Intelligent load acquisition system based on aliasing scene of station power system

Abstract

The invention relates to the technical field of load monitoring, in particular to an intelligent load acquisition system based on a station power system aliasing scene, which comprises a load fluctuation analysis module, a receiving frequency adjustment module, an abnormal threshold adjustment module and an abnormal load identification module. According to the method, the fluctuation of the power load can be accurately evaluated by deploying the sensors of the differentiated equipment, monitoring the power load in real time, receiving and processing the power load data in real time through the cloud server and eliminating data noise caused by start and stop of single equipment, and the data collection is more efficient by dynamically adjusting the data receiving frequency; transmission of invalid data is reduced, the data processing speed and accuracy are improved, the power load average value of the equipment is analyzed according to historical data, the anomaly detection threshold value is adjusted accordingly, the power load anomaly recognition capability and accuracy are improved, power system faults can be prevented, and the power system safety is improved. And subsequent energy management optimization of a power operator is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of load monitoring, and in particular to an intelligent load acquisition system based on an aliasing scenario of a station power system. Background Art

[0002] The field of load monitoring technology mainly involves real-time tracking and analysis of power usage of various electrical devices in the power system. The technology is mainly used in energy management systems to optimize energy consumption, prevent equipment overload, and improve the efficiency and reliability of power grid operations. By using sensors, smart meters and data analysis, load monitoring technology can provide detailed energy usage data to support accurate analysis and management of power demand.

[0003] Among them, the load intelligent acquisition system is a system specifically used to monitor and record the power usage of each load point in the power system. The system integrates sensors and data processing algorithms to achieve real-time monitoring and analysis of power usage. The main uses include monitoring the changing trends of power loads and identifying potential power system failures. The system is suitable for complex power grid environments, such as industrial parks or large buildings, and can help operators reduce energy consumption and improve the stability and economy of power supply.

[0004] Traditional data collection systems face difficulties in processing aliased data, especially in power system environments with complex environments and a wide variety of equipment. Traditional systems use a unified data processing strategy and fail to effectively distinguish load changes caused by different power equipment, resulting in inaccurate data analysis results. Traditional systems usually use fixed standards for power load data reception frequency and abnormal threshold setting, and do not adjust according to actual power load changes. This will lead to delays or false alarms in abnormal monitoring in rapidly changing power demand scenarios, making it difficult to provide data support for subsequent power demand analysis and management. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a load intelligent collection system based on the aliasing scenario of the station power system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a load intelligent collection system based on the aliasing scenario of the station power system, the system comprising: The load fluctuation analysis module is based on the station power system environment. By deploying corresponding sensors on differentiated power equipment, the power load data of differentiated equipment is monitored in real time. The power load data is received through the cloud server, and the aliased load fluctuation data caused by the start and stop of a single device is eliminated. By analyzing the power load data over a period of time, the volatility of the power load of differentiated equipment is evaluated to obtain the load fluctuation analysis results. The receiving frequency adjustment module adjusts the receiving frequency of the power load data of the differentiated equipment based on the load fluctuation analysis result and the basic receiving frequency of the data to obtain the data receiving frequency adjustment result; The abnormal threshold adjustment module receives the frequency adjustment result of the data, extracts the power load records of the differentiated equipment, analyzes the load change trend according to the average power load change in the same period of the day, adjusts the abnormal load detection threshold, and obtains the abnormal load detection threshold adjustment result; Based on the abnormal load detection threshold adjustment result, the abnormal load identification module compares the power load data of the differentiated equipment with the adjusted abnormal load detection threshold, evaluates the degree of load excess, and records the time point of load excess. Combined with the load excess duration, it evaluates the load abnormality level and obtains real-time load data collection results.

[0007] The present invention is improved in that the method for eliminating aliased load fluctuation data caused by the start and stop of a single device is: Based on the station power system environment, by deploying corresponding sensors on differentiated power equipment, the power load data of differentiated equipment is monitored in real time, and the power load data is received through the cloud server to obtain the real-time reception result of the load data; Based on the real-time reception result of the load data, a corresponding timestamp is marked for the differentiated power load data, and the start and stop time points of the differentiated equipment are identified by analyzing the normal operating time range of the differentiated equipment and combining the load data changes, thereby obtaining the equipment start and stop time identification result; Based on the equipment start and stop time identification result, the load data of each device that fluctuates due to the start and stop of a single device at the same time point is removed to obtain aliased load fluctuation removal data.

[0008] The present invention is improved in that the steps of obtaining the load fluctuation analysis result are: Extracting power load data of a target device for a period of time based on the aliased load fluctuation removal data to obtain a power load data extraction result; Based on the power load data, through the formula: ; Calculate the fluctuation of equipment power load , and the load fluctuation analysis results are obtained, where It is in The power load at a point in time, is the average power load in the corresponding time period, is the total number of time points, is the weight coefficient, is the sensitivity index, The fluctuation of the power load of the equipment.

[0009] The present invention is improved in that the step of obtaining the data receiving frequency adjustment result is: Based on the load fluctuation analysis result, extracting the basic receiving frequency of the data to obtain receiving frequency associated data; Based on the received frequency association data, by the formula: ; Calculate the adjusted receiving frequency ,in, The fluctuation of the power load of the equipment, is the receiving frequency of the current device data, is the volatility threshold, is the regulating factor, is the adjusted receiving frequency.

[0010] Based on the adjusted receiving frequency , load data is received according to the corresponding receiving frequency to obtain the data receiving frequency adjustment result.

[0011] The present invention is improved in that the method for analyzing the load change trend is: Based on the data reception frequency adjustment result, extract the power load record of the differentiated equipment, calculate the average power load of the equipment in the target period, and obtain the average power load data of the target period within a period of time to obtain the average power load data acquisition result; Based on the average power load data, the result is obtained by the formula: ; Calculate the degree of power load change , get the power load change trend information, where and Respectively represent Tianhedi The average load during the target period of the day, is the regulating factor, is the baseline load value, The degree of change in power load.

[0012] The present invention is improved in that the step of obtaining the abnormal load detection threshold adjustment result is: Based on the power load change trend information, extract the average power load and the corresponding power load standard deviation data of the target period of the previous day to obtain load detection threshold associated data; Based on the load detection threshold associated data, by formula: ; Calculate the adjusted abnormal load detection threshold , and obtain the abnormal load detection threshold adjustment result, where: is the average power load during the target period of the previous day, is the standard deviation of power load on the previous day, is the degree of change in power load, and The adjustment coefficients for the mean load and the load standard deviation, respectively, is the adjusted abnormal load detection threshold.

[0013] The present invention is improved in that the method for evaluating the degree of load excess is: Based on the abnormal load detection threshold adjustment result, extract the real-time load data of the equipment, and compare the real-time load data with the adjusted abnormal load detection threshold, identify the real-time load data exceeding the adjusted abnormal load detection threshold, and obtain the exceeding data identification result; Based on the exceeded data identification result, the formula is: ; Calculate the load excess , get the load exceeding degree information, where, is the real-time power load value, is the adjusted abnormal load detection threshold, is the scaling factor, is the adjustment factor, Exceeding the load level.

[0014] The present invention is improved in that the steps of acquiring the real-time load data collection result are: Based on the load excess degree information, record the load excess time point, and extract the load excess duration to obtain duration information; Based on the duration information, by the formula: ; Calculate the load anomaly level, where For the The load exceeds the degree, is the total number of deviations that occurred during the target time period, For the The duration of the load exceeding the threshold, is the weight coefficient, is the logarithmic adjustment coefficient, is the abnormal load level; Based on the load anomaly level, the identification of the device with the anomaly is recorded, and the corresponding abnormal load data is extracted to obtain a real-time load data collection result.

[0015] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by deploying sensors of differentiated devices, real-time monitoring of power load, real-time receiving and processing of power load data through cloud servers, and eliminating data noise caused by the start and stop of a single device, the volatility of the power load can be accurately evaluated, and by dynamically adjusting the data receiving frequency, data collection is made more efficient, the transmission of invalid data is reduced, and the speed and accuracy of data processing are improved. The average power load value of the equipment is analyzed according to historical data, and the anomaly detection threshold is adjusted accordingly, thereby improving the ability and accuracy of identifying power load anomalies, helping to prevent power system failures, and helping power operators to perform subsequent energy management optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a system flow chart of the present invention; Figure 2 A flow chart of the present invention for eliminating aliased load fluctuation data caused by the start and stop of a single device; Figure 3 A flow chart for obtaining load fluctuation analysis results for the present invention; Figure 4 A flow chart of obtaining a data receiving frequency adjustment result according to the present invention; Figure 5 A flow chart for analyzing load variation trends in the present invention; Figure 6 A flow chart of obtaining abnormal load detection threshold adjustment results of the present invention; Figure 7 A flow chart for evaluating load excess for the present invention; Figure 8 The present invention is a flow chart for obtaining real-time load data collection results. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0019] See also Figure 1 The present invention provides a technical solution: a load intelligent collection system based on the aliasing scenario of the station power system, the system comprising: The load fluctuation analysis module is based on the station power system environment. By deploying corresponding sensors on differentiated power equipment, the power load data of differentiated equipment is monitored in real time. The power load data is received through the cloud server, and the aliased load fluctuation data caused by the start and stop of a single device is eliminated. By analyzing the power load data over a period of time, the volatility of the power load of differentiated equipment is evaluated to obtain the load fluctuation analysis results. The receiving frequency adjustment module adjusts the receiving frequency of the power load data of the differentiated equipment based on the load fluctuation analysis result and the basic receiving frequency of the data to obtain the data receiving frequency adjustment result; The abnormal threshold adjustment module is based on the data receiving frequency adjustment result, extracts the power load records of differentiated equipment, calculates the average power load of the equipment in the target period, and analyzes the load change trend according to the average power load change in the same period of the day, adjusts the abnormal load detection threshold, and obtains the abnormal load detection threshold adjustment result; Based on the abnormal load detection threshold adjustment result, the abnormal load identification module compares the power load data of differentiated equipment with the adjusted abnormal load detection threshold, evaluates the degree of load excess, and records the time point of load excess. Combined with the load excess duration, it evaluates the load abnormality level and obtains real-time load data collection results.

[0020] The load fluctuation analysis results include the fluctuation frequency, fluctuation amplitude and load stability score of each device. The data receiving frequency adjustment results include the adjusted data update interval and data synchronization frequency. The abnormal load detection threshold adjustment results include the adjusted load detection threshold and the corresponding device identification. The real-time load data collection results include the number of recorded over-threshold events, the abnormal duration of the equipment and the corresponding abnormal level.

[0021] See also Figure 2 ,The method to eliminate the aliased load fluctuation data caused by the start and stop of a single device is: Based on the station power system environment, by deploying corresponding sensors on differentiated power equipment, the power load data of differentiated equipment is monitored in real time, and the power load data is received through the cloud server to obtain the real-time reception result of the load data; Based on the real-time reception results of load data, the corresponding timestamps are marked for differentiated power load data. By analyzing the normal operating time range of differentiated equipment and combining the load data changes, the start and stop time points of differentiated equipment are identified to obtain the equipment start and stop time identification results; Based on the equipment start and stop time identification results, the load data of each device that fluctuates due to the start and stop of a single device at the same time point is removed to obtain the aliased load fluctuation removal data.

[0022] See also Figure 3 , the steps to obtain the load fluctuation analysis results are: Based on the aliased load fluctuation removal data, the power load data of the target device for a period of time is extracted to obtain the power load data extraction result; Based on the power load data, through the formula: ; Calculate the fluctuation of equipment power load , and the load fluctuation analysis results are obtained, where It is in The power load at a point in time, is the average power load in the corresponding time period, is the total number of time points, is the weight coefficient, is the sensitivity index, The fluctuation of the power load of the equipment.

[0023] formula: ; Parameter details and how to obtain them: : No. The power load value at a point in time is the real-time power data obtained directly from the sensor.

[0024] : The average power load in the corresponding time period, through all Sum the values ​​and divide by Calculated.

[0025] : The total number of time points is determined by the sensor monitoring cycle and the total monitoring time.

[0026] : Weight coefficient is set according to the time point. Different time points will have different weight coefficients. It can be set according to whether the device is in normal operation at the corresponding time point.

[0027] : The sensitivity index is set according to the sensitivity requirements of volatility and is an empirical value to adapt to different volatility assessment requirements.

[0028] Calculation example: The power load data is set to 5 time periods: , , the weight of each device , sensitivity index .

[0029] calculate : ; Calculating volatility : ; result The weighted fluctuation value of the power load in each time period is 46. The value reflects the degree of fluctuation of the power load in different time periods. A higher fluctuation value indicates instability or potential problems in the power system.

[0030] See also Figure 4 , the steps for obtaining the data receiving frequency adjustment result are: Based on the load fluctuation analysis results, the basic receiving frequency of the data is extracted to obtain the receiving frequency related data; Based on the received frequency correlation data, the formula is: ; Calculate the adjusted receiving frequency ,in, The fluctuation of the power load of the equipment, is the receiving frequency of the current device data, is the volatility threshold, is the regulating factor, is the adjusted receiving frequency.

[0031] Based on the adjusted receiving frequency , load data is received according to the corresponding receiving frequency to obtain the data receiving frequency adjustment result.

[0032] formula: ; Parameter details and how to obtain them: : The current data reception frequency, which is usually determined by the device default settings or previous operation and maintenance decisions.

[0033] : The fluctuation of the equipment power load is calculated by the previous method.

[0034] : Volatility threshold, based on historical data analysis and system performance target setting, is used to determine whether the receiving frequency needs to be adjusted.

[0035] : Adjustment factor, used to adjust the sensitivity of receiving frequency adjustment to ensure that the frequency adjustment is not too sensitive or slow. It is usually set by system analysts based on device characteristics and operation and maintenance requirements.

[0036] Calculation example: Set the current data receiving frequency The frequency is 1Hz, and the fluctuation of the equipment power load The volatility threshold is set to 46. is 30, the adjustment factor is 20.

[0037] Calculate the adjusted receive frequency: ; Calculation results Hz, which indicates the new data receiving frequency. This means that in order to more effectively capture the rapidly changing power load data, the data receiving frequency has been increased from the original 1Hz to 1.8Hz. This adjustment helps the system respond more quickly to changes in power load, improves the real-time and accuracy of data, and thus enables better power management and fault prevention.

[0038] See also Figure 5 , the method to analyze the load change trend is: Based on the data receiving frequency adjustment result, extract the power load records of the differentiated equipment, calculate the average power load of the equipment in the target period, and obtain the average power load data of the target period within a period of time to obtain the average power load data acquisition result; Based on the average power load data, the results are obtained through the formula: ; Calculate the degree of power load change , get the power load change trend information, where and Respectively represent Tianhedi The average load during the target period of the day, is the regulating factor, is the baseline load value, The degree of change in power load.

[0039] formula: ; Parameter details and how to obtain them: and :Represents the Tianhedi The average load during the target period of the day.

[0040] : The adjustment factor is a parameter adjusted through experience, which is used to adjust the sensitivity of load changes in order to adapt to different power load fluctuations. It helps control the adjustment range of the denominator so that the formula responds more smoothly to load changes.

[0041] :Baseline load value is a preset reference point, usually set based on historical data or the typical operating load of the equipment. This parameter is used to stabilize the denominator and prevent extreme or atypical data from affecting the results.

[0042] Calculation example: Suppose that for two consecutive days, the average power load of the equipment is kW and kW. Set adjustment factor and baseline load values kW.

[0043] Calculate the average power load change: ; ; ; ; result , indicating that the average power load of the equipment increased by about 4.98% from one day to another. The value reflects the daily fluctuation of the power load of the equipment, and this analysis helps to monitor and predict the operating status of the equipment.

[0044] See also Figure 6 , the steps for obtaining the abnormal load detection threshold adjustment result are: Based on the power load change trend information, the average power load and the corresponding power load standard deviation data of the target period of the previous day are extracted to obtain the load detection threshold correlation data; Based on the load detection threshold correlation data, through the formula: ; Calculate the adjusted abnormal load detection threshold , and obtain the abnormal load detection threshold adjustment result, where: is the average power load during the target period of the previous day, is the standard deviation of power load on the previous day, is the degree of change in power load, and The adjustment coefficients for the mean load and the load standard deviation, respectively, is the adjusted abnormal load detection threshold.

[0045] formula: ; Parameter details and how to obtain them: : The average power load during the target period of the previous day, which is obtained by collecting the power load data during the target period of the previous day from the energy management system and calculating its average value.

[0046] : The standard deviation of the power load of the previous day, indicating the volatility of the load data. It is obtained by calculating the square root of the average of the squares of the differences between the power load at each time point of the previous day and its average value.

[0047] : The degree of change in power load, calculated using the previous method.

[0048] and : Adjustment coefficients for average load and load standard deviation, respectively. The coefficients are used to adjust the influence of average load and load volatility in the calculation of anomaly detection thresholds. The coefficients are set based on the system's historical performance and operational experience.

[0049] Calculation example: Set the following values: kW (average load during yesterday's target period), kW (yesterday's load standard deviation), (degree of change in power load), , .

[0050] Calculation process: calculate and : ; ; Add the above results together: ; application Adjustment Factor: ; Calculated kW is the adjusted abnormal load detection threshold. This means that any load reading above this threshold will be considered abnormal. This threshold takes into account recent load growth trends, ensuring that the anomaly detection mechanism can adapt to the latest operating conditions and environmental changes.

[0051] See also Figure 7 , the method for evaluating the degree of load excess is: Based on the abnormal load detection threshold adjustment result, the real-time load data of the equipment is extracted, and the real-time load data is compared with the adjusted abnormal load detection threshold, and the real-time load data exceeding the adjusted abnormal load detection threshold is identified to obtain the exceeding data identification result; Based on the exceeded data identification results, the formula is: ; Calculate the load excess , get the load exceeding degree information, where, is the real-time power load value, is the adjusted abnormal load detection threshold, is the scaling factor, is the adjustment factor, Exceeding the load level.

[0052] formula: ; Parameter details and how to obtain them: : Real-time monitored power load value. The parameter is directly obtained through real-time data sensors and reflects the current power consumption of the equipment.

[0053] : The adjusted abnormal load detection threshold, calculated by the previous method.

[0054] : Scaling factor, used to adjust the impact of the threshold in the logarithmic function. The specific value is set based on past statistical data and operational experience. The purpose is to adjust the sensitivity of the threshold adjustment.

[0055] : Adjustment coefficient, and threshold Used in conjunction with, in logarithmic functions to adjust The selection of this coefficient is based on the risk assessment and threshold adjustment requirements of the system.

[0056] Calculation example: Set the following parameters: kW: current real-time power load, kW: adjusted abnormal load detection threshold, : scaling factor, : Adjustment coefficient.

[0057] Calculation process: Calculation of the logarithmic part: ; This step uses a logarithmic function to adjust the influence of the threshold so that the threshold adjustment is more consistent with the actual load changes.

[0058] Application of the overall formula: ; Calculation results Indicates the real-time load excess degree, which is an important indicator indicating that the equipment is experiencing a higher load than expected. The larger the value, the higher the surface excess degree.

[0059] See also Figure 8 , the steps to obtain the real-time load data collection results are: Based on the load exceeding degree information, the load exceeding time point is recorded, and the load exceeding duration is extracted to obtain the duration information; Based on the duration information, by the formula: ; Calculate the load anomaly level, where For the The load exceeds the degree, is the total number of deviations that occurred during the target time period, For the The duration of the load exceeding the threshold, is the weight coefficient, is the logarithmic adjustment coefficient, is the abnormal load level; Based on the load anomaly level, the abnormal equipment identification is recorded, and the corresponding abnormal load data is extracted to obtain the real-time load data collection results.

[0060] formula: ; Parameter details and how to obtain them: : No. The secondary load excess degree is calculated using the previous method.

[0061] :The total number of deviations that occur within the target time period, determined based on the monitoring period and specific analysis needs.

[0062] : No. The duration of the load exceeding the threshold is recorded through the event log or real-time monitoring system.

[0063] and :The coefficients adjust the impact of the degree and duration of the exceedance respectively. They are set based on the sensitivity of the equipment operation and historical abnormal data to ensure the applicability and accuracy of the formula.

[0064] Calculation example: Set the following parameters: , : Load exceeds the degree, minute, Minutes: duration of the threshold being exceeded, , , .

[0065] Calculation process: Compute the logarithmic term: ; ; Apply the formula to calculate : ; ; Calculated It is a quantitative measure that reflects the combined effect of the degree and duration of power load exceedances in all time periods during the monitoring period. A high value indicates a significant load anomaly that requires further inspection or immediate action to prevent equipment overload or failure.

[0066] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. The load intelligent collection system based on the aliasing scenario of the station power system is characterized by: The system comprises: The load fluctuation analysis module is based on the station power system environment. By deploying corresponding sensors on differentiated power equipment, the power load data of differentiated equipment is monitored in real time. The power load data is received through the cloud server, and the aliased load fluctuation data caused by the start and stop of a single device is eliminated. By analyzing the power load data over a period of time, the volatility of the power load of differentiated equipment is evaluated to obtain the load fluctuation analysis results. The receiving frequency adjustment module adjusts the receiving frequency of the power load data of the differentiated equipment based on the load fluctuation analysis result and the basic receiving frequency of the data to obtain the data receiving frequency adjustment result; The abnormal threshold adjustment module receives the frequency adjustment result of the data, extracts the power load records of the differentiated equipment, analyzes the load change trend according to the average power load change in the same period of the day, adjusts the abnormal load detection threshold, and obtains the abnormal load detection threshold adjustment result; Based on the abnormal load detection threshold adjustment result, the abnormal load identification module compares the power load data of the differentiated equipment with the adjusted abnormal load detection threshold, evaluates the degree of load excess, and records the time point of load excess. Combined with the load excess duration, it evaluates the load abnormality level and obtains real-time load data collection results.

2. The load intelligent collection system based on the aliasing scenario of the station power system according to claim 1 is characterized in that: The method for eliminating the aliased load fluctuation data caused by the start and stop of a single device is: Based on the station power system environment, by deploying corresponding sensors on differentiated power equipment, the power load data of differentiated equipment is monitored in real time, and the power load data is received through the cloud server to obtain the real-time reception result of the load data; Based on the real-time reception result of the load data, a corresponding timestamp is marked for the differentiated power load data, and the start and stop time points of the differentiated equipment are identified by analyzing the normal operating time range of the differentiated equipment and combining the load data changes, thereby obtaining the equipment start and stop time identification result; Based on the equipment start and stop time identification result, the load data of each device that fluctuates due to the start and stop of a single device at the same time point is removed to obtain aliased load fluctuation removal data.

3. The load intelligent collection system based on the aliasing scenario of the station power system according to claim 2 is characterized in that: The steps for obtaining the load fluctuation analysis result are as follows: Extracting power load data of a target device for a period of time based on the aliased load fluctuation removal data to obtain a power load data extraction result; Based on the power load data, through the formula: ； Calculate the fluctuation of equipment power load , and the load fluctuation analysis results are obtained, where It is in The power load at a point in time, is the average power load in the corresponding time period, is the total number of time points, is the weight coefficient, is the sensitivity index, The fluctuation of the power load of the equipment.

4. The load intelligent collection system based on the aliasing scenario of the station power system according to claim 1 is characterized in that: The steps of obtaining the data receiving frequency adjustment result are: Based on the load fluctuation analysis result, extracting the basic receiving frequency of the data to obtain receiving frequency associated data; Based on the received frequency association data, by the formula: ； Calculate the adjusted receiving frequency ,in, The fluctuation of the equipment power load, is the receiving frequency of the current device data, is the volatility threshold, is the regulating factor, is the adjusted receiving frequency; Based on the adjusted receiving frequency , load data is received according to the corresponding receiving frequency to obtain the data receiving frequency adjustment result.

5. The load intelligent collection system based on the aliasing scenario of the station power system according to claim 1 is characterized in that: The method for analyzing load change trend is: Based on the data reception frequency adjustment result, extract the power load record of the differentiated equipment, calculate the average power load of the equipment in the target period, and obtain the average power load data of the target period within a period of time to obtain the average power load data acquisition result; Based on the average power load data, the result is obtained by the formula: ； Calculate the degree of power load change , get the power load change trend information, where and Respectively represent Tianhedi The average load during the target period of the day, is the regulating factor, is the baseline load value, The degree of change in power load.

6. The load intelligent collection system based on the aliasing scenario of the station power system according to claim 5 is characterized in that: The steps for obtaining the abnormal load detection threshold adjustment result are: Based on the power load change trend information, extract the average power load and the corresponding power load standard deviation data of the target period of the previous day to obtain load detection threshold associated data; Based on the load detection threshold associated data, by formula: ； Calculate the adjusted abnormal load detection threshold , and obtain the abnormal load detection threshold adjustment result, where: is the average power load during the target period of the previous day, is the standard deviation of power load on the previous day, is the degree of change in power load, and The adjustment coefficients for the mean load and the load standard deviation, respectively, is the adjusted abnormal load detection threshold.

7. The load intelligent collection system based on the aliasing scenario of the station power system according to claim 1 is characterized in that: The method for evaluating the degree of load excess is: Based on the abnormal load detection threshold adjustment result, extract the real-time load data of the equipment, and compare the real-time load data with the adjusted abnormal load detection threshold, identify the real-time load data exceeding the adjusted abnormal load detection threshold, and obtain the exceeding data identification result; Based on the exceeded data identification result, the formula is: ； Calculate the load excess , get the load exceeding degree information, where, is the real-time power load value, is the adjusted abnormal load detection threshold, is the scaling factor, is the adjustment factor, Exceeding the load level.

8. The load intelligent collection system based on the aliasing scenario of the station power system according to claim 7 is characterized in that: The steps for obtaining the real-time load data collection results are as follows: Based on the load excess degree information, record the load excess time point, and extract the load excess duration to obtain duration information; Based on the duration information, by the formula: ； Calculate the load anomaly level, where For the The load exceeds the degree, is the total number of deviations that occurred during the target time period, For the The duration of the load exceeding the threshold, is the weight coefficient, is the logarithmic adjustment coefficient, is the abnormal load level; Based on the load anomaly level, the identification of the device with the anomaly is recorded, and the corresponding abnormal load data is extracted to obtain a real-time load data collection result.

Images