Automatic load elimination and compensation method and system based on meteorological monitoring

Abstract

The invention discloses an automatic load elimination and compensation method and system based on meteorological monitoring, and relates to the technical field of power system load regulation, and the method comprises the steps: arranging sensors along a power transmission line, and collecting micrometeorological data and load data according to a time sequence; analyzing the influence of meteorological conditions on load fluctuation by using a linear regression model to obtain load prediction values under different meteorological conditions; grading identification is carried out; adjusting the exciting current and the rotating speed of the generator; predicting a load demand change trend of a next time period, and generating a load presetting plan; and executing load adjustment according to the load presetting plan, and adjusting the exciting current and the rotating speed of the generator to reach target load values. According to the automatic load elimination and compensation method based on meteorological monitoring provided by the invention, high quality and no noise interference of data entering the load prediction model are ensured through a multi-point micro-meteorological data acquisition and abnormal data cleaning technology, and the accuracy of load prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of load regulation of electric power systems, and in particular to an automatic load elimination and compensation method and system based on meteorological monitoring. Background Art

[0002] In the process of load regulation of power systems, meteorological conditions are the key factors affecting fluctuations in power demand, especially in areas where wind speed, temperature and humidity change dramatically. Such fluctuations often increase the instability of power system operation. At present, in the operation and maintenance of transmission lines under complex terrain or severe climatic conditions, although traditional monitoring systems can provide large-scale meteorological monitoring, their real-time monitoring capabilities of the local micro-meteorological environment along the transmission lines are insufficient, and it is difficult to capture abnormal meteorological changes in specific areas. In addition, traditional power load regulation schemes usually lack load forecasts based on meteorological conditions, and cannot adjust loads in time according to different meteorological conditions, resulting in lags in load regulation and insufficient response capabilities, making it difficult to meet the stable operation requirements of the power system when meteorological conditions change.

[0003] The meteorological monitoring systems in the prior art generally have the following deficiencies: data collection in the prior art is often single-point or a small number of multi-point monitoring, lacking accurate monitoring and recording of micro-meteorological data along the transmission lines, making it difficult to capture the impact of micro-meteorological data on load fluctuations in real time.

[0004] In extreme weather or sensor failure conditions, traditional monitoring systems lack effective means of detecting and cleaning abnormal data, resulting in abnormal data entering the load forecasting model, affecting the accuracy of the model and the load regulation effect of the system.

[0005] Traditional load forecasting schemes are mainly based on historical data and a single load change law. They are difficult to dynamically adapt to fluctuations in real-time meteorological conditions and cannot timely predict the impact of changes in meteorological conditions on load demand, resulting in load regulation lags.

[0006] Traditional regulation methods often adopt a unified adjustment range and frequency, and are unable to perform dynamic adjustments according to different risk conditions, resulting in excessive adjustment under low-risk conditions and insufficient response under high-risk conditions, increasing the system's energy consumption and load regulation instability.

[0007] In summary, the existing technology lacks a load forecasting and automatic load compensation method based on real-time meteorological monitoring, which can achieve accurate and dynamic load adjustment according to the real-time fluctuations of meteorological conditions to cope with changes in load demand under different risk states and ensure the stability and response speed of the power system. Summary of the invention

[0008] In view of the above-mentioned problems, the present invention is proposed.

[0009] Therefore, the technical problem solved by the present invention is that the existing power system load regulation method can usually only obtain single-point or regional meteorological data, lacks accurate monitoring of micro-meteorological data along the transmission line, and is difficult to capture the real-time impact of micro-meteorological conditions on local load fluctuations. Due to the inaccurate meteorological monitoring data, the load forecast results have large deviations and inaccurate adjustments, which affects the stability of the power system.

[0010] Due to the lack of effective means of detecting abnormal data, abnormal data caused by extreme weather conditions or sensor failures often enter the load forecasting model, causing model inaccuracy, thereby affecting the regulation effect and stability of the entire power system.

[0011] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for automatic load elimination and compensation based on meteorological monitoring, comprising:

[0012] Sensors are placed along the transmission lines to collect micro-meteorological data and load data in time series;

[0013] The linear regression model is used to analyze the impact of meteorological conditions on load fluctuations and obtain load forecast values ​​under different meteorological conditions;

[0014] Compare the load forecast value with the set load safety threshold and make classification identification;

[0015] Set the target value of load adjustment according to the classification mark, and adjust the excitation current and speed of the generator;

[0016] Use the linear regression model to calculate the updated micro-meteorological data, predict the load demand change trend in the next period, and generate a load pre-adjustment plan;

[0017] Perform load adjustment according to the load pre-adjustment plan, and adjust the generator excitation current and speed to achieve the target load value.

[0018] As a preferred solution of the automatic load elimination and compensation method based on meteorological monitoring described in the present invention, wherein: the collection of micro-meteorological data includes using a wind speed sensor to obtain wind speed data, a temperature sensor to obtain temperature data, and a humidity sensor to obtain humidity data at each collection point, and automatically generating a collection timestamp during collection;

[0019] Organize the micrometeorological data of each collection point in time series to form a micrometeorological data record file with the collection point location, timestamp, wind speed, temperature and humidity values;

[0020] Collecting the load data includes using a current sensor to collect the current value in the transmission line in real time, and generating a corresponding timestamp, and recording it as a current data file;

[0021] Use voltage sensors to collect voltage values ​​in transmission lines in real time, generate timestamps, and record them as voltage data files;

[0022] The data server calculates the current and voltage data to generate the load data at each acquisition time point, and stores the calculated load data as a load data file in time series.

[0023] As a preferred solution of the automatic load elimination and compensation method based on meteorological monitoring described in the present invention, wherein: the analysis of the impact of meteorological conditions on load fluctuations includes sorting the collected micro-meteorological data in time series, performing outlier detection according to a preset meteorological parameter range, removing abnormal data points that exceed the normal range of wind speed, temperature and humidity, and generating a cleaned micro-meteorological data file;

[0024] Match the timestamps of the cleaned micro-meteorological data files and load data files to generate micro-meteorological data and load data aligned in the time dimension;

[0025] Inputting the aligned data into a linear regression model, taking wind speed, temperature and humidity as independent variables and load fluctuation as a dependent variable, and training the linear regression model based on the data;

[0026] The trained linear regression model is used to input different meteorological condition data and the load forecast value is obtained through calculation.

[0027] As a preferred solution of the automatic load elimination and compensation method based on meteorological monitoring described in the present invention, wherein: the generation of risk status by graded identification includes setting a first risk threshold and a second risk threshold, wherein the first risk threshold is lower than the second risk threshold;

[0028] The load prediction value is compared with the first risk threshold and the second risk threshold. When the load prediction value is less than the first risk threshold, it is determined to be a safe state; when the load prediction value is greater than or equal to the first risk threshold and less than or equal to the second risk threshold, it is determined to be a low-risk state; when the load prediction value is greater than the second risk threshold, it is determined to be a high-risk state.

[0029] As a preferred solution of the automatic load elimination and compensation method based on meteorological monitoring described in the present invention, wherein: the adjusting the excitation current and speed of the generator includes setting the load adjustment parameters if it is determined to be a low-risk state, so as to adjust the excitation current of the generator within the range of ±5% of the load fluctuation, and maintain the current micro-meteorological data collection frequency, and the collection frequency is set to once every 5 minutes;

[0030] If it is determined to be a high-risk state, the load adjustment parameters are set to adjust the excitation current and speed of the generator to within ±15% of the load fluctuation, and the collection frequency of micrometeorological data is increased to twice the current collection frequency, which is set to once every 2 minutes.

[0031] As a preferred solution of the automatic load elimination and compensation method based on meteorological monitoring described in the present invention, wherein: the generation of the load pre-adjustment plan includes inputting the updated micro-meteorological data into the linear regression model to predict the load demand value of the next period;

[0032] If the predicted value exceeds a preset change threshold of the current load, a load pre-adjustment plan is generated, wherein the change threshold is set based on the standard deviation of historical load fluctuations and the expected range of meteorological fluctuations;

[0033] The load adjustment target value for the next period is set in the load pre-adjustment plan. As a preferred solution of the automatic load elimination and compensation method based on meteorological monitoring described in the present invention, 7. The automatic load elimination and compensation method based on meteorological monitoring described in claim 6 is characterized in that: the load adjustment according to the load pre-adjustment plan includes taking the target value in the load pre-adjustment plan as the adjustment reference, and adjusting the excitation current of the generator to the corresponding pre-adjustment current value;

[0034] Adjust the generator speed to the range set by the load pre-adjustment plan so that the generator output power is close to the load demand target value;

[0035] After the adjustment is completed, the actual output power of the generator and the target value in the current load pre-adjustment plan are recorded to determine whether the deviation exceeds the preset tolerance range;

[0036] If the deviation exceeds the tolerance range, it is judged as an abnormal load state and an abnormal alarm information is generated.

[0037] Another object of the present invention is to provide an automatic load elimination and compensation system based on meteorological monitoring, which can solve the problems of insufficient accurate monitoring of micro-meteorological data, untimely load forecasting, and lack of flexibility in regulation schemes in existing power system load regulation by constructing an automatic load elimination and compensation system based on meteorological monitoring, and realize real-time prediction, hierarchical regulation and abnormal feedback of load demand under complex meteorological conditions.

[0038] To solve the above technical problems, the present invention provides the following technical solutions: a load automatic elimination and compensation system based on meteorological monitoring, comprising: a data acquisition module, a load prediction module, a risk grading module, an adjustment control module, a demand prediction module and a pre-adjustment execution module; the data acquisition module is used to arrange sensors along the transmission line to collect micro-meteorological data and load data in time series; the load prediction module is used to analyze the impact of meteorological conditions on load fluctuations using a linear regression model to obtain load prediction values ​​under different meteorological conditions; the risk grading module is used to compare the load prediction value with the set load safety threshold and perform a grading mark; the adjustment control module is used to set the target value of the load adjustment according to the grading mark, and adjust the excitation current and speed of the generator; the demand prediction module is used to use a linear regression model to calculate the updated micro-meteorological data, predict the load demand change trend in the next period, and generate a load pre-adjustment plan; the pre-adjustment execution module is used to perform load adjustment according to the load pre-adjustment plan, and adjust the excitation current and speed of the generator to reach the target load value.

[0039] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the automatic load elimination and compensation method based on meteorological monitoring as described above are implemented.

[0040] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the automatic load elimination and compensation method based on meteorological monitoring as described above.

[0041] Beneficial effects of the present invention: The automatic load elimination and compensation method based on meteorological monitoring provided by the present invention ensures the high quality and noise-free data entering the load forecasting model through multi-point micro-meteorological data collection and abnormal data cleaning technology, thereby improving the accuracy of load forecasting. The linear regression model constructed based on meteorological data can predict the impact of meteorological conditions on load fluctuations in real time, achieve the accuracy and adaptability of load regulation, and significantly improve the response speed compared with the existing technology.

[0042] The hierarchical regulation mechanism of the present invention sets multi-level risk thresholds and selects different regulation amplitudes and frequencies according to the risk status of load demand, effectively saves energy under low-risk conditions and responds promptly under high-risk conditions, thereby achieving the effect of dynamic energy-saving regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0044] Figure 1 An overall flow chart of an automatic load elimination and compensation method based on meteorological monitoring provided by an embodiment of the present invention.

[0045] Figure 2 An overall structural diagram of an automatic load elimination and compensation system based on meteorological monitoring provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Example 1

[0049] Reference Figure 1 , which is an embodiment of the present invention, provides a method for automatic load elimination and compensation based on meteorological monitoring, comprising:

[0050] Sensors are placed along the transmission lines to collect micro-meteorological data and load data in time series;

[0051] The linear regression model is used to analyze the impact of meteorological conditions on load fluctuations and obtain load forecast values ​​under different meteorological conditions;

[0052] Compare the load forecast value with the set load safety threshold and make classification identification;

[0053] Set the target value of load adjustment according to the classification mark, and adjust the excitation current and speed of the generator;

[0054] Use the linear regression model to calculate the updated micro-meteorological data, predict the load demand change trend in the next period, and generate a load pre-adjustment plan;

[0055] Perform load adjustment according to the load pre-adjustment plan, and adjust the generator excitation current and speed to achieve the target load value.

[0056] The collecting of micro-meteorological data includes using a wind speed sensor to obtain wind speed data, a temperature sensor to obtain temperature data, and a humidity sensor to obtain humidity data at each collection point, and automatically generating a collection timestamp during the collection;

[0057] Organize the micrometeorological data of each collection point in time series to form a micrometeorological data record file with the collection point location, timestamp, wind speed, temperature and humidity values;

[0058] Collecting the load data includes using a current sensor to collect the current value in the transmission line in real time, and generating a corresponding timestamp, and recording it as a current data file;

[0059] Use voltage sensors to collect voltage values ​​in transmission lines in real time, generate timestamps, and record them as voltage data files;

[0060] The data server calculates the current and voltage data to generate the load data at each acquisition time point, and stores the calculated load data as a load data file in time series.

[0061] It should be noted that the present invention collects micro-meteorological data in real time by arranging wind speed, temperature and humidity sensors at various collection points, and automatically generates a timestamp for each data during the collection process, thereby realizing precise spatial and temporal positioning of the collected data. At the same time, current and voltage sensors are used to collect load data and generate load data files that reflect load fluctuations. This multi-point precise collection not only provides more comprehensive micro-meteorological environmental data, but also ensures that meteorological and load data can be aligned in time with high precision, avoiding data misalignment in the time dimension, and improving the accuracy of subsequent load prediction and load adjustment. This collection method provides a high-quality data basis for analyzing the impact of meteorological conditions on load fluctuations. Compared with single-point monitoring, it significantly reduces the noise problem caused by data collection errors, making the subsequent linear regression model training effect more ideal, thereby obtaining reliable prediction results.

[0062] The analysis of the impact of meteorological conditions on load fluctuations includes sorting the collected micro-meteorological data into time series, performing outlier detection according to a preset meteorological parameter range, removing abnormal data points that exceed the normal range of wind speed, temperature and humidity, and generating a cleaned micro-meteorological data file;

[0063] Match the timestamps of the cleaned micro-meteorological data files and load data files to generate micro-meteorological data and load data aligned in the time dimension;

[0064] Inputting the aligned data into a linear regression model, taking wind speed, temperature and humidity as independent variables and load fluctuation as a dependent variable, and training the linear regression model based on the data;

[0065] The trained linear regression model is used to input different meteorological condition data and the load forecast value is obtained through calculation.

[0066] It should be noted that in the data cleaning stage, the present invention performs abnormal data detection on the collected micro-meteorological data, and removes abnormal data points that exceed the normal range of wind speed, temperature and humidity by setting a threshold based on the standard deviation range of historical statistical data. This elimination operation effectively avoids the impact of data noise caused by extreme meteorological conditions or sensor failures while ensuring the stability of the input data for model training. This improves the stability and consistency of load forecasting, enables the prediction model to more concentratedly reflect the load fluctuation trend under normal meteorological conditions, enhances the accuracy and practicality of load forecasting results, and especially ensures the robustness of model training in the face of unstable meteorological environments, thereby improving the applicability of load forecasting.

[0067] The constructed linear regression model takes meteorological data such as wind speed, temperature, and humidity as independent variables, and trains with load fluctuation as the dependent variable to obtain a quantitative model of load fluctuation. The model can generate load forecast values ​​by inputting meteorological data in real time, so as to predict the specific impact of meteorological changes on load demand in advance. Unlike the traditional fixed load forecasting method, this model can adjust the forecast results through real-time data of different meteorological conditions, which greatly improves the system's sensitivity to meteorological changes and the speed of response to changes in load demand. The model ensures that the power system can accurately predict load demand when the weather fluctuates, significantly enhancing the applicability of load forecasting and the regulation and control capabilities of the power system.

[0068] The generating risk status by performing hierarchical identification includes setting a first risk threshold and a second risk threshold, wherein the first risk threshold is lower than the second risk threshold;

[0069] The load prediction value is compared with the first risk threshold and the second risk threshold. When the load prediction value is less than the first risk threshold, it is determined to be a safe state; when the load prediction value is greater than or equal to the first risk threshold and less than or equal to the second risk threshold, it is determined to be a low-risk state; when the load prediction value is greater than the second risk threshold, it is determined to be a high-risk state.

[0070] It should be noted that, in the process of load adjustment, the present invention sets a first and a second risk threshold, compares the load prediction value with the two thresholds, and generates three load states: safe, low risk, and high risk. Different load states provide a hierarchical basis for subsequent load adjustments, enabling the system to respond more quickly under high-risk conditions, while adopting milder adjustment measures under low-risk conditions to avoid excessive adjustments. This hierarchical management strategy solves the problem that traditional load adjustment methods are difficult to cope with sudden changes in load demand, and ensures the rapid response capability of the power system when the load demand suddenly increases. The hierarchical response not only improves the accuracy of load adjustment, but also reduces unnecessary system adjustment actions, making the power system operation more flexible and efficient, and achieving significant energy-saving effects.

[0071] The adjusting of the excitation current and speed of the generator includes setting a load adjustment parameter if it is determined to be a low risk state, so as to adjust the excitation current of the generator within a range of ±5% of the load fluctuation, and maintain the current micro-meteorological data collection frequency, which is set to once every 5 minutes;

[0072] If it is determined to be a high-risk state, the load adjustment parameters are set to adjust the excitation current and speed of the generator to within ±15% of the load fluctuation, and the collection frequency of micrometeorological data is increased to twice the current collection frequency, which is set to once every 2 minutes.

[0073] It should be noted that the present invention sets a small load adjustment range under low-risk conditions and maintains a low data acquisition frequency, thereby avoiding frequent adjustment operations and unnecessary energy consumption while ensuring system stability. Under high-risk conditions, the system will expand the adjustment range of the excitation current and increase the data acquisition frequency to once every 2 minutes, so that the system can capture the impact of meteorological changes more quickly and quickly complete adjustments when load demand surges. The dynamic adjustment strategy based on risk status enables the system to optimize the adjustment range and data acquisition frequency according to the real-time load conditions, effectively improving the system's response speed and energy-saving effect. This dynamic adjustment mechanism significantly enhances the system's load regulation accuracy and energy-saving effect, making the system more stable and reliable when responding to sudden meteorological events.

[0074] The generating of the load pre-adjustment plan includes inputting the updated micro-meteorological data into a linear regression model to predict the load demand value for the next period;

[0075] If the predicted value exceeds a preset change threshold of the current load, a load pre-adjustment plan is generated, wherein the change threshold is set based on the standard deviation of historical load fluctuations and the expected range of meteorological fluctuations;

[0076] Set the load adjustment target value for the next period in the load pre-adjustment plan.

[0077] It should be noted that in the generation of the load pre-adjustment plan and the abnormal load alarm link, the present invention generates the load demand value for the next time period through a prediction model and sets the target load value accordingly. The system sets the excitation current and speed range of the load adjustment in advance according to the predicted value of the load demand, providing an accurate target value for the generator load adjustment. During the actual adjustment process, the system monitors the output power of the generator in real time, and automatically generates abnormal alarm information when its deviation exceeds the preset tolerance range to remind the monitoring personnel or trigger the automatic adjustment program. This strategy combining pre-adjustment and alarm enables the system to not only achieve forward-looking load regulation, but also respond quickly when abnormal load deviations occur, ensuring that load demand is met and the safety of the power system.

[0078] The performing load adjustment according to the load pre-adjustment plan includes taking the target value in the load pre-adjustment plan as an adjustment reference, and adjusting the excitation current of the generator to a corresponding pre-adjustment current value;

[0079] Adjust the generator speed to the range set by the load pre-adjustment plan so that the generator output power is close to the load demand target value;

[0080] After the adjustment is completed, the actual output power of the generator and the target value in the current load pre-adjustment plan are recorded to determine whether the deviation exceeds the preset tolerance range;

[0081] If the deviation exceeds the tolerance range, it is judged as an abnormal load state and an abnormal alarm information is generated.

[0082] Based on the stored exception data, perform the following steps:

[0083] Conduct statistical analysis on the deviation data and calculate the average deviation and fluctuation range between the current load adjustment parameter and the target value;

[0084] The reference value of the excitation current is adjusted according to the average deviation so that the excitation current deviation of the next cycle is reduced to less than 50% of the average deviation;

[0085] Reset the speed adjustment range according to the fluctuation amplitude to reduce the load fluctuation and keep the load fluctuation of the next cycle within the target fluctuation range;

[0086] The updated excitation current reference value and speed adjustment range are stored in the adjustment parameter library for use in the load adjustment operation of the next cycle.

[0087] Example 2

[0088] Reference Figure 2 , which is an embodiment of the present invention, provides a load automatic elimination and compensation system based on meteorological monitoring, comprising:

[0089] Data collection module 100, load forecasting module 200, risk classification module 300, adjustment control module 400, demand forecasting module 500 and pre-adjustment execution module 600;

[0090] The data acquisition module 100 is used to arrange sensors along the transmission line to collect micro-meteorological data and load data in time series;

[0091] The load prediction module 200 is used to analyze the impact of meteorological conditions on load fluctuations using a linear regression model to obtain load prediction values ​​under different meteorological conditions;

[0092] The risk classification module 300 is used to compare the load prediction value with the set load safety threshold value and perform classification identification;

[0093] The adjustment control module 400 is used to set the target value of load adjustment according to the classification mark, and adjust the excitation current and speed of the generator;

[0094] The demand forecasting module 500 is used to calculate the updated micro-meteorological data using a linear regression model, predict the load demand change trend in the next period, and generate a load pre-adjustment plan;

[0095] The pre-adjustment execution module 600 is used to execute load adjustment according to the load pre-adjustment plan, and adjust the excitation current and speed of the generator to reach the target load value.

[0096] Example 3

[0097] An embodiment of the present invention is different from the first two embodiments in that:

[0098] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0099] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0100] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0101] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0102] Example 4

[0103] As an embodiment of the present invention, a method for automatic load elimination and compensation based on meteorological monitoring is provided. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0104] The experiment simulates the transmission line environment under complex meteorological conditions.

[0105] The experimental time was set as a continuous 24-hour monitoring cycle, including time periods with variable meteorological conditions.

[0106] The traditional method is based on a fixed adjustment strategy, with a collection frequency of once every 10 minutes and no graded adjustment. The method of the present invention is based on micro-meteorological monitoring, linear regression model, graded adjustment, load pre-adjustment and feedback mechanism, and the collection frequency is dynamically adjusted according to the risk status. The system of each method collects multi-point meteorological data (wind speed, temperature, humidity) and load data respectively. The traditional method collects at a fixed frequency, and the method of the present invention dynamically adjusts the collection frequency according to the risk level. The traditional method uses historical average data for load forecasting and adjusts the load output in real time. The method of the present invention uses a linear regression model to forecast load, dynamically predicts the load change trend based on real-time meteorological data, and dynamically adjusts the excitation current and speed of the generator according to different risk states. The method of the present invention automatically generates a load pre-adjustment plan under high-risk conditions. If the predicted value deviation exceeds the tolerance range, abnormal feedback is triggered and the adjustment data is recorded; the traditional method does not have this automatic feedback mechanism. Continuous 24-hour monitoring and adjustment records are recorded to generate load adjustment deviation, response time, system energy consumption and stability data. The experimental results are shown in Table 1.

[0107] Table 1 Comparison of experimental results

[0108]

[0109]

[0110] The method of the present invention adopts multi-point micro-meteorological data collection and linear regression model. Traditional methods rely on data from a single or a small number of points, and it is difficult to fully capture the micro-meteorological fluctuations along the transmission line, so the load forecast results are prone to deviations. The present invention collects wind speed, temperature and humidity data by deploying multiple sensors along the line, and aligns the data in combination with timestamps, ensuring the accurate synchronization of meteorological and load data. In this way, the model can use comprehensive micro-meteorological data to predict fluctuations in load demand, so that load forecasts can more accurately reflect real-time meteorological changes. This adjustment method based on precise data input avoids the adjustment deviation caused by incomplete or delayed data in traditional methods, and greatly improves the accuracy of load regulation.

[0111] The traditional method uses a fixed collection frequency and cannot automatically adjust according to the speed of meteorological changes, resulting in the data collection and load regulation speed not keeping up with actual needs when the weather changes rapidly. The present invention uses a risk grading mechanism to automatically increase the collection frequency and adjustment speed under high-risk conditions, so that the system can quickly respond to load changes caused by meteorological fluctuations. At the same time, the linear regression model quickly calculates the load forecast value based on the real-time updated meteorological data, and directly feeds it back to the regulation system, so that the system can closely track meteorological changes. This combination of graded regulation and dynamic collection enables the system to have the ability to respond quickly when the weather fluctuates violently, significantly improving the response speed of load regulation.

[0112] Traditional load regulation schemes do not distinguish between risk states, and uniformly adjust according to fixed amplitudes and frequencies. Even in the case of low load demand, there is over-regulation, resulting in energy waste. The present invention divides load states into low risk and high risk according to risk levels, and adopts a small amplitude and low frequency regulation strategy in low risk states to avoid unnecessary energy consumption; in high risk states, the system ensures the safety of load demand through large amplitude and high frequency regulation. Such a hierarchical regulation method not only reasonably allocates system energy consumption, but also enables the system to maintain optimal energy efficiency under different load states, greatly reducing unnecessary power consumption.

[0113] Due to the lack of forward-looking prediction of future load demand, traditional methods usually make adjustments only after load fluctuations occur, resulting in a slow response of the system when the load changes suddenly, affecting the stability of the system. The present invention generates a load pre-adjustment plan, predicts the load demand of the next period in advance and formulates adjustment parameters, so that the system can more proactively respond to future load changes. At the same time, the automatic feedback mechanism triggers adjustments in time when the load deviation exceeds the preset range, and further reduces load fluctuations by automatically optimizing the excitation current and speed parameters. This combination of forward-looking prediction and real-time feedback enables the system to effectively maintain a stable operating state under complex meteorological conditions, which not only reduces the amplitude of load fluctuations, but also ensures the continuous stability of the system.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for automatic load elimination and compensation based on meteorological monitoring, characterized in that: include: Sensors are placed along the transmission lines to collect micro-meteorological data and load data in time series; The linear regression model is used to analyze the impact of meteorological conditions on load fluctuations and obtain load forecast values ​​under different meteorological conditions; Compare the load forecast value with the set load safety threshold and make classification identification; Set the target value of load adjustment according to the classification mark, and adjust the excitation current and speed of the generator; Use the linear regression model to calculate the updated micro-meteorological data, predict the load demand change trend in the next period, and generate a load pre-adjustment plan; Perform load adjustment according to the load pre-adjustment plan, and adjust the generator excitation current and speed to achieve the target load value.

2. The method for automatic load elimination and compensation based on meteorological monitoring according to claim 1, characterized in that: The collecting of micro-meteorological data includes using a wind speed sensor to obtain wind speed data, a temperature sensor to obtain temperature data, and a humidity sensor to obtain humidity data at each collection point, and automatically generating a collection timestamp during the collection; Organize the micrometeorological data of each collection point in time series to form a micrometeorological data record file with the collection point location, timestamp, wind speed, temperature and humidity values; Collecting the load data includes using a current sensor to collect the current value in the transmission line in real time, and generating a corresponding timestamp, and recording it as a current data file; Use voltage sensors to collect voltage values ​​in transmission lines in real time, generate timestamps, and record them as voltage data files; The data server calculates the current and voltage data to generate the load data at each acquisition time point, and stores the calculated load data as a load data file in time series.

3. The automatic load elimination and compensation method based on meteorological monitoring according to claim 2 is characterized in that: The analysis of the impact of meteorological conditions on load fluctuations includes sorting the collected micro-meteorological data into time series, performing outlier detection according to a preset meteorological parameter range, removing abnormal data points that exceed the normal range of wind speed, temperature and humidity, and generating a cleaned micro-meteorological data file; Match the timestamps of the cleaned micro-meteorological data files and load data files to generate micro-meteorological data and load data aligned in the time dimension; Inputting the aligned data into a linear regression model, taking wind speed, temperature and humidity as independent variables and load fluctuation as a dependent variable, and training the linear regression model based on the data; The trained linear regression model is used to input different meteorological condition data and the load forecast value is obtained through calculation.

4. The method for automatic load elimination and compensation based on meteorological monitoring according to claim 3 is characterized in that: The generating risk status by performing hierarchical identification includes setting a first risk threshold and a second risk threshold, wherein the first risk threshold is lower than the second risk threshold; Compare the load prediction value with the first risk threshold and the second risk threshold, and determine that it is in a safe state when the load prediction value is less than the first risk threshold; When the load forecast value is greater than or equal to the first risk threshold and less than or equal to the second risk threshold, it is determined to be a low risk state; When the load prediction value is greater than the second risk threshold, it is determined to be a high risk state.

5. The automatic load elimination and compensation method based on meteorological monitoring according to claim 4 is characterized in that: The adjusting of the excitation current and speed of the generator includes setting a load adjustment parameter if it is determined to be a low risk state, so as to adjust the excitation current of the generator within a range of ±5% of the load fluctuation, and maintain the current micro-meteorological data collection frequency, which is set to once every 5 minutes; If it is determined to be a high-risk state, the load adjustment parameters are set to adjust the excitation current and speed of the generator to within ±15% of the load fluctuation, and the collection frequency of micrometeorological data is increased to twice the current collection frequency, which is set to once every 2 minutes.

6. The method for automatic load elimination and compensation based on meteorological monitoring according to claim 5, characterized in that: The generating of the load pre-adjustment plan includes inputting the updated micro-meteorological data into a linear regression model to predict the load demand value for the next period; If the predicted value exceeds a preset change threshold of the current load, a load pre-adjustment plan is generated, wherein the change threshold is set based on the standard deviation of historical load fluctuations and the expected range of meteorological fluctuations; Set the load adjustment target value for the next period in the load pre-adjustment plan.

7. The automatic load elimination and compensation method based on meteorological monitoring according to claim 6 is characterized in that: The performing load adjustment according to the load pre-adjustment plan includes taking the target value in the load pre-adjustment plan as an adjustment reference, and adjusting the excitation current of the generator to a corresponding pre-adjustment current value; Adjust the generator speed to the range set by the load pre-adjustment plan so that the generator output power is close to the load demand target value; After the adjustment is completed, the actual output power of the generator and the target value in the current load pre-adjustment plan are recorded to determine whether the deviation exceeds the preset tolerance range; If the deviation exceeds the tolerance range, it is judged as an abnormal load state and an abnormal alarm information is generated.

8. A system using the automatic load elimination and compensation method based on meteorological monitoring as claimed in any one of claims 1 to 7, characterized in that: include: A data collection module (100), a load prediction module (200), a risk classification module (300), an adjustment control module (400), a demand prediction module (500), and a pre-adjustment execution module (600); The data acquisition module (100) is used to arrange sensors along the power transmission line to collect micro-meteorological data and load data in time series; The load prediction module (200) is used to analyze the impact of meteorological conditions on load fluctuations using a linear regression model to obtain load prediction values ​​under different meteorological conditions; The risk classification module (300) is used to compare the load prediction value with the set load safety threshold value and perform classification identification; The adjustment control module (400) is used to set a target value for load adjustment according to the classification mark, and adjust the excitation current and rotation speed of the generator; The demand prediction module (500) is used to calculate the updated micro-meteorological data using a linear regression model, predict the load demand change trend in the next period, and generate a load pre-adjustment plan; The pre-adjustment execution module (600) is used to execute load adjustment according to the load pre-adjustment plan, and adjust the excitation current and rotation speed of the generator to reach the target load value.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the automatic load elimination and compensation method based on meteorological monitoring described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the automatic load elimination and compensation method based on meteorological monitoring according to any one of claims 1 to 7 are implemented.

Images