Power resource regulation method and system based on power distribution network

Abstract

The application provides a power resource regulation method and system based on a power distribution network, and belongs to the technical field of intelligent regulation. The method comprises the following steps: performing feature alignment processing based on power distribution network hierarchical division data and power distribution network source and load characteristic data, and taking the data after feature alignment as power distribution network operation state data; performing similarity matching processing on the power distribution network operation state data and preset typical power distribution network operation state benchmark data to obtain state matching data; determining a dynamic regulation coefficient based on the state matching data and real-time measurement data of the power distribution network; generating power distribution network power resource optimization regulation instruction data based on the dynamic regulation coefficient, the power distribution network hierarchical division data and the power distribution network operation state data; and optimizing and regulating the power distribution network power resource based on the power distribution network power resource optimization regulation instruction data. The power resource regulation method and system based on the power distribution network can improve the regulation accuracy of the power distribution network power resource.

Description

Technical Field

[0001] This application belongs to the field of intelligent control technology, and more specifically, it relates to a power resource control method and system based on power distribution networks. Background Technology

[0002] With the advancement of new power system construction and the large-scale integration of distributed power sources, distribution networks are gradually transforming from traditional passive networks to active bidirectional interactive systems. This significantly increases the randomness of power sources and loads and the heterogeneity of loads, placing higher demands on the precision and adaptability of power resource regulation. Currently, power resource regulation in distribution networks has become a core technical means to ensure the safe and stable operation of distribution networks and promote the local consumption of distributed power sources.

[0003] Most existing power resource regulation methods for distribution networks employ unified regulation strategies or simple zoned regulation modes, allocating power resources by collecting real-time operational data of the distribution network and combining it with preset regulation rules. However, these existing technologies handle the classification and processing of distributed generation output data and load data in a rather coarse manner, failing to fully exploit source-load characteristics. This makes the regulation strategies unable to adapt to source-load fluctuations, easily leading to problems such as voltage exceeding limits and excessive power loss, which are difficult to meet the needs of high-quality development of distribution networks. Therefore, a power resource regulation method for distribution networks that can improve the accuracy of regulation is needed. Summary of the Invention

[0004] This application provides a power resource regulation method and system based on distribution networks to improve the accuracy of power resource regulation in distribution networks.

[0005] According to one aspect of the embodiments of this application, a power resource regulation method based on a distribution network is provided, comprising: The voltage level data and transformer distribution data in the static ledger data of the distribution network are correlated to obtain distribution network hierarchical correlation data; the distribution network hierarchical correlation data is validated to obtain hierarchical validity validation result data, and based on the hierarchical validity validation result data, the distribution network hierarchical division data is determined; the voltage level data is the voltage standard data of different power supply levels in the distribution network. After classifying and processing the distributed power output data and load data in the real-time measurement data of the distribution network, the distribution network source-load characteristic data are obtained by correlation and fusion. Based on the distribution network hierarchical division data and the distribution network source-load characteristic data, feature alignment processing is performed, and the feature-aligned data is used as the distribution network operation status data. The distribution network operation status data is subjected to similarity matching processing with preset typical distribution network operation status benchmark data to obtain status matching data; based on the status matching data and the real-time measurement data of the distribution network, the dynamic control coefficient is determined; the status matching data is the similarity between the current distribution network operation status data and various typical distribution network operation status benchmark data respectively. Based on the dynamic control coefficient, the distribution network hierarchy data, and the distribution network operation status data, distribution network power resource optimization control instruction data is generated; and based on the distribution network power resource optimization control instruction data, the distribution network power resources are optimized and controlled.

[0006] According to one aspect of the embodiments of this application, a power resource regulation system based on a distribution network is provided, comprising: The distribution network hierarchy division processing module is used to perform correlation processing on voltage level data and transformer area distribution data in the static ledger data of the distribution network to obtain distribution network hierarchy correlation data; to perform validity verification processing on the distribution network hierarchy correlation data to obtain hierarchy validity verification result data; and to determine distribution network hierarchy division data based on the hierarchy validity verification result data; the voltage level data is the voltage standard data of different power supply levels in the distribution network; The distribution network operation status determination module is used to classify and process the distributed power output data and load data in the real-time measurement data of the distribution network, and then correlate and fuse them to obtain the distribution network source-load characteristic data; based on the distribution network hierarchical division data and the distribution network source-load characteristic data, feature alignment processing is performed, and the feature-aligned data is used as the distribution network operation status data. The dynamic control coefficient determination module is used to perform similarity matching processing on the distribution network operation status data and preset typical distribution network operation status benchmark data to obtain status matching data; based on the status matching data and the real-time measurement data of the distribution network, the dynamic control coefficient is determined; the status matching data is the similarity between the current distribution network operation status data and various typical distribution network operation status benchmark data respectively; The control instruction generation module is used to generate power resource optimization control instruction data for the distribution network based on the dynamic control coefficient, the distribution network hierarchy division data, and the distribution network operation status data; and to optimize and control the power resources of the distribution network based on the power resource optimization control instruction data.

[0007] According to one aspect of the embodiments of this application, an electronic device is provided, the electronic device including a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the above-described power resource regulation method based on the power distribution network.

[0008] According to one aspect of the embodiments of this application, the computer program product includes a computer program stored in a computer-readable storage medium. A processor of an electronic device reads the computer program from the computer-readable storage medium and executes the computer program, causing the electronic device to perform the aforementioned power resource regulation method based on a power distribution network.

[0009] The technical solutions provided in this application embodiment may have the following beneficial effects: This application embodiment correlates voltage level data and distribution area data in the static ledger of the distribution network, and then determines the distribution network hierarchy data after validity verification. This clarifies the power grid structure of each region and voltage level, avoiding control errors caused by structural confusion and making control more targeted. Simultaneously, this application embodiment classifies and merges distributed power generation output and load data to form distribution network source-load characteristic data, solving the problem of insufficient source-load characteristic mining. This data is then aligned with the hierarchy data to clearly present the power grid's operating status, allowing control personnel to accurately grasp the current power generation and consumption situation and avoid control decision errors caused by data confusion. Next, this application embodiment determines dynamic control coefficients through scenario matching, allowing control to adapt to real-time changes in power grid operation, overcoming the shortcomings of traditional fixed control methods that are difficult to adapt to real-time operating conditions. Finally, based on the dynamic control coefficients, hierarchy data, and distribution network operating status data, optimized control instructions are generated, realizing on-demand control of power resources. This avoids power resource waste, ensures stable operation of the distribution network, and greatly improves the accuracy and reliability of distribution network control. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart illustrating the power resource regulation method based on a power distribution network provided in this application embodiment; Figure 2 A structural block diagram of a power resource control system based on a power distribution network provided in this application embodiment; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0013] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of systems and methods consistent with some aspects of this application as detailed in the appended claims.

[0014] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0015] Figure 1 This is a flowchart illustrating a power resource regulation method based on a distribution network provided in an embodiment of this application. The method is executed by electronic equipment and may include: S101: Perform correlation processing on voltage level data and transformer distribution data in the static ledger data of the distribution network to obtain distribution network hierarchical correlation data; perform validity verification processing on the distribution network hierarchical correlation data to obtain hierarchical validity verification result data, and determine the distribution network hierarchical division data based on the hierarchical validity verification result data; the voltage level data is the voltage standard data of different power supply levels in the distribution network.

[0016] In this embodiment, the static ledger data of the distribution network is static data that records the basic equipment and structural information of the distribution network. It is archived data of all fixed equipment and basic information in the distribution network, including but not limited to transformer parameters, line parameters, voltage levels, distribution area distribution, user information, etc. It is stored and managed using Excel spreadsheets or SQL databases to facilitate data querying, retrieval, and correlation processing. The voltage level data is the voltage standard data corresponding to different power supply levels in the distribution network, specifically including four common levels: 110kV, 35kV, 10kV, and 0.4kV. Among them, 110kV is the regional backbone network voltage, 35kV is the zoned distribution network voltage, 10kV is the distribution area backbone line voltage, and 0.4kV is the user-side power supply voltage. This voltage level classification conforms to the national distribution network design standards and enables hierarchical management of the distribution network. Distribution area data is the basic data for recording the geographical scope and equipment affiliation of distribution network distribution areas. Specifically, it includes distribution area number, geographical location, number of covered users, associated feeder, and transformer capacity. This data is entered and managed using a Geographic Information System (GIS), which provides a clear visual representation of the spatial distribution and affiliation of distribution areas. Voltage level data and distribution area data in the distribution network static ledger are obtained from the distribution network operation and maintenance management ledger system and equipment archive database, and constitute the basic static data of the distribution network. This static data is characterized by long-term stability and does not change in real-time with changes in the distribution network's operational status. The ledger data is only updated when the distribution network structure is adjusted (such as adding distribution areas, line modifications, or voltage level upgrades).

[0017] The correlation processing is a method of linking voltage level data with transformer distribution data. Distribution network hierarchical correlation data is the data obtained after correlation processing, representing the correspondence between voltage levels and transformer distribution. Validity verification processing is a method of checking whether the hierarchical correlation data conforms to the actual structure of the distribution network. Hierarchical validity verification result data is the compliance result data obtained after verification. Distribution network hierarchical division data is the data that clearly defines the hierarchical structure of the distribution network based on the verification results.

[0018] In this embodiment, static data of the distribution network is first extracted from the distribution network operation and maintenance management ledger system. Voltage level data and transformer distribution data are then selected. Voltage level data is obtained from equipment files such as distribution network lines and transformers, while transformer distribution data is obtained from the distribution network geographic information ledger, ensuring the completeness and accuracy of both types of data. Next, the selected voltage level and transformer distribution data are correlated, linking each transformer distribution data with its corresponding voltage level data to clarify the voltage level to which each transformer belongs, resulting in distribution network hierarchical correlation data. Then, the distribution network hierarchical correlation data undergoes validity verification. By comparing the data with the actual physical structure and equipment affiliation of the distribution network, the correspondence between voltage levels and transformer distribution is checked for rationality, data conflicts, or errors, yielding hierarchical validity verification results. Finally, based on the hierarchical validity verification results, valid hierarchical correlation data is retained, invalid data is removed, and data is supplemented and improved, ultimately determining the distribution network hierarchical division data, providing an accurate hierarchical basis for subsequent hierarchical control.

[0019] For example, the validity verification process combines data integrity verification and rationality verification. Integrity verification checks for null values ​​or missing fields in the associated data, such as missing voltage levels or missing transformer area information; if found, the data is marked as invalid. Rationality verification checks whether the voltage level matches the feeder affiliation of the transformer area; for example, a transformer area corresponding to a low-voltage level cannot be assigned to a high-voltage feeder; if they do not match, the data is marked as invalid. After verification, the system outputs the hierarchy validity verification result data, which includes both valid and invalid data. Based on the hierarchy validity verification result data, the distribution network hierarchy division data is determined. Specifically, invalid data in the verification results is removed, and the valid associated data is divided into levels according to voltage levels. Each level corresponds to a clearly defined transformer area range and equipment affiliation, ultimately determining the distribution network hierarchy division data and providing an accurate basis for subsequent hierarchical control.

[0020] This embodiment clarifies the correspondence between voltage level data and transformer distribution data by correlating voltage level data and transformer distribution data, providing a clear basis for hierarchical division. Validity verification eliminates invalid data, improving the reliability of the hierarchical division data. The final distribution network hierarchical division data provides a clear hierarchical basis for determining subsequent operation scenarios and regulating power resources, reducing regulation errors caused by hierarchical confusion, improving the targeting and efficiency of distribution network regulation, and ensuring the stable operation of the distribution network.

[0021] In this embodiment, voltage level data and transformer distribution data in the static ledger data of the distribution network are correlated to obtain distribution network hierarchical correlation data, including: The voltage level data is classified according to the power supply level, and the classified voltage level data is used as the voltage level data. Extract the feeder affiliation information corresponding to the transformer area from the transformer area distribution data to obtain transformer area topology affiliation data; Based on voltage level data and transformer area topology attribution data, correlation matching processing is performed to obtain distribution network level correlation data.

[0022] In this embodiment, the categorized voltage level data refers to the voltage level data organized and classified according to power supply hierarchy rules. Voltage hierarchy data refers to the hierarchy information corresponding to the categorized voltage level data; for example, 10kV corresponds to the low-voltage hierarchy, and 110kV corresponds to the high-voltage hierarchy. Distribution area feeder affiliation information refers to the information of the power supply feeders to which the distribution area belongs, used to clarify the spatial relationship between the distribution area and the feeders. Distribution area topology affiliation data is structured data formed after extracting feeder affiliation information, which can be directly used for association matching. Association matching processing is the operation of establishing the correspondence between voltage hierarchy data and distribution area topology affiliation data. Distribution network hierarchy association data is the final data formed after association matching, completely reflecting the correspondence between the distribution area and the power supply hierarchy.

[0023] In this embodiment, static ledger data of the distribution network is acquired. This data is regularly maintained and updated by the distribution network operation and maintenance department and includes voltage level data and transformer distribution data. The data is processed to ensure a standardized data structure. Secondly, the voltage level data is classified according to the power supply level. Based on the voltage standards of the distribution network industry, the voltage level data is categorized and organized according to high voltage, medium voltage, and low voltage levels, retaining a unique level corresponding to each voltage type. This results in classified voltage level data, which serves as voltage level data. For example, 110kV and 35kV voltage data are classified as high voltage, and 10kV voltage data as medium voltage.

[0024] This embodiment filters the feeder affiliation information corresponding to each transformer substation from the transformer substation distribution data. This information is stored in the association field of the transformer substation distribution data, and after extraction, the transformer substation topology affiliation data is obtained. Next, association matching processing is performed. Based on the voltage level data, the feeder affiliation information corresponding to each transformer substation in the transformer substation topology affiliation data is matched one by one with the voltage level data to clarify the power supply voltage level to which each transformer substation belongs and establish a unique correspondence. Finally, the distribution network level association data is obtained. This data completely records the core information such as transformer substation number, feeder affiliation, and corresponding voltage level, and can be directly used for data processing related to distribution network level division and subsequent control.

[0025] This embodiment achieves precise correlation between voltage levels and transformer distribution areas through step-by-step processing, clearly defining the hierarchical structure of the distribution network and resolving the problem of chaotic hierarchical division in traditional methods. Hierarchical classification and feeder attribution extraction ensure data clarity, while correlation matching processing guarantees the accuracy of hierarchical correlation.

[0026] In this embodiment, correlation matching processing is performed based on voltage level data and transformer area topology attribution data to obtain distribution network level correlation data, including: The voltage level data is deduplicated to obtain the deduplicated voltage level data. Missing values ​​were imputed in the topology attribution data of the transformer area to obtain the imputed topology attribution data of the transformer area. Based on the distribution network hierarchical association specifications, determine the association matching rule data; Preliminary association matching processing is performed based on the association matching rule data, the deduplicated voltage level data, and the data to fill the background area topology attribution data to obtain preliminary hierarchical association data. Perform correlation verification on the preliminary hierarchical correlation data to obtain qualified preliminary hierarchical correlation data; The qualified preliminary hierarchical correlation data is standardized and processed to obtain the distribution network hierarchical correlation data.

[0027] In this embodiment, the voltage level data is traversed one by one, duplicate information is filtered out and deleted, and only unique and valid data is retained to obtain deduplicated voltage level data. Simultaneously, the missing information in the transformer substation topology attribution data is filled using the mean value, combined with the topology attribution patterns of substations in the same region and of the same type, to obtain supplementary background area topology attribution data. Then, industry standards and historical correlation data for distribution network hierarchy are consulted, and the correlation matching rules are determined based on the actual operating architecture of the distribution network, clarifying the correspondence and correlation priority between the two types of data. Next, based on the correlation matching rules, the deduplicated voltage level data is matched one-to-one with the supplementary background area topology attribution data, and the correlation relationship is recorded to obtain preliminary hierarchy correlation data. Afterwards, the correlation of the preliminary hierarchy correlation data is verified to check whether the correspondence logic between voltage level and transformer substation topology attribution is reasonable and whether the correlation is accurate, removing data with incorrect correlation to obtain qualified preliminary hierarchy correlation data. Finally, the qualified preliminary hierarchy correlation data is formatted and fields are standardized, and the data storage format and correlation field naming are unified to obtain distribution network hierarchy correlation data.

[0028] S102: After classifying and processing the distributed power output data and load data in the real-time measurement data of the distribution network, the distribution network source and load characteristic data are obtained by correlation and fusion; feature alignment processing is performed based on the distribution network hierarchical division data and the distribution network source and load characteristic data, and the feature-aligned data is used as the distribution network operation status data.

[0029] In this embodiment, the real-time measurement data of the distribution network refers to the data collected in real time by the online monitoring equipment of the distribution network, reflecting the real-time operating status of the distribution network. Distributed power generation output data refers to the real-time data of the power output during the operation of distributed power sources, such as the real-time output data of photovoltaic power sources. Load data refers to the real-time data of the power consumption of various electrical devices in the distribution network, such as residential electricity load data. Classification processing involves dividing and organizing the distributed power generation output data and load data according to their respective characteristics. Association and fusion processing involves integrating the two types of data after classification processing to form a unified dataset. Distribution network source-load characteristic data is the comprehensive data representing the power output and load status of the distribution network obtained after association and fusion processing. Feature alignment processing involves adjusting the distribution network source-load characteristic data and the distribution network hierarchical classification data to the same data dimension to achieve corresponding matching. Distribution network operating status data is the comprehensive data representing the real-time operating status of the distribution network obtained after feature alignment.

[0030] For example, this embodiment first acquires real-time measurement data of the distribution network. This data is collected in real time by online monitoring terminals at various monitoring nodes of the distribution network. The acquisition frequency can be set to once every 15 minutes according to the control requirements. From this data, distributed power generation output data and load data are selected. The distributed power generation output data comes from dedicated monitoring equipment for distributed power sources such as photovoltaic and wind power, which collects core parameters such as power output and current in real time. The load data comes from power consumption monitoring terminals on the transformer substation and user side, which collects data such as power consumption and power consumption duration of various electrical devices in real time. After collection, preliminary noise reduction processing is performed to ensure that both types of data are real-time, accurate, and complete. Next, the selected two types of data are classified and processed. The distributed power generation output data is organized separately according to power source type, and the load data is organized separately according to power consumption scenario, achieving a clear division between the two types of data. Then, the two types of data after classification and processing are correlated and fused. Using the time dimension as the correlation benchmark, the distributed power generation output data and load data within the same time period are integrated to supplement the data correlation and ensure accurate data correspondence, thus obtaining the source-load characteristic data of the distribution network. Finally, the established distribution network hierarchy data is called, and the dimensions and format of the distribution network source and load characteristic data are adjusted to be consistent with the distribution network hierarchy data, eliminating data dimension differences, completing feature alignment processing, and using the feature-aligned data as the distribution network operation status data.

[0031] In this embodiment, after classifying and processing the distributed generation output data and load data in the real-time measurement data of the distribution network, the data are correlated and fused to obtain the source-load characteristic data of the distribution network, including: The output data of distributed power sources is processed by output threshold classification to obtain the output level corresponding to the output data of distributed power sources, and the output level is used as the power output level data. Determine the priority of the load data; Based on the power output level data and the priority of the load data, the source and load characteristic data of the distribution network are obtained by correlation and fusion processing.

[0032] In this embodiment, the output threshold grading process is a method of classifying distributed generation output data into levels according to a preset output threshold range. For example, distributed generation output data can be divided into three levels: low, medium, and high, based on threshold ranges of 0-30%, 30%-70%, and 70%-100%. The power generation level data is the level information obtained after the distributed generation output data has undergone output threshold grading. The load data priority is the urgency level determined after priority classification of the load data. The correlation and fusion process is a method of integrating the two types of data to form a unified dataset. The distribution network source-load characteristic data is the comprehensive data obtained after correlation and fusion processing, comprehensively representing the power generation level and load priority of the distribution network.

[0033] In this embodiment, the output data of distributed power sources is processed by output threshold classification. Different output threshold ranges are preset, and the output data of each distributed power source is compared with the preset threshold one by one. The corresponding output level is determined according to the comparison result, and this output level is used as the power source output level data. Then, the load data is classified by priority. Combined with the power consumption specifications of the distribution network, different priorities are divided according to the urgency of power consumption to obtain the priority of the load data. Finally, the two types of data are correlated and fused. Using the time dimension and the power grid area as the correlation benchmark, the two types of data in the same time period and the same area are integrated, and the data correlation is verified to ensure logical consistency and accurate matching, so as to obtain the source and load characteristic data of the distribution network.

[0034] For example, for a photovoltaic distributed power source with a rated output of 100kW, three output threshold ranges are preset: 0-30kW, 30-70kW, and 70-100kW, corresponding to low, medium, and high output levels. When the real-time photovoltaic output data is 25kW, after threshold comparison, the data falls within the 0-30kW range, and its output level is determined to be low. The corresponding power source output level data is the low output level. When the real-time output data is 60kW, it falls within the 30-70kW range, and its output level is determined to be medium. And so on, to complete the output threshold classification processing of all distributed power source output data.

[0035] For example, this embodiment divides load data into three priority categories—high priority, medium priority, and low priority—based on the power demand of the distribution network and the urgency of the power consumption scenario. The classification criteria are aligned with actual power consumption scenarios. For instance, high priority corresponds to core power consumption scenarios, such as hospitals, nursing homes, and other essential public services loads. These loads require priority power supply to avoid impacting people's livelihoods due to power outages. Medium priority corresponds to ordinary residential power consumption and general commercial power consumption loads, where power demand is stable and there are no urgent requirements. Low priority corresponds to seasonal and non-essential power consumption loads, such as some temporary commercial power consumption loads.

[0036] The correlation and fusion processing involves prioritizing power output level data and load data, using the time and regional dimensions of distribution network operation as correlation benchmarks. Through standardized data correlation, it achieves precise correspondence and integration of the two types of data, ultimately forming comprehensive distribution network source-load characteristic data that characterizes the source-load matching status of the distribution network. The specific process of correlation and fusion processing can be as follows: First, this embodiment organizes the priority of power output level data and load data, and determines the correlation benchmark as the same time segment and the same distribution network area. This ensures that the two types of data correspond to the same power grid operating conditions, avoids data confusion across time and regions, and provides a unified benchmark for correlation and fusion. The time segment can be set according to the distribution network control requirements, for example, every 15 minutes; the distribution network area is based on the transformer substation, ensuring that the data corresponds to a specific power grid area.

[0037] Secondly, this embodiment uses data comparison to match the power output level data of the same time segment and the same distribution network area with the priority of the load data one by one, verify the correlation between the two types of data, and eliminate data with abnormal correlation (such as cases where there is no corresponding power output data or load data in a certain area), so as to ensure that each set of correlated data corresponds to the same operating condition and the same area, and ensure the accuracy of data correlation.

[0038] Then, this embodiment integrates the correlated data that has passed the comparison. During the integration, the core information of the two types of data is retained, including the power output level and the priority of the load data. At the same time, the corresponding time segment and distribution network area information are added to form a structured dataset to ensure that the data is complete and standardized, which is convenient for subsequent feature alignment processing.

[0039] Finally, this embodiment performs a consistency check on the integrated dataset to confirm that the association logic between the two types of data is unbiased, the data is complete, and the correspondence is accurate. After the check passes, the structured dataset becomes the power distribution network source-load characteristic data. This embodiment uses association fusion processing to compare the two types of data from the same time and the same transformer area. After verification, the dataset is integrated, and the information for that time segment and transformer area is supplemented to form a structured dataset containing time, transformer area, power output level, and load priority. This dataset is the power distribution network source-load characteristic data for that transformer area under that operating condition.

[0040] This embodiment standardizes source-load data by hierarchically and classifying distributed power generation output data and load data, avoiding data chaos and improving data identifiability and correlation. The correlation and fusion processing integrates the core characteristics of power sources and loads, forming comprehensive and accurate source-load characteristic data for the distribution network. Feature alignment processing ensures precise matching between source-load characteristic data and distribution network hierarchical classification data, guaranteeing that the distribution network operating status data accurately reflects the real-time operating status of the power grid.

[0041] S103: Perform similarity matching processing on the distribution network operation status data and the preset typical distribution network operation status benchmark data to obtain status matching data; determine the dynamic control coefficient based on the status matching data and the real-time measurement data of the distribution network; the status matching data is the similarity between the current distribution network operation status data and the various typical distribution network operation status benchmark data respectively.

[0042] In this embodiment, the preset typical distribution network operating status benchmark data are pre-defined standard reference data covering various common operating conditions of the distribution network. For example, these could be standard data corresponding to typical operating conditions such as high load and high output, low load and low output, and normal load and normal output. The similarity matching process compares the distribution network operating status data with the typical distribution network operating status benchmark data to calculate the degree of similarity. The status matching data is the similarity value between the current distribution network operating status data and various typical distribution network operating status benchmark data, such as 0.8, 0.6, etc., with higher values ​​indicating higher similarity. The dynamic control coefficient is a control benchmark parameter determined based on the status matching data and real-time distribution network measurement data, used to adapt to the current power grid operating status.

[0043] In this example, preset benchmark data for typical distribution network operation status is obtained. This data, based on historical distribution network operation data, industry design standards, and common operating conditions, is pre-organized, set, and stored in a data management system, covering typical operating conditions with high, medium, and low loads and output combinations. Next, this embodiment calls the determined distribution network operation status data and real-time distribution network measurement data. Then, similarity matching processing is performed between the distribution network operation status data and the preset benchmark data. The core feature parameters of the two types of data are compared one by one, and the cosine similarity is used to calculate the similarity of each set of data, obtaining the corresponding similarity value, which is the state matching data. Then, based on the state matching data and real-time distribution network measurement data, combined with preset coefficient adjustment rules, the initial control parameters are dynamically adjusted. The focus is on referencing the benchmark coefficient corresponding to the typical operating condition with the highest similarity in the state matching data, and calibrating the adjustment coefficient values ​​based on the fluctuations in real-time measurement data, for example, calibrating the coefficients based on real-time source load fluctuation data. Finally, after completing the coefficient calibration, the final dynamic control coefficient is output, ensuring that the coefficient accurately adapts to the current distribution network operation status.

[0044] In this embodiment, the dynamic control coefficient is determined based on state matching data and real-time measurement data of the distribution network, including: The benchmark control coefficient corresponding to the benchmark data of the typical distribution network operation status with the highest similarity is called, and the benchmark control coefficient is determined as the initial control coefficient. Extract real-time source-load fluctuation data from real-time measurement data of the power distribution network; The fluctuation amplitude is calculated and processed from the real-time fluctuation data of the source load to obtain the fluctuation amplitude data; Calculate the deviation of the initial control coefficient relative to the fluctuation amplitude data, and use it as the initial control coefficient deviation; The initial control coefficient deviation is calibrated and corrected to obtain calibration correction data; Based on the calibration correction data, the initial control coefficient is calibrated and corrected to obtain the dynamic control coefficient.

[0045] In this embodiment, the initial control coefficient is calibrated and corrected based on the calibration correction data to obtain the dynamic control coefficient, including: Determine the weights corresponding to the calibration correction data; The calibration correction data is weighted based on the weights to obtain the corrected calibration correction data. The corrected calibration correction data is then added to the initial control coefficient to obtain the weighted calibration coefficient. The weighted calibration coefficients are subjected to threshold compliance verification to obtain qualified weighted calibration coefficients, which are then used as dynamic control coefficients.

[0046] In this embodiment, the baseline control coefficient is a pre-set control baseline parameter that corresponds one-to-one with the baseline data of various typical distribution network operating states. For example, it can be the baseline control coefficient corresponding to high load and high output conditions. The initial control coefficient is the baseline control coefficient called based on the baseline data of the typical operating conditions corresponding to the highest similarity. The source-load real-time fluctuation data is a parameter extracted from the real-time measurement data of the distribution network, reflecting the real-time changes in power output and load. The fluctuation amplitude calculation processing is a processing method for calculating the magnitude of changes in the source-load real-time fluctuation data. The fluctuation amplitude data is the specific value of the source-load real-time fluctuation. The initial control coefficient deviation data is the difference between the initial control coefficient and the fluctuation amplitude data. The calibration correction processing is a processing method for adjusting the deviation data to meet the control requirements. The calibration correction data is the deviation adjustment data obtained after calibration correction. The calibration correction weight data is a weight parameter assigned to the calibration correction data to measure the degree of correction. The weighted calibration coefficient is the coefficient obtained by adding the corrected calibration correction data to the initial control coefficient. The threshold compliance verification processing is a processing method for checking whether the weighted calibration coefficient meets the preset threshold range. The weighted calibration coefficient that passes the verification is the coefficient that passes the threshold compliance verification.

[0047] In this embodiment, a preset benchmark control coefficient is established based on benchmark data of various typical distribution network operating states, combined with distribution network control experience and industry standards. This ensures a one-to-one correspondence between the two and is stored in the data management system for easy retrieval. Next, state matching data and real-time distribution network measurement data are retrieved to find the typical distribution network operating state benchmark data with the highest similarity in the state matching data. The corresponding benchmark control coefficient is then retrieved through data retrieval and determined as the initial control coefficient. Then, real-time source-load fluctuation data is extracted from the distribution network real-time measurement data. This data is calculated from power output and load data collected in real-time by online monitoring terminals. Fluctuation-related parameters are filtered. Specifically, the real-time measurement data of the distribution network is processed by time-series filtering, retaining power output and load data from multiple consecutive acquisition times. The power output data at adjacent acquisition times is calculated by difference (i.e., power output data at the later time minus power output data at the previous time) to obtain power output change data. Similarly, the load data at adjacent acquisition times is calculated by difference (i.e., load data at the later time minus load data at the previous time) to obtain load change data. The power output change data and load change data are normalized to obtain real-time source-load fluctuation data. Then, the fluctuation amplitude of the real-time source-load fluctuation data is calculated using a difference calculation method to determine the difference in source-load data at different times, thus obtaining the fluctuation amplitude data. Specifically, this involves selecting real-time source-load fluctuation data corresponding to multiple consecutive acquisition times, subtracting the previous time's real-time source-load fluctuation data from the subsequent time's data at the same monitoring location, and obtaining the time-series variation difference data. The absolute value of the time-series variation difference data is then processed to eliminate the numerical influence of positive and negative change directions. This absolute value-processed time-series variation difference data is used as the fluctuation amplitude data to characterize the severity of real-time source-load fluctuations. The difference between the initial control coefficient and the fluctuation amplitude data is calculated as the initial control coefficient deviation data. Next, the initial control coefficient deviation data is calibrated and corrected. Correction rules are set based on control requirements to obtain calibrated and corrected data. Correction weights are assigned to this calibrated and corrected data based on the degree of fluctuation impact, resulting in calibrated and corrected weighted data. A weighted summation method is used to calculate the weighted calibrated and corrected data, and the result is added to the initial control coefficient to obtain the weighted calibration coefficient. Finally, the weighted calibration coefficient undergoes threshold compliance verification. A reasonable coefficient threshold range is preset, and threshold comparison is used to check whether the data is compliant. The weighted calibration coefficients that pass the verification are determined as the dynamic control coefficients.

[0048] In this embodiment, the baseline control coefficient corresponds one-to-one with typical operating conditions, enabling rapid determination of the initial control direction and improving the efficiency of determining the dynamic control coefficient. By combining real-time source-load fluctuation data for deviation calculation and calibration correction, the control coefficient can adapt to real-time changes in grid operation, solving the problem of insufficient adaptability of fixed coefficients. Weight allocation and threshold compliance verification ensure the rationality of calibration correction and the safety of the coefficients, avoiding control errors.

[0049] For example, the preset benchmark control coefficient can be combined with historical operating data of the distribution network and industry control standards. For each type of preset typical distribution network operating state benchmark data, a corresponding benchmark control coefficient is set one by one to ensure a one-to-one correspondence. The set benchmark control coefficients are stored in the distribution network data management system for easy retrieval later. Next, the previously obtained state matching data and real-time measurement data of the distribution network are retrieved. Through data retrieval, the highest similarity value (i.e., the highest similarity) is found in the state matching data. The typical distribution network operating state benchmark data corresponding to this highest similarity value is determined. Then, the benchmark control coefficient corresponding to this typical distribution network operating state benchmark data is retrieved from the data management system and directly determined as the initial control coefficient, serving as the basis for subsequent calibration. Next, real-time source-load fluctuation data is extracted from the real-time measurement data of the distribution network. Real-time change parameters of distributed power generation output data and load data (such as the output difference and load difference between two adjacent acquisition times) are filtered out to obtain the real-time source-load fluctuation data. Then, the fluctuation amplitude of the real-time source-load fluctuation data is calculated. The absolute difference between the source-load data at adjacent acquisition times is calculated, accumulated, and averaged to obtain the fluctuation amplitude data. The fluctuation amplitude data is then subtracted from the initial control coefficient to calculate the difference, which is used as the initial control coefficient deviation data. Next, the initial control coefficient deviation data is calibrated and corrected. Based on the distribution network control requirements and preset correction rules (e.g., reducing deviation when positive, supplementing deviation when negative), the initial control coefficient deviation data is adjusted to obtain calibrated and corrected data. Correction weights are assigned to the calibrated and corrected data, setting weights according to the degree of influence of source-load fluctuations on grid operation (e.g., higher weight for larger fluctuations, lower weight for smaller fluctuations). The calibrated and corrected weight data is obtained by multiplying the calibrated and corrected data by the corresponding weights using a weighted summation method to obtain the corrected calibrated and corrected data. This corrected data is then added to the initial control coefficient to obtain the weighted calibration coefficient. Finally, the weighted calibration coefficients are subjected to threshold compliance verification. The allowable coefficient threshold range for distribution network control is preset (e.g., 0.5-1.2). The weighted calibration coefficients are compared with the preset threshold range one by one. Data that exceeds the threshold range is removed and recalibrated. Data that meets the threshold requirements is retained. The weighted calibration coefficient that passes the verification is determined as the dynamic control coefficient.

[0050] For example, the correction rule for calibration correction processing can be: the preset fluctuation threshold is 5%. If the fluctuation amplitude data is ≤5%, then the calibration correction data = initial control coefficient deviation data × preset basic correction coefficient, and the preset basic correction coefficient is 0.9; if the fluctuation amplitude data is >5%, then the calibration correction data = initial control coefficient deviation data × preset reinforcement correction coefficient, and the preset reinforcement correction coefficient is 1.1; wherein the preset basic correction coefficient and the preset reinforcement correction coefficient are both fixed coefficients between 0.8 and 1.2 determined based on historical control data. In practical applications, other values ​​can also be selected for these coefficients, and this application embodiment does not limit this.

[0051] For example, the calibration correction data is the data obtained after calibrating and correcting the initial control coefficient deviation data. The specific implementation of the correction weight allocation process can be as follows: the correction weight is allocated according to the magnitude of the fluctuation amplitude data. The allocation rule can be: when the fluctuation amplitude data is ≤5%, the correction weight is 0.3; when 5% < fluctuation amplitude data ≤10%, the correction weight is 0.5; when the fluctuation amplitude data >10%, the correction weight is 0.7. The value range of the correction weight is 0.3-0.7. The larger the fluctuation amplitude, the larger the correction weight, which means that the calibration correction data has a greater impact on the dynamic control coefficient. This weight allocation rule is determined based on historical control data and can accurately reflect the correlation between source load fluctuation and correction data. In practical applications, other values ​​can also be selected for this weight. This application embodiment does not limit this.

[0052] For example, the threshold compliance verification process can be implemented by setting the compliance threshold range of the dynamic adjustment coefficient to 0.8-1.2, comparing the weighted calibration coefficient with this threshold range, and if the weighted calibration coefficient is between 0.8 and 1.2, it is determined to be qualified and the data is directly output as the qualified weighted calibration coefficient; if the weighted calibration coefficient is greater than 1.2, then 1.2 is taken as the qualified data; if the weighted calibration coefficient is less than 0.8, then 0.8 is taken as the qualified data.

[0053] This embodiment performs similarity matching processing on distribution network operating status data and preset typical distribution network operating status benchmark data to obtain status matching data. This accurately locates the current operating condition of the distribution network, providing a reliable basis for determining the initial control coefficients. Based on the status matching data, the corresponding benchmark control coefficients are called as the initial control coefficients, ensuring that the initial coefficients fit the current operating scenario. Real-time source-load fluctuation data is extracted from the distribution network's real-time measurement data and processed accordingly to achieve accurate calibration and correction of the initial control coefficients. By assigning correction weights to the calibration and correction data, performing weighted calculations, and verifying threshold compliance, the rationality and compliance of the dynamic control coefficients are ensured, effectively improving the accuracy and adaptability of the dynamic control coefficients and avoiding control errors.

[0054] In this embodiment, the weighted calibration coefficients undergo threshold compliance verification to obtain qualified weighted calibration coefficients, including: Outlier removal is performed on the weighted calibration coefficients to obtain the outlier-free weighted calibration coefficients. Based on the safety specifications for distribution network control, determine the compliance threshold range data for dynamic control coefficients; Based on the dynamic adjustment coefficient compliance threshold range data, the data is divided into graded threshold intervals; The weighted calibration coefficients after anomaly removal are compared with the data in the graded threshold interval to obtain the threshold comparison result data. Based on the threshold comparison results, it is determined whether the weighted calibration coefficient after anomaly removal is within the compliance range, thus obtaining the compliance judgment results data; For compliance judgment results, the weighted calibration coefficients after anomaly removal are retained to obtain preliminary qualified weighted calibration coefficients. For compliance judgment results that are non-compliant, the weighted calibration coefficients after anomaly removal are corrected based on the graded threshold range data to obtain the corrected weighted calibration coefficients. The corrected weighted calibration coefficients are subjected to threshold comparison again to obtain the secondary comparison result data; Based on the secondary comparison results, the corrected weighted calibration coefficients that passed the comparison were retained to obtain the supplementary qualified weighted calibration coefficients. The preliminary qualified weighted calibration coefficients and the supplementary qualified weighted calibration coefficients are integrated to obtain the qualified weighted calibration coefficients.

[0055] In this embodiment, weighted calibration coefficients are obtained. This data comes from intermediate data after previous weighted calculation and processing. After collection, it is imported into the data processing system. The 3σ principle is used to remove outliers from the weighted calibration coefficients. The mean and standard deviation of the data are calculated, and values ​​exceeding the mean ± 3 times the standard deviation are identified as outliers and removed, resulting in the de-outliered weighted calibration coefficients. Next, based on the distribution network control safety specifications and historical control data, the compliance threshold range of the dynamic control coefficients is determined, with a value range of 0.8-1.2. This range is then divided into low, medium, and high-level threshold intervals: 0.8-0.9, 0.9-1.1, and 1.1-1.2, and stored in the system. Then, the de-outliered weighted calibration coefficients are compared with the level threshold interval data one by one, and the comparison result of each set of data is recorded to obtain the threshold comparison result data. Finally, based on the threshold comparison result data, it is determined whether the de-outliered weighted calibration coefficients are within the corresponding level threshold interval, resulting in the compliance judgment result data. Data deemed compliant based on the compliance assessment results is retained to obtain preliminary qualified weighted calibration coefficients. For non-compliant data, adjustments are made based on the upper or lower limits of the corresponding tiered threshold range to obtain corrected weighted calibration coefficients. These corrected weighted calibration coefficients are then subjected to a second threshold comparison to obtain secondary comparison results. Data passing the second comparison is retained to obtain supplementary qualified weighted calibration coefficients. Finally, the preliminary and supplementary qualified weighted calibration coefficients are merged, and duplicate data is removed to obtain the final verified weighted calibration coefficients.

[0056] S104: Based on dynamic control coefficients, distribution network hierarchy data, and distribution network operation status data, generate distribution network power resource optimization control instruction data; and based on the distribution network power resource optimization control instruction data, optimize and control the distribution network power resources.

[0057] In this embodiment, the power resource optimization and control instruction data for the distribution network is standardized instruction information generated based on dynamic control coefficients, distribution network hierarchical division data, and distribution network operating status data. This information guides the optimization and control of power resources in the distribution network. For example, it can be a control instruction to adjust the power output allocation in a certain area. Optimization and control involves adjusting and optimizing the operating status of power resources in the distribution network based on the power resource optimization and control instruction data, thereby achieving a rational allocation of power resources.

[0058] In this embodiment, based on dynamic control coefficients, distribution network hierarchy data, and distribution network operation status data, distribution network power resource optimization control instruction data is generated, including: Based on the distribution network hierarchy data, the distribution network operation status data is split into layers to obtain layered power operation data, which includes: main control layer operation data, distribution area control layer operation data, and user-side control layer operation data. Based on the dynamic control coefficient, a hierarchical coefficient allocation process is performed to obtain the hierarchical control coefficient, which includes: the main control layer sub-coefficient, the transformer area control layer coefficient, and the user side control layer coefficient. Based on the main control layer sub-coefficients, the main control layer operation data is processed to obtain the main control layer optimized operation data. Based on the sub-coefficients of the control layer of the transformer area, the operation data of the control layer of the transformer area is processed to obtain the optimized operation data of the transformer area. Based on the sub-coefficients of the user-side control layer, the user-side control layer operation data is controlled and processed to obtain optimized user-side operation data. The optimized operation data of the main layer, the optimized operation data of the distribution area, and the optimized operation data of the user side are fused and verified to obtain fused optimized data. The fused and optimized data is then processed through standardized mapping of control commands to obtain power resource optimization control command data for the distribution network.

[0059] In this embodiment, the main layer optimized operation data, the station area optimized operation data, and the user-side optimized operation data are fused and verified to obtain fused optimized data, including: The main layer optimization operation data is validated to obtain valid main layer data. The validity of the optimized operation data of the transformer area is verified to obtain the valid data of the transformer area. The user-side optimized operation data is validated to obtain valid user-side data. Delete conflicting data from the main layer valid data and the transformer area valid data to obtain conflict resolution data; The conflict resolution data is collaboratively corrected to obtain collaboratively corrected data. The collaboratively corrected data and the valid data from the user side are fused together to obtain fused and optimized data.

[0060] In this embodiment, the power resource optimization and control instruction data for the distribution network refers to instruction information used to guide the optimization and control of power resources in the distribution network. The hierarchical splitting process involves dividing the data according to the distribution network hierarchy, splitting the distribution network operation status data hierarchically. The hierarchical power operation data consists of the operation status data for each level obtained after the hierarchical splitting process; for example, it could be the operation status data corresponding to the 110kV main control layer. The hierarchical coefficient allocation process involves allocating dynamic control coefficients to corresponding sub-coefficients according to the needs of each level. The hierarchical control coefficients are the sub-coefficients for each level obtained after the hierarchical coefficient allocation process. The fusion verification process involves verifying and fusion the optimized operation data for each level. The fused optimized data is the unified optimized data obtained after the fusion verification process. The standardized mapping process for control instructions involves converting the fused optimized data into standardized control instructions.

[0061] In this embodiment, firstly, dynamic control coefficients, distribution network hierarchy data, and distribution network operation status data are acquired. Secondly, based on the distribution network hierarchy data, the distribution network operation status data is split into layers: main control layer, distribution area control layer, and user-side control layer, resulting in corresponding layered power operation data. Next, based on the control requirements of each layer, the dynamic control coefficients are allocated in layers, and corresponding sub-coefficients are assigned based on the load characteristics of each layer to obtain the layered control coefficients.

[0062] Then, in this embodiment, the corresponding layered power operation data are regulated and processed using sub-coefficients at each level to adjust the operating parameters at each level, resulting in optimized operation data for the main layer, optimized operation data for distribution areas, and optimized operation data for the user side. Next, the three types of data undergo fusion verification, with validity checks performed on each type of data. Conflicts between the main layer and the valid data for distribution areas are identified, conflicting data is deleted and collaboratively corrected, and then the corrected data is fused with the valid data for the user side to obtain fused optimized data. Finally, the fused optimized data is converted into an instruction format conforming to the distribution network control specifications to obtain distribution network power resource optimization control instruction data. Based on this instruction data, the power resources of the distribution network are optimized and controlled.

[0063] The tiered control coefficients are the set of control coefficients corresponding to each control level after tiered coefficient allocation processing. The main control layer sub-coefficients are the exclusive control coefficients corresponding to the main control layer within the tiered control coefficients. The main control layer operating data is the operating status data corresponding to the main control layer, and the optimized operating data is the optimized operating data obtained after processing the main control layer operating data. The transformer area control layer sub-coefficients are the exclusive control coefficients corresponding to the transformer area control layer within the tiered control coefficients. The transformer area control layer operating data is the operating status data corresponding to the transformer area control layer, and the optimized operating data is the optimized operating data obtained after processing the transformer area control layer operating data. The user-side control layer sub-coefficients are the exclusive control coefficients corresponding to the user-side control layer within the tiered control coefficients. The user-side control layer operating data is the operating status data corresponding to the user-side control layer, and the optimized operating data is the optimized operating data obtained after processing the user-side control layer operating data.

[0064] The fusion verification process integrates optimized operational data from various levels, verifies data consistency and rationality, and eliminates abnormal data. The fused optimized data is a unified and compliant set of optimized operational data from various levels, obtained after the fusion verification process. The validity verification process checks whether the optimized operational data at each level conforms to the distribution network operation specifications and whether there are any abnormal handling methods. Main-level valid data is compliant data obtained after validity verification of the main-level optimized operational data; transformer area valid data is compliant data obtained after validity verification of the transformer area optimized operational data; and user-side valid data is compliant data obtained after validity verification of the user-side optimized operational data.

[0065] For example, the control processing of the main control layer's operational data uses the main control layer sub-coefficients in the hierarchical control coefficients as the core control basis. The main control layer's operational data mainly covers core operational parameters such as the power of the main distribution network lines, the load rate of the main transformers, and the voltage amplitude of the main grid. During the control process, the main control layer sub-coefficients and the core parameters in the main control layer's operational data are calculated collaboratively. Based on the calculation results, the power distribution of the main grid lines, the operating load of the main transformers, and the voltage amplitude of the main grid are adjusted to maintain the various parameters in the main control layer's operational data within the preset optimization range. This ensures the stable and efficient operation of the main control layer's power resources, ultimately yielding optimized operational data for the main control layer. For instance, when the main control layer sub-coefficient is 1.05, the upper limit of the main grid line power transmission is appropriately increased, and the load rate of the main transformers is adjusted to a reasonable range, so that the operating status of the main control layer meets the overall optimization requirements.

[0066] For example, the control and processing of distribution area control layer operational data is based on the distribution area control layer sub-coefficients in the hierarchical control coefficient system. The distribution area control layer operational data mainly includes distribution area feeder power, distribution area transformer operating parameters, and distribution area voltage quality parameters. During control, the power distribution ratio of the distribution area feeders is adjusted based on the distribution area control layer sub-coefficients, the operating level of the distribution area transformers is optimized, and the voltage at each node in the distribution area is calibrated. This addresses issues such as uneven power distribution and excessive voltage fluctuations within the distribution area, ensuring that the distribution area control layer operational data conforms to the optimization standards of that level, thereby obtaining optimized distribution area operational data. During the control process, the power demand of various loads within the distribution area is simultaneously considered to ensure reasonable allocation of power resources and stable operation after control.

[0067] For example, the regulation and processing of user-side control layer operational data is based on the user-side control layer sub-coefficients in the hierarchical control coefficients. User-side control layer operational data mainly includes parameters such as user-side power consumption, user-side voltage, and power load distribution. By combining the user-side control layer sub-coefficients, the timing of user-side power load distribution is adjusted, the peak power consumption is optimized, and user-side voltage stability is calibrated to avoid localized overload problems caused by concentrated user-side power loads. This ensures that the user-side power resource operation meets optimization requirements, ultimately yielding optimized user-side operational data. During the regulation process, user-side power demand is guaranteed while achieving efficient utilization of user-side power resources.

[0068] In this embodiment, the specific process of deleting conflicting data from the main layer valid data and the station area valid data to obtain conflict resolution data is as follows: First, the core correlation parameters of the main layer valid data and the distribution area valid data are identified. Conflicts between the two types of data mainly manifest as inconsistencies in the values ​​of corresponding core operating parameters within the same time segment and distribution network area, exceeding the reasonable deviation range allowed for distribution network operation. Core correlation parameters include line power, voltage amplitude, and load factor, all of which are critical parameters for distribution network operation. Second, the main layer valid data and the distribution area valid data are matched one-to-one according to time and region dimensions to ensure that the compared data correspond to the same operating condition and the same power grid area, avoiding invalid comparisons across time and regions. Then, parameter deviation thresholds are set. These thresholds are determined based on distribution network operation specifications and historical operating data to determine whether conflicts exist between the two types of data. For example, the reasonable deviation threshold for line power can be set to 5%, and the reasonable deviation threshold for voltage amplitude can be set to ±5%. Next, the values ​​of corresponding parameters are compared one by one. If the deviation between a parameter value in the main layer valid data and the corresponding parameter value in the distribution area valid data exceeds the preset deviation threshold, the data set is determined to be conflicting data; if the deviation is within the preset threshold range, it is determined to be conflict-free data and the data set is retained. Finally, all data identified as conflicting is deleted, and only the non-conflicting main layer valid data and station area valid data are retained. The retained data is integrated to form a structured dataset, which is the conflict resolution data, ensuring that the conflict resolution data has no parameter contradictions and is logically consistent.

[0069] In this embodiment, the specific process of performing collaborative correction processing on the conflict resolution data to obtain collaboratively corrected data is as follows: First, a comprehensive review of the conflict investigation data was conducted to identify abnormal data exhibiting unusual fluctuations or values ​​deviating from the normal operating range of the distribution network. These abnormal data primarily manifested as parameter values ​​exceeding preset standard ranges without supporting reasonable operating conditions. Examples include main transformer load rates exceeding the reasonable range of 80% in the main layer's valid data, and voltage amplitudes deviating excessively from standard values ​​in the distribution area's valid data. Second, collaborative correction rules were formulated. These rules were determined based on the distribution network's hierarchical operating logic, historical control data, and industry standards. The core principle was that the main control layer had higher priority than the distribution area control layer, while also incorporating real-time distribution network operating trends to ensure that the corrected data analysis closely aligned with actual operational needs. Third, correction processing was carried out based on the collaborative correction rules. For abnormal parameters in the main layer's valid data, parameter calibration techniques were used to correct them, referencing the distribution network's historical optimal operating parameters and the optimization requirements corresponding to the current dynamic control coefficients, bringing the parameter values ​​back to a reasonable range. For abnormal parameters in the distribution area's valid data, collaborative calibration was performed, combining the corrected parameters from the corresponding main layer's valid data with the actual load characteristics of the distribution area, to ensure logical consistency and parameter matching between the distribution area data and the main layer data. During the correction process, the basis for the correction and the parameter values ​​before and after the correction are recorded simultaneously to facilitate subsequent traceability and verification, and to avoid data deviations caused by blind correction. After the correction is completed, all corrected data undergoes consistency verification to check whether the logical relationships between the data are reasonable and whether the parameters comply with the power distribution network operation specifications. Finally, after passing the verification, all corrected data are integrated to form a complete, standardized, and logically consistent dataset, which is the collaboratively corrected data.

[0070] This embodiment employs a layered splitting process to clearly identify power operation data at each level, avoiding chaotic control and laying the foundation for precise control. Layered coefficient allocation ensures that dynamic control coefficients adapt to the needs of each level, improving control accuracy. Fusion verification eliminates invalid and conflicting data, guaranteeing data reliability and preventing control errors due to data issues. Standardized mapping of control commands converts the fused and optimized data into standardized commands, ensuring that commands can be directly implemented.

[0071] As can be seen from the above, this embodiment of the application correlates voltage level data and distribution area data in the static ledger of the distribution network, and then determines the distribution network hierarchical division data after validity verification. This clarifies the power grid structure of each region and voltage level, avoiding control errors caused by structural confusion and making control more targeted. Simultaneously, this embodiment classifies and correlates distributed power generation output and load data to form distribution network source-load characteristic data, which is then aligned with the hierarchical division data to clearly present the operating status of the power grid. This allows control personnel to accurately grasp the current power generation and consumption situation, avoiding control decision errors caused by data confusion. Then, this embodiment determines dynamic control coefficients through scenario matching, allowing control to adapt to changes in power grid operation in real time, solving the shortcomings of traditional fixed control that is difficult to adapt to real-time operating conditions. Finally, based on the dynamic control coefficients, hierarchical division data, and distribution network operating status data, optimized control instructions are generated, realizing on-demand control of power resources. This avoids power resource waste, ensures stable operation of the distribution network, and greatly improves the accuracy and reliability of distribution network control.

[0072] Corresponding to the power resource regulation method based on the distribution network in the above embodiment, Figure 2 This is a structural block diagram of a power resource control system based on a distribution network, provided as an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The power resource regulation system 20 based on the distribution network includes: a distribution network hierarchy division and processing module 21, a distribution network operation status determination module 22, a dynamic regulation coefficient determination module 23, and a regulation command generation module 24.

[0073] Among them, the distribution network hierarchy division processing module 21 is used to perform correlation processing on the voltage level data and transformer area distribution data in the static ledger data of the distribution network to obtain distribution network hierarchy correlation data; to perform validity verification processing on the distribution network hierarchy correlation data to obtain hierarchy validity verification result data; and to determine the distribution network hierarchy division data based on the hierarchy validity verification result data; the voltage level data is the voltage standard data of different power supply levels in the distribution network; The distribution network operation status determination module 22 is used to classify and process the distributed power output data and load data in the real-time measurement data of the distribution network, and then correlate and fuse them to obtain the distribution network source-load characteristic data; based on the distribution network hierarchical division data and the distribution network source-load characteristic data, feature alignment processing is performed, and the feature-aligned data is used as the distribution network operation status data. The dynamic control coefficient determination module 23 is used to perform similarity matching processing on the distribution network operation status data and the preset typical distribution network operation status benchmark data to obtain status matching data; based on the status matching data and the real-time measurement data of the distribution network, the dynamic control coefficient is determined; the status matching data is the similarity between the current distribution network operation status data and the benchmark data of various typical distribution network operation statuses respectively; The control instruction generation module 24 is used to generate power resource optimization control instruction data for the distribution network based on dynamic control coefficients, distribution network hierarchical division data, and distribution network operation status data; and to optimize and control the power resources of the distribution network based on the power resource optimization control instruction data.

[0074] In one embodiment of this application, the power distribution network hierarchy division processing module 21 is specifically used for: The voltage level data is classified according to the power supply level, and the classified voltage level data is used as the voltage level data. Extract the feeder affiliation information corresponding to the transformer area from the transformer area distribution data to obtain transformer area topology affiliation data; Based on voltage level data and transformer area topology attribution data, correlation matching processing is performed to obtain distribution network level correlation data.

[0075] In one embodiment of this application, the power distribution network operating status determination module 22 is specifically used for: The output data of distributed power sources is processed by output threshold classification to obtain the output level corresponding to the output data of distributed power sources, and the output level is used as the power output level data. Determine the priority of the load data; Based on the power output level data and the priority of the load data, the source and load characteristic data of the distribution network are obtained by correlation and fusion processing.

[0076] In one embodiment of this application, the dynamic control coefficient determination module 23 is specifically used for: The benchmark control coefficient corresponding to the benchmark data of the typical distribution network operation status with the highest similarity is called, and the benchmark control coefficient is determined as the initial control coefficient. Extract real-time source-load fluctuation data from real-time measurement data of the power distribution network; The fluctuation amplitude is calculated and processed from the real-time fluctuation data of the source load to obtain the fluctuation amplitude data; Calculate the deviation of the initial control coefficient relative to the fluctuation amplitude data, and use it as the initial control coefficient deviation; The initial control coefficient deviation is calibrated and corrected to obtain calibration correction data; Based on the calibration correction data, the initial control coefficient is calibrated and corrected to obtain the dynamic control coefficient.

[0077] In one embodiment of this application, the dynamic control coefficient determination module 23 is further used for: Determine the weights corresponding to the calibration correction data; The calibration correction data is weighted based on the weights to obtain the corrected calibration correction data. The corrected calibration correction data is then added to the initial control coefficient to obtain the weighted calibration coefficient. The weighted calibration coefficients are subjected to threshold compliance verification to obtain qualified weighted calibration coefficients, which are then used as dynamic control coefficients.

[0078] In one embodiment of this application, the control instruction generation module 24 is specifically used for: Based on the distribution network hierarchy data, the distribution network operation status data is split into layers to obtain layered power operation data, which includes: main control layer operation data, distribution area control layer operation data, and user-side control layer operation data. Based on the dynamic control coefficient, a hierarchical coefficient allocation process is performed to obtain the hierarchical control coefficient, which includes: the main control layer sub-coefficient, the transformer area control layer coefficient, and the user side control layer coefficient. Based on the main control layer sub-coefficients, the main control layer operation data is processed to obtain the main control layer optimized operation data. Based on the sub-coefficients of the control layer of the transformer area, the operation data of the control layer of the transformer area is processed to obtain the optimized operation data of the transformer area. Based on the sub-coefficients of the user-side control layer, the user-side control layer operation data is controlled and processed to obtain optimized user-side operation data. The optimized operation data of the main layer, the optimized operation data of the distribution area, and the optimized operation data of the user side are fused and verified to obtain fused optimized data. The fused and optimized data is then processed through standardized mapping of control commands to obtain power resource optimization control command data for the distribution network.

[0079] In one embodiment of this application, the control instruction generation module 24 is further configured to: The main layer optimization operation data is validated to obtain valid main layer data. The validity of the optimized operation data of the transformer area is verified to obtain the valid data of the transformer area. The user-side optimized operation data is validated to obtain valid user-side data. Delete conflicting data from the main layer valid data and the transformer area valid data to obtain conflict resolution data; The conflict resolution data is collaboratively corrected to obtain collaboratively corrected data. The collaboratively corrected data and the valid data from the user side are fused together to obtain fused and optimized data.

[0080] It should be noted that the specific limitations of the above-described embodiment of the power resource regulation system 20 based on the distribution network can be found in the limitations of the power resource regulation method based on the distribution network described above, and will not be repeated here. Each module of the above system can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in the processor of the electronic device in hardware form or independent of the processor, or it can be stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of each module.

[0081] This application provides an electronic device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the method provided in any optional embodiment of this application.

[0082] In one alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3 The illustrated electronic device 300 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may further include a transceiver 304, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0083] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0084] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0085] The memory 303 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium capable of carrying or storing computer programs and capable of being read by a computer, without limitation herein.

[0086] The memory 303 is used to store computer programs that execute the embodiments of this application, and the execution is controlled by the processor 301. The processor 301 is used to execute the computer programs stored in the memory 303 to implement the steps shown in the foregoing method embodiments.

[0087] In an exemplary embodiment, a computer-readable storage medium is also provided, which stores at least one computer program, which is loaded and executed by a processor of a computer device to enable the computer to implement any of the above-described power resource regulation methods based on a power distribution network.

[0088] In one possible implementation, the aforementioned computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a solid-state drive (SSD), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc. The random access memory can include resistive random access memory (ReRAM) and dynamic random access memory (DRAM).

[0089] In an exemplary embodiment, a computer program or computer program product is also provided, which includes computer instructions loaded and executed by a processor to enable the computer to implement any of the above-described power resource regulation methods based on a power distribution network.

[0090] It should be noted that all information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the static ledger data of the distribution network involved in this application were obtained with full authorization.

[0091] In other words, the data collection and processing in this application should strictly comply with the requirements of relevant national laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of laws and regulations and the authorization of the personal information subject.

[0092] It should be further noted that the terms "first," "second," etc., used in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The implementation methods described in the above exemplary embodiments do not represent all implementation methods consistent with this application. Rather, they are merely examples of systems and methods consistent with some aspects of this application.

[0093] It should be understood that "multiple" as used in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0094] Furthermore, the step numbers described herein are merely illustrative of one possible execution order between steps. In some other embodiments, the steps may not be executed in the order of their numbers, such as two steps with different numbers being executed simultaneously, or two steps with different numbers being executed in the reverse order of the illustration. This application does not limit this.

[0095] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. Optionally, the program is stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0096] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A power resource regulation method based on a distribution network, characterized in that, include: The voltage level data and transformer area distribution data in the static ledger data of the distribution network are correlated to obtain the hierarchical correlation data of the distribution network. The data associated with the distribution network hierarchy is subjected to validity verification to obtain hierarchy validity verification result data. Based on the hierarchy validity verification result data, the distribution network hierarchy division data is determined. The voltage level data is the voltage standard data for different power supply levels in the distribution network. After classifying and processing the distributed power output data and load data in the real-time measurement data of the distribution network, the distribution network source-load characteristic data are obtained by correlation and fusion. Based on the distribution network hierarchical division data and the distribution network source-load characteristic data, feature alignment processing is performed, and the feature-aligned data is used as the distribution network operation status data. The distribution network operation status data is subjected to similarity matching processing with the preset typical distribution network operation status benchmark data to obtain status matching data; Based on the state matching data and the real-time measurement data of the distribution network, the dynamic control coefficient is determined; the state matching data is the similarity between the current distribution network operating state data and the benchmark data of various typical distribution network operating states. Based on the dynamic control coefficient, the distribution network hierarchy data, and the distribution network operation status data, power resource optimization control instruction data for the distribution network is generated. Based on the power resource optimization and control instruction data of the power distribution network, the power resources of the power distribution network are optimized and controlled.

2. The power resource regulation method based on distribution network as described in claim 1, characterized in that, The process of correlating voltage level data and transformer distribution data in the static ledger data of the distribution network to obtain hierarchical correlated data of the distribution network includes: The voltage level data is classified according to the power supply level to obtain the classified voltage level data, which is used as voltage level data. Extract the feeder affiliation information corresponding to the transformer area from the transformer area distribution data to obtain transformer area topology affiliation data; Based on the voltage level data and the transformer substation topology attribution data, correlation matching processing is performed to obtain distribution network level correlation data.

3. The power resource regulation method based on distribution network as described in claim 1, characterized in that, After classifying and processing the distributed generation output data and load data in the real-time measurement data of the distribution network, the resulting data is correlated and fused to obtain the source-load characteristic data of the distribution network, including: The distributed power output data is subjected to output threshold classification processing to obtain the output level corresponding to the distributed power output data, and the output level is used as the power output level data. Determine the priority of the load data; Based on the power output level data and the priority of the load data, the power distribution network source-load characteristic data are obtained by performing correlation and fusion processing.

4. The power resource regulation method based on distribution network as described in claim 1, characterized in that, The determination of dynamic control coefficients based on the state matching data and the real-time measurement data of the distribution network includes: The benchmark control coefficient corresponding to the benchmark data of the typical distribution network operation status with the highest similarity is called, and the benchmark control coefficient is determined as the initial control coefficient. Extract real-time source load fluctuation data from the real-time measurement data of the power distribution network; The fluctuation amplitude is calculated and processed by the real-time fluctuation data of the source load to obtain the fluctuation amplitude data; Calculate the deviation of the initial control coefficient relative to the fluctuation amplitude data, and use it as the initial control coefficient deviation; The initial control coefficient deviation is calibrated and corrected to obtain calibration correction data; Based on the calibration correction data, the initial control coefficient is calibrated and corrected to obtain the dynamic control coefficient.

5. The power resource regulation method based on distribution network as described in claim 4, characterized in that, The step of calibrating and correcting the initial control coefficient based on the calibration correction data to obtain the dynamic control coefficient includes: Determine the weights corresponding to the calibration correction data; The calibration correction data is weighted based on the weights to obtain the corrected calibration correction data, and the corrected calibration correction data is added to the initial control coefficient to obtain the weighted calibration coefficient. The weighted calibration coefficients are subjected to threshold compliance verification to obtain qualified weighted calibration coefficients, which are used as the dynamic control coefficients.

6. The power resource regulation method based on distribution network as described in claim 1, characterized in that, The process of generating power resource optimization and control instruction data for the distribution network based on the dynamic control coefficient, the distribution network hierarchy data, and the distribution network operation status data includes: Based on the distribution network hierarchy data, the distribution network operation status data is split into layers to obtain layered power operation data, which includes: main control layer operation data, distribution area control layer operation data, and user-side control layer operation data. Based on the dynamic control coefficient, a hierarchical coefficient allocation process is performed to obtain the hierarchical control coefficient, which includes: main control layer sub-coefficient, station area control layer coefficient, and user side control layer coefficient. Based on the main control layer sub-coefficients, the main control layer operation data is controlled and processed to obtain the main layer optimized operation data; Based on the sub-coefficients of the transformer area control layer, the operating data of the transformer area control layer is processed to obtain optimized operating data of the transformer area. Based on the sub-coefficients of the user-side control layer, the operating data of the user-side control layer is controlled and processed to obtain optimized operating data of the user side. The main layer optimized operation data, the transformer area optimized operation data, and the user side optimized operation data are fused and verified to obtain fused optimized data. The fused and optimized data is subjected to standardized mapping processing of control commands to obtain the power resource optimization and control command data of the distribution network.

7. The power resource regulation method based on distribution network as described in claim 6, characterized in that, The process of fusing and verifying the main layer optimized operation data, the transformer area optimized operation data, and the user-side optimized operation data to obtain fused optimized data includes: The main layer optimized operation data is subjected to validity verification to obtain valid main layer data; The optimized operation data of the transformer area is subjected to validity verification to obtain valid data of the transformer area; The user-side optimized operation data is subjected to validity verification to obtain valid user-side data; Delete conflicting data from the main layer valid data and the transformer area valid data to obtain conflict resolution data; The conflict resolution data is then subjected to collaborative correction processing to obtain collaboratively corrected data; The collaboratively corrected data and the valid user-side data are subjected to data fusion processing to obtain fused optimized data.

8. A power resource regulation and control system based on a distribution network, characterized in that, include: The distribution network hierarchy division processing module is used to perform correlation processing on voltage level data and transformer area distribution data in the static ledger data of the distribution network to obtain distribution network hierarchy correlation data; to perform validity verification processing on the distribution network hierarchy correlation data to obtain hierarchy validity verification result data; and to determine distribution network hierarchy division data based on the hierarchy validity verification result data; the voltage level data is the voltage standard data of different power supply levels in the distribution network; The distribution network operation status determination module is used to classify and process the distributed power output data and load data in the real-time measurement data of the distribution network, and then correlate and fuse them to obtain the distribution network source-load characteristic data; based on the distribution network hierarchical division data and the distribution network source-load characteristic data, feature alignment processing is performed, and the feature-aligned data is used as the distribution network operation status data. The dynamic control coefficient determination module is used to perform similarity matching processing on the power distribution network operation status data and the preset typical power distribution network operation status benchmark data to obtain status matching data. Based on the state matching data and the real-time measurement data of the distribution network, the dynamic control coefficient is determined; the state matching data is the similarity between the current distribution network operating state data and the benchmark data of various typical distribution network operating states. The control instruction generation module is used to generate power resource optimization control instruction data for the distribution network based on the dynamic control coefficient, the distribution network hierarchy division data, and the distribution network operation status data. Based on the power resource optimization and control instruction data of the power distribution network, the power resources of the power distribution network are optimized and controlled.

9. The power resource regulation system based on the distribution network as described in claim 8, characterized in that, The power distribution network hierarchy division processing module is specifically used for: The voltage level data is classified according to the power supply level to obtain the classified voltage level data, which is used as voltage level data. Extract the feeder affiliation information corresponding to the transformer area from the transformer area distribution data to obtain transformer area topology affiliation data; Based on the voltage level data and the transformer substation topology attribution data, correlation matching processing is performed to obtain distribution network level correlation data.

10. The power resource regulation system based on the distribution network as described in claim 8, characterized in that, The power distribution network operation status determination module is specifically used for: The distributed power output data is subjected to output threshold classification processing to obtain the output level corresponding to the distributed power output data, and the output level corresponding to the distributed power output data is used as the power output level data. Determine the priority of the load data; Based on the power output level data and the priority of the load data, the power distribution network source-load characteristic data are obtained by performing correlation and fusion processing.

Images