Line loss determination method and device of power grid system, equipment and storage medium

Abstract

The invention discloses a line loss determination method and device of a power grid system, equipment and a storage medium. The line loss determination method comprises the steps of determining a predicted value and a normal fluctuation range of actual load electric energy data according to historical load electric energy data of each target node; determining abnormal load electric energy data according to the normal fluctuation range and the actual load electric energy data; correcting the abnormal load electric energy data for the first time according to the specific hierarchical relationship; correcting the abnormal load electric energy data for the second time according to the node load type; correcting the abnormal load electric energy data of the target node of the long-time continuous abnormal data for the third time according to the adjacent nodes; obtaining total input load electric energy and total output load electric energy of each layer according to the corrected actual load electric energy data; and determining the line loss of each layer according to the total input and total output load electric energy. According to the method, the problem that the loss source is difficult to locate accurately because the existing line loss determination method can only perform overall analysis on the line loss and cannot deeply analyze the local loss is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power systems, and particularly relates to a line loss determination method, device and equipment of a power grid system and a storage medium. BACKGROUND

[0002] In the line loss management of a power system, line loss analysis is a key link, which directly affects the operation efficiency and economic benefits of the power grid. The commonly used line loss determination method at present is mainly to compare the total power input of the power grid with the total power measured at the user side, and take the difference between the two as the basis for determining the line loss, so as to reflect the energy loss in the power transmission process of the power grid at a macro level. However, this method can only realize overall analysis of line loss, and it is difficult to deeply evaluate the loss situation of a local area, and it is impossible to accurately locate the loss source, which is not conducive to formulating targeted loss reduction measures. In addition, this method is highly dependent on the accuracy and integrity of the measurement data, and once the data has errors or is missing, the reliability of the calculation result will be significantly affected. SUMMARY

[0003] The embodiments of the present application provide a line loss determination method, device and equipment of a power grid system to solve the problem that the existing line loss determination method can only perform overall analysis of line loss and cannot deeply analyze local loss, thereby making it difficult to accurately locate the loss source.

[0004] A line loss determination method of a power grid system comprises: According to the power grid topology structure of the specific hierarchical relationship of the current power grid system, historical load energy data of each node in a historical time period and actual load energy data of each target node in a target time period are obtained; According to the historical load energy data of each target node, a predicted value of the actual load energy data is determined; according to the predicted value of the actual load energy data, a normal fluctuation range of the actual load energy data is determined; according to the normal fluctuation range and the actual load energy data of each target node in the target time period, abnormal load energy data of each target node in the target time period is determined; According to the specific hierarchical relationship of each target node, the abnormal load energy data of each target node in the target time period is first corrected; the first correction further comprises: according to the node load type of the target node, the abnormal load energy data of the target node corresponding to the preset node load type in the target time period is secondly corrected; and / or according to the historical load energy data of the adjacent nodes of each target node, the abnormal load energy data of the target node with long-time continuous abnormal data in the target time period is thirdly corrected; According to the modified actual load energy data and the power grid topology structure, total input load energy and total output load energy of each layer are obtained; according to the total input load energy and the total output load energy of each layer, line loss of each layer is determined, and line loss values of each layer in the power grid topology structure are obtained.

[0005] A line loss determination device of a power grid system comprises: A load data acquisition module is configured to acquire historical load energy data of each node in a historical time period and actual load energy data of each target node in a target time period according to a power grid topology structure of a specific hierarchical relationship of a current power grid system. An abnormal load judgment module is configured to determine a predicted value of the actual load energy data according to the historical load energy data of each target node; determine a normal fluctuation range of the actual load energy data according to the predicted value of the actual load energy data; and determine abnormal load energy data of each target node in the target time period according to the normal fluctuation range and the actual load energy data of each target node in the target time period. An abnormal data correction module is configured to perform a first correction on the abnormal load energy data of each target node in the target time period according to a specific hierarchical relationship of each target node; the first correction further comprises: performing a second correction on abnormal load energy data of a target node in the target time period corresponding to a preset node load type according to a node load type of the target node; and / or performing a third correction on abnormal load energy data of a target node in the target time period with long-time continuous abnormal data according to historical load energy data of adjacent nodes of each target node. A line loss determination module is configured to obtain total input load energy and total output load energy of each layer according to the modified actual load energy data and the power grid topology structure; determine line loss of each layer according to the total input load energy and the total output load energy of each layer, and obtain line loss values of each layer in the power grid topology structure.

[0006] A computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the line loss determination method of the power grid system when executing the computer program.

[0007] A computer readable storage medium stores a computer program, and the computer program is executable on a processor to implement the line loss determination method of the power grid system.

[0008] The embodiment of the present application provides a line loss determination method, device and equipment of a power grid system and a storage medium, which comprises the following steps: obtaining historical and actual load power data, determining a predicted value of the actual load power according to the historical data, thereby defining a normal fluctuation range, and realizing accurate identification of abnormal load power data of a target node in a target time period. Then, the first correction is performed according to the hierarchical relationship between nodes, and the abnormal data is preliminarily adjusted from the perspective of the power grid topology. Then, the second correction is performed in combination with the load type corresponding to the node, and the characteristic differences of different types of loads are fully considered, so that the correction is more targeted and accurate. For the abnormal data that appears continuously for a long time, the third correction is performed by using the historical load data of adjacent nodes, and the data quality is further improved by means of the correlation between the nodes. Through this multi-level correction mechanism, the reliability of the actual load power data is effectively guaranteed. On the basis of obtaining high-quality corrected data, the total input and total output load power of each level can be accurately calculated in combination with the power grid topology, so as to determine the line loss value of each level. This not only helps to comprehensively grasp the energy loss of the power grid at different levels, but also can accurately locate the loss source by analyzing the local loss of each level, provides key data support for the optimized operation, energy saving and consumption reduction and equipment maintenance of the power grid, and significantly improves the overall operation efficiency and economic benefit of the power grid. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0010] Figure 1 is a flowchart of the line loss determination method of the power grid system in an embodiment of the present application; Figure 2 is a hierarchical relationship structure diagram of the line loss determination method of the power grid system in an embodiment of the present application; Figure 3 is a flowchart of the line loss determination method of the power grid system in an embodiment of the present application; Figure 4 is a flowchart of the line loss determination method of the power grid system in an embodiment of the present application; Figure 5 is a schematic diagram of the line loss determination device of the power grid system in an embodiment of the present application; Figure 6 is a schematic diagram of the computer equipment in an embodiment of the present application. DETAILED DESCRIPTION

[0011] In order to make the technical problems, technical solutions and beneficial effects solved by the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0012] In an embodiment, as shown in Figure 1 a line loss determination method of a power grid system is provided, comprising the following steps: S01: According to the power grid topology structure of the specific hierarchical relationship of the current power grid system, the historical load power data of each node in the historical time period and the actual data of the load power of each target node in the target time period are obtained.

[0013] In this embodiment, the power grid topology structure of the power grid system refers to the electrical connection relationship between various elements in the power system, such as high-voltage transmission grid, transformer, transmission line, bus, load, etc. According to the voltage level and power transmission process of the power grid and other factors, each node in the topology structure is hierarchically divided. For example, the transmission of power in the power grid follows the order from high voltage to low voltage. The high-voltage power generated by the generator is first transmitted to the transformer substation for voltage reduction, and then distributed to each district area through the transmission line, and finally supplied to the user after being reduced in voltage again in the district area. This transmission process from high voltage to low voltage determines the hierarchical relationship of the power grid equipment: the high-voltage transmission grid is at the highest level, the transformer substation is next, the transmission line is next, the district area is next, and the user is at the bottom. Among them, the full name of the district area is the distribution district area, which usually refers to the area centered on the distribution transformer, which supplies power to the users within a certain range. It is the direct connection link between the power grid and the user, responsible for converting medium-voltage power into low-voltage power and distributing it to each user. Each district area has its specific power supply range and user group, and has relatively independent operating characteristics.

[0014] In this embodiment, according to the scale and complexity of the power grid, a tree data structure is selected to store the power grid topology information. The tree structure is suitable for power grid systems with clear hierarchical relationship and explicit branches, such as Figure 2 as shown, for example, a simple radial power grid. Among them, the high-voltage transmission grid is the root node, with a level of 1; the transformer substation is its child node, with a level of 2; the line is the child node of the transformer substation, with a level of 3; the district area is further the child node of the line, with a level of 4; and the user is the child node of the district area, with a level of 5; and the whole constitutes a multi-fork tree structure.

[0015] In this embodiment, the target node is directly related to the line loss determination, which can cover all nodes or be a part of specific designated nodes.

[0016] In this embodiment, the acquisition of historical and real-time load energy data is achieved through the dispatching automation system configured in the power grid. These systems can collect and store the load energy data of each node in the power grid in real time. By interfacing with the data interface of the dispatching automation system and following the established data format and transmission protocol, the required historical and real-time load energy data of the target node is periodically read from the system. The real-time load energy data is the actual load energy data. A constant value is used to fill in the missing values in the actual load energy data, for example, using 0 to fill in the missing parts.

[0017] S02: According to the historical load energy data of each target node, the predicted value of the actual load energy data is determined; according to the predicted value of the actual load energy data, the normal fluctuation range of the actual load energy data is determined; according to the normal fluctuation range and the actual load energy data of each target node in the target time period, the abnormal load energy data of each target node in the target time period is determined.

[0018] In this embodiment, the normal fluctuation range of the actual load energy data is used to quantify the natural change amplitude of the actual load energy data in the time sequence. If the change amplitude of the actual load energy data is within the normal fluctuation range, the actual load energy data is normal data. If the change amplitude of the actual load energy data exceeds the upper and lower limit values of the normal fluctuation range, the actual load energy data is abnormal load energy data. Among them, the abnormal load energy data may be represented as data missing, or may be represented as data value abnormality.

[0019] S03: According to the specific hierarchical relationship of each target node, the abnormal load energy data of each target node in the target time period is corrected for the first time; the first correction further includes: according to the node load type of the target node, the abnormal load energy data of the target node corresponding to the preset node load type in the target time period is corrected for the second time; and / or according to the historical load energy data of the adjacent nodes of the target node, the abnormal load energy data of the target node in the target time period is corrected for the third time.

[0020] In this embodiment, the hierarchical position refers to the specific level of the node in the power grid topology structure, for example, as shown in FIG. 1, the hierarchical position of C1 area is 4. According to the hierarchical position of each target node in the power grid topology structure, a suitable basic prediction model is selected, and the model is used to correct the missing values or abnormal values in the abnormal load energy data of different hierarchical nodes for the first time. The correction here includes the completion of the missing data and the correction of the abnormal data values. Figure 2

[0021] ​In this embodiment, node load types include industrial loads, commercial loads, residential loads, and agricultural loads. Preset node load types refer to several load types manually set by the user; these can cover all node load types or only a portion of them. Based on the abnormal load power data that has undergone the first correction, and according to the specific load type of the target node, other applicable correction algorithms are further selected for different types of loads, or the basic prediction model used in the first correction is optimized. Therefore, based on the newly selected correction algorithm or the optimized prediction model, the abnormal load power data is further corrected to improve the accuracy of the data correction.

[0022] In this embodiment, the adjacent nodes of the target node refer to the parent node or sibling nodes of the current target node. For example, such as Figure 2 As shown, the parent node of transformer C1 is the direct superior node that has a power supply relationship with it, such as feeder B node; while its sibling nodes are other nodes at the same level as transformer C1, such as transformer C2 node and transformer C3 node.

[0023] In this embodiment, based on the abnormal load power data that has been corrected for the first or second time, the load power data of adjacent nodes of each target node is further corrected for the third time by combining the historical load power data.

[0024] S04: Based on the corrected actual load power data and the power grid topology, obtain the total input load power and total output load power of each layer; determine the line loss of each layer based on the total input load power and total output load power of each layer, and obtain the line loss value of each layer in the power grid topology.

[0025] In this embodiment, as Figure 3 As shown, the total input load of each layer refers to the total electrical energy flowing into a specific power grid level (such as a substation, feeder, or distribution substation), which is usually collected in real time by smart meters or metering devices at the entrance of that level. The total output load of each layer refers to the total electrical energy output from that power grid level and actually used by the next level of equipment or end users, and recorded by the metering device.

[0026] In this embodiment, line loss refers to the collective term for energy loss caused by physical losses and metering differences during the transmission of electrical energy from the generation end to the user end in a power system. Layered line loss calculation is performed to decompose the total line loss of the entire network into specific layers based on the power grid topology and specific levels, thereby achieving precise location of losses and determination of responsibility. The line loss value of each layer in the power grid topology is the difference between the total input load and the total output load of each layer. For example, as... Figure 2As shown, level 1 is a high-voltage power transmission network, corresponding to the main trunk transmission line, and the line loss value of this level is equal to the power generation plant on-grid power minus the sum of the input power of each regional substation. Level 2 is a regional substation, taking a large substation as a unit, and the line loss value of this level is equal to the total input power of the station minus the sum of the power of all outgoing lines of the station. Level 3 is a medium-voltage distribution feeder, taking a 10kV or 35kV distribution line as a unit, and the line loss value of this level is equal to the metering power at the start of the line minus the sum of the metering power at the high-voltage side of all area transformer substations on the line. Level 4 is a distribution area, which is the most common basic unit, referring to the area powered by a distribution transformer, and the line loss value of this level is equal to the total power of the low-voltage outlet meter of the area transformer minus the sum of the power of all end-user meters under the area transformer. Level 5 is the indoor line, and the line loss value of this level is equal to the total metering power of the user incoming line minus the sum of the power consumption of the indoor electrical equipment.

[0027] The line loss determination method of the power grid system of the embodiment comprises: first, according to the historical data, the predicted value of the actual load power is determined, thereby defining the normal fluctuation range, and the abnormal load power data of the target node in the target time period is accurately identified. Subsequently, the first correction is carried out according to the hierarchical relationship between the nodes, and the abnormal data is preliminarily adjusted from the perspective of the power grid topology. Then, the second correction is carried out in combination with the load type corresponding to the node, and the characteristic differences of different types of loads are fully considered, so that the correction is more targeted and accurate. For the abnormal data that appears continuously for a long time, the third correction is carried out by using the historical load data of the adjacent nodes, and the data quality is further improved by means of the correlation between the nodes. Through this multi-level correction mechanism, the reliability of the actual load power data is effectively guaranteed. On the basis of obtaining high-quality corrected data, in combination with the power grid topology, the total input and total output load power of each level can be accurately calculated, and the line loss value of each level is determined. This not only helps to comprehensively grasp the energy loss of the power grid at different levels, but also can accurately locate the loss source by analyzing the local loss of each level, provide key data support for the optimized operation, energy saving and consumption reduction and equipment maintenance of the power grid, and significantly improve the overall operation efficiency and economic benefit of the power grid.

[0028] Optionally, in step S02, the predicted value of the actual load power data is determined according to the historical load power data of each target node, specifically including the following steps: S201: Determine a load baseline prediction model according to the time sequence characteristics of the historical load power data of each target node and external influencing factors.

[0029] In this embodiment, the time series features are timestamp information extracted at different time scales, such as one day (24 hours), one week (7 days), or one year (season), etc. The external influencing factors include weather (such as temperature, humidity), holiday identification, and other factors that affect the load value. The load baseline prediction model adopts a random forest regressor model. The historical load energy data includes fields such as timestamp, temperature, humidity, holiday identification, and load value. The historical load energy data is divided into a load energy training data set and a load energy verification data set. The load energy training data set is input into the random forest regressor model, and the complex nonlinear relationship between temperature, humidity, time, and holiday factors and the load value in the historical data is learned through the model. Subsequently, the load energy verification data set is input into the trained random forest regressor model, and the predicted value of the load value is output. The mean square error between the predicted value and the actual value of the load value is taken as the objective function, and the parameters of the random forest regressor model are optimized accordingly. When the objective function reaches the minimum value, the corresponding model parameters are the optimal parameter configuration. The model is configured according to the optimal parameter configuration, and a trained random forest regressor model is finally obtained.

[0030] S202: Determine the predicted value of the load energy actual data according to the load baseline prediction model of each target node.

[0031] In this embodiment, the timestamp, temperature, humidity, and holiday identification fields in the load energy actual data of each target node are input into the corresponding trained random forest regressor model in step S201, thereby obtaining the predicted value of the load energy actual data. The predicted value specifically refers to the predicted result of the load value, and different target nodes correspond to different random forest regressor models.

[0032] The determination of the normal fluctuation range of the load energy actual data according to the predicted value of the load energy actual data specifically includes the following steps: S203: Obtain the normal fluctuation range of the load energy actual data according to the predicted value of the load energy actual data and the statistical distribution characteristics of the historical load energy data.

[0033] In this embodiment, the predicted value of the load energy actual data refers to the predicted result of the load value in step S202, and the statistical distribution characteristics of the historical load energy data refer to the standard deviation of the load data; the standard deviation is a measure of the volatility of historical load data, specifically referring to the degree of dispersion of historical load sampling values around the mean value. Accordingly, the calculation formula of the normal fluctuation range is: wherein, is the predicted value; k is the two-sided 95% quantile of the standard normal distribution, taking the value of 1.96; is the standard deviation of historical load energy data.

[0034] The line loss determination method of the power grid system of the embodiment realizes accurate prediction and intelligent abnormal monitoring of load energy data by constructing a load baseline prediction model that integrates time series features and external influencing factors, and defining a dynamic fluctuation range in combination with statistical distribution. The load baseline prediction model not only fully considers the internal laws in historical load data, such as trend, periodicity and seasonality, but also introduces external influencing factors such as temperature, humidity and holidays, so that the prediction result is closer to the actual load change under complex environment. At the same time, by combining the predicted value with the statistical distribution characteristics (such as standard deviation) of historical data to dynamically define the fluctuation range, the threshold can be automatically adjusted according to the load level, season and time period, etc. Not only can it effectively avoid misjudgment of normal fluctuations, but also significantly improve the identification sensitivity of real abnormalities, thereby significantly enhancing the accuracy and robustness of abnormal detection.

[0035] Optionally, in step S02, the abnormal load energy data of each target node in the target time period is determined according to the normal fluctuation range and the load energy actual data of each target node in the target time period, specifically including the following steps: S301: If the value of any sampling point in the load energy actual data exceeds the normal fluctuation range, and the load energy actual data values in the subsequent one or two sampling periods return to the normal fluctuation range, it is determined that the load energy actual data value of the sampling point exceeding the normal fluctuation range is a sharp value fluctuation anomaly.

[0036] In the embodiment, the value of the sampling point refers to the actual load value in the load energy actual data. When the actual load value at a certain time instant instantaneously and greatly exceeds the upper limit or lower limit of the normal fluctuation range (for example, more than 3 times the standard deviation), and quickly returns to the normal fluctuation range within the subsequent one to two sampling points, it is determined that the actual load value of the sampling point exceeding the normal fluctuation range is a sharp value fluctuation anomaly.

[0037] S302: If the load energy actual data values of the continuous N sampling points in the load energy actual data all exceed the normal fluctuation range, it is determined that the load energy actual data values of the continuous N sampling points are continuous fluctuation anomalies; wherein N is a preset positive integer threshold.

[0038] In this embodiment, when the actual load values of a plurality of consecutive sampling points (for example, N, N can be set according to business needs, such as N>5) continuously exceed or are lower than the normal fluctuation range, even if the deviation of a single sampling point is not large, it will be determined that the actual load energy data of the consecutive N sampling points has a continuous fluctuation anomaly. Such anomalies usually indicate that the metering device has a fault or a persistent problem such as data transmission interruption.

[0039] S303: Determine the curve similarity between the time series curve of the actual load energy data and the preset standard curve, and if the curve similarity is greater than a preset similarity threshold, determine that there is a shape fluctuation anomaly in the actual load energy data. The abnormal load energy data includes the sharp value fluctuation anomaly, the continuous fluctuation anomaly, and the shape fluctuation anomaly.

[0040] In this embodiment, the time series curve is a broken line or a smooth curve formed by connecting consecutive points with time as the horizontal axis and the actual load energy value as the vertical axis, which is used to intuitively present the change rule of the data over time. The time series curve of the actual load is compared with the preset standard time series curve, and the similarity of the two curves is calculated. When the similarity of the two curves is greater than a preset similarity threshold, it indicates that there is a significant difference in the shape of the two curves, for example, there is an unexpected load peak during the low load period such as early morning, even if the peak value does not exceed the upper limit of the range, it is also judged as a shape anomaly, which may indicate electricity theft or sudden heavy load at night.

[0041] The line loss determination method of the power grid system in this embodiment can more accurately and intelligently identify abnormal data that needs to be intervened by performing multi-dimensional anomaly judgment on the sharp value fluctuation anomaly, continuous fluctuation anomaly and shape fluctuation anomaly in the actual load energy data, effectively avoiding the misjudgment and omission caused by the traditional fixed threshold method.

[0042] Optionally, in step S03, the abnormal load energy data of each target node in the target time period is corrected for the first time according to the specific hierarchical relationship of each target node, specifically including the following steps: S401: According to the level of each target node in the power grid topology structure, if the level of the target node is greater than a preset level threshold, a first load prediction model for extracting periodic global features of data is selected to correct the abnormal load energy data of each target node in the target time period for the first time.

[0043] In the embodiment, the data periodic global feature refers to that the historical data of the target node as a whole exhibits strong regularity and periodicity. The first load prediction model can be a time series prediction model, through which the data periodic global feature can be extracted, such as a random forest model, an autoregressive integrated moving average (ARIMA) model, a Prophet model, and the like. The level of each target node in the power grid topology is determined, and if the level of the target node is greater than a preset level threshold (for example, the level threshold is set to 3), the nodes whose level is greater than 3 are divided into high-level nodes (such as high-voltage power transmission grids and substations). Such nodes collect a large amount of downstream load, and the overall behavior thereof exhibits strong regularity and periodicity. Therefore, when the data of such nodes is missing, the time series prediction model is preferentially selected. These models can effectively capture the inherent trend and seasonality (day, week, season), thereby performing high-precision filling. The process of training the time series prediction model using the historical load and energy data of the target node is prior art and is not the improvement of the present application, and will not be described here.

[0044] In the embodiment, the time information in the abnormal load and energy data of the target node in the target time period is input into the trained time series prediction model, and the predicted value of the load value in the abnormal load and energy data is output. The abnormal load and energy data of the target node in the target time period is corrected for the first time according to the predicted value of the load value.

[0045] S402: If the level of the target node is not greater than a preset level threshold, and the number of abnormal load and energy data is less than a preset number threshold, a second load prediction model for extracting data local change features is selected to correct the abnormal load and energy data of each target node in the target time period for the first time.

[0046] In the embodiment, the data local change feature refers to the continuity, smoothness, and correlation of the data in a local range. The second load prediction model can adopt a local smoothing algorithm (such as a cubic spline interpolation). When the level of the target node does not exceed the preset level threshold (for example, the level threshold is set to 3), the target node and the nodes whose level is not higher than 3 are divided into low-level nodes (such as a transformer area and a user side). The load of such nodes has stronger randomness and volatility. If the data is missing and the missing time is short (for example, 1 to 2 sampling points), the local smoothing algorithm is preferentially selected to ensure the smoothness of data change.

[0047] The line loss determination method of the power grid system of the embodiment can improve the correction accuracy of the abnormal load electric energy data by selecting a corresponding load prediction model according to different levels of target nodes to predict the abnormal load electric energy data and correcting the abnormal data based on the prediction result. The method effectively enhances the accuracy and integrity of the actual load electric energy data and significantly improves the reliability of the line loss calculation result.

[0048] Optionally, in step S03, the abnormal load electric energy data of the target node corresponding to the preset node load type in the target time period is corrected for the second time according to the node load type of the target node, and specifically includes the following steps: S501: According to the node load type of the current target node, if it is determined that the current target node is an industrial load or a commercial load, the workday or rest day and production shift are added as external variable features to the first load prediction model to obtain a third load prediction model; and the abnormal load electric energy data of the corresponding target node in the target time period determined as an industrial load or a commercial load is corrected for the second time according to the third load prediction model.

[0049] In the embodiment, the load type includes industrial load, commercial load, residential load, agricultural load, etc. Among them, industrial and commercial loads have strong start-stop regularity and are closely related to production and operation activities. By introducing the workday and rest day, typical production shift, etc. as external regression variables into the first load prediction model (time series model), a third load prediction model is constructed. This model not only can effectively capture the inherent trend and seasonal characteristics of the load (such as daily, weekly, quarterly changes), but also can further reflect the workday or rest day, typical production shift, etc. closely related to production and operation activities, thereby improving the accuracy of load prediction. The process of training the third load prediction model using the historical load electric energy data of the target node is all prior art and is not the improvement of the present application, which will not be described here.

[0050] In the embodiment, the time information in the abnormal load electric energy data of the target node in the target time period is input into the trained third load prediction model, and the predicted value of the load value in the abnormal load electric energy data is output. The abnormal load electric energy data of the target node in the target time period is corrected for the second time according to the predicted value of the load value.

[0051] S502: If the current target node is determined as a residential load, the similarity of the time series curve of the historical load energy data of the current target node and the time series curve of the historical load energy data of each neighbor node is compared; if the similarity is greater than a preset first similarity threshold, the abnormal load energy data of the target node in the target time period is corrected for the second time according to the average load curve of the historical load energy data of the neighbor node with the similarity greater than the preset first similarity threshold.

[0052] In the embodiment, the residential load refers to the total amount of electrical energy consumed by residential users in daily life and production activities. Although individual electricity consumption behavior has great randomness, it generally shows obvious morning and evening double-peak characteristics on the whole region. Based on the template matching method of similar load curve, a group of adjacent nodes with the most similar load value curve to the target node is identified from the same type nodes according to the load value curve of the historical load data of the target node, for example, by calculating the similarity of the load curve of the historical load data of the target node and the load curve of the historical load data of other adjacent nodes of the same type, if the similarity of the two is greater than the first similarity threshold, the adjacent node is added to the similar adjacent node group, and finally the load value on the average load curve of the adjacent nodes in the similar adjacent node group is calculated and used to correct the abnormal load energy data of the target node in the target time period of the node determined as a residential load for the second time.

[0053] The line loss determination method of the power grid system of the embodiment introduces a new external variable (such as a working day or a shift) to realize model correction for nodes of industrial or commercial load types; and for nodes of residential load types, data correction is performed through the similarity of adjacent nodes with similar load types. According to the characteristics of different load types, the most suitable correction method for the electricity consumption characteristics is adopted to perform secondary processing on abnormal data. This targeted correction strategy significantly improves the accuracy of the second correction, effectively avoids the systematic deviation that may be caused by using a single model to correct all types of data, and thus improves the accuracy of data correction and the robustness of the system as a whole.

[0054] Optionally, in step S03, that is, the abnormal load energy data of the target node in the target time period is corrected for the third time according to the historical load energy data of the adjacent nodes of the target node, specifically including the following steps: S601: Obtain the load correlation coefficient between each target node and its adjacent nodes.

[0055] In the embodiment, the load correlation coefficient between the load curve of the historical load energy data of each target node and the load curve of the historical load data of its adjacent nodes is calculated and stored in advance.

[0056] S602: If the load correlation coefficient is greater than the preset correlation threshold, the abnormal load energy data of the target node in the target time period is corrected for the third time according to the historical load energy data of the corresponding adjacent node.

[0057] In this embodiment, first, the size relationship between the load correlation coefficient obtained in step S601 and the preset correlation threshold is judged. If the load correlation coefficient is greater than the preset correlation threshold (for example, the load correlation coefficient > 0.8), it indicates that the two have high correlation, and it is indicated that the historical load energy data between the target node with abnormal data and its adjacent nodes (parent nodes or sibling nodes) is highly synchronized. At this time, a multiple regression model can be constructed according to the historical load energy data of these adjacent nodes with strong data synchronization. The real-time, accurate and highly correlated parameter variables (such as time stamp, temperature, humidity, etc.) of the adjacent nodes at the same time are input into the multiple regression model as input data, and the predicted value of the target node load value to be corrected is output. The predicted value is used to correct the long-time continuous abnormal load energy data of the target node in the target time period for the third time. This method makes full use of the spatial correlation between nodes, and is usually more accurate than the correction method that only relies on the historical data of the target node itself.

[0058] If the correlation between the two is not significant (for example, the load correlation coefficient < 0.8), the data of the adjacent nodes is not used for direct estimation, but the model selected only according to the attributes of the target node (such as hierarchical position and load type) is used to avoid introducing noise interference.

[0059] The line loss determination method of the power grid system in this embodiment adopts a spatial correlation correction strategy based on the load correlation coefficient, and for the target node with long-time continuous abnormal data, the historical load data of its adjacent nodes is used for the third correction. By introducing the historical load data of the strongly correlated neighbor nodes as the correction reference, the reference information in the spatial dimension is fused, the influence of single node data noise is effectively reduced, and the robustness and accuracy of abnormal data correction are improved.

[0060] Optionally, as shown in Figure 3 and Figure 4 The line loss determination method further comprises the following steps: S701: According to the line loss values of each layer in the power grid topology structure and the preset line loss threshold, locate the high-loss line loss layer in the power grid topology structure.

[0061] In the embodiment, the size relationship between the line loss value of each layer in the power grid topology and the preset line loss threshold is judged. If the line loss value of a layer is greater than the preset line loss threshold, the layer is divided into a high-loss line loss layer.

[0062] S702: configuring a switching switch in the area corresponding to the high-loss line loss layer of the power grid topology, setting the on-off state of the switching switch and the equipment selection in the area as independent variables, and re-determining and judging the line loss corresponding to the high-loss line loss layer. When the re-determined line loss value corresponding to the high-loss line loss layer meets the preset target condition, the on-off state of the current switching switch and the equipment selection are determined as the optimal decision variable value.

[0063] In the embodiment, the high-loss line loss layer is optimized according to the preset optimization model, and a corresponding improvement suggestion is proposed. For example, the load distribution of the high-loss line loss layer can be adjusted through simulation calculation, or the loss parameters of different types of equipment are compared, and then the suggestion of equipment replacement is proposed. These optimization measures all need to rely on the optimization algorithm to provide decision support.

[0064] In the embodiment, the preset optimization model is a mathematical programming model aiming at minimizing the line loss of the region. The construction of the optimization model mainly includes three core links of defining the objective function, the decision variable and the constraint condition, aiming to provide strong decision support for generating optimization suggestions such as load distribution adjustment and equipment replacement. Specifically, the construction process of the optimization model includes the following steps: 1) Defining the objective function: the core objective of the optimization model is to minimize the total active power loss in the specified power grid region (Ptotal). P loss The objective function is expressed as: Wherein, L represents the set of all line and transformer branches in the area corresponding to the high-loss line loss layer, I i is the current flowing through the branch i , R i is the resistance of the branch i .

[0065] Decision variables: In order to achieve the minimum of the objective function, the optimization model needs to adjust a series of controllable parameters, which are the decision variables. The main ones include: network topology variables (Sk), for the area corresponding to the high-loss line loss layer, configure the tie switch or sectionalizing switch k, define a binary variable Sk∈{0, 1} for the switch, where 1 represents the closing of the switch and 0 represents the opening. By changing the switch combination, the load transfer between different feeders can be realized. Equipment selection variables (Ej), for the equipment points that can be transformed (such as old transformer j), define one or more binary variables Ej to represent whether to replace it with a new model. For example, Ej_new=1 represents replacing the original equipment model, and Ej_old=1 represents not replacing the original equipment model. Among them, different models of equipment correspond to different loss parameters, such as resistance Rj and reactance Xj.

[0066] Constraints: Any optimization scheme must be within the boundaries of grid safety and stability. Therefore, the optimization model contains the following key constraints: ① Power flow balance constraint: the injected power of each node must be equal to the sum of the outgoing power, which ensures that the solution of the model satisfies Kirchhoff's law.

[0067] ② Voltage constraint: the voltage amplitude (V) of all nodes must be maintained within the safe range specified by the state or industry, for example: Vi ) must be maintained within the safe range specified by the state or industry, for example: wherein, represents the rated voltage.

[0068] ③ Branch capacity constraint: the load current (or power) of all lines and transformers must not exceed its rated maximum capacity (Pmax), i.e. Ii_max ). Ii Ii_max .

[0069] ④ Network connectivity and radial constraint: the optimized network topology must ensure reliable power supply to all users (network connectivity), and for distribution networks, it is usually required to maintain a radial structure, i.e. there is no loop.

[0070] After locating the high-loss line loss layer, the system inputs the grid topology structure, line parameters and load data of the area corresponding to the high-loss line loss layer into the optimization model. By solving the above mixed integer nonlinear programming problem, a set of optimal decision variable values that minimize the objective function (line loss) can be obtained. The pre-set target conditions are the above constraints.

[0071] S703: Optimize and adjust the high-loss line loss layer according to the optimal decision variable values.

[0072] ​In this example, the high-loss line loss layer is optimized and adjusted based on the optimal decision variable values ​​obtained in step S702. For example, if the solution shows that a certain switch state variable Sk has changed, a suggestion to adjust the load distribution is generated, such as: "It is recommended to close the XX tie switch and open the YY section switch to transfer part of the load in the high-load area to the light-load line, which is expected to reduce the line loss by Z%."

[0073] If the equipment selection variable Ej in the solution results points to a new type of equipment, the system generates equipment replacement suggestions, such as: "It is recommended to replace the S7 transformer in XX distribution area with the S13 energy-saving transformer. Considering its no-load and load loss characteristics, it is expected to reduce line loss by W kW under typical load conditions in this area."

[0074] This embodiment presents a method for determining line losses in a power grid system. It constructs a mathematical optimization model for high-loss areas, aiming to minimize regional line losses. This model transforms the line loss problem into a mathematical optimization problem with a definite solution by defining an objective function, setting decision variables, and establishing constraints. This allows optimization recommendations to move beyond empirical judgment and instead rely on precise decisions calculated by the model, thus providing scientific and reliable decision support for optimization measures such as load allocation adjustments and equipment replacement.

[0075] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0076] In one embodiment, a line loss determination device for a power grid system is provided, which corresponds one-to-one with the line loss determination method for the power grid system described in the above embodiments. For example... Figure 5 As shown, the line loss determination device for this power grid system includes a load data acquisition module 101, an abnormal load judgment module 102, an abnormal data correction module 103, and a line loss determination module 104. Detailed descriptions of each functional module are as follows: The load data acquisition module 101 is used to acquire historical load power data of each node in a historical time period, and actual load power data of each target node in a target time period, based on the power grid topology structure of the current power grid system and the specific hierarchical relationship. The abnormal load judgment module 102 is used to determine the predicted value of the actual load power data based on the historical load power data of each target node; determine the normal fluctuation range of the actual load power data based on the predicted value of the actual load power data; and determine the abnormal load power data of each target node within the target time period based on the normal fluctuation range and the actual load power data of each target node within the target time period.

[0077] The abnormal data correction module 103 is configured to correct abnormal load energy data of each target node in a target time period according to a specific hierarchical relationship of the target node; the first correction further comprises: correcting abnormal load energy data of a target node corresponding to a preset node load type in a target time period according to a node load type of the target node; and / or correcting abnormal load energy data of a target node with long-time continuous abnormal data in a target time period according to historical load energy data of a neighboring node of the target node.

[0078] The line loss determination module 104 is configured to obtain total input load energy and total output load energy of each layer according to the corrected load energy actual data and the power grid topology structure; and determine line loss of each layer according to the total input load energy and the total output load energy of each layer, to obtain line loss values of each layer in the power grid topology structure.

[0079] Optionally, the abnormal load judgment module 102 comprises: The model construction sub-module is configured to determine a load baseline prediction model according to time sequence characteristics of the historical load energy data of each target node and external influencing factors.

[0080] The prediction sub-module is configured to determine a predicted value of the load energy actual data according to the load baseline prediction model of each target node.

[0081] The normal fluctuation determination sub-module is configured to determine a normal fluctuation range of the load energy actual data according to the predicted value of the load energy actual data and statistical distribution characteristics of the historical load energy data.

[0082] Optionally, the abnormal load judgment module 102 comprises: The sharp value fluctuation abnormality judgment unit is configured to determine that the load energy actual data value of a sampling point exceeding the normal fluctuation range is a sharp value fluctuation abnormality if the load energy actual data value of the sampling point exceeds the normal fluctuation range and the load energy actual data value in a subsequent continuous one or two sampling periods returns to the normal fluctuation range.

[0083] The continuous fluctuation abnormality judgment unit is configured to determine that the load energy actual data values of continuous N sampling points are continuous fluctuation abnormalities if the load energy actual data values of the continuous N sampling points exceed the normal fluctuation range; wherein N is a preset positive integer threshold.

[0084] The morphological fluctuation anomaly judgment unit is configured to judge a curve similarity between a time series curve of the actual load power data and a preset standard curve, and determine that the actual load power data contains a morphological fluctuation anomaly if the curve similarity is greater than a preset similarity threshold.

[0085] Optionally, the abnormal data correction module 103 specifically includes: The first type of hierarchical correction submodule is configured to select a first load prediction model for extracting data periodic global features to perform a first correction on the abnormal load power data of each target node in the target time period if the hierarchical level of the target node is greater than a preset hierarchical threshold.

[0086] The second type of hierarchical correction submodule is configured to select a second load prediction model for extracting data local change features to perform a first correction on the abnormal load power data of each target node in the target time period if the hierarchical level of the target node is not greater than the preset hierarchical threshold and the number of abnormal load power data is less than a preset number threshold.

[0087] Optionally, the abnormal data correction module 103 specifically includes: The first load type submodule is configured to add a workday or a rest day and a production shift as external variable features into the first load prediction model to obtain a third load prediction model if the current target node is determined to be an industrial load or a commercial load according to the node load type of the current target node, and perform a second correction on the abnormal load power data of the corresponding target node in the target time period according to the third load prediction model.

[0088] The second load type submodule is configured to compare a time series curve of historical load power data of the current target node with time series curves of historical load power data of each neighbor node if the current target node is determined to be a residential load, and perform a second correction on the abnormal load power data of the target node in the target time period according to an average load curve of historical load power data of the neighbor node whose similarity is greater than a preset first similarity threshold if the similarity is greater than the preset first similarity threshold.

[0089] Optionally, the abnormal data correction module 103 specifically includes: The load correlation coefficient acquisition submodule is configured to acquire a load correlation coefficient between each target node and its adjacent node.

[0090] The load correlation coefficient correction submodule is configured to, if the load correlation coefficient is greater than a preset correlation threshold, correct the abnormal load energy data of the target node in the target time period according to historical load energy data of the corresponding adjacent nodes.

[0091] Optionally, the line loss determination device of the power grid system further comprises: The high-loss line loss layer positioning submodule is configured to position a high-loss line loss layer in the power grid topology according to line loss values of layers in the power grid topology and a preset line loss threshold.

[0092] The optimization submodule is configured to configure a switching switch in a region corresponding to the high-loss line loss layer of the power grid topology, set a state of the switching switch and equipment selection in the region as independent variables, and re-determine and judge line loss corresponding to the high-loss line loss layer, and when the re-determined line loss value corresponding to the high-loss line loss layer meets a preset target condition, determine the state of the switching switch and the equipment selection as optimal decision variable values. The optimization adjustment submodule is configured to optimize and adjust the high-loss line loss layer according to the optimal decision variable values.

[0093] The line loss determination device of the power grid system provided by the embodiment of the application comprises the following steps: first, the historical and actual load energy data are obtained, the predicted value of the actual load energy is determined according to the historical data, so as to define the normal fluctuation range, and the abnormal load energy data of the target node in the target time period is accurately identified. Then, the first correction is performed according to the hierarchical relationship between nodes, and the abnormal data is preliminarily adjusted from the perspective of the power grid topology. Then, the second correction is performed in combination with the load type corresponding to the node, and the characteristic differences of different types of loads are fully considered, so that the correction is more targeted and accurate. For the abnormal data that appears continuously for a long time, the third correction is performed by using the historical load data of adjacent nodes, and the data quality is further improved by using the correlation between the nodes. Through the multi-level correction mechanism, the reliability of the actual load energy data is effectively guaranteed. On the basis of obtaining high-quality corrected data, the total input and total output load energy of each level can be accurately calculated in combination with the power grid topology, so as to determine the line loss value of each level. This not only helps to comprehensively grasp the energy loss of the power grid at different levels, but also can accurately locate the loss source by analyzing the local loss of each level, provide key data support for the optimized operation, energy saving and equipment maintenance of the power grid, and significantly improve the overall operation efficiency and economic benefit of the power grid.

[0094] The specific definitions of the line loss determination device of the power grid system can refer to the definitions of the line loss determination method of the power grid system, which will not be repeated here. Each module in the line loss determination device of the power grid system can be realized by software, hardware, and a combination thereof, in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0095] In an embodiment, as shown in Figure 6 , a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the line loss determination method of the power grid system in the above-mentioned embodiments is implemented, for example Figure 1 S01-S04, or Figures 2 to 4 , which will not be repeated here to avoid repetition. Alternatively, when the processor executes the computer program, the functions of each module / unit in the embodiment of the line loss determination device of the power grid system are implemented, for example Figure 5 the functions of the load data acquisition module 101, the abnormal load judgment module 102, the abnormal data correction module 103, and the line loss determination module 104 shown in , which will not be repeated here to avoid repetition.

[0096] In an embodiment, a computer readable storage medium is provided, which stores a computer program. When the processor executes the computer program, the line loss determination method of the power grid system in the above-mentioned embodiments is implemented, for example Figure 1 S01-S04, or Figures 2 to 4 , which will not be repeated here to avoid repetition. Alternatively, when the processor executes the computer program, the functions of each module / unit in the embodiment of the line loss determination device of the power grid system are implemented, for example Figure 5 the functions of the load data acquisition module 101, the abnormal load judgment module 102, the abnormal data correction module 103, and the line loss determination module 104 shown in , which will not be repeated here to avoid repetition.

[0097] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, rather than limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for determining line losses in a power grid system, characterized in that, The line loss estimation method includes: Based on the power grid topology structure of the current power grid system, historical load power data of each node in the historical time period and actual load power data of each target node in the target time period are obtained. Based on the historical load power data of each target node, the predicted value of the actual load power data is determined; based on the predicted value of the actual load power data, the normal fluctuation range of the actual load power data is determined; based on the normal fluctuation range and the actual load power data of each target node within the target time period, the abnormal load power data of each target node within the target time period is determined. Based on the specific hierarchical relationship of each target node, the abnormal load power data of each target node within the target time period is corrected for the first time. After the first correction, the method further includes: based on the node load type of the target node, the abnormal load power data of the target node corresponding to the preset node load type within the target time period is corrected for the second time. And / or based on the historical load power data of the adjacent nodes of each target node, the abnormal load power data of the target node with long-term continuous abnormal data within the target time period is corrected for the third time. Based on the corrected actual load power data and the power grid topology, the total input load power and total output load power of each layer are obtained; based on the total input load power and total output load power of each layer, the line loss of each layer is determined, and the line loss value of each layer in the power grid topology is obtained.

2. The method for determining line losses in a power grid system according to claim 1, characterized in that, The step of determining the predicted value of the actual load power data based on the historical load power data of each target node includes: Based on the time series characteristics and external influencing factors of the historical load power data of each target node, a load baseline prediction model is determined. Based on the load baseline prediction model for each target node, the predicted value of the actual load power data is determined; The step of determining the normal fluctuation range of the actual load power data based on the predicted value of the actual load power data includes: Based on the predicted value of the actual load power data and the statistical distribution characteristics of the historical load power data, the normal fluctuation range of the actual load power data is determined.

3. The method for determining line losses in a power grid system according to claim 1 or 2, characterized in that, The step of determining the abnormal load power data of each target node within the target time period based on the normal fluctuation range and the actual load power data of each target node within the target time period includes: If any sampling point in the actual load power data exceeds the normal fluctuation range, and the actual load power data value recovers to the normal fluctuation range in one or two subsequent consecutive sampling periods, then the actual load power data value of the sampling point that exceeds the normal fluctuation range is determined to be an abnormal peak value fluctuation. If the actual load power data of N consecutive sampling points exceeds the normal fluctuation range, then the actual load power data of the N consecutive sampling points is determined to be a continuous fluctuation abnormality; where N is a preset positive integer threshold. The similarity between the time series curve of the actual load power data and the preset standard curve is determined. If the curve similarity is greater than the preset similarity threshold, it is determined that there is an abnormal morphological fluctuation in the actual load power data. The abnormal load power data includes the peak value fluctuation anomaly, the continuous fluctuation anomaly, and the morphological fluctuation anomaly.

4. The method for determining line losses in a power grid system according to claim 1, characterized in that, The first correction, based on the specific hierarchical relationship of each target node, of the abnormal load power data of each target node within the target time period, includes: Based on the level of each target node in the power grid topology, if the level of the target node is greater than a preset level threshold, a first load prediction model for extracting the periodic global features of the data is selected to perform the first correction on the abnormal load power data of each target node in the target time period. If the level of the target node is not greater than a preset level threshold, and the number of abnormal load power data is less than a preset quantity threshold, then the second load prediction model used to extract local change features of the data is selected to perform the first correction on the abnormal load power data of each target node within the target time period.

5. The method for determining line losses in a power grid system according to claim 4, characterized in that, The second correction, based on the node load type of the target node, involves performing a second correction on the abnormal load power data of the target node within the target time period corresponding to the preset node load type, including: Based on the load type of the current target node, if the current target node is determined to be an industrial load or a commercial load, then extracting workdays or rest days and production shifts as external variable features and adding them to the first load prediction model to obtain a third load prediction model; based on the third load prediction model, the abnormal load power data of the target node corresponding to the industrial load or commercial load within the target time period is corrected for the second time. If the current target node is determined to be a residential load, the similarity between the time series curve of the historical load power data of the current target node and the time series curve of the historical load power data of each neighboring node is compared. If the similarity is greater than a preset first similarity threshold, the abnormal load power data of the target node determined to be a residential load in the target time period is corrected a second time based on the average load curve of the historical load power data of the neighboring nodes whose similarity is greater than the preset first similarity threshold.

6. The method for determining line losses in a power grid system according to claim 4 or 5, characterized in that, The third correction is performed on the abnormal load power data of the target nodes within the target time period based on the historical load power data of the adjacent nodes of each target node, including: Obtain the load correlation coefficient between each target node and its neighboring nodes; If the load correlation coefficient is greater than the preset correlation threshold, then based on the historical load power data of the corresponding adjacent nodes, the abnormal load power data of the target node with long-term continuous abnormal data within the target time period will be corrected for the third time.

7. The method for determining line losses in a power grid system according to claim 1, characterized in that, The method for determining line loss also includes: Based on the line loss values ​​of each layer in the power grid topology and the preset line loss threshold, locate the high-loss line loss layer in the power grid topology; In the region corresponding to the high-loss line loss layer of the power grid topology, a switching switch is configured. The on / off state of the switching switch and the equipment selection in the region are set as independent variables. The line loss corresponding to the high-loss line loss layer is re-determined and judged. When the re-determined line loss value corresponding to the high-loss line loss layer meets the preset target conditions, the on / off state of the current switching switch and the equipment selection are determined as the optimal decision variable values. The high-loss line-loss layer is optimized and adjusted based on the optimal decision variable values.

8. A device for determining line losses in a power grid system, characterized in that, The load data acquisition module is used to acquire historical load power data of each node within a historical time period, and actual load power data of each target node within a target time period, based on the specific hierarchical relationship of the current power grid system and the power grid topology. An abnormal load judgment module is used to determine the predicted value of the actual load power data based on the historical load power data of each target node. Based on the predicted value of the actual load power data, determine the normal fluctuation range of the actual load power data; Based on the normal fluctuation range and the actual load power data of each target node within the target time period, the abnormal load power data of each target node within the target time period are determined. The abnormal data correction module is used to perform the first correction on the abnormal load power data of each target node within the target time period according to the specific hierarchical relationship of each target node. The first correction is followed by: a second correction based on the node load type of the target node, for the abnormal load power data of the target node corresponding to the preset node load type within the target time period; and / or a third correction based on the historical load power data of the adjacent nodes of each target node, for the abnormal load power data of the target node with long-term continuous abnormal data within the target time period. The line loss determination module is used to obtain the total input load energy and total output load energy of each layer based on the corrected actual load energy data and the power grid topology; and to determine the line loss of each layer based on the total input load energy and total output load energy of each layer, thereby obtaining the line loss value of each layer in the power grid topology.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for determining line losses in the power grid system according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for determining line losses in the power grid system according to any one of claims 1 to 7.

Images