A dynamic knowledge graph construction method for power grid resource scheduling

Abstract

The present invention belongs to the technical field of power grid resource scheduling, and discloses a method for constructing a dynamic knowledge graph for power grid resource scheduling. The present invention establishes a multi-level scheduling analysis mechanism that includes scheduling demand identification, power transmission unit screening set construction, and target power transmission unit set generation. This mechanism takes into account distance efficiency, voltage quality, and user risk, dynamically adapts to the real-time status of the power grid, and significantly improves the accuracy, safety, and efficiency of resource allocation, providing a systematic solution for the dynamic scheduling of smart grids. When identifying the target power transmission unit, the present invention establishes a multi-level screening rule that integrates geographic location, power supply capacity, number of path nodes, and transformer stability to obtain the target power transmission unit set, thereby achieving precise filtering of the power transmission units, avoiding the one-sidedness of traditional single-indicator screening, and significantly improving the reliability of the target set and the comprehensive benefits of the scheduling scheme.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid resource scheduling and relates to a method for constructing a dynamic knowledge graph for power grid resource scheduling. Background Art

[0002] With the advancement of smart grid construction, grid resource scheduling faces challenges such as diverse user electricity usage behaviors and dynamic changes in grid topology. Traditional scheduling methods rely heavily on static grid data and single-metric analysis, making it difficult to respond in real time to load fluctuations, path losses, and differences in user electricity usage characteristics. This results in scheduling solutions with deficiencies in efficiency, stability, and risk control. Building a dynamic scheduling system that covers electricity demand identification, transmission resource selection, path optimization, and prioritization has become a key issue in improving grid resource utilization and power supply reliability.

[0003] Traditional technical solutions have not established a multi-level scheduling analysis of electricity scheduling demand identification - power transmission unit screening set construction - target power transmission unit set generation, and lack of quantitative control and dynamic filtering of the entire chain from demand to execution. Problems such as delayed demand response, blind path selection, and lack of risk prevention and control are prone to occur. It is difficult to achieve a dynamic balance of accuracy, safety, and efficiency in a complex power grid environment, which restricts the improvement of the real-time and refined scheduling capabilities of the smart grid.

[0004] Traditional technical solutions lack multi-level screening rule analysis that integrates geographical location, power supply capacity, number of path nodes and transformer stability when selecting target power transmission units. This may lead to increased transmission losses, decreased voltage stability or large-scale power supply impacts, reducing the rationality of the scheduling plan. Summary of the Invention

[0005] In view of this, in order to solve the problems raised in the above background technology, a dynamic knowledge graph construction method for power grid resource scheduling is proposed.

[0006] The purpose of the present invention can be achieved through the following technical solutions: a method for constructing a dynamic knowledge graph for power grid resource scheduling, comprising: obtaining the electricity consumption behavior data of the target electricity user, including load fluctuation rate, peak-to-valley ratio and load rate, and then identifying the electricity scheduling needs of the target electricity user.

[0007] When it is identified that a target power consumer has a power dispatching demand, a power transmission unit is pre-identified based on the geographical location of the target power consumer to obtain a power transmission unit screening set.

[0008] The geographical location and power transmission status of each power transmission unit corresponding to the power transmission unit filter set are obtained, and a power transmission path is constructed based on the geographical location of the target power user unit and the geographical location of each power transmission unit.

[0009] The number of path nodes and the degree of path transformation are analyzed based on the power transmission path, and the number of associated power users and their correlation are analyzed based on the power transmission status.

[0010] A target power transmission unit set is generated based on the predefined scheduling rules according to the number of path nodes, the path voltage transformation degree and the number of associated power consumption units, and a power scheduling priority list is further output.

[0011] Compared with the existing technology, the beneficial effects of the present invention are as follows: (1) The present invention establishes a multi-level scheduling analysis mechanism of scheduling demand identification-transmission unit screening set construction-target transmission unit set generation, taking into account distance efficiency, voltage quality and user risk, dynamically adapting to the real-time status of the power grid, significantly improving the accuracy, safety and efficiency of resource allocation, and providing a systematic solution for the dynamic scheduling of smart grids.

[0012] (2) When identifying the target power transmission units, the present invention establishes a multi-level screening rule that integrates geographical location, power supply capacity, number of path nodes and transformer stability to obtain the target power transmission unit set, thereby achieving accurate filtering of the power transmission units. This method avoids the one-sidedness of traditional single indicator screening, shortens the transmission distance and reduces physical loss, ensures power supply quality through transformer consistency, and avoids the impact on highly sensitive users, significantly improving the reliability of the target set and the comprehensive benefits of the scheduling plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 Schematic diagram of the steps of the method of the present invention.

[0015] Figure 2 A flowchart for identifying and judging electricity dispatching demand corresponding to an embodiment provided by the present invention.

[0016] Figure 3 This is a flow chart for identifying and judging a target power transmission unit corresponding to an embodiment provided by the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] See also Figure 1 As shown, the present invention provides a method for constructing a dynamic knowledge graph for power grid resource scheduling, including: obtaining the electricity consumption behavior data of the target electricity consumer, including load fluctuation rate, peak-to-valley difference ratio and load rate, and then identifying the electricity scheduling needs of the target electricity consumer.

[0019] In a preferred embodiment of the present invention, the specific analysis method of the electricity consumption behavior data is: constructing a load-time change curve based on the historical electricity consumption records of the target electricity user within a preset monitoring period, where the horizontal axis of the change curve is time and the vertical axis is load.

[0020] The monitoring points are arranged on the horizontal axis based on the preset equal-interval time difference to obtain the load corresponding to each monitoring point.

[0021] The absolute difference between the load of each monitoring point and the load of the previous monitoring point is calculated to obtain the load fluctuation of each monitoring point. The load fluctuation is compared with the preset load fluctuation threshold. The number of monitoring points with a load fluctuation greater than the load fluctuation threshold is counted, and then the load fluctuation rate is calculated by ratio with the total number of monitoring points.

[0022] The loads corresponding to each monitoring point are compared to obtain the maximum load and the minimum load, the difference between the maximum load and the minimum load is calculated to obtain the peak-to-valley difference of the target electricity unit, and then the ratio is calculated with the maximum load to obtain the peak-to-valley difference ratio.

[0023] The load corresponding to each monitoring point is averaged to obtain the average load of the target electricity unit, and then the ratio is calculated with the maximum load to obtain the load rate.

[0024] In a preferred embodiment of the present invention, the specific method of identifying the power dispatching demand of the target power consumer is as follows: comparing the load fluctuation rate, peak-to-valley difference ratio and load rate of the target power consumer with preset thresholds respectively.

[0025] See also Figure 2 If any of the load fluctuation rate, peak-to-valley ratio and load rate exceeds the corresponding threshold, it is identified that the target power user has a power dispatch demand.

[0026] It's important to note that a simple, single-indicator over-limit rule avoids scheduling delays caused by multiple constraints and ensures the grid's timely response to abnormal power usage. Exceeding the load fluctuation rate limit indicates significant fluctuations in power demand, necessitating dynamic adjustments to power supply lines or energy storage configurations. Exceeding the peak-to-valley ratio limit indicates excessive differences in peak and valley loads, potentially causing grid overload and requiring optimized power source scheduling. Exceeding the load factor limit indicates underutilized or overloaded equipment, necessitating adjustments to power supply capacity.

[0027] It should be noted that the basis for setting the threshold values ​​corresponding to the load fluctuation rate, peak-to-valley ratio and load rate includes: first, the grid operation standards and equipment safety parameters to ensure system stability; second, the differences in the types of electricity users, such as the electricity consumption characteristics of users with different attributes such as industry and residents; third, the grid peak-shaving capacity and resource allocation, combined with the power supply structure and energy storage capacity; fourth, policy guidance and energy efficiency goals to promote electricity optimization; fifth, a dynamic adjustment mechanism based on historical data, seasonal time periods, etc. to ensure the rationality and adaptability of the threshold values ​​and achieve accurate judgment of scheduling needs.

[0028] When it is identified that a target power consumer has a power dispatching demand, a power transmission unit is pre-identified based on the geographical location of the target power consumer to obtain a power transmission unit screening set.

[0029] In a preferred embodiment of the present invention, the specific construction method of the power transmission unit screening set is as follows: the load of each monitoring point is averaged to obtain the average load of the current monitoring period.

[0030] The instantaneous demand load of the target electricity consumer is obtained by calculating the difference between the rated capacity and the average load of the target electricity consumer.

[0031] The geographical location of each power transmission unit is obtained, and then compared with the geographical location of the target power consumption unit to obtain the distance between each power transmission unit and the target power consumption unit.

[0032] The available load of each power transmission unit is compared with the immediate required load of the target power consumption unit, and the distance between each power transmission unit and the target power consumption unit is compared with a preset distance threshold.

[0033] The power transmission units that can provide a load greater than the immediate demand load and whose distance is less than a preset distance threshold are recorded, thereby constructing a power transmission unit screening set.

[0034] It should be noted that the above module selects transmission units with scheduling feasibility by quantitatively matching electricity demand with transmission capacity and combining geographical location. Specifically, the available load of the transmission unit is compared with the immediate load demand of the target electricity user, and only transmission units with a load capacity greater than the immediate load demand are retained, ensuring that the transmission unit has sufficient redundant power to meet scheduling requirements. At the same time, the distance between the transmission unit and the target electricity user is calculated and compared with a preset distance threshold. Only transmission units with a distance less than the preset threshold are retained, giving priority to close transmission units to reduce transmission line losses, construction costs, and scheduling delays.

[0035] It's important to note that the preset distance threshold setting depends on the grid layout. For example, in densely populated cities, the threshold can be set at 5 kilometers, while in rural areas, the threshold can be relaxed to 15 kilometers. Essentially, the goal is to strike a balance between power supply capacity and transmission costs: excessive distances may result in high line investment and losses, while close distances may be limited by local grid capacity.

[0036] It should be noted that the above content uses dual filtering of load and distance to quickly locate feasible objects from the power transmission units across the entire network, thereby improving scheduling efficiency.

[0037] The geographical location and power transmission status of each power transmission unit corresponding to the power transmission unit filter set are obtained, and a power transmission path is constructed based on the geographical location of the target power user unit and the geographical location of each power transmission unit.

[0038] In a preferred embodiment of the present invention, the specific method of constructing the power transmission path based on the geographical location of the target power user and the geographical location of each power transmission unit is as follows: based on the geographical location of the target power user and the geographical location of each power transmission unit, all lines that can perform power scheduling are identified.

[0039] Obtain the distances corresponding to the lines of each power dispatch, compare them, and select the power dispatch line with the shortest distance as the power transmission path.

[0040] It should be noted that, while ensuring the feasibility of power dispatch, the shortest transmission line is selected as the transmission path to reduce transmission losses, shorten dispatch time, and reduce line construction and maintenance costs. Transmission distance is proportional to line losses, so shorter routes are more economical and efficient.

[0041] It's important to note that all feasible routes meet power transmission capacity requirements. This means the load capacity of the transmission unit has been verified by the filter set. Therefore, there's no need to repeatedly verify capacity matching, focusing solely on distance optimization. In practice, if new lines are added to the grid or existing lines fail, the set of feasible routes must be updated in real time, and the shortest path recalculated to ensure the knowledge graph reflects the grid's real-time status.

[0042] The number of path nodes and the degree of path transformation are analyzed based on the power transmission path, and the number of associated power users and their correlation are analyzed based on the power transmission status.

[0043] In a preferred embodiment of the present invention, the specific analysis method of the path transformation degree is: statistics are collected on the high-voltage side rated voltage and the low-voltage side rated voltage of each transformer in the power transmission path corresponding to each power transmission unit, and then the ratio is calculated to obtain the transformation ratio of each transformer.

[0044] The standard deviation of the transformer ratio in the power transmission path corresponding to each power transmission unit is calculated to obtain the path transformation index of each power transmission unit.

[0045] In a preferred embodiment, the specific calculation formula of the path voltage index is: ,in It represents the standard deviation of the transformer ratio in the power transmission path corresponding to each power transmission unit. Indicates the power supply unit number, , Indicates the number of power transmission units, Indicates the transformation ratio of each transformer in the power transmission path corresponding to each power transmission unit, It represents the average value of the transformer ratio in the power transmission path corresponding to each power transmission unit.

[0046] It's important to note that the purpose of analyzing path transformation index is: 1. Paths with a small standard deviation in transformation ratios provide a more uniform voltage conversion process, reducing voltage quality issues caused by voltage fluctuations and ensuring the safety of electrical equipment. 2. Inconsistent transformation ratios can lead to the accumulation of multi-stage transformation losses. For example, the total loss of multiple high-voltage, medium-voltage, and low-voltage transformations is higher than that of a single transformation. Using the path transformation index to select low-loss paths improves grid energy efficiency.

[0047] For example, assume that the transformer ratio data of the two power transmission paths are as follows: the transformation ratio of path A is 10:1, 10:1, 10:1, the transformation ratio of path B is 12:1, 8:1, 10:1, the path transformation index of path A is 0, and the path transformation index of path A is 1.63. According to the rules, the transformation degree of path A is better, and the corresponding power transmission unit has more advantages in screening and priority sorting.

[0048] In a preferred embodiment of the present invention, a specific method for analyzing the number of associated power consuming units and their correlation is as follows: obtaining the power consuming units and their loads transmitted by each power transmission unit.

[0049] Based on the electricity consumption units whose load is greater than a preset load threshold and the pre-identified special electricity consumption units, corresponding associated electricity consumption unit sets are constructed, and the number of associated electricity consumption units corresponding to the associated electricity consumption unit sets is counted.

[0050] It should be noted that associated power users refer to those directly supplied by the transmission unit. A large number of associated power users means that dispatching the transmission unit may affect more users. This requires careful assessment, especially when multiple high-load or special users are involved.

[0051] It should be noted that the correlation degree measures the degree of dependence of the electricity consumption of the associated power user and the power transmission unit. The larger the value, the higher the proportion of electricity consumption of the user, and the more significant the impact of scheduling on it.

[0052] The correlation degree of each associated power user is calculated by comparing the load of each associated power user to the output load of the power transmission unit. If the power correlation degree of a user is large, it means that the power transmission unit is highly specialized in supplying power to that user. Scheduling may cause a decrease in power stability for that user, and ensuring the stability of their power supply should be prioritized.

[0053] A target power transmission unit set is generated based on the predefined scheduling rules according to the number of path nodes, the path voltage transformation degree and the number of associated power consumption units, and a power scheduling priority list is further output.

[0054] In a preferred embodiment of the present invention, the specific method of generating the target power transmission unit set is as follows: the number of path nodes, path transformation index and number of associated power consumption units of each power transmission unit are compared with the pre-set path node number threshold, path transformation index threshold and associated power consumption unit number threshold respectively.

[0055] The predefined scheduling rule is: the number of path nodes is less than or equal to a path node number threshold.

[0056] The path voltage variation index is less than or equal to the path voltage variation index threshold.

[0057] The number of associated power consumption units is less than or equal to the threshold number of associated power consumption units.

[0058] See also Figure 3 As shown, when a power transmission unit satisfies the three conditions in the predefined scheduling rules at the same time, the power transmission unit is identified as a target power transmission unit, and then a target power transmission unit set is constructed.

[0059] It should be noted that the above content eliminates high-risk or inefficient paths through a rigid match of three key indicators with preset thresholds, ensuring that the power transmission units included in the collection meet the scheduling feasibility and stability requirements.

[0060] It should be noted that the number of path nodes refers to the total number of transmission line nodes included in the transmission path, such as substations, switch stations, and other equipment nodes. A greater number of nodes increases the path complexity, potentially leading to increased transmission losses and a higher probability of failure. The path transformation index refers to the standard deviation of the transformation ratios of each transformer in the transmission path, reflecting the consistency of transformation. A higher index indicates a more unstable transformation process, potentially causing voltage fluctuations or increased losses. The number of associated power users refers to the number of high-load or special power users supplied by the transmission unit. A larger number of these users increases the scope of dispatch impact and the risk.

[0061] It should be noted that the above content quickly filters out invalid options through hard thresholds, narrows the scope of subsequent priority sorting, and reduces computational complexity; ensures that all power transmission units in the target set have low-risk and high-stability characteristics, laying the foundation for generating reliable scheduling plans.

[0062] It should be noted that the setting basis of the path node number threshold, path transformation index threshold and associated power unit number threshold is: 1. Grid operation efficiency and reliability: The path node number threshold refers to the transmission line level restriction. Too many nodes are likely to increase losses and failure risks, and is usually set according to grid planning standards; the path transformation index threshold is based on the transformer ratio consistency requirement. An excessively high index may cause voltage fluctuations, and needs to be set in combination with equipment parameters and power supply quality standards.

[0063] 2. User impact range control: The threshold for the number of associated electricity users is based on the dispatch risk tolerance. Too many units may cause large-scale impacts and need to be dynamically adjusted based on user types to prioritize critical loads.

[0064] 3. Historical data and simulation verification: By analyzing the indicator distribution of the target path in historical dispatch cases and combining it with grid simulation to simulate the dispatch effects under different thresholds, the threshold values ​​are optimized to ensure that the selected power transmission units are both stable and feasible.

[0065] 4. Dynamic adjustment mechanism: The threshold can be flexibly adjusted according to real-time conditions such as grid load peaks and valleys and equipment maintenance. For example, during peak load periods, the node number threshold can be tightened to reduce path loss and ensure power supply efficiency.

[0066] In a preferred embodiment of the present invention, the specific method of the power dispatch priority list is as follows: the power dispatch feasibility evaluation index of each target power transmission unit is calculated using the power dispatch feasibility evaluation index calculation formula according to the number of path nodes, path transformation index and number of associated power consumption units of each target power transmission unit in the target power transmission unit set.

[0067] The power dispatch feasibility evaluation indexes are arranged in descending order to generate an output power dispatch priority list, wherein the power dispatch priority list includes the name of the target power transmission unit, the geographical location and the power dispatch feasibility evaluation index.

[0068] It's important to note that the evaluation index of each target transmission unit is ranked from highest to lowest, with a higher index indicating greater dispatch feasibility and higher priority. Outputting the results in a table format allows for a visual display of the differences in dispatch priorities. A weighted calculation of multiple indicators avoids the limitations of a single metric and comprehensively balances factors such as path complexity, user impact, and voltage stability.

[0069] It should be noted that, when identifying the target power transmission units, the present invention obtains the target power transmission unit set by establishing a multi-level screening rule that integrates geographical location, power supply capacity, number of path nodes and transformer stability, thereby achieving accurate filtering of the power transmission units. This method avoids the one-sidedness of traditional single indicator screening, shortens the transmission distance and reduces physical losses, ensures power supply quality through transformer consistency, and avoids the impact on highly sensitive users, significantly improving the reliability of the target set and the comprehensive benefits of the scheduling plan.

[0070] In a preferred embodiment of the present invention, the calculation formula of the power dispatch feasibility evaluation index can be: Calculate the power dispatch feasibility evaluation index of each target power transmission unit , Indicates the number of the target power transmission unit, , represents the number of target power transmission units, where 、 、 Respectively represent the number of path nodes, path transformation index and number of associated power consumption units of each target power transmission unit, The maximum value of the correlation degree of each target power transmission unit and each associated power consumption unit, 、 、 They represent the preset number of reference path nodes, reference path transformation index and reference associated power unit number, respectively. They represent the impact factors corresponding to the preset number of path nodes, path transformation index and number of associated electricity units respectively.

[0071] It should be noted that the construction idea of ​​the above formula is: based on the quantitative weighting of multiple indicators and reverse optimization logic, by integrating core scheduling factors such as path complexity, voltage stability, and user impact risk, it is converted into a comparable comprehensive evaluation index. Specifically: 1. The more path nodes there are, the more complex the path, and the higher the loss and failure risk. The smaller the number of nodes, the higher the index value. 2. The larger the path transformation index, the worse the voltage stability. A positive mapping is achieved, where smaller indexes correspond to higher indicator values. Specifically, low volatility corresponds to high stability. 3. The greater the number of electricity users or the higher the maximum correlation, the greater the scope of dispatch impact and the higher the risk. 4. Dynamic weight adjustment allows the formula to adapt to different dispatch objectives. By positively transforming and standardizing inverse indicators, a scientific overlay of indicators from different dimensions is achieved, ensuring the rationality and interpretability of priority sorting.

[0072] It should be noted that the basis for setting the reference path node number, reference path transformation index and reference associated electricity unit number is: 1. Grid planning standards: refer to the requirements for transmission line hierarchy and transformer configuration in industry specifications. For example, urban power grids usually require that the number of path nodes does not exceed 10 to control complexity, and the transformation index needs to be lower than 0.8 to ensure voltage stability.

[0073] 2. Historical optimal data: Analyze the indicator distribution of efficient paths in historical scheduling cases and take the mean or minimum value as a reference. For example, the average number of nodes on historical high-quality paths is 6-8 to ensure that the reference value is practical.

[0074] 3. Equipment operating parameters: Combined with the rated voltage level of the transformer and the load capacity of the transmission line, avoid reference values ​​exceeding the safety limit of the equipment, such as the allowable fluctuation range of the transformer ratio of the transformer index.

[0075] 4. Risk control target: The number of related electricity users should refer to the grid's tolerance limit for the impact of a single dispatch, such as no more than 5 high-load users, to prevent large-scale power supply fluctuations.

[0076] 5. Dynamic correction mechanism: Real-time adjustment based on grid load peaks and valleys, the proportion of new energy access, etc. For example, when the load is low, the reference value of the number of nodes is relaxed to improve equipment utilization, ensuring that the reference value adapts to changes in the grid operating status.

[0077] The influencing factor corresponding to the number of associated power consuming units in the above formula needs to be adjusted in real time according to the backup power supply configuration of the associated units and the particularity of the associated power consuming units.

[0078] It should be noted that the setting basis of the influencing factors corresponding to the number of path nodes, path transformation index and the number of associated power users is: the setting basis of the influencing factors corresponding to the number of path nodes, path transformation index and the number of associated power users is based on the degree of influence of the indicators on dispatching efficiency and safety, user demand priority, real-time status of the power grid, historical dispatching case effect verification and policy guidance. By comprehensively considering the actual effect of various factors on the dispatching results, weights are dynamically allocated to ensure that the multi-indicator evaluation system meets the operation needs of the power grid and achieve balanced optimization of path complexity, voltage stability and user impact risks.

[0079] It should be noted that the present invention establishes a multi-level scheduling analysis mechanism of scheduling demand identification-transmission unit screening set construction-target transmission unit set generation, taking into account distance efficiency, voltage quality and user risks, dynamically adapting to the real-time status of the power grid, and significantly improving the accuracy, safety and efficiency of resource allocation, providing a systematic solution for the dynamic scheduling of smart grids.

[0080] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A method for constructing a dynamic knowledge graph for power grid resource scheduling, characterized in that: include: Obtain the target electricity user's electricity consumption behavior data, including load fluctuation rate, peak-to-valley ratio, and load rate, to identify the target electricity user's electricity scheduling needs; When it is identified that the target power user has a power dispatching demand, the power transmission unit is pre-identified based on the geographical location of the target power user to obtain a power transmission unit screening set; Obtain the geographical location and power transmission status of each power transmission unit corresponding to the power transmission unit filter set, and construct a power transmission path based on the geographical location of the target power user and the geographical location of each power transmission unit; Analyze the number of nodes and the degree of voltage transformation based on the power transmission path, and analyze the number of associated power users and their degree of correlation based on the power transmission status; According to the number of path nodes, the degree of path transformation, and the number of associated power users, a target power transmission unit set is generated based on predefined scheduling rules, and a power scheduling priority list is output; The specific analysis method of the path voltage transformation degree is as follows: Count the rated voltages on the high-voltage side and the rated voltages on the low-voltage side of each transformer in the power transmission path corresponding to each power transmission unit, and then calculate the ratio to obtain the transformation ratio of each transformer; Calculate the standard deviation of the transformer ratio in the power transmission path corresponding to each power transmission unit to obtain the path transformation index of each power transmission unit; The specific analysis method for the number of related electricity users is as follows: Obtain the electricity consuming units and their loads transmitted by each electricity transmission unit; Based on the electricity consumption units whose load is greater than a preset load threshold and the pre-identified special electricity consumption units, corresponding associated electricity consumption unit sets are constructed, and the number of associated electricity consumption units corresponding to the associated electricity consumption unit sets is counted.

2. A method for constructing a dynamic knowledge graph for power grid resource scheduling according to claim 1, characterized in that: Specific analysis method of the electricity consumption behavior data: Constructing a load-time variation curve based on the historical electricity consumption records of the target electricity user within a preset monitoring period, wherein the abscissa of the variation curve is time and the ordinate is load; The monitoring points are arranged on the horizontal coordinate based on the preset equal-interval time difference, and the load corresponding to each monitoring point is obtained; The absolute difference between the load at each monitoring point and the load at the previous monitoring point is calculated to obtain the load fluctuation of each monitoring point. The load fluctuation is compared with a preset load fluctuation threshold. The number of monitoring points with a load fluctuation greater than the threshold is counted, and the ratio is calculated with the total number of monitoring points to obtain the load fluctuation rate. Compare the loads corresponding to each monitoring point to obtain the maximum load and the minimum load, calculate the difference between the maximum load and the minimum load to obtain the peak-to-valley difference of the target electricity unit, and then calculate the ratio with the maximum load to obtain the peak-to-valley difference ratio; The load corresponding to each monitoring point is averaged to obtain the average load of the target electricity unit, and then the ratio is calculated with the maximum load to obtain the load rate.

3. The method for constructing a dynamic knowledge graph for power grid resource scheduling according to claim 1, characterized in that: The specific method of identifying the power dispatching demand of the target power user is as follows: Comparing the load fluctuation rate, peak-to-valley ratio, and load rate of the target electricity user with preset thresholds respectively; If any one of the load fluctuation rate, peak-to-valley ratio and load rate exceeds a corresponding threshold, it is identified that the target electricity user has a demand for electricity scheduling.

4. The method for constructing a dynamic knowledge graph for power grid resource scheduling according to claim 2, characterized in that: The specific construction method of the power transmission unit screening set is as follows: Calculate the average load of each monitoring point to obtain the average load of the current monitoring period; The instantaneous required load of the target electricity consumer is obtained by calculating the difference between the rated capacity and the average load of the target electricity consumer; Obtain the geographical location of each power transmission unit, and then compare it with the geographical location of the target power consumption unit to obtain the distance between each power transmission unit and the target power consumption unit; Compare the available load of each power transmission unit with the immediate demand load of the target power consumption unit, and compare the distance between each power transmission unit and the target power consumption unit with a preset distance threshold; The power transmission units that can provide a load greater than the immediate demand load and whose distance is less than a preset distance threshold are recorded, thereby constructing a power transmission unit screening set.

5. The method for constructing a dynamic knowledge graph for power grid resource scheduling according to claim 1, characterized in that: The specific method of constructing the power transmission path based on the geographical location of the target power user and the geographical locations of each power transmission unit is as follows: Identify all lines that can perform power dispatch based on the geographic location of the target power user and the geographic location of each power transmission unit; Obtain the distances corresponding to the lines of each power dispatch, compare them, and select the power dispatch line with the shortest distance as the power transmission path.

6. The method for constructing a dynamic knowledge graph for power grid resource scheduling according to claim 1, characterized in that: The specific analysis method of the correlation degree of the associated electricity users is as follows: The correlation degree of each associated power consuming unit is obtained by calculating the ratio of the load of each associated power consuming unit to the output load of the power transmitting unit.

7. A method for constructing a dynamic knowledge graph for power grid resource scheduling according to claim 6, characterized in that: The specific method of generating the target power transmission unit set is as follows: Compare the number of path nodes, path transformation index, and number of associated power consumption units of each power transmission unit with the pre-set thresholds for the number of path nodes, path transformation index, and number of associated power consumption units, respectively; The predefined scheduling rules are: The number of path nodes is less than or equal to the path node number threshold; The path voltage change index is less than or equal to the path voltage change index threshold; The number of associated electricity users is less than or equal to the threshold number of associated electricity users; When a power transmission unit satisfies the three conditions in the predefined scheduling rules at the same time, the power transmission unit is identified as a target power transmission unit, and then a target power transmission unit set is constructed.

8. The method for constructing a dynamic knowledge graph for power grid resource scheduling according to claim 6, characterized in that: The specific form of the power dispatch priority list is as follows: According to the number of path nodes, path transformation index and number of associated power consumption units of each target power transmission unit in the target power transmission unit set, the power dispatch feasibility evaluation index of each target power transmission unit is calculated using the power dispatch feasibility evaluation index calculation formula; The power dispatch feasibility evaluation indexes are arranged in descending order to generate an output power dispatch priority list, wherein the power dispatch priority list includes the name of the target power transmission unit, the geographical location and the power dispatch feasibility evaluation index.

9. A method for constructing a dynamic knowledge graph for power grid resource scheduling according to claim 8, characterized in that: The calculation formula for the power dispatch feasibility evaluation index is: Using the formula Calculate the power dispatch feasibility evaluation index of each target power transmission unit , Indicates the number of the target power transmission unit, , represents the number of target power transmission units, where 、 、 Respectively represent the number of path nodes, path transformation index and number of associated power consumption units of each target power transmission unit, The maximum value of the correlation degree of each target power transmission unit and each associated power consumption unit, 、 Respectively represent the preset number of reference path nodes and the number of reference associated electricity units, They represent the impact factors corresponding to the preset number of path nodes, path transformation index, and number of associated power units respectively; The influencing factor corresponding to the number of associated power consuming units in the above formula needs to be adjusted in real time according to the backup power supply configuration of the associated units and the particularity of the associated power consuming units.

Images