Smart power grid load prediction system and method

Abstract

The invention relates to the technical field of power load prediction, in particular to an intelligent power grid load prediction system and method, and the system comprises a power grid load coupling relation calculation module, a power grid load dynamic adjustment module, a meteorological influence power grid load correction module, a load prediction model input optimization module, and a power grid load prediction error evaluation module. According to the method, the load change rate is extracted, the load increment and the load flow proportion are calculated, the load dynamic coupling relation is described, the voltage phase angle deviation is calculated in combination with the power grid topology, the load prediction area linkage is enhanced, parameters are adjusted based on the previous load propagation delay, the sudden fluctuation response capacity of the model is improved, and the load slope is analyzed in combination with meteorological data. A temperature and humidity sensitive interval is set, extreme weather adaptability is enhanced, input parameters are optimized by using a load coupling correction value, data distortion is reduced, long-term prediction stability is improved, load dynamic adjustment, meteorological influence modeling and input optimization precision are improved, and accurate support is provided for power grid dispatching.

Description

Technical Field

[0001] The present invention relates to the technical field of power load forecasting, and in particular to a smart grid load forecasting system and method. Background Art

[0002] The field of power load forecasting technology includes methods and technologies for analyzing and predicting the load demand of power systems. The core content of this technical field involves using multiple data sources such as past load data, meteorological information, user behavior patterns, and power grid operation status, combined with mathematical modeling, statistical analysis, and machine learning technology to predict future power loads. The research directions in this field mainly include short-term, medium-term, and long-term load forecasting, and the forecasting methods at different time scales have different focuses. For example, short-term load forecasting is mainly used for real-time scheduling and optimization of power grids, relying on time series analysis methods and neural network models, while medium- and long-term forecasting relies more on macro factors such as economic growth trends, industrial structure adjustments, and population changes to provide a basis for power planning and investment decisions. In addition, this technical field also involves uncertainty analysis of load forecasting, abnormal load detection, and the construction of adaptive forecasting models to improve the accuracy and reliability of forecasts.

[0003] Among them, the smart grid load forecasting system refers to a system that combines power load forecasting technology and uses the Internet of Things, big data processing and artificial intelligence to intelligently predict the load demand of the power grid. The system includes multiple links such as data collection, data preprocessing, feature extraction, load forecasting modeling and forecast result analysis. The data collection link is responsible for collecting user power consumption data, environmental data and power grid operation status information. The data preprocessing link processes the original data through methods such as denoising, missing value filling and data normalization. The feature extraction link selects key factors that have a greater impact on load changes. The load forecasting modeling link uses deep learning models, regression analysis or combined forecasting methods to build a load forecasting model. The forecast result analysis link is used to evaluate the accuracy of the forecast and adjust and optimize the results. The main goal of the system is to improve the accuracy of load forecasting and provide a scientific basis for the optimal dispatching, demand response management and new energy consumption of the power system.

[0004] Existing technologies fail to accurately quantify load coupling relationships and are difficult to reflect the inter-regional load linkage effects, resulting in large deviations in the prediction model under load mutation conditions. The lack of a load propagation delay correction mechanism makes it impossible to effectively adjust the prediction parameters to cope with the impact of past load fluctuations, reducing the ability to adapt to short-term drastic load changes. The method for handling meteorological factors is single, and the temperature and humidity sensitive ranges and grid voltage fluctuation characteristics are not fully considered. The prediction error is significantly increased under extreme weather conditions. The input data is not optimized enough, the synergy between dynamic load adjustment and environmental factors is ignored, and the model parameter configuration lacks real-time adjustment, affecting the stability of long-term predictions. The above problems restrict the reliability of grid load forecasting in complex environments and are not conducive to refined power dispatching. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a smart grid load forecasting system and method.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A smart grid load forecasting system comprises: The grid load coupling relationship calculation module extracts the load change rate from the regional grid load data, calculates the load increment and the power flow ratio of adjacent substations, calls the grid topology parameters to calculate the voltage phase angle offset, and calculates the weight ratio to obtain the grid load coupling weight matrix; The grid load dynamic adjustment module calls the grid load coupling weight matrix, obtains the real-time load change rate, calculates the load mutation factor, extracts the supply and demand offset and the power flow adjustment, calculates the voltage offset change, and calls the previous load fluctuation propagation delay after adjusting the weight matrix to obtain the load coupling dynamic correction value; The weather-affected grid load correction module obtains the past regional weather data, combines the load change rate, calculates the load slope, obtains the temperature sensitive range and humidity critical value, calls the grid voltage fluctuation range, and obtains the weather load correction factor; The load forecasting model input optimization module calls the load coupling dynamic correction value, adjusts the load weight of the adjacent area in the load forecasting model, calls the meteorological load correction factor, corrects the proportion of meteorological parameters, and calculates the input adjustment range to obtain the optimized forecast input parameters; The power grid load forecast error evaluation module calls the optimized forecast input parameters, runs the load forecast model, calculates the error rate according to the power grid load data and the forecast error distribution trend, and obtains the load forecast error evaluation result.

[0007] As a further solution of the present invention, the power grid load coupling weight matrix includes load increment, adjacent substation flow ratio, voltage phase angle offset, and weight ratio; the load coupling dynamic correction value includes load mutation factor, supply and demand offset, power flow adjustment amount, voltage offset change, and previous load fluctuation propagation delay; the meteorological load correction factor includes load slope, temperature sensitive interval, humidity critical value, and power grid voltage fluctuation range; the optimized prediction input parameters include load coupling dynamic correction value, adjacent area load weight, meteorological load correction factor, meteorological parameter proportion, and input adjustment amplitude; the load prediction error evaluation result includes power grid load data, prediction error distribution trend, and error rate.

[0008] As a further solution of the present invention, the power grid load coupling relationship calculation module includes: The load change rate extraction submodule obtains regional power grid load data, extracts load changes in multiple time periods, calculates the load change rate per unit time, filters abnormal data based on load change trends, and obtains a load change rate sequence; The load increment calculation submodule calculates the load increments in adjacent time periods based on the load change rate sequence, collects the power flow change data of the substation, matches the load increment distribution according to the power flow change trend, and obtains the load increment matching sequence; The load coupling weight matrix calculation submodule calculates the voltage phase angle offset based on the load increment matching sequence and calls the grid topology parameters, and constructs the load distribution relationship between substations according to the offset, using the formula: ; Calculate the load coupling weight ratios between multiple substations, aggregate the calculation results, and establish a grid load coupling weight matrix; in, Representative substation and The load coupling weight between Representative substation The load power, Representative substation The voltage phase angle, Representative substation The sum of the load differences with all substations, Representative substation The sum of squares of voltage phase angle differences with all substations.

[0009] As a further solution of the present invention, the power grid load dynamic adjustment module includes: The load change calculation submodule calls the grid load coupling weight matrix, calculates the real-time load change rate, extracts the load mutation factor in the grid operation, and screens the key load fluctuation nodes based on the load change rate, calculates the load propagation ratio between multiple nodes, and generates the key load change ratio; The load offset adjustment submodule calls the key load change ratio, extracts the supply and demand difference data, calculates the supply and demand offset, and combines the load propagation ratio to obtain the power flow adjustment of multiple load nodes using the formula: ; Calculate and obtain the power adjustment values ​​of multiple load nodes, integrate the adjusted voltage offset data, and obtain the voltage offset change; in, represents the power flow adjustment, Represents load node The weight of the overall load adjustment, Represents load node The current load demand value, Represents load node The current power supply value, To avoid small parameters with zero denominator, it represents the total number of grid load nodes; The load coupling dynamic correction submodule calls the voltage offset change, adjusts the grid load coupling weight matrix, and calculates the load coupling correction coefficient in combination with the propagation delay of previous load fluctuations to obtain the load coupling dynamic correction value.

[0010] As a further solution of the present invention, the weather-affected grid load correction module comprises: The meteorological data extraction submodule obtains the past meteorological data of the area, extracts the parameters of temperature and humidity, screens the meteorological information that meets the data integrity requirements, excludes data missing items, calculates the temperature and humidity change ranges in differentiated time periods, calculates the temperature change trend and humidity change rate, and adjusts the abnormal data fluctuation range to generate a regional meteorological parameter set; The meteorological load change calculation submodule calls the power grid load data based on the regional meteorological parameter set, calculates the load change trend under differentiated meteorological conditions, obtains the load change rate based on the time series data, and combines the temperature and humidity change rate to adopt the formula: ; The load slope is calculated; in, represents the load slope, Representative time period The load variation within Representative time period The weight coefficient of represents the temperature change, Representative time period The humidity value, represents the humidity threshold, Represents the total number of time periods considered in calculating the load slope; The meteorological load correction factor calculation submodule calls the load slope, combines the regional meteorological parameter set, screens the temperature sensitive range, calculates the proportion of temperature on load change, obtains the humidity critical value, and calls the grid voltage fluctuation range, calculates the meteorological influencing factor weight, and combines multiple influencing parameters to calculate the meteorological load correction factor.

[0011] As a further solution of the present invention, the load forecasting model input optimization module includes: The load weight adjustment submodule adjusts the load weights of adjacent areas in the load forecasting model based on the load coupling dynamic correction value, compares the differentiated regional load data, screens the load weight change trend of adjacent areas, adjusts the load weight value according to the load coupling dynamic correction value, calculates the corrected regional load proportion, and obtains the corrected load weight coefficient; The meteorological parameter correction submodule calls the meteorological load correction factor, calculates the correction value according to the change in the proportion of the meteorological parameters, compares the load changes under differentiated meteorological conditions, adjusts the proportion of the meteorological parameters in the load forecast, calculates the corrected meteorological impact parameters, and obtains the corrected meteorological impact factors; The input parameter optimization calculation submodule calls the modified load weight coefficient and the modified meteorological influence factor, combines the current load forecast input data, and adopts the formula: ; The optimized and adjusted input parameter values ​​are obtained by operation to obtain the optimized predicted input parameters; in, represents the optimized prediction input parameters, represents the corrected load weight coefficient, Represents the adjacent area load data, represents the corrected meteorological impact factor, Represents the proportion of meteorological parameters, represents the load change rate factor, represents the time period parameter, represents the time decay factor of the load effect, Represents the upper limit of the calculation, which is the maximum value of an indicator or range.

[0012] As a further solution of the present invention, the system further includes a power grid load forecast error assessment module; The power grid load forecast error evaluation module calls the optimized forecast input parameters, runs the load forecast model, calculates the error rate according to the power grid load data and the forecast error distribution trend, and obtains the load forecast error evaluation result; The load forecast error evaluation result includes power grid load data, forecast error distribution trend, and error rate.

[0013] As a further solution of the present invention, the power grid load forecast error evaluation module includes: The prediction input optimization submodule calls the optimized prediction input parameters, obtains the power grid load data and prediction error distribution data, screens the key variables that affect the load prediction accuracy, calculates the deviation degree of multiple variables, compares the deviation amplitude and the error distribution interval, adjusts the variable weights, and obtains the optimized variable weight values; The error rate calculation submodule obtains the grid load data and the prediction error distribution data based on the optimization variable weight value, calculates the error amplitude in multiple time intervals, and monitors the relationship between the error amplitude and the load mean using the formula: ; Calculate the error trend change amplitude to obtain the error trend amplitude value; in, Representative period Error rate, Representative period The actual load value, Representative period Forecast load values, Representative period Load deviation correction value, Representative Variables in the period The optimization weight of represents the total number of variables, Representative period Error adjustment parameters; The error assessment result generation submodule analyzes the error distribution change based on the error trend amplitude value, calculates the degree of deviation between the error rate and the error threshold, determines the fluctuation of the error rate, and obtains the load forecast error assessment result.

[0014] A smart grid load forecasting method, which is executed based on the above-mentioned smart grid load forecasting system, comprises the following steps: S1: Obtain regional power grid load data, extract multi-node load change rates, calculate load increments and power flow ratios of adjacent substations, call power grid topology parameters to calculate voltage phase angle offsets, normalize and calculate load coupling ratios between multiple substations, and adjust weight ratios to obtain power grid load coupling weight matrix; S2: Based on the power grid load coupling weight matrix, obtain the real-time load change rate, calculate the load mutation factor, extract the supply and demand offset and the power flow adjustment according to the power flow ratio, call the voltage phase angle offset to calculate the voltage offset change, adjust the power grid load coupling weight matrix in combination with the previous load fluctuation propagation delay, calculate the load coupling dynamic correction value, and obtain the load coupling dynamic correction value; S3: Obtain the regional past meteorological data, calculate the load slope in combination with the load coupling dynamic correction value, extract the temperature sensitive range and humidity critical value, calculate the meteorological load offset by calling the grid voltage fluctuation range, and obtain the meteorological load correction factor; S4: calling the load coupling dynamic correction value to adjust the adjacent area load weight in the load forecast input, calling the meteorological load correction factor to correct the meteorological parameter proportion, calculating the input adjustment range, and obtaining the optimized forecast input parameters; S5: Call the optimized prediction input parameters, run the load prediction calculation, analyze the prediction error distribution trend based on the power grid load data, calculate the error rate, and obtain the load prediction error evaluation result.

[0015] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by extracting the load change rate, calculating the load increment and the flow ratio, the dynamic coupling relationship between the loads is accurately portrayed, and the voltage phase angle offset is calculated in combination with the power grid topology, so that the load forecast has regional linkage characteristics. The forecast parameters are adjusted based on the previous load propagation delay to improve the model's responsiveness to sudden load fluctuations. The load slope is analyzed in combination with meteorological data, the temperature and humidity sensitive range is set, the weights of meteorological factors are optimized, and the adaptability of the forecast model under extreme weather conditions is enhanced. The load coupling correction value is used to optimize the input parameter configuration, reduce data distortion, and improve long-term forecast stability. This solution improves the forecast accuracy in terms of load dynamic adjustment, meteorological impact modeling, and input parameter optimization, providing more accurate support for power grid dispatching. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a system flow chart of the present invention; Figure 2 This is a flow chart of a calculation module for power grid load coupling relationship of the present invention; Figure 3 This is a flow chart of the power grid load dynamic adjustment module of the present invention; Figure 4 This is a flow chart of the weather-affected grid load correction module of the present invention; Figure 5 Input optimization module flow chart for the load forecasting model of the present invention; Figure 6 This is a flow chart of the power grid load forecasting error evaluation module of the present invention. 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" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the 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, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0019] Example 1: Please refer to Figure 1 The present invention provides a technical solution: a smart grid load forecasting system comprising: The grid load coupling relationship calculation module extracts the load change rate from the regional grid load data, calculates the load increment and the power flow ratio of adjacent substations, calls the grid topology parameters to calculate the voltage phase angle offset, and calculates the weight ratio to obtain the grid load coupling weight matrix; The grid load dynamic adjustment module calls the grid load coupling weight matrix, obtains the real-time load change rate, calculates the load mutation factor, extracts the supply and demand offset and the power flow adjustment, calculates the voltage offset change, and calls the previous load fluctuation propagation delay after adjusting the weight matrix to obtain the load coupling dynamic correction value; The weather-affected grid load correction module obtains the regional past weather data, combines the load change rate, calculates the load slope, obtains the temperature sensitive range and humidity critical value, calls the grid voltage fluctuation range, and obtains the weather load correction factor; The load forecasting model input optimization module calls the load coupling dynamic correction value, adjusts the load weights of adjacent areas in the load forecasting model, calls the meteorological load correction factor, corrects the proportion of meteorological parameters, and calculates the input adjustment range to obtain the optimized forecast input parameters; The power grid load forecast error assessment module calls the optimized forecast input parameters, runs the load forecast model, calculates the error rate based on the power grid load data and the forecast error distribution trend, and obtains the load forecast error assessment result.

[0020] The grid load coupling weight matrix includes load increment, adjacent substation power flow ratio, voltage phase angle offset, and weight ratio. The load coupling dynamic correction value includes load mutation factor, supply and demand offset, power flow adjustment, voltage offset change, and previous load fluctuation propagation delay. The meteorological load correction factor includes load slope, temperature sensitive range, humidity critical value, and grid voltage fluctuation range. The optimized prediction input parameters include load coupling dynamic correction value, adjacent area load weight, meteorological load correction factor, meteorological parameter proportion, and input adjustment range. The load forecast error evaluation results include grid load data, forecast error distribution trend, and error rate.

[0021] See also Figure 2 , the grid load coupling relationship calculation module includes: The load change rate extraction submodule obtains regional power grid load data, extracts load changes in multiple time periods, calculates the load change rate per unit time, filters abnormal data based on load change trends, and obtains a load change rate sequence; The historical load power value of each substation is recorded by SCADA (Supervisory Control and Data Acquisition). The load data of each time period is stored in the database, as shown in Table 1, which contains the power data of four substations in a certain area at different time points. The system first extracts the data in chronological order, arranges the time series load power values ​​of each substation according to the time axis, and calculates the load change between adjacent time points. The calculation method is: Assume time The load power at the moment is , then the adjacent time intervals The load change rate within is calculated as: ; ; in, The value is 15 minutes (i.e. 0.25 hours), and the load change rate The unit is MW / h. During the calculation process, all substation data must be traversed. When screening abnormal data, it is necessary to determine whether the load change rate exceeds the set threshold. For example, if the normal load change rate of a substation is MW / h, when the load change rate within a certain period of time exceeds this range (such as the change rate reaches 10MW / h), the data is determined to be an abnormal value and is removed or adjusted. The load change rate sequence can be obtained through the above steps.

[0022] Table 1 Substation load power data: ; As shown in Table 1, substation A has arrive The load change is MW, the rate of change in 15 minutes is MW / h. If it exceeds the set threshold range, its load value will be removed or adjusted. This result shows that the load fluctuation in this time period is large, and it is necessary to further check whether there is any abnormality in the data source, and adjust the data or perform compensation calculations to ensure the stability and rationality of the final load change rate sequence.

[0023] The load increment calculation submodule calculates the load increments in adjacent time periods based on the load change rate sequence, collects the power flow change data of the substation, matches the load increment distribution according to the power flow change trend, and obtains the load increment matching sequence; Based on the filtered load change rate sequence, the load increment in adjacent time periods is calculated as follows: ; The power flow change data of the substation needs to be collected through the power flow monitoring system. The system records the active power flow of the substation in and out in real time. The load increment needs to be matched with the power flow data. Assuming that a substation The current flow data is as follows: Table 2 Substation power flow data: ; In time , the incoming power of substation A changes to MW, if the outgoing power remains unchanged, the load power increases MW, matches the load change rate. If the load change trend of a substation is consistent with the flow change trend (for example, the flow increases when the load increases), the load increment matching of the substation is successful. This result shows that the load change of the substation is consistent with the flow data, which can be used for subsequent load coupling analysis and ensure the accuracy of the load increment matching sequence.

[0024] The load coupling weight matrix calculation submodule calculates the voltage phase angle offset based on the load increment matching sequence and calls the grid topology parameters. It then constructs the load distribution relationship between substations based on the offset using the formula: ; Calculate the load coupling weight ratios between multiple substations, aggregate the calculation results, and establish a grid load coupling weight matrix; in, Representative substation and The load coupling weight between Representative substation The load power, Representative substation The voltage phase angle, Representative substation The sum of the load differences with all substations, Representative substation The sum of squares of voltage phase angle differences with all substations.

[0025] Substation and The load powers are and , calculate the load power difference, and aggregate the total load power difference between all substations. The calculation formula is: ; in, Representative substation The voltage phase angle and voltage phase angle offset can be measured by PMU (synchronous phasor measurement unit). For example, the voltage phase angle data of a substation in a certain area is as follows: Table 3 Substation voltage phase angle data: ; Calculate the load coupling weight between substations A and B, assuming MW, MW, calculate the load power difference MW, assuming that the total load difference of all substations is 40MW, then: ; The voltage phase angle difference is calculated as , the sum of the squares of the voltage phase angle differences of all substations is , calculate the weight coefficient: ; Final load coupling weight: ; The result shows that the load coupling degree between substations A and B is 5.7%, indicating that their load changes have a low impact on each other and have a small weight in the load distribution relationship, which can be used for subsequent grid load optimization analysis.

[0026] See also Figure 3 , the power grid load dynamic adjustment module includes: The load change calculation submodule calls the grid load coupling weight matrix, calculates the real-time load change rate, extracts the load mutation factor in the grid operation, and screens the key load fluctuation nodes based on the load change rate, calculates the load propagation ratio between multiple nodes, and generates the key load change ratio; When calculating specifically, first select the past The historical load data within a time step is used to establish a time series, and the load change rate is determined by calculating the trend of load growth or decrease. The calculation method is: ; in, Indicates the load change rate, is the current time step, To observe the time window, during the calculation process, the system compares the current load change rate with the normal operation threshold. If it exceeds the set threshold (for example, the load change rate threshold is set to ), then mark the node as a possible load mutation node. Then, screen all marked load mutation nodes and compare whether their load fluctuation exceeds the standard deviation range of the mean load fluctuation of the whole network (set standard deviation As a measurement indicator, if For example, if the load demand change rate of a node is 0.15 pu, and the average load change rate set by the system is pu, standard deviation pu, the node is determined to be a critical load fluctuation node.

[0027] The load propagation ratio between the selected key load fluctuation nodes is obtained through historical data calculation, and the calculation method is: ; in, Representation Node and The load transmission ratio between nodes is used to evaluate the mutual influence of load fluctuations. For example, if the load demands of nodes 1 and 2 are MW and MW, then the propagation ratio is This result shows that the load fluctuation of node 1 has a low impact on node 2, which means that during load adjustment, the fluctuation of node 1 will not significantly affect the power flow of node 2, so in the subsequent load adjustment calculation, the interaction coefficient between node 1 and node 2 should be small.

[0028] The load offset adjustment submodule calls the key load change ratio, extracts the supply and demand difference data, calculates the supply and demand offset, and combines the load propagation ratio to obtain the power flow adjustment of multiple load nodes using the formula: ; Calculate and obtain the power adjustment values ​​of multiple load nodes, integrate the adjusted voltage offset data, and obtain the voltage offset change; in, represents the power flow adjustment, Represents load node The weight of the overall load adjustment, Represents load node The current load demand value, Represents load node The current power supply value, To avoid small parameters with zero denominator, Represents the total number of grid load nodes; First call the key load change ratio The data is collected and the supply and demand difference data is extracted from the historical load database, that is, the supply and demand offset of each load node is calculated. The calculation method of supply and demand offset is as follows: ; in, Represents load node The current load demand value, Represents load node The current power supply value. If , it means that there is a load gap at the node and additional power supply is needed to meet the load demand; if , it means that the node has supply redundancy and the power output of the node needs to be reduced.

[0029] (1) Calculate the supply and demand offset of each node: Taking three nodes in a power grid as an example, their current load demand and supply power are set as follows: Table 4 Load node power parameters: ; As shown in Table 4, the supply-demand offset of node 1 is the largest, which is 20MW, indicating that the load demand of this node is high and needs to be adjusted; the supply-demand offset of node 2 is smaller, which is 10MW, and also needs some adjustment; the supply power of node 3 exceeds the demand power, so its supply-demand offset is negative (-20MW), indicating that the node has excess power output and needs to reduce output or increase load to balance the supply and demand of the power grid.

[0030] (2) Calculate the power flow adjustment: In order to optimize load distribution, the system needs to calculate the power flow adjustment of multiple load nodes. , the calculation formula is as follows: ; Based on the grid impact weight of the load node, the following weight parameters are set: Node 1 (largest load gap): ; Node 2 (smaller load gap): ; Node 3 (overpowered): ; (3) Input the data to calculate the power adjustment value: Substitute the load data in Table 4 for calculation: ; Calculate item by item: ; ; ; The final calculation is: ; (4) Significance and relevance of numerical results: The result shows that during the current load adjustment process, the system needs to adjust the power of multiple nodes by 1.6253MW to achieve overall power balance. This means: It is necessary to cut about 0.57MW of power delivery from nodes with excess power supply (such as node 3); It is necessary to provide corresponding power adjustments to nodes with unbalanced supply and demand (such as node 1 and node 2) to reduce the load gap.

[0031] The load coupling dynamic correction submodule calls the voltage offset change, adjusts the grid load coupling weight matrix, and calculates the load coupling correction coefficient in combination with the propagation delay of previous load fluctuations to obtain the load coupling dynamic correction value.

[0032] Calculate the voltage change rate based on the load-adjusted power flow data : ; in, is the adjusted node voltage, is the node voltage before adjustment. For example, if the voltage of a node is 1.02pu before adjustment and 1.01pu after adjustment, the voltage change rate is: ; According to the voltage change, the system adjusts the grid load coupling weight matrix. The adjustment of the matrix is ​​based on the load coupling correction coefficient calculated according to the historical load fluctuation propagation delay. The calculation method of the load coupling correction coefficient is as follows: ; in, represents the time delay of load adjustment response. Assuming that the adjustment data of the past five time steps in the historical records are MW, the corresponding propagation delay is seconds, the load coupling correction factor is calculated as: ; The results show that during the historical load adjustment process, the propagation impact of load adjustment at each node is relatively stable. The current load coupling correction value is 5.4MW, which means that in subsequent load adjustments, the grid load coupling weight matrix can be optimized based on this correction value, making the load adjustment more accurate and reducing the voltage offset caused by load fluctuations.

[0033] See also Figure 4 , the weather impact power grid load correction module includes: The meteorological data extraction submodule obtains the regional meteorological data of the past, extracts the parameters of temperature and humidity, selects the meteorological information that meets the data integrity requirements, excludes the data missing items, calculates the temperature and humidity variation range in the differentiated time period, calculates the temperature variation trend and humidity variation rate, and adjusts the fluctuation range of abnormal data to generate the regional meteorological parameter set; Call the meteorological historical data of the specified area in the past five years, including temperature and humidity parameters, extract basic parameters such as daily average temperature, maximum temperature, minimum temperature, relative humidity, etc. from multiple data sources, and screen out data sets that meet statistical conditions based on data integrity requirements, that is, when the proportion of missing values ​​in a certain time period is less than 5%, the data will be included in the calculation range, otherwise the data in this time period needs to be eliminated or interpolated using adjacent data, and then calculate the temperature and humidity variation range of different time periods. The specific method is to calculate the difference between the highest and lowest temperatures within 24 consecutive hours, and perform monthly statistics to obtain long-term trends. For example, in January of a certain year in a certain area, the average maximum temperature is 5°C and the average minimum temperature is - 2℃, then the temperature variation range of that month is 7℃. Similarly, the humidity variation range can be calculated by statistically calculating the difference between the maximum and minimum daily average humidity and summarizing them by week or month, thereby evaluating the humidity variation trend. In addition, the abnormal data adjustment step needs to eliminate or correct the mutation data in combination with the historical mean. The specific method is to calculate the standard deviation of the data in each time period, and regard the data beyond the range of ±3 times the standard deviation of the mean as an outlier, and replace it with the mean of the data of the two days before and after. For example, the temperature data on a certain day in July 2023 suddenly increases to 50℃, and the historical average of the highest temperature in that month is only 38℃, then the data should be corrected to the mean of two adjacent days to ensure that the final generated regional meteorological parameter set meets the requirements of statistical analysis.

[0034] The meteorological load change calculation submodule calls the power grid load data based on the regional meteorological parameter set, calculates the load change trend under differentiated meteorological conditions, obtains the load change rate based on the time series data, and combines the temperature and humidity change rate to use the formula: ; The load slope is calculated; in, represents the load slope, Representative time period The load variation within Representative time period The weight coefficient of represents the temperature change, Representative time period The humidity value, represents the humidity threshold, Represents the total number of time periods considered in calculating the load slope; The specific execution steps are as follows: extract the load data set corresponding to the meteorological data time series. For example, in a certain area, the maximum temperature on January 1, 2023 is 5°C, the minimum temperature is -3°C, and the relative humidity is 65%. Under this meteorological condition, the maximum load value on that day is 250MW and the minimum load value is 180MW. Then the load change is The calculation is 250MW-180MW=70MW. Then the load change rate is calculated based on the time series data. The method is to calculate the load increment in hours. For example, the load increases from 180MW to 200MW from 08:00 to 09:00 on a certain day. The load change rate for that hour is (200-180)MW / 1h=20MW / h. Next, the load slope is calculated based on the temperature and humidity change rates using the formula: ; Among them, setting the weight coefficient is 0.8, the humidity critical value Set to 60%, if the temperature change measured within a week The humidity values ​​are [3,5,2,4,6,3,5]℃ respectively. They are [55, 60, 65, 58, 62, 59, 64]% respectively, corresponding to the load change For [15,18,12,16,22,14,20]MW, the calculation process is as follows: ; ; ; The calculation results show that under this meteorological condition, changes in temperature and humidity will result in a load change slope of 2.13MW / ℃, which is used in the subsequent calculation of the meteorological load correction factor.

[0035] The meteorological load correction factor calculation submodule calls the load slope, combines the regional meteorological parameter set, screens the temperature sensitive range, calculates the proportion of temperature on load change, obtains the humidity critical value, and calls the grid voltage fluctuation range to calculate the meteorological influencing factor weight. Combined with multiple influencing parameters, the meteorological load correction factor is calculated.

[0036] The temperature change data throughout the year is counted, and the interval with the strongest correlation between temperature and load is selected. For example, when the temperature in a certain area is between -5℃ and 10℃, the load change is most significant. This range is set as the temperature sensitive interval. Then the effect of temperature on load change is calculated by calculating the proportion of load change in the temperature interval to the total load change. For example, the total load change throughout the year is 500MW, of which the load change in the temperature sensitive interval is 300MW, then the effect ratio is 300 / 500=60%. Then the humidity critical value is obtained, and the grid voltage fluctuation range is called. The specific operation is to extract the humidity and voltage data throughout the year. For example, if the humidity fluctuation range is 40%-80% throughout the year and the grid voltage fluctuation range is ±5V, the humidity influence factor weight is calculated, and the normalized calculation formula is used: ; If the current humidity is 65%, the humidity impact weight is: ; Finally, the meteorological load correction factor is calculated by combining multiple parameters such as temperature, humidity, and voltage fluctuation, and the temperature influence weight is set. is 0.6, voltage influence weight is 0.4, then the correction factor is: ; The result shows that after comprehensive consideration of meteorological factors, the calculated meteorological load correction factor is 3.46, which is used to correct the power grid load forecasting model.

[0037] As shown in Table 5: Table 5 Meteorological load calculation data table: ; Table 5 gives the load change data in different time periods and the calculated load slope, indicating the impact of changes in temperature and humidity on the load.

[0038] See also Figure 5 , the load forecasting model input optimization module includes: The load weight adjustment submodule adjusts the load weights of adjacent areas in the load forecasting model based on the dynamic correction value of load coupling, compares the load data of differentiated areas, screens the change trend of load weights of adjacent areas, adjusts the load weight value according to the dynamic correction value of load coupling, calculates the load proportion of the area after correction, and obtains the load weight coefficient after correction; First, the historical load data of the target area and adjacent areas are obtained, and they are decomposed into several time periods according to the time series. The data of each time period includes the load peak, valley and daily average load values. The load change rate of adjacent areas in these time periods is calculated. By comparing the differences in load change rates, adjacent areas with similar load change trends are screened out, and their load change ratios are recorded as preliminary weight coefficients. Subsequently, adjustments are made based on the dynamic correction value of load coupling. The correction value is obtained by analyzing the degree of load coupling between different regions. For example, if a region is greatly affected by meteorological factors, it is necessary to increase the meteorological coupling factor to correct its influence weight. If a region is significantly affected by industrial load fluctuations, If the weight of meteorological influence is significant, the weight of industrial load influence needs to be reduced and the weight of industrial load influence needs to be increased. The calculation method of the revised weight is as follows: if the initial value of the target area load weight is 0.5, the initial value of the load weight of adjacent area A is 0.3, and that of area B is 0.2. Assuming that the calculated dynamic correction value is 0.1, the final revised target area weight is 0.5×(1+0.1)=0.55, the weight of adjacent area A is adjusted to 0.3×(1-0.1)=0.27, and that of area B is adjusted to 0.2×(1-0.1)=0.18. When calculating the revised regional load share, the normalization process is performed so that the sum of all regional weights is equal to 1, that is, the final weight value should be adjusted to , thereby obtaining the corrected load weight coefficient. The result shows that the corrected load weight can more accurately reflect the dynamic influence relationship of the load in each area, and provide reliable parameter support for the subsequent load forecasting model input optimization.

[0039] The meteorological parameter correction submodule calls the meteorological load correction factor, calculates the correction value according to the change in the proportion of meteorological parameters, compares the load changes under differentiated meteorological conditions, adjusts the proportion of meteorological parameters in load forecasting, calculates the corrected meteorological impact parameters, and obtains the corrected meteorological impact factors; First, obtain meteorological data, including factors such as temperature, humidity, wind speed and solar radiation, establish a correlation model between each meteorological factor and the load, and calculate the proportion of each meteorological factor on the load. For example, in summer, the impact of temperature may account for 60%, humidity accounts for 20%, wind speed accounts for 10%, and solar radiation accounts for 10%. In winter, the impact of temperature drops to 40%, wind speed accounts for 30%, humidity accounts for 20%, and solar radiation accounts for 10%. According to the weights of meteorological factors calculated in different periods, determine the preliminary meteorological impact factor F. Then, by comparing the changes in meteorological load in different periods, calculate the correction value. Assuming that the historical data of a certain area shows that when the temperature rises by 5°C, the load increases by 8%. If the current meteorological data changes show that the temperature rises by 3°C, the impact can be calculated proportionally. Suppose the initial value of the correction factor is 1.0, then the new correction factor can be calculated according to the formula The revised meteorological impact factor is calculated and used in the subsequent load forecast input optimization to improve the forecast accuracy. The result shows that the revised meteorological impact factor can more accurately describe the influence of meteorological factors on load changes, thereby avoiding forecast errors caused by abnormal fluctuations in meteorological conditions and improving the stability and applicability of the load forecasting model.

[0040] The input parameter optimization calculation submodule calls the corrected load weight coefficient and the corrected meteorological influence factor, combined with the current load forecast input data, using the formula: ; The optimized and adjusted input parameter values ​​are obtained by operation to obtain the optimized predicted input parameters; in, represents the optimized prediction input parameters, represents the corrected load weight coefficient, Represents the adjacent area load data, represents the corrected meteorological impact factor, Represents the proportion of meteorological parameters, represents the load change rate factor, represents the time period parameter, represents the time decay factor of the load effect, Represents the upper limit of the calculation, which is the maximum value of an indicator or range.

[0041] First, the modified load weight coefficient W and the adjacent area load data L are called and weighted to reflect the degree of correction of the load weight to the input data. Then, the modified meteorological influence factor F is called and combined with the meteorological parameter weight P to calculate its correction value to the input data. In order to avoid the prediction deviation caused by extreme meteorological data, the meteorological parameter part is processed by square root transformation, that is, Then, considering the time decay effect of load influence, the load change rate factor λ is set, and the exponential decay factor is calculated according to the time period parameter T. Finally, the optimized prediction input parameters are calculated , using a specific example, assuming that there are three adjacent areas, whose load data L are 500MW, 450MW, and 480MW respectively, the corresponding modified weight coefficients W are 0.4, 0.35, and 0.25, the modified meteorological influence factors F are 1.2, 1.1, and 1.3 respectively, the corresponding meteorological parameter weights P are 0.5, 0.6, and 0.4, the load change rate factor λ is 0.02, and the time period parameter T is 10h, then the calculation process is as follows: ;

[0042] Calculate the optimized forecast input parameters =382.6MW.

[0043] Result description: The results show that after comprehensively considering the load weight adjustment and meteorological parameter correction, the optimized forecast input parameters It is 382.6MW. This value, as the optimized input of the load forecasting model, can more accurately reflect the adjustment of load affected by load changes in adjacent areas and meteorological factors. Compared with the original forecast input, the revised value can more accurately fit the actual load fluctuation trend and avoid the forecast error caused by a single factor deviation, making the load forecasting model more adaptable and reliable in different regions and under different meteorological conditions.

[0044] Table 6 Load weight and meteorological influence factor correction calculation table: ; As shown in Table 6, the corrected weights and meteorological influence factors of each region are involved in the calculation, and the optimized forecast input parameter of 382.6MW is finally obtained. This value can be used for subsequent load forecast calculations. The results show that the corrected input parameters can be more reasonably used as inputs to the load forecast model after considering the regional load influence and meteorological influence, ensuring that the predicted value is closer to the actual load demand.

[0045] See also Figure 6 ,The power grid load forecast error evaluation module includes: The prediction input optimization submodule calls the optimized prediction input parameters, obtains the power grid load data and prediction error distribution data, screens the key variables that affect the load prediction accuracy, calculates the deviation degree of multiple variables, compares the deviation amplitude and the error distribution interval, adjusts the variable weights, and obtains the optimized variable weight values; The historical load data in the power grid operation database is called, which includes the actual load values ​​of a certain area in different time periods. The load data for 24 hours a day is extracted according to the time series. At the same time, the predicted load data calculated by the previous prediction model is obtained, and the error distribution between the actual load value and the predicted load value is calculated. For the error distribution data, the mean, standard deviation and maximum error value of the error in different time periods are extracted to obtain the overall distribution of the error. In the process of screening the key variables that affect the accuracy of load forecasting, the contribution of each variable to the error is calculated, and a contribution threshold is set. For example, under the benchmark of 0.05, only variables with a contribution greater than this threshold are retained, such as temperature, humidity, electricity price, historical load data, etc., and variables with low contribution are discarded. When calculating the degree of deviation of multiple variables, the screened variable data is normalized to ensure that variables of different dimensions are comparable. When calculating the degree of deviation of each variable, the deviation calculation formula is used. ,in is the value of the variable at a certain moment, is the mean value of the variable, is the standard deviation. For variables with a large degree of deviation, , marked as high deviation variables. In the process of comparing the deviation amplitude and the error distribution interval, the degree of deviation of the variable is compared with the fluctuation range of the prediction error. For example, if the 99% interval of the error distribution is , then the variables whose deviation degree falls into this interval are normal variables, otherwise they are abnormal variables, and then the variable weights are adjusted, and the weights of the variables are redistributed according to the deviation degree, using the weight adjustment rule ,in is the initial weight value, The maximum deviation value of all variables is obtained after adjustment. The optimized variable weight value is obtained. This result shows that in the process of variable weight optimization, by calculating the degree of deviation of each variable, the weight distribution of the variable can be effectively adjusted, so that the sensitivity of the prediction error to the key variables is reduced, thereby improving the stability and accuracy of the overall prediction.

[0046] The error rate calculation submodule obtains the grid load data and forecast error distribution data based on the optimized variable weight value, calculates the error amplitude in multiple time intervals, and monitors the relationship between the error amplitude and the load mean using the formula: ; Calculate the error trend change amplitude to obtain the error trend amplitude value; in, Representative period Error rate, Representative period The actual load value, Representative period Forecast load values, Representative period Load deviation correction value, Representative Variables in the period The optimization weight of represents the total number of variables, Representative period Error adjustment parameters; When calculating the error amplitude in multiple time intervals, select different time periods, such as hours, days, weeks, etc. for error calculation, call the forecast input parameters optimized in the early stage to obtain load data, and calculate the error according to the time dimension. The error calculation formula is: ; in, For the period The actual load value of the grid is retrieved through the dispatching system database. For example, the load data of a certain area at 16:00 is 980MW. The load value is predicted by the prediction model. For example, the predicted value is 960MW. is the load deviation correction value, which is calculated as follows: , assuming the correction factor , then the correction value , For the The optimization weights of the variables are as follows, for example, the weight of temperature is 0.3, the weight of humidity is 0.2, and the weight of electricity price is 0.5. It is the error adjustment parameter, which is used to smooth the error effect. Its value is set to 5MW. 2 , substitute the above data into the calculation: ; The result shows that the error rate in the current period is relatively high, indicating that the calculation results of the prediction model deviate greatly from the actual load value and may be affected by external factors such as temperature, humidity, and sudden changes in grid load. Therefore, it is necessary to combine the calculation results of the error trend amplitude and further analyze the error change trend to determine whether the prediction model needs to be corrected.

[0047] The error assessment result generation submodule analyzes the error distribution change based on the error trend amplitude value, calculates the degree of deviation between the error rate and the error threshold, determines the fluctuation of the error rate, and obtains the load forecast error assessment result.

[0048] For example, the error threshold is set to 5%, and the calculated error rate is compared. If the error rate is higher than the threshold, it is determined that the current period forecast error is large. Monitor the change of the error rate in different time periods. For example, set the time interval to 1 hour, record the error rate in the last 24 hours, use the time series analysis method to calculate the error change trend, determine the fluctuation of the error rate, and calculate the standard deviation of the error. ,in is the error mean, and the error rate data set for the last 24 hours is set to , calculate the mean , calculate the standard deviation: ; If the standard deviation is greater than 2%, it is determined that the error fluctuates greatly, and the final load forecast error evaluation result is obtained. The result shows that the error fluctuates greatly, which may indicate that the adaptability of the forecast model in a specific time period is poor, or the influence of external factors exceeds the compensation capacity of the forecast model. Therefore, it is necessary to adjust the forecast parameters or optimize the input variables to reduce the forecast error in future time periods and improve the forecast accuracy.

[0049] A smart grid load forecasting method, which is executed based on the above-mentioned smart grid load forecasting system, comprises the following steps: S1: Obtain regional power grid load data, extract multi-node load change rates, calculate load increments and power flow ratios of adjacent substations, call power grid topology parameters to calculate voltage phase angle offsets, normalize and calculate load coupling ratios between multiple substations, and adjust weight ratios to obtain power grid load coupling weight matrix; S2: Based on the grid load coupling weight matrix, obtain the real-time load change rate, calculate the load mutation factor, extract the supply and demand offset and power flow adjustment according to the flow ratio, call the voltage phase angle offset to calculate the voltage offset change, adjust the grid load coupling weight matrix in combination with the previous load fluctuation propagation delay, calculate the load coupling dynamic correction value, and obtain the load coupling dynamic correction value; S3: Obtain the regional past meteorological data, calculate the load slope in combination with the load coupling dynamic correction value, extract the temperature sensitive range and humidity critical value, calculate the meteorological load offset by calling the grid voltage fluctuation range, and obtain the meteorological load correction factor; S4: Call the load coupling dynamic correction value to adjust the adjacent area load weight in the load forecast input, call the meteorological load correction factor to correct the meteorological parameter proportion, calculate the input adjustment range, and obtain the optimized forecast input parameters; S5: Call the optimized forecast input parameters, run the load forecast calculation, analyze the forecast error distribution trend based on the power grid load data, calculate the error rate, and obtain the load forecast error evaluation result.

[0050] 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. A smart grid load forecasting system, characterized in that: The system comprises: The grid load coupling relationship calculation module extracts the load change rate from the regional grid load data, calculates the load increment and the power flow ratio of adjacent substations, calls the grid topology parameters to calculate the voltage phase angle offset, and calculates the weight ratio to obtain the grid load coupling weight matrix; The power grid load dynamic adjustment module calls the power grid load coupling weight matrix, obtains the real-time load change rate, calculates the load mutation factor, extracts the supply and demand offset and the power flow adjustment, calculates the voltage offset change, and calls the previous load fluctuation propagation delay after adjusting the weight matrix to obtain the load coupling dynamic correction value; The weather-affected grid load correction module obtains the past regional weather data, combines the load change rate, calculates the load slope, obtains the temperature sensitive range and humidity critical value, calls the grid voltage fluctuation range, and obtains the weather load correction factor; The load forecasting model input optimization module calls the load coupling dynamic correction value, adjusts the load weights of adjacent areas in the load forecasting model, calls the meteorological load correction factor, corrects the proportion of meteorological parameters, and calculates the input adjustment range to obtain optimized forecast input parameters.

2. The smart grid load forecasting system according to claim 1, characterized in that: The grid load coupling weight matrix includes load increment, adjacent substation power flow ratio, voltage phase angle offset, and weight ratio; the load coupling dynamic correction value includes load mutation factor, supply and demand offset, power flow adjustment, voltage offset change, and previous load fluctuation propagation delay; the meteorological load correction factor includes load slope, temperature sensitive range, humidity critical value, and grid voltage fluctuation range; the optimized prediction input parameters include load coupling dynamic correction value, adjacent area load weight, meteorological load correction factor, meteorological parameter proportion, and input adjustment amplitude.

3. The smart grid load forecasting system according to claim 2, characterized in that: The grid load coupling relationship calculation module includes: The load change rate extraction submodule obtains regional power grid load data, extracts load changes in multiple time periods, calculates the load change rate per unit time, filters abnormal data based on load change trends, and obtains a load change rate sequence; The load increment calculation submodule calculates the load increments in adjacent time periods based on the load change rate sequence, collects the power flow change data of the substation, matches the load increment distribution according to the power flow change trend, and obtains the load increment matching sequence; The load coupling weight matrix calculation submodule calculates the voltage phase angle offset based on the load increment matching sequence and calls the grid topology parameters, and constructs the load distribution relationship between substations according to the offset, using the formula: ； Calculate the load coupling weight ratios between multiple substations, aggregate the calculation results, and establish a grid load coupling weight matrix; in, Representative substation and The load coupling weight between Representative substation The load power, Representative substation The voltage phase angle, Representative substation The sum of the load differences with all substations, Representative substation The sum of squares of voltage phase angle differences with all substations.

4. The smart grid load forecasting system according to claim 3, characterized in that: The power grid load dynamic adjustment module includes: The load change calculation submodule calls the grid load coupling weight matrix, calculates the real-time load change rate, extracts the load mutation factor in the grid operation, and screens the key load fluctuation nodes based on the load change rate, calculates the load propagation ratio between multiple nodes, and generates the key load change ratio; The load offset adjustment submodule calls the key load change ratio, extracts the supply and demand difference data, calculates the supply and demand offset, and combines the load propagation ratio to obtain the power flow adjustment of multiple load nodes using the formula: ； Calculate and obtain the power adjustment values ​​of multiple load nodes, integrate the adjusted voltage offset data, and obtain the voltage offset change; in, represents the power flow adjustment, Represents load node The weight of the overall load adjustment, Represents load node The current load demand value, Represents load node The current power supply value, To avoid small parameters with zero denominator, Represents the total number of grid load nodes; The load coupling dynamic correction submodule calls the voltage offset change, adjusts the grid load coupling weight matrix, and calculates the load coupling correction coefficient in combination with the propagation delay of previous load fluctuations to obtain the load coupling dynamic correction value.

5. The smart grid load forecasting system according to claim 4, characterized in that: The weather-affected power grid load correction module comprises: The meteorological data extraction submodule obtains the past meteorological data of the area, extracts the parameters of temperature and humidity, screens the meteorological information that meets the data integrity requirements, excludes data missing items, calculates the temperature and humidity change ranges in differentiated time periods, calculates the temperature change trend and humidity change rate, and adjusts the abnormal data fluctuation range to generate a regional meteorological parameter set; The meteorological load change calculation submodule calls the power grid load data based on the regional meteorological parameter set, calculates the load change trend under differentiated meteorological conditions, obtains the load change rate based on the time series data, and combines the temperature and humidity change rate to adopt the formula: ； The load slope is calculated; in, represents the load slope, Representative time period The load variation within Representative time period The weight coefficient of represents the temperature change, Representative time period The humidity value, represents the humidity threshold, Represents the total number of time periods considered in calculating the load slope; The meteorological load correction factor calculation submodule calls the load slope, combines the regional meteorological parameter set, screens the temperature sensitive range, calculates the proportion of temperature on load change, obtains the humidity critical value, and calls the grid voltage fluctuation range, calculates the meteorological influencing factor weight, and combines multiple influencing parameters to calculate the meteorological load correction factor.

6. The smart grid load forecasting system according to claim 5, characterized in that: The load forecasting model input optimization module includes: The load weight adjustment submodule adjusts the load weights of adjacent areas in the load forecasting model based on the load coupling dynamic correction value, compares the differentiated regional load data, screens the load weight change trend of adjacent areas, adjusts the load weight value according to the load coupling dynamic correction value, calculates the corrected regional load proportion, and obtains the corrected load weight coefficient; The meteorological parameter correction submodule calls the meteorological load correction factor, calculates the correction value according to the change in the proportion of the meteorological parameters, compares the load changes under differentiated meteorological conditions, adjusts the proportion of the meteorological parameters in the load forecast, calculates the corrected meteorological impact parameters, and obtains the corrected meteorological impact factors; The input parameter optimization calculation submodule calls the modified load weight coefficient and the modified meteorological influence factor, combines the current load forecast input data, and adopts the formula: ； The optimized and adjusted input parameter values ​​are obtained by operation to obtain the optimized predicted input parameters; in, represents the optimized prediction input parameters, represents the corrected load weight coefficient, Represents the adjacent area load data, represents the corrected meteorological impact factor, Represents the proportion of meteorological parameters, represents the load change rate factor, represents the time period parameter, represents the time decay factor of the load effect, Represents the upper limit of the calculation, which is the maximum value of an indicator or range.

7. The smart grid load forecasting system according to claim 6, characterized in that: The system also includes a power grid load forecast error assessment module; The power grid load forecast error evaluation module calls the optimized forecast input parameters, runs the load forecast model, calculates the error rate according to the power grid load data and the forecast error distribution trend, and obtains the load forecast error evaluation result; The load forecast error evaluation result includes power grid load data, forecast error distribution trend, and error rate.

8. The smart grid load forecasting system according to claim 7, characterized in that: The power grid load forecast error evaluation module includes: The prediction input optimization submodule calls the optimized prediction input parameters, obtains the power grid load data and prediction error distribution data, screens the key variables that affect the load prediction accuracy, calculates the deviation degree of multiple variables, compares the deviation amplitude and the error distribution interval, adjusts the variable weights, and obtains the optimized variable weight values; The error rate calculation submodule obtains the grid load data and the prediction error distribution data based on the optimization variable weight value, calculates the error amplitude in multiple time intervals, and monitors the relationship between the error amplitude and the load mean using the formula: ； Calculate the error trend change amplitude to obtain the error trend amplitude value; in, Representative period Error rate, Representative period The actual load value, Representative period Forecast load values, Representative period Load deviation correction value, Representative Variables in the period The optimization weight of represents the total number of variables, Representative period Error adjustment parameters; The error assessment result generation submodule analyzes the error distribution change based on the error trend amplitude value, calculates the degree of deviation between the error rate and the error threshold, determines the fluctuation of the error rate, and obtains the load forecast error assessment result.

9. A smart grid load forecasting method, characterized in that: The smart grid load forecasting system according to any one of claims 1 to 8 comprises the following steps: S1: Obtain regional power grid load data, extract multi-node load change rates, calculate load increments and power flow ratios of adjacent substations, call power grid topology parameters to calculate voltage phase angle offsets, normalize and calculate load coupling ratios between multiple substations, and adjust weight ratios to obtain power grid load coupling weight matrix; S2: Based on the power grid load coupling weight matrix, obtain the real-time load change rate, calculate the load mutation factor, extract the supply and demand offset and the power flow adjustment according to the power flow ratio, call the voltage phase angle offset to calculate the voltage offset change, adjust the power grid load coupling weight matrix in combination with the previous load fluctuation propagation delay, calculate the load coupling dynamic correction value, and obtain the load coupling dynamic correction value; S3: Obtain the regional past meteorological data, calculate the load slope in combination with the load coupling dynamic correction value, extract the temperature sensitive range and humidity critical value, calculate the meteorological load offset by calling the grid voltage fluctuation range, and obtain the meteorological load correction factor; S4: calling the load coupling dynamic correction value to adjust the adjacent area load weight in the load forecast input, calling the meteorological load correction factor to correct the meteorological parameter proportion, calculating the input adjustment range, and obtaining the optimized forecast input parameters; S5: Call the optimized prediction input parameters, run the load prediction calculation, analyze the prediction error distribution trend based on the power grid load data, calculate the error rate, and obtain the load prediction error evaluation result.

Images