Industrial Internet cloud platform based on data intelligence

Abstract

The present invention discloses an industrial Internet cloud platform based on data intelligence, which relates to the technical field of industrial Internet, including a power load dynamic analysis module, which obtains the power load dynamic information of each transformer in real time, and analyzes it after acquisition, predicts the influence of power demand fluctuation of power equipment on the load of each transformer, and divides each transformer into high-load transformer, medium-load transformer and low-load transformer according to the prediction result; a load adjustment mechanism module, which constructs a load adjustment mechanism for adjusting the power load of the transformer according to the division result of each transformer; and an adjustment feedback evaluation module, which collects the load adjustment feedback information of each transformer in real time during the process of load adjustment of each transformer by the load adjustment mechanism, and analyzes it after collection. The present invention solves the problem of untimely load adjustment of transformers under power demand fluctuation, and improves the response speed of load adjustment and system stability.

Description

Technical Field

[0001] The present invention relates to the field of industrial Internet technology, and in particular to an industrial Internet cloud platform based on data intelligence. Background Art

[0002] The Industrial Internet cloud platform is a digital platform that helps industrial enterprises achieve equipment interconnection, data collection, production process optimization and remote management through the Internet of Things, cloud computing, big data and artificial intelligence technologies, aiming to improve production efficiency, reduce operating costs and improve product quality. It can monitor the operating status of equipment in real time, analyze production data, predict faults and optimize maintenance, thereby reducing downtime and optimizing resource allocation. The Industrial Internet cloud platform based on data intelligence further utilizes big data analysis and machine learning to mine potential patterns and trends from massive industrial data, provide more accurate predictions and optimization suggestions, and help enterprises make more intelligent operational decisions in a dynamic environment.

[0003] The existing industrial Internet cloud platform technology based on data intelligence is a solution that integrates the Internet of Things, cloud computing, big data analysis and artificial intelligence, and is widely used in the production and operation of industrial enterprises. The platform collects multi-dimensional data from industrial equipment in real time, including key parameters such as temperature, pressure, speed, etc., through the Internet of Things technology deployed on equipment, sensors and production lines, and transmits these data to the cloud for storage and processing. Subsequently, using big data analysis and machine learning algorithms, the platform can monitor the operating status of equipment in real time, detect potential failures in production, predict equipment maintenance time, and optimize production processes through data modeling. At the same time, based on the deep learning ability of data, the platform can also provide dynamic adjustment suggestions for production lines, supply chain optimization strategies and market demand forecasts, thereby helping enterprises improve operational efficiency, reduce resource waste, and enhance production flexibility and sustainability. Overall, the existing technology not only improves the refined management of industrial enterprises on the operation process, but also provides strong technical support for achieving the goals of intelligent manufacturing and Industry 4.0.

[0004] The prior art has the following deficiencies:

[0005] In large-scale industrial parks, the existing industrial Internet cloud platform technology based on data intelligence is used to monitor the load status of multiple power transformers in real time. However, during a specific time period, with the frequent start and stop of industrial equipment, the power demand will fluctuate violently, resulting in frequent changes in load. Because these load fluctuations are too fast, it is difficult for the existing platform to predict and respond in time, resulting in the transformer adjustment speed not keeping up with the changes in power demand, and overload or underload operation may occur. The existing technology cannot quickly adjust the load distribution of power equipment, causing the transformer to operate under inappropriate load for a long time, increasing the risk of equipment failure, resulting in excessive energy consumption or reduced efficiency. Furthermore, this fluctuation in the power system will not only affect the normal operation of industrial equipment, which may cause unstable equipment operation, but also lead to reduced production efficiency. In severe cases, it may even cause equipment shutdown, affecting the stability of the entire industrial production line.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an industrial Internet cloud platform based on data intelligence to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: an industrial Internet cloud platform based on data intelligence, including a power demand modeling module, a power load dynamic analysis module, a load regulation mechanism module, a regulation feedback evaluation module and an intelligent optimization monitoring module;

[0009] The power demand modeling module determines the type and power demand of industrial equipment according to the operation objectives of the power system in the industrial park, and builds a basic data model of power demand and load changes to provide a reference for subsequent real-time data collection and load regulation;

[0010] The power load dynamic analysis module obtains the power load dynamic information of each transformer in real time, analyzes it after acquisition, predicts the impact of power demand fluctuations of power equipment on the load of each transformer, and divides each transformer into high-load transformer, medium-load transformer and low-load transformer according to the prediction results;

[0011] The load regulation mechanism module constructs a load regulation mechanism for regulating the power load of the transformer according to the division results of each transformer, and performs different load regulation operations on the high-load transformer, the medium-load transformer and the low-load transformer respectively;

[0012] The regulation feedback evaluation module collects the load adjustment feedback information of each transformer in real time during the process of load regulation of each transformer by the load regulation mechanism, and analyzes it after collection to evaluate whether the regulation degree of each transformer by the load regulation mechanism can meet the balance requirements of power demand fluctuations, and optimizes the load regulation mechanism according to the evaluation results;

[0013] The intelligent optimization monitoring module conducts long-term monitoring and comprehensive analysis of the load data, feedback information and adjustment records in the entire load regulation process, continuously optimizes the load regulation mechanism based on the intelligent learning algorithm, and improves the regulation strategy in real time.

[0014] Preferably, in the power load dynamic analysis module, after the power load dynamic information of each transformer is acquired in real time, it is preprocessed to extract the power load dynamic response information and power system fluctuation assessment information from the preprocessed power load dynamic information of each transformer, and the information is analyzed after extraction to generate the load response coefficient and load fluctuation index of each transformer respectively.

[0015] Preferably, the logic for obtaining the load response coefficient and load fluctuation index of each transformer is as follows:

[0016] The power load dynamic response information is extracted from the preprocessed power load dynamic information of each transformer, including the actual power load of each transformer at different times within a period of time, the adjustment rate, and the actual power load of each transformer at different times in the historical time period, and calibrated as , and , Indicates A transformer in a period of time The actual power load at the moment, Indicates A transformer in a period of time The adjustment rate of time, Indicates Transformers in the historical period The actual power load at the moment, , , , , and are all positive integers;

[0017] Calculate the historical load change rate of each transformer. The specific calculation formula is as follows:

[0018] ;

[0019] In the formula, For the Historical load change rate of each transformer;

[0020] Calculate the load response coefficient of each transformer. The specific calculation formula is as follows:

[0021] ;

[0022] In the formula, For the The load response factor of each transformer;

[0023] The power system fluctuation assessment information is extracted from the pre-processed power load dynamic information of each transformer, including the voltage of each transformer at different times within a period of time and the preset power load, and calibrated as and , Indicates A transformer in a period of time The voltage at the moment, Indicates A transformer in a period of time The preset power load at the time;

[0024] Calculate the load fluctuation index of each transformer. The specific calculation formula is as follows:

[0025] ;

[0026] In the formula, For the The load fluctuation index of a transformer.

[0027] Preferably, when generating the load response coefficient of each transformer and load fluctuation index Finally, a load impact prediction model is constructed, and the load impact coefficient of each transformer is generated by weighted summation. , and the load influence coefficient of each transformer generated The load impact factor threshold interval is set in advance. The comparison is carried out, and the influence of the power demand fluctuation of the power equipment on the load of each transformer is predicted according to the comparison results. According to the prediction results, each transformer is divided into high-load transformer, medium-load transformer and low-load transformer. The specific comparison analysis and division are as follows:

[0028] like , the power demand fluctuation of the power equipment has a low impact on the load of the transformer, and the transformer is classified as a low-load transformer;

[0029] like ,The power demand fluctuation of the power equipment has a high impact on the load of the transformer, and the transformer is classified as a high-load transformer.

[0030] Preferably, in the load regulation mechanism module, a load regulation mechanism for regulating the transformer power load is constructed according to the division results of each transformer, specifically including: according to the division results of high-load transformers, medium-load transformers and low-load transformers, different load regulation parameters are set respectively to form a load regulation mechanism; the load regulation mechanism is based on the load influence coefficient of each transformer and the current power demand fluctuation, and automatically determines the priority and adjustment range of load adjustment through pre-set rules;

[0031] Different load regulation operations are performed on high-load transformers, medium-load transformers and low-load transformers respectively. Specifically: in high-load transformers, high-load adjustment parameters in the load regulation mechanism are used to give priority to load transfer and reduce load distribution; in medium-load transformers, standard load adjustment parameters in the load regulation mechanism are maintained to maintain the current load level and adjust the load balance; in low-load transformers, low-load adjustment parameters in the load regulation mechanism are used to reduce load regulation operations and maintain the existing load level.

[0032] Preferably, in the regulation feedback evaluation module, after the load adjustment feedback information of each transformer is collected in real time, it is preprocessed, and the load stability feedback information and voltage regulation efficiency information in the preprocessed load adjustment feedback information of each transformer are extracted, and analyzed after extraction to generate the regulation stability coefficient and voltage regulation efficiency index of each transformer respectively.

[0033] Preferably, the acquisition logic of the regulation stability coefficient and voltage regulation efficiency index of each transformer is as follows:

[0034] Extract the load stability feedback information from the pre-processed load adjustment feedback information of each transformer, including the load change, output power, average load value of the connected power equipment and the corresponding time point of each transformer at different times within a period of time after the load adjustment mechanism is used for load adjustment, and use the function to calculate the load stability feedback information of each transformer according to the time series. , and To express, For time point, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The load change at each moment, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The output power at the moment, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The average load value of the connected power equipment at the time, the time period is defined as , , is a positive integer;

[0035] Calculate the regulation stability coefficient of each transformer. The specific calculation formula is as follows:

[0036] ;

[0037] In the formula, For the The regulation stability factor of each transformer;

[0038] The voltage regulation efficiency information is extracted from the pre-processed load adjustment feedback information of each transformer, including the output voltage value, voltage recovery time, target voltage value and corresponding time point of each transformer at different times within a period of time after the load adjustment mechanism is used for load adjustment, and the function is used to perform the calculation according to the time series. , and To express, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The output voltage value at the moment, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The voltage recovery time at time Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The target voltage value at the moment;

[0039] Calculate the voltage regulation efficiency index of each transformer. The specific calculation formula is as follows:

[0040] ;

[0041] In the formula, For the The voltage regulation efficiency index of a transformer.

[0042] Preferably, when generating the regulation stability coefficient of each transformer and voltage regulation efficiency index Finally, the regulation degree evaluation model is constructed, and the regulation coefficient of each transformer is generated by weighted summation. , and the adjustment coefficients of each transformer generated The regulation coefficient thresholds of each transformer are set in advance Compare and evaluate whether the load regulation mechanism can meet the balance requirements of power demand fluctuations based on the comparison results. Optimize the load regulation mechanism based on the evaluation results. The specific comparison and analysis are as follows:

[0043] like The load regulation mechanism cannot meet the balance requirements of power demand fluctuations. The load regulation mechanism needs to be optimized, including: adjusting the load transfer mechanism of high-load transformers to increase the load transfer speed; improving the load balance adjustment parameters of medium-load transformers to optimize the adjustment sensitivity; slowing down the adjustment range of low-load transformers to maintain the existing load level;

[0044] like The degree of regulation of the transformer by the load regulation mechanism can meet the balancing requirements of power demand fluctuations, and there is no need to optimize the load regulation mechanism.

[0045] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0046] 1. The present invention obtains the dynamic information of the power load of each transformer in real time and conducts in-depth analysis. The system can quickly respond and predict the impact of power demand fluctuations on the load of each transformer when the load changes frequently. This not only ensures that the system can adjust the load regulation mechanism according to real-time data, but also ensures that each transformer can quickly and accurately regulate the load under different power demand fluctuations through accurate calculation of the load response coefficient and load fluctuation index. In this way, the problem of transformer overload or underload caused by response lag is effectively avoided, thereby significantly improving the operating efficiency of the system.

[0047] 2. The load regulation mechanism in the present invention sets different regulation parameters and regulation strategies according to the load type of the transformer (high load, medium load, low load), and adopts different regulation methods for different load conditions. This differentiated regulation method avoids a one-size-fits-all regulation operation, ensuring that high-load transformers can quickly reduce their loads, medium-load transformers can balance their loads, and low-load transformers can maintain system stability and reduce unnecessary operations. This hierarchical regulation method improves the overall regulation efficiency of the power system, reduces energy consumption, and effectively avoids over-regulation or under-regulation.

[0048] 3. By introducing an intelligent optimization monitoring module, the present invention enables the system to not only monitor real-time load changes, but also conduct long-term analysis and self-optimization based on historical data. The intelligent learning algorithm can continuously optimize the regulation strategy based on past load data and feedback information, so that the system can adaptively adjust when facing fluctuations in power demand. This self-learning and dynamic optimization capability ensures the continuous improvement of the regulation mechanism, which not only reduces manual intervention, but also ensures that the system is always in the best regulation state in different time periods, effectively reducing equipment failure rate and energy consumption costs, and greatly improving the system's operational stability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0050] Figure 1 This is a module schematic diagram of the industrial Internet cloud platform based on data intelligence of the present invention. DETAILED DESCRIPTION

[0051] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0052] The present invention provides Figure 1 The data intelligence-based industrial Internet cloud platform shown includes a power demand modeling module, a power load dynamic analysis module, a load regulation mechanism module, a regulation feedback evaluation module, and an intelligent optimization monitoring module;

[0053] The power demand modeling module determines the type and power demand of industrial equipment according to the operation objectives of the power system in the industrial park, and builds a basic data model of power demand and load changes to provide a reference for subsequent real-time data collection and load regulation;

[0054] Software can be used in a variety of ways to determine the type and power demand of industrial equipment. First, the model, workload, operating hours and other parameters of each device can be obtained by extracting relevant information from the existing industrial equipment management database. Then, based on the overall operating goals of the power system (such as maximizing production efficiency and minimizing energy consumption), data analysis algorithms are used to classify and predict the energy consumption and operating modes of various types of equipment to determine the type of equipment and its power demand. This process can be combined to form a detailed load demand model for each device through historical power consumption data analysis, equipment operation logs and real-time sensor data collection.

[0055] The construction of a basic data model for power demand and load changes can be achieved through software algorithms. The specific steps are based on the aforementioned determined equipment types and power demand, combined with the historical power consumption data, operation cycle, load fluctuations and other information of each device, and using mathematical models such as regression analysis and time series analysis to predict future power demand trends. By real-time monitoring of the daily operating status of various types of equipment and combining external influencing factors (such as seasonal load fluctuations, equipment maintenance plans, etc.), the model is gradually improved to provide more accurate load forecasts. In addition, clustering algorithms can be used to group and manage equipment, thereby building a more refined load change model to provide a reference for subsequent load regulation.

[0056] The reason for this is that the power demand in the industrial park fluctuates frequently, especially when multiple devices are frequently started and stopped, and the prediction of power demand becomes extremely critical. By accurately constructing the basic data model of power demand and load changes, the system can make accurate predictions of future power demand changes, thereby providing the necessary basis for subsequent real-time data collection and load regulation. In this way, the system's prediction accuracy of power demand fluctuations can be greatly improved, so as to better distribute the load of the transformer, avoid overload or underload operation problems, reduce the risk of equipment failure, and improve the energy efficiency of the system. Ultimately, the construction of this data model can effectively solve the problems of reduced efficiency, increased energy consumption, and equipment downtime in the existing technology due to rapid load fluctuations and the difficulty of the system to predict and respond in time.

[0057] The power load dynamic analysis module obtains the power load dynamic information of each transformer in real time, analyzes it after acquisition, predicts the impact of power demand fluctuations of power equipment on the load of each transformer, and divides each transformer into high-load transformer, medium-load transformer and low-load transformer according to the prediction results;

[0058] In this embodiment, in the power load dynamic analysis module, after the power load dynamic information of each transformer is acquired in real time, it is preprocessed to extract the power load dynamic response information and power system fluctuation assessment information from the preprocessed power load dynamic information of each transformer, and the information is analyzed after extraction to generate the load response coefficient and load fluctuation index of each transformer respectively.

[0059] The dynamic information of power load can be obtained through a real-time monitoring system with multiple channels and devices. First, each transformer can be equipped with smart sensors that can monitor the power parameters of the transformer, such as voltage, current and power, and generate real-time load data. The sensors are connected to the industrial Internet cloud platform through the Internet of Things (IoT) technology, and edge computing devices are used for preliminary data processing to reduce data transmission delays. At the same time, the data is transmitted to the cloud platform through wireless communication protocols (such as 4G / 5G) or wired networks (such as optical fiber or dedicated cables). In the cloud, the system receives the load data of each transformer in real time through the data acquisition interface and stores it in the database for subsequent analysis. The entire process runs automatically without human intervention, ensuring real-time and continuous data updating.

[0060] The purpose of preprocessing is to improve the quality of data, reduce noise and errors, and ensure the accuracy of subsequent analysis. Raw data often contain noise, erroneous data or missing values, and using these data directly may lead to incorrect analysis results. Preprocessing usually includes several steps: first, data cleaning, removing or correcting outliers and missing data, such as filling missing data through interpolation or removing data points that deviate from a reasonable range. Secondly, data normalization is another important step, which unifies the values ​​of different scales to the same range (such as 0 to 1) so that different features have consistent weights in subsequent analysis. Finally, data noise reduction is performed, and filtering algorithms (such as Kalman filtering or moving average filtering) are used to smooth the data and eliminate instantaneous extreme fluctuations. The preprocessing process can be executed on the cloud platform by writing an automated algorithm to process the collected power load data in real time to ensure that the data is standardized and of high quality before entering the analysis stage.

[0061] Extracting "power load dynamic response information" and "power system fluctuation assessment information" from the preprocessed power load dynamic information can be achieved through a variety of data analysis and feature extraction algorithms. First, in the preprocessed data, the system can use feature selection algorithms (such as principal component analysis PCA or information gain method) to preliminarily screen the data and find features with high correlation with power load changes. For "power load dynamic response information", the extraction method can be extracted by analyzing the rate of change of load over time, the real-time response of transformer load, etc. The specific operation includes calculating the derivative (rate of change) of the load and the amplitude of each load fluctuation. For "power system fluctuation assessment information", it is necessary to conduct in-depth analysis of the load fluctuation trend, historical fluctuation data, and the fluctuation stability of the current power system to extract features reflecting system stability and load fluctuation frequency. This can be achieved through time series analysis (such as autoregressive model ARIMA) or frequency domain analysis (such as Fourier transform) to capture periodic fluctuations or abnormal fluctuations in the data. All extracted information is stored in the form of structured data for subsequent algorithms to calculate response coefficients and fluctuation indexes.

[0062] In this embodiment, the logic for obtaining the load response coefficient and load fluctuation index of each transformer is as follows:

[0063] The power load dynamic response information is extracted from the preprocessed power load dynamic information of each transformer, including the actual power load of each transformer at different times within a period of time, the adjustment rate, and the actual power load of each transformer at different times in the historical time period, and calibrated as , and , Indicates A transformer in a period of time The actual power load at the moment, Indicates A transformer in a period of time The adjustment rate of time, Indicates Transformers in the historical period The actual power load at the moment, , , , , and are all positive integers;

[0064] Extracting the dynamic response information of the power load of each transformer after preprocessing, including the actual power load, adjustment rate and historical load data, can be achieved through intelligent sensor networks and industrial Internet of Things (IIoT) systems. First, the actual power load data is obtained through the current and voltage sensors in the real-time monitoring equipment of the transformer. These sensors are installed on the output port of the transformer and can monitor the output power of the transformer in real time. The data is collected by the IoT device and uploaded to the cloud server for subsequent analysis. The adjustment rate is obtained by collecting the control signal of the transformer in real time. The control signal of the transformer reflects the response speed of the transformer during the load adjustment process. These control signals are also collected by the control module of the transformer and uploaded to the cloud platform after real-time processing by the edge computing device. The historical load data is extracted from the data storage module. These data come from long-term load monitoring records, usually based on time series data stored according to daily, weekly and monthly load changes. Through the time series database or big data storage system (such as Hadoop or SQL database), the software can retrieve the actual power load data in the historical period for the calculation of the load change rate. After preprocessing, the relevant information in a specific time period is extracted, analyzed and the load response coefficient is generated.

[0065] Calculate the historical load change rate of each transformer. The specific calculation formula is as follows:

[0066] ;

[0067] In the formula, For the Historical load change rate of each transformer;

[0068] Calculate the load response coefficient of each transformer. The specific calculation formula is as follows:

[0069] ;

[0070] In the formula, For the The load response factor of each transformer;

[0071] In this formula, the load response coefficient The calculation first takes the actual load of the transformer at each moment The numerator represents the real-time load level of the transformer, which directly affects the response capability; the historical load change rate in the denominator Used to measure load fluctuations. The greater the fluctuation, the smaller the weight; adjust the rate Indicates the regulation capability of the transformer. The higher the rate, the smaller the impact of the load, so it is placed in the denominator. By summing each moment in the entire time period, the response capability of the transformer is comprehensively calculated, and finally divided by the average value to measure the overall load response level of the transformer in the time period. This weighted summation and average calculation can accurately reflect the sensitivity and regulation capability of the transformer to load changes.

[0072] No. Load response factor of each transformer It reflects the transformer's ability to respond to load fluctuations in different time periods. The larger the load response coefficient, the lower the sensitivity of the load response when the transformer has large historical load fluctuations or a slow adjustment rate, that is, the transformer has weaker adaptability when dealing with power demand fluctuations; on the contrary, a smaller load response coefficient indicates that the transformer can quickly and effectively adapt to power demand fluctuations. Therefore, the size of the load response coefficient directly affects the degree of impact of the power demand fluctuations of power equipment on the transformer load. A larger load response coefficient indicates that the transformer has a lower load response sensitivity when dealing with power demand fluctuations. This means that the transformer is more susceptible to overloading or underloading when faced with fluctuations in power demand and requires further adjustment, while smaller This means that the transformer can adapt to load changes better and the load impact is small.

[0073] The power system fluctuation assessment information is extracted from the pre-processed power load dynamic information of each transformer, including the voltage of each transformer at different times within a period of time and the preset power load, and calibrated as and , Indicates A transformer in a period of time The voltage at the moment, Indicates A transformer in a period of time The preset power load at the time;

[0074] Extracting pre-processed power system fluctuation assessment information of each transformer, including voltage and preset power load, can be achieved through smart sensors and industrial IoT systems installed on the transformer.

[0075] Extracting the power system fluctuation assessment information of each pre-processed transformer, including voltage and preset power load, can be achieved through the intelligent sensors and industrial Internet of Things systems installed on the transformer. First, the voltage data can be monitored in real time through the voltage sensor of the transformer. The sensor will collect the voltage value of the transformer at different times and transmit the data to the central data processing system through the Internet of Things device. These data will be obtained through the data acquisition interface and stored in the real-time database. Secondly, the preset power load is set according to the operation goals and planning of the power system for the transformer, and is generated by the dispatching system in the industrial Internet cloud platform. The dispatching system dynamically generates the preset power load value of each transformer based on historical operation data, equipment operation requirements and load demand prediction model. These data can be automatically recorded by the dispatching system and stored in the database synchronously with the real-time voltage data for subsequent analysis. Through software data call and integration, the voltage and preset load of each transformer over a period of time can be extracted to form power system fluctuation assessment information, which further provides a basis for load regulation.

[0076] Calculate the load fluctuation index of each transformer. The specific calculation formula is as follows:

[0077] ;

[0078] In the formula, For the The load fluctuation index of a transformer.

[0079] This formula is used to calculate the load fluctuation index of each transformer , by measuring the relationship between load fluctuation and voltage fluctuation of the transformer at different time points, the sensitivity of the transformer to power system fluctuations is evaluated. Each operation step in the formula has a specific meaning: First, the numerator It indicates the load change of the transformer between two adjacent time points, reflecting the amplitude of load fluctuation; It represents the change of voltage at these two adjacent time points. Voltage fluctuation can indirectly reflect the stability of the system. The purpose of multiplying these two changes is to relate the load fluctuation to the voltage fluctuation and ensure that the impact of voltage change on load fluctuation is taken into account. It represents the difference between the predicted load and the actual load, and measures the impact of the prediction error on the load fluctuation. The smaller the prediction error, the more stable the system. Therefore, the larger the denominator, the smaller the exponent value. Finally, the summation symbol accumulates the load fluctuations at all times in the time period to capture the fluctuation trend in the entire time period. Finally, through Standardization is performed to ensure that the calculation results can reflect the average fluctuations over the entire time period, and the final results are limited to a reasonable numerical range through square root operations.

[0080] No. Load fluctuation index of each transformer It reflects the sensitivity of the transformer to load and voltage fluctuations over a period of time. The larger the index, the more frequent or more severe the load fluctuation of the transformer, and the greater the system instability. When the load fluctuation index is large, it means that the fluctuation of power demand of power equipment has a more significant impact on the transformer, and the transformer is more difficult to adapt to these fluctuations, which may cause the transformer to be overloaded or unstable. When it is small, it means that the transformer is relatively stable in the face of power demand fluctuations, the load fluctuation is small, the power system has little impact on the transformer, and the transformer can better adapt to load changes. Therefore, the size of the load fluctuation index is directly related to the degree of impact of power demand fluctuations on the transformer load. The larger the index, the more difficult it is for the transformer to cope with demand fluctuations and the greater the risk; the smaller the index, the more stable the transformer load and the smaller the risk.

[0081] In this embodiment, when generating the load response coefficient of each transformer and load fluctuation index Finally, a load impact prediction model is constructed, and the load impact coefficient of each transformer is generated by weighted summation. , and the load influence coefficient of each transformer generated The load impact factor threshold interval is set in advance. The comparison is carried out, and the influence of the power demand fluctuation of the power equipment on the load of each transformer is predicted according to the comparison results. According to the prediction results, each transformer is divided into high-load transformer, medium-load transformer and low-load transformer. The specific comparison analysis and division are as follows:

[0082] like , the power demand fluctuation of the power equipment has a low impact on the load of the transformer, and the transformer is classified as a low-load transformer;

[0083] This situation means that the load impact of the transformer is small, and the fluctuation of power demand of the power equipment has little effect on it. The transformer is in a low-load state and operates stably. The impact of this situation is that the transformer does not need to make additional load adjustments, can maintain the current operating state, avoid unnecessary adjustments, and thus save energy and reduce operating costs. The software can monitor the load in real time. , and compare it with Thresholds are compared and when detected Less than When the system is in a low load state, the system will automatically classify the transformer as a low load transformer. The classification can be automatically generated by the dispatching system, updated in real time and fed back to the transformer management system.

[0084] like , the influence of power demand fluctuation of power equipment on the transformer load is medium, and the transformer is classified as a medium load transformer;

[0085] This indicates that the load of the transformer is within the normal fluctuation range, the power demand has a moderate impact on it, and the transformer is in a medium load state. The impact is that although the transformer can continue to operate normally, it needs to be continuously monitored to prevent the stability from being affected when the load fluctuates greatly. The system can continuously collect load data through software and calculate , and by comparing and The software classifies the transformer as a medium-load transformer and performs regular load monitoring and recording to ensure that load fluctuations are within a controllable range.

[0086] like ,The power demand fluctuation of the power equipment has a high impact on the load of the transformer, and the transformer is classified as a high-load transformer.

[0087] This means that the load fluctuation of the transformer is large, and the fluctuation of power demand has a significant impact on it, and there is a risk of overload or underload. The impact at this time is that the transformer may be in an unstable state, and load adjustment or load redistribution needs to be carried out in time to avoid equipment failure or reduced energy efficiency. The software can detect through the real-time load monitoring system Exceed When the transformer is overloaded, the alarm is automatically triggered and the transformer is classified as a high-load transformer. At the same time, the dispatching system will automatically analyze the load distribution and adjust the load to reduce the burden on the high-load transformer to ensure safe and stable operation of the system.

[0088] When generating the load response factor for each transformer and load fluctuation index After that, the load impact prediction model can be constructed to comprehensively evaluate the load condition of the transformer. and load fluctuation index As two core parameters, the load influence coefficient is generated by weighted summation The weighted summation formula is: ;in, and are weight coefficients, which respectively indicate the contribution of load response and load fluctuation to the overall load impact. The weight coefficient setting can be dynamically adjusted according to historical data and system operation requirements. Generally speaking, if the load fluctuation of the transformer has a greater impact on the system stability, then The weight of can be appropriately increased; on the contrary, if the load response is more important (i.e., the regulation rate has a greater impact), then By weighted summation, the transformer's performance in load fluctuation and regulation ability can be comprehensively considered, thus generating a coefficient that reflects the overall load impact. , providing a basis for subsequent load regulation and classification.

[0089] The "pre-set load impact coefficient threshold interval" can be dynamically determined through the analysis of historical operating data and system performance requirements. The specific approach is to first collect and store transformer operating data over a long period of time, including historical load response coefficients, through the industrial Internet of Things platform or big data analysis tools. and load fluctuation index , and the system operating status related to these parameters, such as operating data when the load is stable, fault records when overload or underload, etc. By performing statistical analysis on these historical data, such as calculating the load influence coefficient of each transformer under stable operation and fault conditions , the threshold range for normal operation of the system can be determined. The relationship between the load influence coefficient and the transformer operating status can be analyzed by using machine learning algorithms or regression analysis models to determine a reasonable threshold range. Through dynamic adjustment and learning of the software, the system can automatically update this range according to the actual situation, ensuring that it can adapt to different power demand and load change scenarios, and realize effective monitoring of system stability.

[0090] The load regulation mechanism module constructs a load regulation mechanism for regulating the power load of the transformer according to the division results of each transformer, and performs different load regulation operations on the high-load transformer, the medium-load transformer and the low-load transformer respectively;

[0091] In this embodiment, in the load regulation mechanism module, a load regulation mechanism for regulating the transformer power load is constructed according to the division results of each transformer, specifically including: setting different load regulation parameters according to the division results of high-load transformers, medium-load transformers and low-load transformers to form a load regulation mechanism; the load regulation mechanism automatically determines the priority and adjustment range of load adjustment based on the load influence coefficient of each transformer and the current power demand fluctuation through pre-set rules;

[0092] In the load regulation mechanism module, the implementation method of constructing the load regulation mechanism according to the division results of high-load transformers, medium-load transformers and low-load transformers can be carried out through the following steps:

[0093] Based on the classification results of high-load transformers, medium-load transformers and low-load transformers, the software automatically generates an adjustment plan. Through the software scheduling module, the system sets different load adjustment parameters for each category of transformers. For high-load transformers, the software can prioritize load transfer and reduce its load distribution through the load priority setting mechanism. Load transfer is achieved through a distributed power management system, which automatically reallocates part of the power demand of high-load transformers to transformers with lighter loads. At the same time, the load adjustment parameters will take into account the current operating conditions of the power system to prevent overload.

[0094] The load regulation mechanism realizes automatic regulation based on preset rules. The software pre-sets the priority and adjustment range of load adjustment through rule-based algorithms or machine learning models (such as decision trees or reinforcement learning). The rule setting can refer to the historical operating data of the transformer and the dynamic fluctuation of power demand to form regulation strategies for different load types. For example, the software will give priority to adjusting high-load transformers when the load fluctuates greatly, and maintain the current allocation when the load is more stable. In addition, for medium-load transformers, the system moderately adjusts the load balance through standard load adjustment parameters to ensure that it works in a stable state, while the load adjustment of low-load transformers is more conservative to reduce unnecessary adjustment operations.

[0095] The entire load regulation process is monitored in real time by the software system, and the load change feedback of the transformer is obtained in real time through the industrial Internet of Things devices. The system analyzes the current regulation effect based on the feedback information, and uses dynamic adjustment algorithms (such as PID control algorithms or dynamic load distribution algorithms) to optimize the load regulation strategy to ensure that the transformer load operates within the expected range. When the load fluctuation exceeds the threshold, the system will automatically trigger the load regulation operation, and automatically adjust the priority and adjustment range of the load distribution according to the current power demand.

[0096] Different load regulation operations are performed on high-load transformers, medium-load transformers and low-load transformers respectively. Specifically: in high-load transformers, high-load adjustment parameters in the load regulation mechanism are used to give priority to load transfer and reduce load distribution; in medium-load transformers, standard load adjustment parameters in the load regulation mechanism are maintained to maintain the current load level and adjust the load balance; in low-load transformers, low-load adjustment parameters in the load regulation mechanism are used to reduce load regulation operations and maintain the existing load level.

[0097] In high-load transformers, the implementation of load transfer and load reduction using the high-load adjustment parameters in the load regulation mechanism can be achieved through automated load management software. First, when the software detects that the load of a transformer exceeds the preset high-load threshold through the real-time monitoring system, the system triggers the load transfer operation. Load transfer is achieved through a distributed power management system, which automatically reallocates part of the power demand to other transformers in low or medium load states based on the current load conditions. The software will ensure that load transfer is prioritized on high-load transformers based on preset load priority rules, and dynamically adjust the load distribution ratio based on the overall operation of the power grid to reduce the pressure on high-load transformers.

[0098] In medium-load transformers, load regulation maintains the current load level by maintaining the standard load adjustment parameters in the load regulation mechanism, and performs load balancing adjustments according to the needs of the power system. The software continuously monitors the load fluctuations of medium-load transformers through real-time data acquisition, and automatically performs standard adjustment operations to ensure that the load operates within a safe range. The specific implementation method is that the system can use load balancing algorithms (such as balancing models based on load prediction) to dynamically adjust the load distribution between transformers to prevent a medium-load transformer from being overloaded due to fluctuations. This operation analyzes the load data of medium-load transformers, balances load fluctuations, and ensures the stability of the system when the load changes.

[0099] In low-load transformers, the low-load adjustment parameters in the load regulation mechanism are used to reduce load regulation operations to maintain the existing load level. The main implementation method is to set the lowest priority of load regulation through the software system to reduce unnecessary adjustment operations. The software will monitor the load status of the low-load transformer in real time. When the load remains within the safe range, the system will automatically limit the adjustment intervention on the low-load transformer through the load adjustment mechanism. Specifically, the software will determine whether the low-load transformer needs to be adjusted according to the preset adjustment rules. Usually, the system will trigger the adjustment operation only when the load fluctuates greatly or is abnormal. Otherwise, the software will maintain the current load level to avoid frequent and unnecessary adjustments to the low-load transformer to improve the efficiency of the entire system.

[0100] The regulation feedback evaluation module collects the load adjustment feedback information of each transformer in real time during the process of load regulation of each transformer by the load regulation mechanism, and analyzes it after collection to evaluate whether the regulation degree of each transformer by the load regulation mechanism can meet the balance requirements of power demand fluctuations, and optimizes the load regulation mechanism according to the evaluation results;

[0101] In this embodiment, in the regulation feedback evaluation module, after the load adjustment feedback information of each transformer is collected in real time, it is preprocessed, and the load stability feedback information and voltage regulation efficiency information in the preprocessed load adjustment feedback information of each transformer are extracted, and analyzed after extraction to generate the regulation stability coefficient and voltage regulation efficiency index of each transformer respectively.

[0102] In the process of load regulation mechanism adjusting each transformer, load adjustment feedback information can be realized through the sensor network and Industrial Internet of Things (IIoT) system installed on the transformer. The sensor network monitors the operating status of the transformer in real time, including power output power, voltage change, load adjustment rate, etc., to form complete load adjustment feedback information. Through the IoT gateway, these real-time data are uploaded to the central monitoring system or cloud data platform. The software system obtains the load adjustment feedback information of each transformer through these data interfaces and stores it in the database in real time for further analysis. In this way, the data collection process is fully automated, and the real-time and accuracy of the feedback information can be ensured. The software can perform the next adjustment optimization based on the collected data.

[0103] The purpose of preprocessing is to improve the quality and effectiveness of data and provide a reliable data basis for subsequent analysis and decision-making. The real-time collected load adjustment feedback information may contain noise, outliers or missing data, so the data needs to be cleaned and corrected. The first step of preprocessing is to denoise the data, such as removing the signal noise that may be generated during the acquisition process through a filtering algorithm. Next, the software system will detect and correct abnormal data, such as identifying values ​​that exceed a reasonable range through statistical analysis, and make reasonable estimates and supplements based on historical data. Finally, the system will normalize the data and unify the dimensions of various types of data so that different indicators can be compared fairly in subsequent analysis. Through these preprocessing steps, it can be ensured that the extracted load stability feedback information and voltage regulation efficiency information have sufficient accuracy and consistency, thereby providing a reliable basis for generating the regulation stability coefficient and voltage regulation efficiency index.

[0104] In this embodiment, the logic for obtaining the regulation stability coefficient and voltage regulation efficiency index of each transformer is as follows:

[0105] Extract the load stability feedback information from the pre-processed load adjustment feedback information of each transformer, including the load change, output power, average load value of the connected power equipment and the corresponding time point of each transformer at different times within a period of time after the load adjustment mechanism is used for load adjustment, and use the function to calculate the load stability feedback information of each transformer according to the time series. , and To express, For time point, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The load change at each moment, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The output power at the moment, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The average load value of the connected power equipment at the time, the time period is defined as , , is a positive integer;

[0106] In the process of load regulation, the extraction of pre-processed load stability feedback information of each transformer can be achieved by combining the sensor network with the industrial Internet of Things system. First, the load change is monitored in real time by the power sensors installed on each transformer. These sensors will regularly collect the actual load values ​​of the transformer at different times and upload them to the cloud data center. The output power can be obtained through the current sensor and the voltage sensor, and the software system will calculate it according to the power formula P(t)=V(t)*I(t). At the same time, the average load value of the power equipment connected to the transformer can be connected to the load sensor on the device side, and the load sensor will continuously monitor the load demand of the power equipment and regularly feedback to the central system. All these data will be transmitted to the central control platform together with the corresponding timestamp and pre-processed by the software system. The pre-processing process includes data cleaning, denoising, outlier processing and normalization to ensure that the extracted data is accurate and available, and finally used for further analysis and generation of load stability feedback information.

[0107] Calculate the regulation stability coefficient of each transformer. The specific calculation formula is as follows:

[0108] ;

[0109] In the formula, For the The regulation stability factor of each transformer;

[0110] This formula is used to calculate the regulation stability factor of each transformer Its core purpose is to measure the transformer's ability to respond to load fluctuations during load regulation. Indicates the load change during the load regulation process. By integrating the load change, the cumulative change over a period of time can be obtained, thereby measuring the regulation stability of the transformer. Output power in the denominator and device load average It is used to standardize the load change to ensure that the regulation stability factor can match the actual output capacity and load level of the transformer. This processing can reflect the relative regulation efficiency of the transformer under different output power and load conditions. It is used to represent the entire regulation cycle. By taking the definite integral of the data in this time interval, the dynamic changes of the load in the entire regulation process can be fully captured to ensure that the result can reflect the comprehensive performance of the regulation process. Finally, by dividing by the time period , a standardized regulation stability factor is obtained, which makes it comparable and can be used for performance evaluation of different transformers.

[0111] No. The regulation stability factor of a transformer The size of directly reflects the relationship between the load regulation mechanism's regulation effect on the transformer and its adaptability to power demand fluctuations. Specifically, the higher This shows that during the load regulation process, the transformer can respond quickly and effectively to load changes and achieve stable load regulation in a relatively short period of time, indicating that the regulation mechanism can well cope with power demand fluctuations and meet balance requirements. This means that the transformer has a slow load response and low regulation efficiency during the regulation process, and may not be able to effectively cope with the rapid fluctuations in power demand, resulting in an imbalance in the power system. Therefore, the size of the regulation stability coefficient is a key indicator for evaluating whether the load regulation mechanism can balance the fluctuations in power demand in a timely manner. The value of can be used to determine whether the regulation mechanism needs to be optimized.

[0112] The voltage regulation efficiency information is extracted from the pre-processed load adjustment feedback information of each transformer, including the output voltage value, voltage recovery time, target voltage value and corresponding time point of each transformer at different times within a period of time after the load adjustment mechanism is used for load adjustment, and the function is used to perform the calculation according to the time series. , and To express, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The output voltage value at the moment, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The voltage recovery time at time Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The target voltage value at the moment;

[0113] Extracting the voltage regulation efficiency information of each transformer after preprocessing can be achieved by combining the voltage sensor installed on the transformer, the industrial Internet of Things platform, and the cloud data processing system. During the load regulation process, the voltage sensor will monitor and collect the output voltage values ​​of each transformer at different times in real time, and these data will be uploaded to the central control system through the IIoT platform. The voltage recovery time is calculated by detecting the time difference between the voltage deviation and the target voltage. The voltage deviation can be calculated by comparing the current output voltage with the preset target voltage. The target voltage value is a standard value pre-set by the power system. It has been loaded into the control platform by the system at the beginning of load regulation for real-time comparison of the voltage adjustment effect. All these data will be accompanied by timestamp information and transmitted to the cloud in real time through the IIoT system for preprocessing. The preprocessing steps include data denoising, anomaly detection and supplementation, and data synchronization to ensure the accuracy and consistency of each data point, thereby providing reliable data support for voltage regulation efficiency analysis.

[0114] Calculate the voltage regulation efficiency index of each transformer. The specific calculation formula is as follows:

[0115] ;

[0116] In the formula, For the The voltage regulation efficiency index of a transformer.

[0117] This formula is used to calculate the Voltage Regulation Efficiency Index of a Transformer , which aims to evaluate the efficiency of the transformer in restoring voltage stability during load regulation. Indicates the preset target voltage, It represents the actual voltage deviation. By integrating the difference between the two, the accumulation of voltage deviation in the entire time period can be quantified to reflect the voltage regulation effect. Represents the voltage recovery time. As the denominator, it is used to measure the time required for the transformer to recover from the voltage deviation state to the target voltage. The shorter the recovery time, the higher the regulation efficiency. As part of the denominator, it is used to normalize the voltage deviation and ensure the comparability of the index. , the formula can capture the dynamic performance of voltage regulation over the entire time period and can be used to The results are normalized to ensure that the index has a consistent evaluation standard among different transformers.

[0118] The voltage regulation efficiency index of the transformer The size of directly reflects the relationship between the load regulation mechanism's voltage recovery capability of the transformer and its adaptability to power demand fluctuations. This indicates that the transformer can quickly recover to the preset target voltage during the voltage regulation process, and the voltage deviation is small, which means that the load regulation mechanism can effectively cope with power demand fluctuations and maintain the voltage stability and balance requirements of the system. It indicates that the voltage recovery time is long and the deviation is large, indicating that the load regulation mechanism cannot balance the power demand fluctuation in a timely and effective manner, which may lead to system instability. Therefore, the size of the voltage regulation efficiency index is a key indicator for evaluating whether the regulation mechanism can maintain voltage stability and meet the balance requirements of the power system.

[0119] In this embodiment, when generating the regulation stability coefficient of each transformer and voltage regulation efficiency index Finally, the regulation degree evaluation model is constructed, and the regulation coefficient of each transformer is generated by weighted summation. , and the adjustment coefficients of each transformer generated The regulation coefficient thresholds of each transformer are set in advance Compare and evaluate whether the load regulation mechanism can meet the balance requirements of power demand fluctuations based on the comparison results. Optimize the load regulation mechanism based on the evaluation results. The specific comparison and analysis are as follows:

[0120] like The load regulation mechanism cannot meet the balance requirements of power demand fluctuations. The load regulation mechanism needs to be optimized, including: adjusting the load transfer mechanism of high-load transformers to increase the load transfer speed; improving the load balance adjustment parameters of medium-load transformers to optimize the adjustment sensitivity; slowing down the adjustment range of low-load transformers to maintain the existing load level;

[0121] This situation indicates that the current load regulation mechanism has a poor regulation effect on the transformer and cannot fully cope with the fluctuation of power demand, resulting in the system failing to meet the balance requirements of power load. This shows that the load regulation mechanism needs to be optimized. The current regulation mechanism has insufficient response speed in certain load scenarios, or the regulation parameters are not accurate enough, making it difficult to ensure stability when the load changes. For optimization, the software system can monitor the load response data in real time, dynamically adjust the load transfer speed of the high-load transformer, and modify the load transfer parameters in the regulation algorithm to enable the load to be distributed more quickly. The regulation sensitivity of the medium-load transformer can be enhanced by adjusting the feedback loop in the regulation rule to ensure a more balanced load regulation process and avoid system fluctuations. For low-load transformers, the software can be optimized by reducing unnecessary regulation actions. The system will detect the fluctuation amplitude of the load change and reduce or delay the small load regulation operation according to the preset threshold of its fluctuation amount, thereby reducing the impact on the overall efficiency of the system. All these operations adjust the load regulation algorithm and optimization strategy in real time through the central control system, making the load regulation mechanism more flexible and responsive.

[0122] like The degree of regulation of the transformer by the load regulation mechanism can meet the balancing requirements of power demand fluctuations, and there is no need to optimize the load regulation mechanism.

[0123] This situation shows that the current load regulation mechanism can effectively cope with fluctuations in power demand, and the load regulation degree of the transformer has reached the system balance requirements. The load regulation mechanism in the system works well when dealing with load fluctuations and does not require further optimization or adjustment. In this case, the software can continue to maintain the existing load regulation mechanism to ensure that the transformer maintains the current regulation strategy. At the same time, through the long-term monitoring of historical load data and regulation feedback information by the central control system, the software can regularly analyze and self-learn the regulation rules so that the load regulation mechanism can be dynamically adjusted when power demand fluctuates more violently in the future. The system can also use adaptive algorithms to identify potential trends or patterns, adjust some regulation parameters before power fluctuations are about to occur, and ensure that the load regulation mechanism can continue to maintain efficient response and stable operation.

[0124] In generating the regulation stability coefficient of each transformer and voltage regulation efficiency index Finally, the key to constructing the regulation degree evaluation model is to combine these two parameters through weighted summation to generate a regulation coefficient that comprehensively reflects the transformer regulation ability. The specific operation is to first set weight coefficients for the regulation stability coefficient and the voltage regulation efficiency index respectively, and the weight setting is based on their influence on the regulation performance. For example, if the system has higher requirements for the stability of load response, the regulation stability coefficient can be set to Give higher weight , and is the voltage regulation efficiency index Give lower weight (The sum of the weights is 1, i.e. ). The weight can be adjusted based on historical data, empirical rules or the actual needs of the system. Then, through the formula: ; Generate a comprehensive adjustment coefficient , which represents the overall performance of the transformer in load regulation. This weighted summation operation allows the system to flexibly adjust the regulation mechanism, which can not only balance the load response speed of the power system, but also ensure the efficiency of voltage regulation. Reasonable setting of the weight coefficient can dynamically adjust the different needs of the system according to different scenarios to cope with various power demand fluctuations.

[0125] The intelligent optimization monitoring module conducts long-term monitoring and comprehensive analysis of the load data, feedback information and adjustment records in the entire load regulation process, continuously optimizes the load regulation mechanism based on the intelligent learning algorithm, and improves the regulation strategy in real time.

[0126] Long-term monitoring of transformer load data, feedback information, and adjustment records can be achieved through software, which can be achieved by establishing a real-time data acquisition and storage system. The real-time load changes, output voltage, adjustment feedback, and other information of each transformer are collected by installed sensors and transmitted to the central control platform through the Industrial Internet of Things (IIoT) system. In the central platform, these data will be continuously stored in the cloud database and backed up regularly to ensure data integrity and historical traceability. The software system will track these historical data for a long time to enable comprehensive analysis and optimization of system performance in the future. At the same time, the monitoring system will display real-time data and its trends through a graphical interface, which is convenient for system managers to view and manage the adjustment in real time.

[0127] Comprehensive analysis of load data and feedback information can be achieved by introducing data analysis modules and systems based on intelligent learning algorithms (such as machine learning). The software system will use big data analysis technology to analyze a large amount of historical load data and regulation feedback stored in the database to extract the laws of system load changes and the trends of regulation performance. By applying intelligent learning algorithms, the system can automatically learn the effectiveness of the regulation mechanism from these data and identify which regulation measures perform best under specific load conditions. For example, machine learning algorithms can identify which load fluctuation patterns are most likely to lead to insufficient regulation and optimize future regulation strategies based on these patterns. In addition, the system can also build a prediction model based on the analysis results to predict future load demand changes and adjust the regulation mechanism in advance.

[0128] The optimization strategy generated by the intelligent learning algorithm will be automatically applied by the system to optimize the load regulation mechanism. By analyzing load data and feedback information in real time, the system can dynamically adjust the load regulation parameters. For example, the system can automatically adjust the load transfer speed of high-load transformers and the regulation sensitivity of medium-load transformers. The optimization process of the load regulation mechanism will also be iteratively improved based on the system's historical regulation records to ensure that each optimization is based on the latest data and regulation results. The system will continuously self-evaluate and update the regulation effect, and the optimized regulation mechanism can adapt to new power demand fluctuations more quickly and accurately. In addition, the optimization of the regulation mechanism can also be achieved through an adaptive algorithm, that is, the regulation parameters are automatically adjusted according to the real-time feedback of load changes to ensure that the system is always in the best state.

[0129] Based on the optimization results of the intelligent learning algorithm, the system will improve the regulation strategy in real time to ensure the balance and stability of the power system. The software system will dynamically update the regulation parameters and strategies by monitoring the current load data and voltage conditions in real time. For example, when the system finds that the load changes greatly, it can automatically enable the fast regulation strategy to ensure that the system can cope with severe load fluctuations through higher frequency data updates and fast response algorithms. On the other hand, when the system load is relatively stable, the system can choose to enable a gentler regulation strategy to reduce unnecessary regulation operations and reduce the system's energy consumption and operating costs. All these strategy adjustments are automatically performed in the background through the software's self-learning and optimization algorithms to ensure that the regulation strategy always matches the actual load conditions.

[0130] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0131] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0132] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0133] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0137] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The industrial Internet cloud platform based on data intelligence is characterized by: It includes power demand modeling module, power load dynamic analysis module, load regulation mechanism module, regulation feedback evaluation module and intelligent optimization monitoring module; The power demand modeling module determines the type and power demand of industrial equipment according to the operation objectives of the power system in the industrial park, and builds a basic data model of power demand and load changes to provide a reference for subsequent real-time data collection and load regulation; The power load dynamic analysis module obtains the power load dynamic information of each transformer in real time, analyzes it after acquisition, predicts the impact of power demand fluctuations of power equipment on the load of each transformer, and divides each transformer into high-load transformer, medium-load transformer and low-load transformer according to the prediction results; In the power load dynamic analysis module, after the power load dynamic information of each transformer is obtained in real time, it is preprocessed, and the power load dynamic response information and power system fluctuation assessment information in the preprocessed power load dynamic information of each transformer are extracted, and analyzed after extraction to generate the load response coefficient and load fluctuation index of each transformer respectively; The logic for obtaining the load response coefficient and load fluctuation index of each transformer is as follows: The power load dynamic response information is extracted from the preprocessed power load dynamic information of each transformer, including the actual power load of each transformer at different times within a period of time, the adjustment rate, and the actual power load of each transformer at different times in the historical time period, and calibrated as , and , Indicates A transformer in a period of time The actual power load at the moment, Indicates A transformer in a period of time The adjustment rate of time, Indicates Transformers in the historical period The actual power load at the moment, , , , , and All are positive integers; Calculate the historical load change rate of each transformer. The specific calculation formula is as follows: ； In the formula, For the Historical load change rate of each transformer; Calculate the load response coefficient of each transformer. The specific calculation formula is as follows: ； In the formula, For the The load response factor of each transformer; The power system fluctuation assessment information is extracted from the pre-processed power load dynamic information of each transformer, including the voltage of each transformer at different times within a period of time and the preset power load, and calibrated as and , Indicates A transformer in a period of time The voltage at the moment, Indicates A transformer in a period of time The preset power load at the time; Calculate the load fluctuation index of each transformer. The specific calculation formula is as follows: ； In the formula, For the Load fluctuation index of each transformer; The load regulation mechanism module constructs a load regulation mechanism for regulating the power load of the transformer according to the division results of each transformer, and performs different load regulation operations on the high-load transformer, the medium-load transformer and the low-load transformer respectively; The regulation feedback evaluation module collects the load adjustment feedback information of each transformer in real time during the process of load regulation of each transformer by the load regulation mechanism, and analyzes it after collection to evaluate whether the regulation degree of each transformer by the load regulation mechanism can meet the balance requirements of power demand fluctuations, and optimizes the load regulation mechanism according to the evaluation results; The intelligent optimization monitoring module conducts long-term monitoring and comprehensive analysis of the load data, feedback information and adjustment records in the entire load regulation process, continuously optimizes the load regulation mechanism based on the intelligent learning algorithm, and improves the regulation strategy in real time.

2. The data intelligence-based industrial Internet cloud platform according to claim 1 is characterized in that: When generating the load response factor for each transformer and load fluctuation index Finally, a load impact prediction model is constructed, and the load impact coefficient of each transformer is generated by weighted summation. , and the load influence coefficient of each transformer generated The load impact factor threshold interval is set in advance. The comparison is carried out, and the influence of the power demand fluctuation of the power equipment on the load of each transformer is predicted according to the comparison results. According to the prediction results, each transformer is divided into high-load transformer, medium-load transformer and low-load transformer. The specific comparison analysis and division are as follows: like , the power demand fluctuation of the power equipment has a low impact on the load of the transformer, and the transformer is classified as a low-load transformer; like , the influence of power demand fluctuation of power equipment on the transformer load is medium, and the transformer is classified as a medium load transformer; like ,The power demand fluctuation of the power equipment has a high impact on the load of the transformer, and the transformer is classified as a high-load transformer.

3. The data intelligence-based industrial Internet cloud platform according to claim 2 is characterized in that: In the load regulation mechanism module, according to the division results of each transformer, a load regulation mechanism for regulating the transformer power load is constructed, which specifically includes: according to the division results of high-load transformers, medium-load transformers and low-load transformers, different load regulation parameters are set respectively to form a load regulation mechanism; the load regulation mechanism is based on the load influence coefficient of each transformer and the current power demand fluctuation, and automatically determines the priority and adjustment range of load adjustment through pre-set rules; Different load regulation operations are performed on high-load transformers, medium-load transformers and low-load transformers respectively. Specifically: in high-load transformers, high-load adjustment parameters in the load regulation mechanism are used to give priority to load transfer and reduce load distribution; in medium-load transformers, standard load adjustment parameters in the load regulation mechanism are maintained to maintain the current load level and adjust the load balance; in low-load transformers, low-load adjustment parameters in the load regulation mechanism are used to reduce load regulation operations and maintain the existing load level.

4. The data intelligence-based industrial Internet cloud platform according to claim 3 is characterized in that: In the regulation feedback evaluation module, after the load adjustment feedback information of each transformer is collected in real time, it is preprocessed, and the load stability feedback information and voltage regulation efficiency information in the preprocessed load adjustment feedback information of each transformer are extracted, and analyzed after extraction to generate the regulation stability coefficient and voltage regulation efficiency index of each transformer respectively.

5. The data intelligence-based industrial Internet cloud platform according to claim 4 is characterized in that: The acquisition logic of the regulation stability coefficient and voltage regulation efficiency index of each transformer is as follows: Extract the load stability feedback information from the pre-processed load adjustment feedback information of each transformer, including the load change, output power, average load value of the connected power equipment and the corresponding time point of each transformer at different times within a period of time after the load adjustment mechanism is used for load adjustment, and use the function to calculate the load stability feedback information of each transformer according to the time series. , and To express, For time point, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The load change at each moment, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The output power at the moment, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The average load value of the connected power equipment at the time, the time period is defined as , , is a positive integer; Calculate the regulation stability coefficient of each transformer. The specific calculation formula is as follows: ； In the formula, For the The regulation stability factor of each transformer; The voltage regulation efficiency information is extracted from the pre-processed load adjustment feedback information of each transformer, including the output voltage value, voltage recovery time, target voltage value and corresponding time point of each transformer at different times within a period of time after the load adjustment mechanism is used for load adjustment, and the function is used to perform the calculation according to the time series. , and To express, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The output voltage value at the moment, Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The voltage recovery time at time Indicates that after the load regulation mechanism performs load regulation A transformer in a period of time The target voltage value at the moment; Calculate the voltage regulation efficiency index of each transformer. The specific calculation formula is as follows: ； In the formula, For the The voltage regulation efficiency index of a transformer.

6. The data intelligence-based industrial Internet cloud platform according to claim 5 is characterized in that: In generating the regulation stability coefficient of each transformer and voltage regulation efficiency index Finally, the regulation degree evaluation model is constructed, and the regulation coefficient of each transformer is generated by weighted summation. , and the adjustment coefficients of each transformer generated The regulation coefficient thresholds of each transformer are set in advance Compare and evaluate whether the load regulation mechanism can meet the balance requirements of power demand fluctuations based on the comparison results. Optimize the load regulation mechanism based on the evaluation results. The specific comparison and analysis are as follows: like The load regulation mechanism cannot meet the balance requirements of power demand fluctuations. The load regulation mechanism needs to be optimized, including: adjusting the load transfer mechanism of high-load transformers to increase the load transfer speed; improving the load balance adjustment parameters of medium-load transformers to optimize the adjustment sensitivity; slowing down the adjustment range of low-load transformers to maintain the existing load level; like The degree of regulation of the transformer by the load regulation mechanism can meet the balancing requirements of power demand fluctuations, and there is no need to optimize the load regulation mechanism.

Images