, core temperature, vibration data, and insulation resistance values, are transmitted to the operation safety evaluation channel. First, a cyclic redundancy check algorithm is used at the channel entrance to verify data integrity. Combined with the normal operating parameter range, threshold judgment is used to screen for obviously abnormal data, and a moving average filtering algorithm is used to process fluctuating data. Next, a rule-based safety indicator comparison stage is entered, comparing temperature with the upper limit of winding and core temperatures, vibration data with the standard vibration range, and insulation resistance values ​​with the minimum insulation resistance standard. Once a standard is exceeded, high temperature, abnormal vibration, and insulation warnings are triggered respectively. Simultaneously, machine learning models such as support vector machines and autoencoders are trained using historical operation and fault data. Even if the data does not reach the hard threshold, the model will detect hidden anomalies based on dynamic data changes and parameter correlations and issue early warnings. Finally, based on the combined results of the two-stage testing, various safety hazards are assigned weights according to factors such as the degree of threat, and the weighted sum is used to output an operational safety coefficient between 0 and 1 through a scoring conversion formula. Based on this, maintenance personnel can understand the situation, take measures, and ensure the reliable operation of the power system.

[0024] Step S250: The reactor efficiency coefficient, reactor energy efficiency coefficient, and reactor operating safety factor are output as the electrical performance evaluation results. Specifically, the system automatically collects basic data related to the reactor's efficiency coefficient, energy efficiency coefficient, and operating safety factor through high-precision power monitoring equipment. The efficiency coefficient is obtained by averaging reactive power monitored by multiple sets of sensors; the energy efficiency coefficient is obtained by automatically calibrating the current transformer and verifying the winding resistance measurement; and the operating safety factor is obtained by deploying multiple types of sensors to monitor key indicators in real time, triggering a data re-collection mechanism when an anomaly occurs. After data collection, the system converts the efficiency coefficient according to preset standards, converting it into a reactive power compensation ratio form accurate to three decimal places; the energy efficiency coefficient is calculated as the ratio of unit power loss to input power while retaining appropriate accuracy; and the operating safety factor is normalized to a value range of 0-1 and a timestamp is added uniformly. Subsequently, the system generates a visual interface suitable for power system monitoring. The interface is divided into three areas: the upper left corner dynamically displays the efficiency coefficient value in green, yellow, and red; the upper right corner displays the energy efficiency coefficient through a gradient from dark blue to dark red; and the bottom center uses a dynamic signal light icon that changes color according to the operational safety factor to provide early warnings, automatically adding an identification code and time information accurate to the minute. Finally, the system pushes the visual interface data in real time to the main control room's large screen and the handheld smart inspection terminals of maintenance personnel via a high-speed transmission network, facilitating real-time monitoring of reactor status and rapid handling of anomalies, ensuring the efficient and stable operation of the power system.

[0025] In one possible implementation, the reactor monitoring data is input into the reactor efficiency evaluation channel to obtain the reactor efficiency coefficient. Step S220 further includes step S221, where the reactor efficiency evaluation channel includes S reactor efficiency evaluation models, where S is a positive integer greater than 1. Specifically, the system automatically determines the number of evaluation models to be constructed based on the characteristics of reactors in various application scenarios such as industrial production, substations, and residential communities, and according to the emphasis on reactor efficiency under different operating conditions (e.g., industrial scenarios emphasize rapid reactive power regulation, while residential power supply emphasizes harmonic suppression). The system specifies that the number of models is a positive integer S greater than 1. The system collects massive amounts of operating data such as current and voltage under different operating conditions, as well as performance cases of similar reactors, through a large-scale data acquisition module. Simultaneously, it automatically analyzes professional literature and industry standards to extract key evaluation indicators such as reactive power response time and harmonic attenuation rate, providing theoretical and data support for model construction. Subsequently, the system combines machine learning algorithms and mathematical modeling techniques to automatically generate multiple efficiency evaluation models: for example, a dynamic reactive power compensation model is constructed using a neural network algorithm, and a harmonic mitigation model is constructed using regression analysis. Each model, based on a unique structure, parameters, and algorithm, accurately measures the efficiency of the reactor from different dimensions, ultimately forming a reactor efficiency evaluation channel, providing a scientific basis for subsequent performance optimization and operation monitoring.

[0026] Step S222: Input the reactor monitoring data into the S reactor efficiency evaluation models to obtain S reactor efficiency evaluation coefficients. Specifically, the system deploys high-precision power monitoring equipment to collect data such as current, voltage, reactive power, harmonic content, and temperature during reactor operation in real time, and automatically performs preprocessing, such as filtering and noise reduction, standard correction, and model calibration, to ensure that the data meets the model input requirements. Subsequently, according to the characteristics and input requirements of the S evaluation models, the system extracts key data such as reactive power time series and harmonic spectrum, encapsulates them in the correct format, and inputs them into the corresponding models. The models calculate and generate efficiency evaluation coefficients through built-in algorithms, reflecting reactive power compensation efficiency and harmonic mitigation capabilities. The generated coefficients are automatically compared and verified with historical data. If abnormal fluctuations are found, the system backtracks and checks the input data or model status to ensure that the evaluation results are true and reliable.

[0027] Step S223: The average of the S reactor efficiency evaluation coefficients is calculated to generate the reactor efficiency coefficients. Specifically, after obtaining the S reactor efficiency evaluation coefficients, the system automatically reviews the S coefficients based on the standard coefficient range for similar reactors under similar operating conditions, focusing on whether the numerical range is reasonable. If a coefficient is found to deviate too much, the system automatically backtracks and checks the corresponding evaluation model and input monitoring data to ensure the reliability of the coefficients. Subsequently, based on the actual operating characteristics of the reactors, the accuracy of the evaluation models, and historical data accumulation, the system automatically selects the averaging method. When the accuracy and reliability of each model are similar, a simple arithmetic average method is used, adding the S coefficients and dividing by S; when some models need to be assigned higher weights due to superior technology or algorithms, the system reasonably allocates weights based on historical data and actual operating feedback, using a weighted arithmetic average method for calculation. Finally, the system uses the selected method to calculate the reactor efficiency coefficient and automatically compares it with the average value under recent operating conditions to check whether the fluctuation is reasonable. At the same time, it performs reverse verification by combining the actual operating status such as reactive power output and harmonic suppression effect. If any discrepancies are found, the relevant links are immediately reviewed to ensure that the efficiency coefficient is accurate and reliable.

[0028] Step S300: Determine whether the electrical performance evaluation results meet the electrical performance evaluation constraints. Specifically, based on national and industry standards, reactor design specifications, and a large amount of actual operating data, the system automatically formulates detailed quantitative indicator rules for the three constraints of reactor effectiveness, energy efficiency, and operational safety. For example, it specifies the accuracy of reactive power compensation under different loads, clarifies the upper limit of unit energy loss, and sets thresholds for temperature and vibration amplitude. Subsequently, a high-precision electrical performance monitoring system is deployed to collect relevant reactor operation data in real time: for effectiveness indicators, power data is collected and automatically converted into reactive power compensation rate; for energy efficiency indicators, electrical parameters are accurately measured and energy efficiency coefficient is calculated; for operational safety indicators, sensor data is collected in real time and compiled into comparable values. Finally, the system compares the compiled electrical performance evaluation result data with the quantitative indicator rules one by one according to constraint type: effectiveness checks the reactive power compensation rate, energy efficiency compares the energy efficiency coefficient, and operational safety checks temperature and vibration amplitude. If any indicator is not met, the system records the details; if all indicators are met, the electrical performance is deemed to meet the standards, and the evaluation process is completed.

[0029] Step S400: If the electrical performance evaluation result does not meet the electrical performance evaluation constraints, the reactor is adjusted and optimized based on the reactor load data and the electrical performance evaluation constraints to generate a first optimization strategy for reactor adjustment. Specifically, after the system generates the electrical performance evaluation result, it automatically compares it with the electrical performance evaluation constraints, accurately checks the reactive power compensation and power factor in reactor efficiency, whether the unit energy loss exceeds the standard in energy efficiency, and whether indicators such as temperature and vibration amplitude exceed the threshold in operational safety, automatically locating specific problems that do not meet the constraints. Simultaneously, the system deeply analyzes the reactor load data using a built-in data mining algorithm to explore load change patterns, including the time of peak and valley occurrences, fluctuation frequency, and duration under different load levels, comprehensively analyzing the impact mechanism of load on electrical performance. Based on these analyses, the system combines power system control rules and electrical equipment optimization objectives, and uses intelligent optimization algorithms to automatically generate a first optimization strategy for reactor adjustment. For example, adjusting switching times to address reactive power issues, optimizing operating parameters to address energy efficiency issues, and controlling temperature or adjusting operating settings to address operational safety issues can generate comprehensive and targeted adjustment strategies, providing reliable guidance for the optimized operation of reactors.

[0030] In one possible implementation, if the electrical performance evaluation result does not meet the electrical performance evaluation constraints, the reactor is adjusted and optimized based on the reactor load data and the electrical performance evaluation constraints to generate a first optimization strategy for reactor adjustment. Step S400 further includes step S410, making adjustment decisions for the reactor based on the reactor load data to obtain a first space for reactor adjustment decisions. Specifically, the system deploys high-precision power monitoring equipment to automatically collect data from the power system where the reactor is located, focusing on monitoring real-time current, voltage, power, and other parameters of the load and their changing trends, and plotting fluctuation curves, recording the peak and valley values ​​of the system, while automatically identifying and classifying load types. Through a built-in data cleaning algorithm, the system processes the collected data to ensure the accuracy and completeness of the data. Subsequently, the system uses big data analysis technology and a built-in professional model to automatically analyze the dynamic change characteristics of the load, identify the operating characteristics of different loads such as industrial motors and residential electricity, and classify the load conditions into categories such as stable high load, frequent fluctuation, and low load standby. Based on operating condition analysis, the system generates preliminary adjustment schemes, such as increasing the number of reactors under high load, using intelligent switching during fluctuations, and reducing voltage or the number of reactors under low load. This forms the first space for reactor adjustment decisions, providing a foundation for subsequent optimization.

[0031] Step S420: Based on the three channels of electrical performance evaluation, the system performs optimization analysis on the first space of reactor adjustment decision according to the constraints of the electrical performance evaluation, and establishes the second space of reactor adjustment decision. Specifically, based on a large amount of experimental data, actual operation cases, and authoritative standards, the system automatically sorts out the connotation of the three channels of electrical performance evaluation, clarifies the key indicators and constraints of each channel of reactor efficiency, energy efficiency, and operational safety, such as the reactive power compensation accuracy in the efficiency channel, the upper limit of unit energy loss in the energy efficiency channel, and the winding temperature threshold in the operational safety channel. Subsequently, the system imports all adjustment schemes in the first space of reactor adjustment decision into the electrical performance evaluation platform with integrated simulation technology in a standard format. The platform simulates each scheme one by one according to the three-channel indicators and constraints, and automatically outputs preliminary performance evaluation results such as reactive power compensation deviation and unit energy loss value. Finally, the system uses a built-in multi-objective optimization algorithm to conduct in-depth optimization based on the preliminary evaluation results, automatically weighs the advantages and disadvantages of each scheme in terms of effectiveness, energy efficiency, and operational safety, selects the scheme with better performance, and integrates and generates a second space for reactor regulation decision-making, providing a reliable basis for further optimization of reactor operation.

[0032] Step S430: Introducing a reactor regulation fitness evaluation network, and optimizing the second space of reactor regulation decision based on the reactor regulation fitness evaluation network to maximize the regulation fitness, outputting the first optimization strategy for reactor regulation. The reactor regulation fitness evaluation network includes reactor efficiency weights, reactor energy efficiency weights, and reactor operational safety weights. Specifically, the system automatically analyzes the actual operating environment, application scenarios, and user needs of the reactor, combines historical operating data, and uses methods such as analytic hierarchy process (AHP) and fuzzy comprehensive evaluation to assign reasonable weights to reactor efficiency, energy efficiency, and operational safety, automatically constructing the reactor regulation fitness evaluation network. For example, for densely populated industrial areas, the efficiency weight is set to 0.5, energy efficiency to 0.3, and operational safety to 0.2. Subsequently, the system imports the regulation schemes from the second space of reactor regulation decision-making one by one according to the network's preset interface specifications. The network uses machine learning algorithms and built-in mathematical models to calculate the fitness score of each scheme according to weights, simulates operation to generate reactive power compensation, power loss, and operational safety index data, and converts them into a comprehensive fitness score. Finally, the system initiates an optimization algorithm, using intelligent optimization methods such as genetic algorithms or particle swarm optimization algorithms to iteratively search for the maximum regulation fitness, dynamically adjusting the schemes. After multiple rounds of optimization, it outputs the first optimal reactor regulation strategy corresponding to the maximum fitness, providing precise guidance for regulation operations in actual operation.

[0033] In one possible implementation, the reactor is adjusted based on the reactor load data to obtain a first space for reactor adjustment decisions. Step S410 further includes step S411, where the reactor is searched for control schemes based on the reactor load data to obtain a set of searched control schemes. Specifically, the system deploys high-precision, multi-parameter power monitoring equipment at key nodes in the power system where the reactor is located to collect real-time and accurate reactor load data such as current, voltage, power factor, active power, reactive power, and their dynamic change curves, and transmits the data to a data processing center. The system cleans the collected data using built-in advanced data processing algorithms, automatically removing outliers and noise, and completing missing data to ensure data integrity and accuracy, laying the foundation for subsequent retrieval. Subsequently, the system combines the reactor's electrical characteristics, common operating conditions, and industry standards to construct an intelligent retrieval system. A built-in semantic parsing module is used to parse control requirements described in natural language, and machine learning classification and matching algorithms are used to locate relevant control schemes based on load data characteristics, while simultaneously identifying search conditions during peak hours or under low load conditions. The system inputs the processed load data into the intelligent retrieval module, which searches a massive database based on preset rule algorithms. It comprehensively analyzes dynamic characteristics such as real-time load values, trends, and fluctuation frequencies to select control schemes suitable for the operating conditions. For situations with large periodic fluctuations, the system prioritizes adaptive adjustment schemes, ultimately forming a set of retrieved control schemes.

[0034] Step S412: Data cleaning is performed based on the retrieved control scheme set to obtain the reactor control space. Specifically, after generating the retrieved control scheme set, the system automatically reviews each scheme in the set based on the actual operating parameters such as the reactor's rated current, voltage level, and load variation range, marking schemes suitable for high-voltage, large-capacity reactors but unsuitable for current medium- and low-voltage, small-capacity reactors. Subsequently, the system cleans and optimizes the scheme set through its built-in data cleaning module, including correcting issues such as voltage regulation range numerical deviations and control parameter unit confusion caused by input errors; automatically verifying data accuracy by comparing authoritative data with similar schemes; estimating data for missing reactive power compensation strategies under low load conditions by combining reactor characteristics, similar cases, and built-in theoretical models; and eliminating redundant and duplicate information to ensure the simplicity and efficiency of the scheme set. Ultimately, the system retains the optimized and reliable control scheme after cleaning, and establishes a reactor control space that covers strategies such as precise switching under high load conditions to ensure reactive power balance and reducing operating losses under low load conditions to improve energy efficiency, laying a solid foundation for subsequent analysis of triggering conditions and formulation of adjustment decisions.

[0035] Step S413: Analyze the trigger ranges of each dimension based on the reactor control space to establish the reactor control trigger domain. Specifically, the system focuses on the schemes within the reactor control space and their key dimensions, including reactive power compensation, voltage regulation, and current control, automatically analyzing the operating rules and trigger conditions of each dimension. For the reactive power compensation dimension, the system analyzes the changes in reactive power demand under different load conditions using a large amount of historical load data and reactor operating data, combined with a power system analysis model. It determines the trigger range for switching to a small-capacity reactor under light load and power factor below 0.8, and to switching to a large-capacity reactor under heavy load and power factor below 0.6. In the voltage regulation dimension, the system sets trigger conditions based on grid voltage standards and actual voltage fluctuation data, using circuit analysis and simulation models: step-down regulation is initiated when the system voltage is continuously higher than the rated voltage by 5% for a certain period; step-up regulation is initiated when the voltage is lower than the rated voltage by 3% for an extended period. In terms of current control, the system combines the reactor's rated current and real-time load current data to set trigger conditions: current limiting protection is triggered when the load current approaches or exceeds 120% of the rated current, and current control is optimized to improve energy efficiency when it falls below 50% of the rated current. Ultimately, the system integrates the trigger ranges of each dimension to establish a reactor control trigger domain, providing a scientific basis for precise control of reactor operation.

[0036] Step S414: The system makes adjustment decisions for the reactor based on the reactor control trigger domain, generating a first space for reactor adjustment decisions. Specifically, the system automatically analyzes key triggering conditions in the reactor control trigger domain, such as reactive power compensation trigger points, voltage regulation thresholds, and current control limits. Based on the clearly defined reactive power demand nodes in the trigger domain, the system monitors the actual load in real time. For example, under medium load and when the power factor is close to the critical value for small-capacity reactor activation, the system automatically formulates an activation decision, comprehensively considering system stability, subsequent load changes, reactor performance parameters, estimating the reactive power improvement effect, power factor optimization degree, and potential problems, and generating contingency plans in advance. When the system voltage approaches the regulation threshold, the system weighs the overall operating situation: when the voltage is slightly high and the fluctuation is small, the reactor value is finely adjusted to smoothly reduce the voltage; when the deviation is large and the duration is long, the reactor is decisively switched on or off to pull back the voltage, while simultaneously considering reactive power distribution and subsequent adjustment needs. In terms of current control, the system monitors the load current and current control limits in real time. When the load approaches the overload limit, it makes current-limiting decisions based on the reactor's rated parameters and cooperative characteristics, automatically adjusting the connection method or optimizing circuit parameters to ensure current compliance and maintain reactive power supply, while optimizing energy loss. Finally, the system summarizes these fine-tuning strategies to generate the reactor regulation decision space, providing a basis for precise operation control.

[0037] In one possible implementation, based on the three channels of electrical performance evaluation, an optimization analysis is performed on the first space of reactor adjustment decisions according to the constraints of the electrical performance evaluation to establish a second space of reactor adjustment decisions. Step S420 further includes step S421, extracting the k-th reactor adjustment decision based on the first space of reactor adjustment decisions, where k is a positive integer. Specifically, when extracting the k-th reactor adjustment decision, the system automatically analyzes the adjustment decisions and their generation basis formulated in the first space for operating conditions such as reactive power shortage, voltage fluctuation, and load change. Combined with the real-time operating status, the system assesses reactive power demand, voltage stability, and load change trends, and selects decisions that prioritize meeting current needs. Through a built-in evaluation system, weights are allocated according to dimensions such as reactive power, voltage regulation, and load adaptability to comprehensively evaluate the overall value of all adjustment decisions. Intelligent algorithms are used to score each decision according to its weight, assigning higher scores to decisions that are balanced in all aspects and adapted to the operating conditions. Finally, the k-th decision is accurately extracted, refining the switching and voltage adjustment parameters of the reactor, providing reliable guidance for power system operation in specific scenarios.

[0038] Step S422: Based on the k-th decision of reactor adjustment, the system performs state prediction on the reactor to obtain the k-th state prediction result. Specifically, when performing state prediction on the reactor based on the k-th decision of reactor adjustment, the system automatically analyzes the details of the k-th decision, extracts key information such as the number of switching groups and voltage regulation parameters, and combines it with its core objectives of addressing reactive power fluctuations, voltage stability, and load adaptability requirements. The system constructs a high-fidelity simulation model based on the reactor's electrical principles and historical operating data, using precise mathematical formulas to describe physical phenomena such as electromagnetic characteristics, heat conduction, and mechanical vibration. It also incorporates operating data under different operating conditions to determine key parameters, such as the influence of load change rate on the temperature rise curve and vibration amplitude. Subsequently, the parameter values ​​of the k-th decision are input into the simulation model as initial conditions, and the simulation program is started to simulate the future operation process, calculating key state indicators such as reactive power output, winding temperature change, core magnetic flux density fluctuation, vibration amplitude, and frequency in real time. The system processes simulation data using trend extrapolation and time series analysis techniques. For example, it predicts extreme values ​​over longer periods based on short-term temperature rise trends and analyzes periodic changes in vibration amplitude to assess potential resonance risks. Ultimately, the system generates a detailed report predicting the reactor's k-th state, clearly listing the reactive power output range, expected maximum winding temperature, possible maximum vibration amplitude, and corresponding time points for different future periods. This provides a scientific basis for developing measures to ensure the reactor's stable operation in advance.

[0039] Step S423: Input the predicted result of the reactor's k-th state into the three channels of electrical performance evaluation to obtain the k-th decision electrical performance evaluation result. Specifically, when inputting the predicted result of the reactor's k-th state into the three channels of electrical performance evaluation to obtain the k-th decision electrical performance evaluation result, the system first automatically analyzes the architecture and function of the three channels, focusing on three key aspects: reactive power compensation accuracy, voltage regulation stability, and power loss, clarifying the evaluation points, index calculation methods, and data processing flow for each channel. Subsequently, the system preprocesses the predicted result of the k-th state, filters data directly related to electrical performance, and formats and organizes it according to the requirements of each channel, such as extracting the predicted reactive power value to generate time series data to adapt to the corresponding channel. Next, the system inputs the preprocessed data into the three channels respectively: in the reactive power compensation accuracy channel, the deviation rate is calculated by comparing the predicted value with the ideal target value; in the voltage regulation stability channel, whether the standard is met is judged based on the voltage fluctuation value combined with the preset standard; in the power loss channel, whether it exceeds the reasonable range is evaluated based on the active power loss prediction curve. Finally, the system integrates the preliminary evaluation results of each channel, assigns different weights according to their importance to the overall electrical performance of the reactor, and calculates the comprehensive k-th decision electrical performance evaluation result by weighted summation, providing a scientific basis for optimizing regulation strategies and ensuring the efficient operation of the power system.

[0040] Step S424: Determine whether the electrical performance evaluation result of the k-th decision meets the electrical performance evaluation constraints. Specifically, when determining whether the electrical performance evaluation result of the k-th decision meets the electrical performance evaluation constraints, the system automatically parses the detailed rules of the electrical performance evaluation constraints. These rules are based on power industry standards, reactor operating experience thresholds, and current power system requirements, covering key indicators such as the reactive power compensation accuracy deviation range, voltage regulation fluctuation amplitude and recovery time limits, and maximum power loss. The system checks the quantitative data such as reactive power, voltage, and power loss in the electrical performance evaluation result of the k-th decision one by one, compares the reactive power compensation deviation rate with the allowable range, analyzes whether the voltage regulation fluctuation amplitude and recovery time are compliant, and calculates whether the measured value of power loss exceeds the limit. Through rigorous logical comprehensive judgment, the overall system is judged to be satisfied only when all indicators meet the constraints; if any indicator is not satisfied (such as the reactive power deviation rate exceeding the limit), even if other aspects are good, it is judged to be unsatisfactory. Based on the judgment results, the system automatically provides feedback: if the constraints are met, it is marked as a feasible solution and enters subsequent operation and control; if not, an alarm is triggered, the cause is analyzed, and targeted adjustments are made to ensure the safety and stability of the power system operation.

[0041] Step S425: If the electrical performance evaluation result of the k-th decision satisfies the electrical performance evaluation constraints, the k-th reactor regulation decision is added to the second space of the reactor regulation decision. Specifically, when the electrical performance evaluation result of the k-th decision satisfies the electrical performance evaluation constraints and the k-th reactor regulation decision needs to be added to the second space of the reactor regulation decision, the system first automatically verifies whether the electrical performance evaluation result of the k-th decision truly meets all constraints, and reviews whether indicators such as reactive power compensation accuracy, voltage regulation stability, and power loss values ​​meet the standards to ensure accuracy and avoid errors that could lead to power system problems. Next, the system checks the storage architecture, storage space, and data index of the second space of the reactor regulation decision to ensure that it has a good storage status and can accept new data. Subsequently, the system converts the key parameters of the k-th reactor regulation decision (such as reactor switching schemes, voltage regulation values, etc.) into a unified format according to preset format specifications. Finally, the system uses the database entry module to accurately add the processed k-th decision to the second space, and automatically verifies the integrity and accuracy of the data after the addition is completed, ensuring that the decision can be retrieved and used by the subsequent power system control.

[0042] Step S426: If the electrical performance evaluation result of the k-th decision does not meet the electrical performance evaluation constraints, the k-th reactor adjustment decision is eliminated. Specifically, when the system determines that the electrical performance evaluation result of the k-th decision does not meet the electrical performance evaluation constraints, the system first comprehensively analyzes the specific reasons for not meeting the constraints, deeply analyzes the root causes of insufficient reactive power compensation accuracy, insufficient voltage regulation stability, or excessive power loss, and accumulates data and experience for subsequent optimization decisions. Next, the system automatically locates the storage location of the decision in the entire decision-making process, accurately locking its position. Subsequently, according to the preset process and data management specifications, the system carefully removes the decision from the storage location using built-in tools, and follows data security rules to prevent accidental deletion of other data or impact on other records. Finally, the system automatically records the entire elimination process, including key information such as reasons, time nodes, and executed operations, generating a detailed archive for easy retrospective analysis, providing a reliable reference for the formulation of new decisions, and ensuring the efficient and safe operation of the power system.

[0043] Step S500: If the electrical performance evaluation result meets the electrical performance evaluation constraints, trend prediction is performed based on the reactor load data to obtain the load trend prediction result. Then, combined with the electrical performance evaluation constraints, the reactor is adjusted and optimized to generate a second optimization strategy for reactor adjustment. Specifically, when the electrical performance evaluation result meets the electrical performance evaluation constraints, the system automatically cleans and preprocesses the reactor load data, using an ARIMA model or LSTM algorithm to remove outliers and restore the true load change trend. Subsequently, based on the processed data, power system operating rules, and historical data, the system selects a suitable prediction model to predict the load trend: for simple systems, linear regression combined with a moving average method is used; for complex systems, a neural network model is used to accurately predict the load trend over the next few hours or days. Based on the prediction, the system combines the electrical performance evaluation constraints and uses a genetic algorithm or particle swarm optimization algorithm to optimize the reactor adjustment parameters in multiple rounds to ensure that requirements such as reactive power compensation accuracy, voltage regulation stability, and upper limit of power loss are met. During the optimization process, the system explores and adjusts the number and timing of reactive power compensation switching groups, optimizes voltage regulator parameters, and other key operations. Ultimately, it generates a precise second optimization strategy for reactor regulation, clarifies the regulation operations for different time periods under different load trends, and provides a reliable basis for the efficient and stable operation of the power system.

[0044] In one possible implementation, if the electrical performance evaluation result satisfies the electrical performance evaluation constraints, a trend prediction is performed based on the reactor load data to obtain a load trend prediction result. This result is then combined with the electrical performance evaluation constraints to optimize the reactor adjustment, generating a second optimization strategy for reactor adjustment. Step S500 further includes step S510, where a change rate evaluation is performed based on the load trend prediction result to obtain the load change rate. Specifically, when evaluating the change rate based on the load trend prediction result to obtain the load change rate, the system automatically analyzes the data details of the load trend prediction result, including the reactor load size, change rate, and fluctuation period at different future time periods. The system uses a built-in data cleaning algorithm to automatically remove outliers caused by sensor failures or electromagnetic interference, ensuring the data is accurate and reliable. Subsequently, the system selects appropriate metrics based on the power system operating characteristics and load change patterns. For example, when the power system operates smoothly and fluctuates slowly, the standard deviation is used to measure the dispersion of the load deviation from the mean; when the system is complex and exhibits significant nonlinear changes, the slope change rate is used to capture the speed of the increasing or decreasing trend. The system calculates load fluctuations in different time periods using formulas, such as substituting the standard deviation formula, or calculating the rate of change of load difference between adjacent time periods using the slope change rate. Finally, the system organizes and normalizes the calculation results to obtain the load variation degree, providing a scientific basis for subsequent reactor adjustment decisions.

[0045] Step S520: Determine whether the load change rate is greater than or equal to the predetermined load change rate. Specifically, when determining whether the load change rate is greater than or equal to the predetermined load change rate, the system automatically analyzes the setting basis of the predetermined load change rate, combining historical operating data of the power system, electricity consumption patterns, seasonal characteristics, and system fluctuation tolerance parameters to comprehensively analyze the drastic load changes during the summer peak electricity consumption period and the system's carrying capacity after upgrades, ensuring that the predetermined value is scientifically reasonable. Subsequently, the system accurately acquires the load change rate value, ensuring the data is authentic, reliable, and accurately reflects the load fluctuation situation by checking the data acquisition source, sensor accuracy, acquisition frequency, and algorithm processing flow. The system makes a judgment based on preset logic: if the load change rate is greater than or equal to the predetermined value, it indicates that the load fluctuation is severe, and the system will generate adjustment suggestions, such as optimizing reactor switching or voltage regulation; if it is less than the predetermined value, it indicates that the load fluctuation is moderate, and the system records the current situation for continuous monitoring. Finally, the system forms corresponding decision suggestions based on the judgment results. If adjustment is required, a detailed adjustment plan is automatically generated and submitted to the control department; if no adjustment is required, the data is recorded for subsequent analysis and traceability.

[0046] Step S530: If the load change rate is greater than or equal to the predetermined load change rate, an adjustment decision is made for the reactor based on the load trend prediction result, obtaining the third space for reactor adjustment decision. Specifically, when the reactor is adaptively adjusted according to the first and second optimization strategies for reactor adjustment, the system automatically analyzes the core objectives of the two optimization strategies. The first optimization strategy focuses on normal load fluctuations, formulating time-specific reactor switching schemes based on historical load curves to maintain reactive power balance; the second optimization strategy targets complex extreme conditions, handling sudden situations such as concentrated equipment startup, dynamically optimizing voltage regulation parameters, and rapidly adjusting the number of switching groups. The system receives data such as load size, rate of change, and power factor collected by high-precision sensors at each node of the power grid in real time, and judges the current load state and strategy matching status through fast data transmission and processing technology. If the load is stable, the adjustment is executed in an orderly manner according to the first strategy; if the load changes drastically, the second strategy takes precedence, and an emergency plan is activated, such as rapidly increasing or decreasing the number of switching groups and finely adjusting the voltage regulation tap position. During execution, the system translates the strategy into automated instructions and inputs them into the intelligent control system. It employs precise algorithms to ensure the accuracy of adjustment actions and monitors the adjustment effect in real time. If a deviation is detected, the system immediately backtracks and adjusts to ensure the stable operation of the power system.

[0047] Step S540: Based on the three channels of electrical performance evaluation, the system performs optimization analysis on the third space of reactor regulation decision according to the electrical performance evaluation constraints to establish a fourth space for reactor regulation decision. Specifically, when performing optimization analysis on the third space of reactor regulation decision based on the three channels of electrical performance evaluation and according to the electrical performance evaluation constraints to establish the fourth space, the system first analyzes the functions and evaluation indicators of the three channels, clarifies the calculation methods, data sources, and weight allocation of indicators in the three major areas of reactive power compensation accuracy, voltage regulation stability, and power loss, and analyzes the electrical performance evaluation constraints, clarifying specific constraints such as minimum reactive power compensation accuracy, voltage fluctuation limit and recovery time, and upper limit of power loss, providing boundaries for optimization. Subsequently, the system sequentially inputs the regulation decision schemes of the third space into the three channels for analysis: in the reactive power compensation accuracy channel, the deviation rate is calculated and sorted; in the voltage regulation stability channel, it is determined whether the standard is met and schemes that do not meet the standard are marked; in the power loss channel, schemes that exceed the standard are compared with the upper limit of loss. Next, the system performs a comprehensive weighted evaluation of the schemes based on weight allocation. Reactive power compensation accuracy and voltage regulation stability have higher weights due to their significant impact, while power loss has a lower weight. The system calculates a comprehensive score through weighted summation and selects the highest-scoring schemes to form the fourth space. Ultimately, the fourth space generated by the system provides a reliable basis for precise control and efficient operation of the power system, ensuring that reactor performance reaches its optimal state.

[0048] Step S550: The reactor regulation fitness evaluation network is used to maximize the regulation fitness of the fourth space of the reactor regulation decision, outputting the second optimization strategy for reactor regulation. Specifically, when the reactor regulation fitness evaluation network is used to maximize the regulation fitness of the fourth space to output the second optimization strategy for reactor regulation, the system first analyzes the network architecture and operating logic, calculating the fitness score through multi-dimensional information such as the timeliness of reactive power compensation, the smoothness of voltage regulation, and the rationality of power loss. Subsequently, the system accurately inputs each scheme in the fourth space according to the network requirements, organizing key data such as switching time series and voltage regulation parameters. The network calculates the regulation fitness score of each scheme using its built-in algorithm, evaluating the schemes' advantages and disadvantages in terms of system stability, load matching, and operating efficiency, and sorting the scores to select high-quality schemes. The system comprehensively considers real-time operating conditions, recent changes in operating conditions, and potential risks, prioritizing schemes with strong emergency adaptability. After multiple rounds of optimization, the second optimization strategy for reactor regulation is finally generated, clarifying the precise regulation methods under different operating conditions and providing a scientific basis for the stable and efficient operation of the power system.

[0049] Step S600: Adaptive load regulation of the reactor is performed according to the first and second optimization strategies for reactor adjustment. Specifically, when adaptive load regulation of the reactor is performed according to the first and second optimization strategies, the system first analyzes the core content and applicable scope of the two strategies. The first optimization strategy addresses normal load fluctuations by formulating time-based switching schemes based on historical load curves to maintain reactive power balance. The second optimization strategy addresses complex extreme conditions, such as sudden load changes or concentrated equipment startup, by dynamically optimizing voltage regulation parameters and rapidly adjusting the number of switching groups. The system collects data such as current, voltage, power factor, and load change rate of the grid nodes in real time, and quickly analyzes and matches the strategies. When the load is stable, the reactor operating status is gradually adjusted according to the first strategy; when the load changes drastically, the second strategy is used for rapid response, addressing fluctuations by increasing or decreasing the number of switching groups and optimizing the position of voltage regulation taps. During execution, the system converts the strategies into automated commands, operates precisely through the intelligent control system, and monitors the regulation effect in real time. If a deviation is detected, the system will automatically backtrack and analyze and adjust the strategy to ensure that reactive power compensation, voltage stability and load adaptability all meet the standards, thereby achieving efficient and stable operation of the power system.

[0050] In the above text, refer to Figure 1 A reactor load regulation method based on electrical performance optimization according to an embodiment of the present invention is described in detail. Next, reference will be made to... Figure 2 A reactor load regulation system based on electrical performance optimization according to an embodiment of the present invention is described.

[0051] The reactor load regulation system based on electrical performance optimization according to embodiments of the present invention solves the technical problem in the prior art that the regulation of reactors cannot adapt to complex load changes, resulting in low regulation accuracy and poor electrical performance. It achieves the technical effect of improving reactor regulation accuracy and optimizing electrical performance. The reactor load regulation system based on electrical performance optimization includes: a real-time monitoring module 10, an evaluation result acquisition module 20, an evaluation result judgment module 30, a regulation optimization module 40, a load trend prediction result acquisition module 50, and an adaptive load regulation module 60.

[0052] The real-time monitoring module 10 is used to monitor the reactor in real time and obtain reactor monitoring data and reactor load data.

[0053] The evaluation result acquisition module 20 is used to input the reactor monitoring data into the three-channel electrical performance evaluation to obtain the electrical performance evaluation result.

[0054] The evaluation result judgment module 30 is used to determine whether the electrical performance evaluation result meets the electrical performance evaluation constraints.

[0055] The adjustment optimization module 40 is used to perform adjustment optimization on the reactor based on the reactor load data and the electrical performance evaluation constraints if the electrical performance evaluation result does not meet the electrical performance evaluation constraints, and generate a first optimization strategy for reactor adjustment.

[0056] The load trend prediction result acquisition module 50 is used to perform trend prediction based on the reactor load data if the electrical performance evaluation result meets the electrical performance evaluation constraints, obtain the load trend prediction result, and combine the electrical performance evaluation constraints to adjust and optimize the reactor, thereby generating a second optimization strategy for reactor adjustment.

[0057] The adaptive load adjustment module 60 is used to adaptively adjust the reactor according to the reactor adjustment first optimization strategy and the reactor adjustment second optimization strategy.

[0058] The specific configuration of the evaluation result acquisition module 20 will be described in detail below. As mentioned above, the reactor monitoring data is input into the three electrical performance evaluation channels to obtain the electrical performance evaluation results. The evaluation result acquisition module 20 further includes: an evaluation three-channel component unit, wherein the three electrical performance evaluation channels include a reactor efficiency evaluation channel, a reactor energy efficiency evaluation channel, and a reactor operation safety evaluation channel; a reactor efficiency coefficient acquisition unit, wherein the reactor efficiency coefficient acquisition unit is used to input the reactor monitoring data into the reactor efficiency evaluation channel to obtain the reactor efficiency coefficient; and a reactor energy efficiency coefficient acquisition unit. The reactor energy efficiency coefficient acquisition unit is used to input the reactor monitoring data into the reactor energy efficiency evaluation channel to obtain the reactor energy efficiency coefficient; the reactor operation safety coefficient output unit is used to input the reactor monitoring data into the reactor operation safety evaluation channel to output the reactor operation safety coefficient; the electrical performance evaluation result output unit is used to output the reactor efficiency coefficient, the reactor energy efficiency coefficient and the reactor operation safety coefficient as the electrical performance evaluation result.

[0059] The reactor monitoring data is input into the reactor efficiency evaluation channel to obtain the reactor efficiency coefficient. The reactor efficiency coefficient acquisition unit further includes: a reactor efficiency evaluation channel composition subunit, wherein the reactor efficiency evaluation channel includes S reactor efficiency evaluation models, where S is a positive integer greater than 1; an efficiency evaluation coefficient acquisition subunit, wherein the reactor monitoring data is input into the S reactor efficiency evaluation models to obtain S reactor efficiency evaluation coefficients; and a mean calculation subunit, wherein the mean calculation subunit is used to calculate the mean based on the S reactor efficiency evaluation coefficients to generate the reactor efficiency coefficient.

[0060] The specific configuration of the optimization module 40 will be described in detail below. As described above, if the electrical performance evaluation result does not meet the electrical performance evaluation constraints, the reactor is adjusted and optimized according to the reactor load data and the electrical performance evaluation constraints to generate a first optimization strategy for reactor adjustment. The adjustment optimization module 40 further includes: an adjustment decision unit, which is used to make adjustment decisions for the reactor according to the reactor load data to obtain a first space for reactor adjustment decisions; an optimization analysis unit, which is used to perform optimization analysis on the first space for reactor adjustment decisions based on the three channels of electrical performance evaluation and the electrical performance evaluation constraints to establish a second space for reactor adjustment decisions; and a first optimization strategy output unit, which is used to introduce a reactor adjustment fitness evaluation network and perform adjustment fitness maximization optimization on the second space for reactor adjustment decisions according to the reactor adjustment fitness evaluation network to output the first optimization strategy for reactor adjustment. The reactor adjustment fitness evaluation network includes reactor efficiency weight, reactor energy efficiency weight, and reactor operation safety weight.

[0061] The reactor adjustment decision unit further includes: a control scheme retrieval subunit, which performs control scheme retrieval on the reactor based on the reactor load data to obtain a retrieval control scheme set; a data cleaning subunit, which performs data cleaning on the retrieval control scheme set to obtain a reactor control space; a trigger range analysis subunit, which performs trigger range analysis on each dimension of the reactor control space to establish a reactor control trigger domain; and an adjustment decision subunit, which performs adjustment decisions on the reactor based on the reactor control trigger domain to generate the reactor adjustment decision first space.

[0062] Specifically, based on the three channels of electrical performance evaluation, an optimization analysis is performed on the first space of reactor adjustment decisions according to the electrical performance evaluation constraints to establish a second space of reactor adjustment decisions. The optimization analysis unit further includes: a decision extraction subunit, which is used to extract the k-th reactor adjustment decision according to the first space of reactor adjustment decisions, where k is a positive integer; a state prediction subunit, which is used to predict the state of the reactor according to the k-th reactor adjustment decision to obtain the k-th state prediction result of the reactor; and a decision electrical performance evaluation result acquisition subunit, which is used to obtain the k-th state prediction result of the reactor. The results are input into the three channels of the electrical performance evaluation to obtain the electrical performance evaluation result of the k-th decision; the electrical performance evaluation constraint judgment subunit is used to determine whether the electrical performance evaluation result of the k-th decision satisfies the electrical performance evaluation constraints; the decision second space addition subunit is used to add the reactor adjustment k-th decision to the reactor adjustment decision second space if the electrical performance evaluation result of the k-th decision satisfies the electrical performance evaluation constraints; the decision elimination subunit is used to eliminate the reactor adjustment k-th decision if the electrical performance evaluation result of the k-th decision does not satisfy the electrical performance evaluation constraints.

[0063] The specific configuration of the load trend prediction result acquisition module 50 will be described in detail below. As mentioned above, if the electrical performance evaluation result meets the electrical performance evaluation constraints, a trend prediction is performed based on the reactor load data to obtain the load trend prediction result. The reactor is then adjusted and optimized in conjunction with the electrical performance evaluation constraints to generate a second optimization strategy for reactor adjustment. The load trend prediction result acquisition module 50 further includes: a variability evaluation unit, used to evaluate the variability based on the load trend prediction result to obtain the load variability; a predetermined load variability judgment unit, used to determine whether the load variability is greater than or equal to a predetermined load variability; and a decision third space acquisition unit, used to determine whether the decision third space... The load change rate acquisition unit is used to make adjustment decisions for the reactor based on the load trend prediction results if the load change rate is greater than or equal to the predetermined load change rate, thereby obtaining a third space for reactor adjustment decisions. The fourth space construction unit is used to perform optimization analysis on the third space for reactor adjustment decisions based on the three channels of electrical performance evaluation and the constraints of the electrical performance evaluation, thereby establishing a fourth space for reactor adjustment decisions. The second optimization strategy output unit is used to perform adjustment fitness maximization optimization on the fourth space for reactor adjustment decisions based on the reactor adjustment fitness evaluation network, and output the second optimization strategy for reactor adjustment.

[0064] The reactor load regulation system based on electrical performance optimization provided in the embodiments of the present invention can execute the reactor load regulation method based on electrical performance optimization provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0065] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0066] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A reactor load regulation method based on electrical performance optimization, characterized in that, The method includes: Real-time monitoring of the reactor is performed to obtain reactor monitoring data and reactor load data; The reactor monitoring data is input into the three-channel electrical performance evaluation system to obtain the electrical performance evaluation results. Determine whether the electrical performance evaluation results meet the electrical performance evaluation constraints; If the electrical performance evaluation result does not meet the electrical performance evaluation constraint, the reactor is adjusted and optimized according to the reactor load data and the electrical performance evaluation constraint to generate a first optimization strategy for reactor adjustment. If the electrical performance evaluation result satisfies the electrical performance evaluation constraint, trend prediction is performed based on the reactor load data to obtain the load trend prediction result, and the reactor is adjusted and optimized in combination with the electrical performance evaluation constraint to generate a second optimization strategy for reactor adjustment. The reactor is adaptively load regulated according to the first optimization strategy and the second optimization strategy for reactor regulation. The reactor monitoring data is input into the three-channel electrical performance evaluation system to obtain the electrical performance evaluation results, including: The three channels for electrical performance evaluation include a reactor efficiency evaluation channel, a reactor energy efficiency evaluation channel, and a reactor operation safety evaluation channel. The reactor monitoring data is input into the reactor efficiency evaluation channel to obtain the reactor efficiency coefficient. Input the reactor monitoring data into the reactor energy efficiency evaluation channel to obtain the reactor energy efficiency coefficient; The reactor monitoring data is input into the reactor operation safety evaluation channel, and the reactor operation safety factor is output. The reactor efficiency coefficient, the reactor energy efficiency coefficient, and the reactor operating safety coefficient are output as the electrical performance evaluation results; Specifically, the reactor monitoring data is input into the reactor efficiency evaluation channel to obtain the reactor efficiency coefficient, including: The reactor performance evaluation channel includes S reactor performance evaluation models, where S is a positive integer greater than 1; The reactor monitoring data is input into the S reactor performance evaluation models to obtain S reactor performance evaluation coefficients; The reactor efficiency coefficient is generated by calculating the mean of the S reactor efficiency evaluation coefficients. Wherein, if the electrical performance evaluation result satisfies the electrical performance evaluation constraint, a trend prediction is performed based on the reactor load data to obtain a load trend prediction result, and the reactor is adjusted and optimized in conjunction with the electrical performance evaluation constraint to generate a second optimization strategy for reactor adjustment, including: The degree of load variability is evaluated based on the load trend prediction results to obtain the load variability. Determine whether the load variation is greater than or equal to the predetermined load variation. If the load variation is greater than or equal to the predetermined load variation, an adjustment decision is made for the reactor based on the load trend prediction result to obtain the third space for reactor adjustment decision. Based on the three channels of electrical performance evaluation, an optimization analysis is performed on the third space of reactor adjustment decision according to the constraints of electrical performance evaluation to establish the fourth space of reactor adjustment decision. Based on the reactor adjustment fitness evaluation network, the fourth space of the reactor adjustment decision is optimized to maximize the adjustment fitness, and the second optimization strategy for reactor adjustment is output. If the electrical performance evaluation result does not meet the electrical performance evaluation constraints, the reactor is adjusted and optimized based on the reactor load data and the electrical performance evaluation constraints to generate a first optimization strategy for reactor adjustment, including: Based on the reactor load data, an adjustment decision is made for the reactor to obtain a first space for reactor adjustment decision. Based on the three channels of electrical performance evaluation, an optimization analysis is performed on the first space of reactor adjustment decision according to the constraints of electrical performance evaluation to establish the second space of reactor adjustment decision. A reactor regulation fitness evaluation network is introduced, and the second space of reactor regulation decision is optimized to maximize the regulation fitness based on the reactor regulation fitness evaluation network, and the first optimization strategy of reactor regulation is output. The reactor regulation fitness evaluation network includes reactor efficiency weight, reactor energy efficiency weight and reactor operation safety weight. Based on the reactor load data, an adjustment decision is made for the reactor to obtain a first space for reactor adjustment decisions, including: Based on the reactor load data, a control scheme retrieval is performed on the reactor to obtain a set of retrieved control schemes; Data cleaning is performed based on the aforementioned retrieval control scheme set to obtain the reactor control space; Based on the reactor control space, the trigger range of each dimension is analyzed to establish the reactor control trigger domain; Based on the reactor control trigger domain, an adjustment decision is made on the reactor to generate the first space of the reactor adjustment decision; Based on the three channels of electrical performance evaluation, an optimization analysis is performed on the first space of reactor adjustment decision according to the constraints of the electrical performance evaluation to establish a second space of reactor adjustment decision, including: Based on the reactor adjustment decision first space, extract the reactor adjustment k-th decision, where k is a positive integer; Based on the k-th decision of reactor adjustment, the state prediction of the reactor is performed to obtain the k-th state prediction result of the reactor. The prediction result of the k-th state of the reactor is input into the three channels of the electrical performance evaluation to obtain the decision electrical performance evaluation result of the k-th state. Determine whether the electrical performance evaluation result of the k-th decision satisfies the electrical performance evaluation constraints; If the electrical performance evaluation result of the k-th decision satisfies the electrical performance evaluation constraint, the k-th decision of reactor adjustment is added to the second space of reactor adjustment decision. If the electrical performance evaluation result of the k-th decision does not meet the electrical performance evaluation constraints, the k-th decision for reactor adjustment is eliminated.

2. A reactor load regulation system based on electrical performance optimization, characterized in that, The system is used to implement the reactor load regulation method based on electrical performance optimization as described in claim 1, and the system includes: The real-time monitoring module is used to monitor the reactor in real time and obtain reactor monitoring data and reactor load data. The evaluation result acquisition module is used to input the reactor monitoring data into the three-channel electrical performance evaluation system to obtain the electrical performance evaluation result. An evaluation result judgment module is used to determine whether the electrical performance evaluation result meets the electrical performance evaluation constraints. An adjustment optimization module is used to perform adjustment optimization on the reactor based on the reactor load data and the electrical performance evaluation constraints if the electrical performance evaluation result does not meet the electrical performance evaluation constraints, and generate a first optimization strategy for reactor adjustment. The load trend prediction result acquisition module is used to perform trend prediction based on the reactor load data if the electrical performance evaluation result meets the electrical performance evaluation constraints, obtain the load trend prediction result, and combine the electrical performance evaluation constraints to adjust and optimize the reactor, thereby generating a second optimization strategy for reactor adjustment. An adaptive load adjustment module is used to adaptively adjust the load of the reactor according to a first optimization strategy and a second optimization strategy for reactor adjustment.

Images