Direct current transmission data management method, system and device based on knowledge graph

Abstract

The invention relates to the technical field of data management, and particularly discloses a direct-current power transmission data management method, system and device based on a knowledge graph, and the method comprises the steps: dividing a complex power grid into target units which can be dynamically regulated and controlled, and achieving the intelligent matching and optimization of a data transmission mode through the combination of a real-time parameter collection and knowledge graph reasoning technology; the method can accurately identify data characteristics of different areas, automatically select an efficient transmission protocol, effectively analyze noise data through embedded data cleaning analysis, guarantee the reliability of DC power transmission operation state analysis, monitor data quality indexes in real time, dynamically trigger a transmission strategy adjustment mechanism, and improve the reliability of DC power transmission operation state analysis. Closed-loop management of collection-transmission-cleaning-feedback is formed, the data management flexibility of operation and maintenance of the direct-current power transmission area is remarkably enhanced, a multi-dimensional early warning model is further constructed through continuous updating of the knowledge graph, potential faults can be recognized in advance, and full-process intelligent guarantee is provided for safe and efficient operation of the direct-current power transmission system.

Description

Technical Field

[0001] The present invention relates to the field of data management technology, and specifically to a direct current transmission data management method, system, and device based on a knowledge graph. Background Art

[0002] In direct current transmission systems, thermal damage is one of the key issues threatening the safe operation of equipment. Its causes are complex and involve the coupling of multiple physical fields. Knowledge graph technology systematically reveals the deep correlation between the thermal state of equipment and operating conditions, environmental parameters and material properties by constructing a "thermal damage association network", providing data-driven decision support for thermal damage prevention and control.

[0003] For example, the invention patent with announcement number CN118657256B announces a method for predicting links in a dynamic knowledge graph of a power grid based on quantum walks and quantum thermodynamics, which involves the field of defect diagnosis and dynamic graph representation learning technology for main equipment in power systems. The method includes collecting relevant data of the dynamic knowledge graph of a power grid, including the status, connection relationship, and timestamp of power grid equipment, constructing a data set, and dividing the data set into a training set and a test set; constructing a link prediction model for a dynamic knowledge graph of a power grid based on quantum walks and quantum thermodynamics, the model including a quantum migration-aware encoder and a temperature-aware hybrid expert model decoder; training the model using training set data, optimizing the model parameters through a back-propagation algorithm, and obtaining a trained model; and evaluating the trained model using a test set.

[0004] For example, the invention patent with announcement number CN117151445B announces a power grid dispatching knowledge graph management system and its dynamic update method, which involves the field of power grid dispatching knowledge graph management technology, including a graph update data acquisition module, a central processing unit, an analysis module and a prompt module; the graph update data acquisition module collects multiple data information during the operation of the power grid dispatching knowledge graph dynamic update system, and monitors the quality of power grid dispatching related data obtained by the power grid dispatching knowledge graph dynamic update system in real time. When the quality of power grid dispatching related data obtained by the power grid dispatching knowledge graph dynamic update system deteriorates, an early warning is issued to remind relevant power dispatching personnel who rely on the information in the knowledge graph to make key decisions and may make incorrect operations.

[0005] However, in the process of implementing the embodiments of the present application, the present application discovered that the above-mentioned technology has at least the following technical problems: when processing the data of the input knowledge graph, the existing technology often directly adopts or only gives early warning prompts when anomalies are found, lacks sufficient automated data quality improvement capabilities, and makes decisions based on knowledge graphs of low quality and delayed updates, which increases the risk of decision-making, and erroneous reasoning and judgment may lead to serious consequences. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention provides a direct current transmission data management method, system and device based on knowledge graph, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides a direct current transmission data management method based on a knowledge graph, including: step 1, marking each direct current transmission area as a target area, collecting and analyzing the transmission parameters of each target area, and matching the data transmission mode of each target area; step 2, based on the data transmission mode corresponding to each target area, transmitting the power data of each target area, and performing data cleaning, while monitoring and analyzing the data cleaning process parameters of the power data of each target area, and determining whether to adjust and manage the data transmission mode of each target area; step 3, the knowledge graph receives the power data of each target area and updates the knowledge graph, so as to determine whether to issue a data warning for each target area.

[0008] As a further method, the data transmission mode of each target area is matched, and the specific matching process is: by analyzing the transmission parameters of each target area, the data transmission complexity index of each target area is obtained; the data transmission complexity index of each target area is compared with the data transmission complexity index reference interval. If the data transmission complexity index of a target area is greater than the maximum value of the data transmission complexity index reference interval, the data transmission mode of the target area is the first transmission mode; if the data transmission complexity index of a target area belongs to the data transmission complexity index reference interval, the data transmission mode of the target area is the second transmission mode; if the data transmission complexity index of a target area is less than the minimum value of the data transmission complexity index reference interval, the data transmission mode of the target area is the third transmission mode.

[0009] As a further method, the determination of whether to adjust and manage the data transmission mode of each target area is as follows: by analyzing the data cleaning process parameters of the power data of each target area, the data transmission anomaly factor of each target area within the data cleaning period is obtained; the data transmission anomaly factor of each target area within the data cleaning period is compared with the data transmission anomaly threshold; if the data transmission anomaly factor of a target area within the data cleaning period is less than or equal to the data transmission anomaly threshold, it is determined that the data transmission mode of the target area is not adjusted and managed; if the data transmission anomaly factor of a target area within the data cleaning period is greater than the data transmission anomaly threshold, the operation anomaly index of the target area within the historical monitoring period is obtained and compared with the operation anomaly threshold; if the operation anomaly index of the target area within the historical monitoring period is less than or equal to the operation anomaly threshold, it is determined that the target area is not adjusted and managed. The data transmission mode of the target area is adjusted and managed. If the operation anomaly index of the target area during the historical monitoring period is greater than the operation anomaly threshold, it is determined that the data transmission mode of the target area is adjusted and managed. The specific adjustment and management process is: obtain the data transmission mode of the target area and the data transmission anomaly deviation value of the target area during the data cleaning period. If the data transmission mode of the target area is the first transmission mode, the data port transmission rate of the target area is adjusted and managed according to the data transmission anomaly deviation value of the target area during the data cleaning period; if the data transmission mode of the target area is the second transmission mode, the data transmission links of the target area are merged and adjusted; if the data transmission mode of the target area is the third transmission mode, the antenna transmission power of the target area is adjusted and managed according to the data transmission anomaly deviation value of the target area during the data cleaning period.

[0010] As a further method, the determination of whether to issue a data warning to each target area is as follows: extracting the operation anomaly index of each target area in the first cycle from the knowledge graph and comparing it with the operation anomaly threshold; if the operation anomaly index of a target area in the first cycle is less than or equal to the operation anomaly threshold, it is determined that no data warning is issued to the target area; if the operation anomaly index of a target area in the first cycle is greater than the operation anomaly threshold, the operation anomaly tolerance value of the target area is obtained from the data graph, and the difference is processed with the operation anomaly index of the target area in the first cycle, and the processing result is marked as the operation anomaly tolerance residual value of the target area in the first cycle. The abnormal critical time point of the target area is matched from the management database according to the operation abnormal tolerance margin value of the target area in the first cycle, and compared with the reference time point stored in the management database. If the abnormal critical time point of the target area is after the reference time point, it is determined that no data warning is issued for the target area. If the abnormal critical time point of the target area is before the reference time point or is at the reference time point, the target area is marked as an abnormal area, and a data warning is issued for the target area according to the abnormal critical time point of the target area; at the same time, several abnormal areas are counted and marked as each abnormal area, and the data map is updated and managed according to each abnormal area.

[0011] The second aspect of the present invention provides a direct current transmission data management system based on a knowledge graph, including: a transmission mode matching module, which is used to mark each direct current transmission area as a target area, collect and analyze the transmission parameters of each target area, and match the data transmission mode of each target area; a data cleaning management module, which is used to transmit the power data of each target area based on the data transmission mode corresponding to each target area, and perform data cleaning, while monitoring and analyzing the data cleaning process parameters of the power data of each target area, and determining whether to adjust and manage the data transmission mode of each target area; a power data early warning module, which is used to receive the power data of each target area through the knowledge graph and update the knowledge graph, so as to determine whether to issue a data early warning for each target area.

[0012] A third aspect of the present invention provides a device that applies the direct current transmission data management method based on the knowledge graph, characterized in that it includes: a processor and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; when the processor is running, it calls a computer program from the non-volatile memory through the network interface and runs the computer program through the memory to execute the direct current transmission data management method based on the knowledge graph.

[0013] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0014] (1) The present invention provides a method, system and device for DC transmission data management based on knowledge graph. By dividing a complex power grid into dynamically controllable target units, and combining real-time parameter acquisition with knowledge graph reasoning technology, the method realizes intelligent matching and optimization of data transmission modes. The method can accurately identify data characteristics of different regions, automatically select efficient transmission protocols, and effectively analyze noise data by embedding data cleaning analysis to ensure the reliability of DC transmission operation status analysis. At the same time, the method monitors data quality indicators in real time, dynamically triggers the transmission strategy adjustment mechanism, and forms a closed-loop management of "acquisition-transmission-cleaning-feedback", which significantly enhances the data management flexibility of DC transmission regional operation and maintenance. The continuous update of the knowledge graph further constructs a multi-dimensional early warning model, which can identify potential faults in advance and provide full-process intelligent protection for the safe and efficient operation of the DC transmission system.

[0015] (2) The present invention monitors the key parameters in the data cleaning process in real time, automatically calculates the data transmission anomaly factor and compares it with the data transmission anomaly threshold to form a preliminary adjustment judgment. For areas where the data transmission anomaly factor is higher than the data transmission anomaly threshold, a historical operation data verification mechanism is further introduced to eliminate the risk of misjudgment by comparing historical failure modes. This two-layer decision-making architecture can not only capture instantaneous anomalies in a timely manner, but also avoid excessive intervention.

[0016] (3) The present invention achieves accurate early warning through a dual-threshold dynamic verification mechanism, which not only monitors the real-time operation abnormality index, but also conducts risk quantitative assessment in combination with the historical tolerance margin value, introduces the prediction of abnormal critical time points, and can identify the time window of potential failure in advance, thus transforming the traditional passive response into active prevention and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0018] Figure 1 Schematic diagram of the method steps of the present invention.

[0019] Figure 2 This is a schematic diagram of system module connections of the present invention. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0021] Reference Figure 1 As shown, the first aspect of the present invention provides a direct current transmission data management method based on a knowledge graph, including: step 1, marking each direct current transmission area as a target area, collecting and analyzing the transmission parameters of each target area, and matching the data transmission mode of each target area.

[0022] Data analysts logically divided the aforementioned DC transmission areas based on a three-level architecture of "geographic distribution - operational characteristics - key nodes." First, the grid's macro-geographic boundaries were defined by intercontinental / national administrative divisions. Second, meso-functional units were divided based on equipment attributes such as voltage levels and converter station types. Finally, micro-management units were defined using physical nodes such as current intersections and monitoring sections. Each target area was mapped using a composite coding system of "area code + functional identifier + node number," forming a clearly hierarchical and dynamically linked knowledge network structure, ensuring that data traceability paths strictly correspond to the physical topology.

[0023] Specifically, the data transmission mode of each target area is matched, and the specific matching process is: by analyzing the transmission parameters of each target area, the data transmission complexity index of each target area is obtained; the data transmission complexity index of each target area is compared with the data transmission complexity index reference interval. If the data transmission complexity index of a target area is greater than the maximum value of the data transmission complexity index reference interval, the data transmission mode of the target area is the first transmission mode; if the data transmission complexity index of a target area belongs to the data transmission complexity index reference interval, the data transmission mode of the target area is the second transmission mode; if the data transmission complexity index of a target area is less than the minimum value of the data transmission complexity index reference interval, the data transmission mode of the target area is the third transmission mode; the above-mentioned data transmission complexity index reference interval is the data transmission complexity index dynamic range preset in the management database, which divides the data transmission complexity index into three levels, corresponding to different data transmission modes; the first transmission mode is Ethernet transmission, the second transmission mode is dual-link transmission, and the third transmission mode is satellite transmission. It should also be explained that the data transmission mode of each target area is matched, and the specific parameters in the transmission mode are further matched from the management database through the data transmission complexity index of each target area. For example, the data transmission complexity index of a target area is S, and the data transmission mode of the target area is matched to the first transmission mode. The data transmission complexity index S of the target area belongs to the data transmission complexity index interval (S-20%, S+20%) in the management database. The specific parameters of the transmission mode corresponding to the data transmission complexity index interval (S-20%, S+20%) in the management database include: using an adaptive bandwidth adjustment algorithm to dynamically fluctuate ±30% on a preset basic bandwidth (e.g., 1 gigabit per second) according to the real-time data flow density, ensuring that the link utilization rate is stable in the range of 85% to 95% in high-throughput scenarios, and implementing 802. 1p traffic priority marking, reserving 30% of the bandwidth for key control signals, and adopting a strict priority queue scheduling algorithm to ensure that the end-to-end jitter of control instructions is less than 20 microseconds. The specific parameters of the transmission method in the target area include: adopting an adaptive bandwidth adjustment algorithm, dynamically floating ±30% on the preset basic bandwidth (such as 1 gigabit per second) according to the real-time data flow density, ensuring that the link utilization rate in high-throughput scenarios is stable in the range of 85% to 95%, implementing 802.1p traffic priority marking, reserving 30% of the bandwidth for key control signals, and adopting a strict priority queue scheduling algorithm to ensure that the end-to-end jitter of control instructions is less than 20 microseconds.

[0024] Furthermore, the data transmission complexity index of each target area is analyzed in detail as follows: the transmission parameters of each target area include the data transmission attenuation factor of each target area, the data transmission distance of each target area, and the average electromagnetic interference intensity of each target area; the data transmission attenuation factor refers to the intensity attenuation of the signal due to dielectric loss, distance increase, or electromagnetic interference during the transmission process. The specific expression of the data transmission attenuation factor is: Among them A n is the unit distance attenuation coefficient of the nth type of obstacle, for example, vegetation coverage is 0.2-0.4 dB / m (the higher the humidity, the higher the value), extracted from the management database, D n The cumulative distance the signal traverses the nth type of obstacle. Using the spatial overlay analysis function of the geographic information system, the obstacle distribution vector layer is digitally coupled with the geographic topology of the transmission path. The obstacle types (such as walls or vegetation) traversed by the path are automatically identified. The obstacle boundary intersections are analyzed based on the path topology. The segmented traversal distance for each obstacle type is calculated through coordinate difference, achieving accurate quantification of the obstacle impact range. DO is the data transmission distance, n is the obstacle number (n = {1, 2, 3, ..., z}), and z is the total number of obstacle types. The data transmission distance refers to the physical path length from the center of the target area to the physical device belonging to the knowledge graph, calculated by the shortest straight-line distance between the two using methods such as the Pythagorean theorem. The average electromagnetic interference intensity represents the level of interference from the electromagnetic environment to data transmission in the target area, measured in decibel microvolts. This is achieved by sampling multiple time periods at regional grid points using a distributed electromagnetic field probe. The interference power spectrum density of each frequency band is obtained through spectrum analyzer processing, and the average value is then calculated to obtain the average electromagnetic interference intensity. For example, a typical value in industrial areas can reach 50 dB microvolts, while it may be less than 10 dB microvolts in remote areas.

[0025] By introducing influence values, the influence of the normalized ratio between the data transmission attenuation factor and the defined data transmission attenuation factor on the data transmission complexity index, the influence of the normalized ratio between the data transmission distance and the defined data transmission distance on the data transmission complexity index, and the influence of the normalized ratio between the average electromagnetic interference intensity and the defined average electromagnetic interference intensity on the data transmission complexity index are quantified respectively. The influence degrees are summarized and aggregated to finally obtain the data transmission complexity index. The data transmission complexity index of each target area is used to quantify the complexity of the data transmission process of each target area. The specific analysis process is as follows:

[0026] GTP k =FI k +AD k +TP k ;

[0027]

[0028] Where GTP k is the data transmission complexity index of the kth target area, k is the number of each target area, k={1,2,3,...,g}, g is the total number of target areas, FI k is the data transmission attenuation factor affecting the kth target area, AD k is the data transmission distance impact component of the kth target area, TP k is the average electromagnetic interference intensity impact component of the kth target area, AF k is the data transmission attenuation factor of the kth target area, DA k is the data transmission distance of the kth target area, PT k is the average electromagnetic interference intensity of the kth target area, JAF is the defined data transmission attenuation factor preset in the management database, JDA is the defined data transmission distance preset in the management database, JPT is the defined average electromagnetic interference intensity preset in the management database, ao1 is the impact value corresponding to the data transmission attenuation factor preset in the management database, ao2 is the impact value corresponding to the data transmission distance preset in the management database, and ao3 is the impact value corresponding to the average electromagnetic interference intensity preset in the management database.

[0029] The above-mentioned definition of the data transmission attenuation factor indicates the maximum allowable value of the data transmission attenuation factor; the above-mentioned definition of the data transmission distance indicates the maximum allowable value of the data transmission distance; the above-mentioned definition of the average electromagnetic interference intensity indicates the maximum allowable value of the average electromagnetic interference intensity; the above-mentioned data transmission attenuation factor influence component indicates the degree of influence of the data transmission attenuation factor component on the data transmission complexity index; the above-mentioned data transmission distance influence component indicates the degree of influence of the data transmission distance component on the data transmission complexity index; the above-mentioned average electromagnetic interference intensity influence component indicates the degree of influence of the average electromagnetic interference intensity component on the data transmission complexity index.

[0030] The impact value corresponding to the above-mentioned data transmission attenuation factor is used to quantify the degree of influence of the unit value of the data transmission attenuation factor on the data transmission complexity index; the impact value corresponding to the above-mentioned data transmission distance is used to quantify the degree of influence of the unit value of the data transmission distance on the data transmission complexity index; the impact value corresponding to the above-mentioned average electromagnetic interference intensity is used to quantify the degree of influence of the unit value of the average electromagnetic interference intensity on the data transmission complexity index; the management database stores the correspondence between the data transmission attenuation factor, the data transmission distance and the average electromagnetic interference intensity and their corresponding impact values. For example, the data transmission attenuation factor, the data transmission distance and the average electromagnetic interference intensity are input into the management database, and the management database can match the impact value corresponding to the data transmission attenuation factor, the impact value corresponding to the data transmission distance and the impact value corresponding to the average electromagnetic interference intensity, and the value range is between 0 and 1.

[0031] It needs to be explained that the extension of transmission distance leads to a linear decline in signal quality through dielectric loss and obstacle attenuation effects; the electromagnetic interference intensity further amplifies the degradation amplitude of the attenuation factor through the noise superposition mechanism, forming a "distance-interference" synergistic attenuation effect. When the transmission path passes through a complex electromagnetic environment or an area with dense obstacles, the three produce a nonlinear superposition effect, requiring data transmission to simultaneously cope with the triple challenges of signal attenuation, noise interference and distance loss, resulting in an upward trend in the complexity index.

[0032] Step 2: Based on the data transmission method corresponding to each target area, transmit the power data of each target area and perform data cleaning. At the same time, monitor and analyze the data cleaning process parameters of the power data of each target area to determine whether to adjust the data transmission method of each target area.

[0033] In an example embodiment, the above-mentioned data cleaning includes but is not limited to identifying instantaneous values that deviate from the historical mean by more than 3 standard deviations (such as isolated points with a sudden increase of 500% in current) through a standard score algorithm, using a density-based noisy spatial clustering algorithm to identify sparse points that deviate from the main data cluster (such as terminals whose voltage values deviate from the regional mean by more than 15% for a long time), and performing wavelet denoising on electromagnetic interference pulses in Ethernet transmission (duration less than 10 milliseconds and amplitude exceeding a threshold of 20%).

[0034] Specifically, the determination of whether to adjust and manage the data transmission mode of each target area is as follows: by analyzing the data cleaning process parameters of the power data of each target area, the data transmission anomaly factor of each target area within the data cleaning cycle is obtained; the data transmission anomaly factor of each target area within the data cleaning cycle is compared with the data transmission anomaly threshold; if the data transmission anomaly factor of a target area within the data cleaning cycle is less than or equal to the data transmission anomaly threshold, it is determined that the data transmission mode of the target area is not adjusted and managed; the above-mentioned data transmission anomaly threshold represents the maximum value of a reasonable range of the data transmission anomaly factor, which is extracted from the management database.

[0035] If the data transmission anomaly factor of a target area during the data cleaning cycle is greater than the data transmission anomaly threshold, the target area's operation anomaly index during the historical monitoring cycle is obtained and compared with the operation anomaly threshold. If the target area's operation anomaly index during the historical monitoring cycle is less than or equal to the operation anomaly threshold, it is determined that no adjustment will be made to the target area's data transmission mode. If the target area's operation anomaly index during the historical monitoring cycle is greater than the operation anomaly threshold, it is determined that the target area's data transmission mode will be adjusted. The historical monitoring cycle refers to the benchmark time window for evaluating the target area's historical operating status, which is determined by power engineers. The operation anomaly index of the target area during the historical monitoring cycle is obtained in the same manner as the operation anomaly index of the target area during the first cycle, with the only difference being the setting of the parameter collection time window. If the operation anomaly index of the target area during the historical monitoring cycle is greater than the operation anomaly threshold, it indicates that the abnormal characteristics detected during the data cleaning process are primarily due to inherent fluctuations in the target area's operation process, rather than occasional interference introduced by the data transmission link. In this case, the target area's power data needs to be rolled back to its original collection state, and the initial, uncleaned data should be directly transferred to the knowledge graph to preserve the original operating characteristics for in-depth mechanism analysis.

[0036] The above determination adjusts and manages the data transmission mode of the target area. The specific adjustment and management process is: obtain the data transmission mode of the target area and the data transmission abnormality deviation value of the target area during the data cleaning cycle. If the data transmission mode of the target area is the first transmission mode, the data port transmission rate of the target area is adjusted and managed according to the data transmission abnormality deviation value of the target area during the data cleaning cycle; if the data transmission mode of the target area is the second transmission mode, the data transmission link of the target area is merged and adjusted; if the data transmission mode of the target area is the third transmission mode, the target area is merged and adjusted according to the data transmission abnormality deviation value of the target area during the data cleaning cycle. The antenna transmission power is adjusted and managed; the above-mentioned data transmission method for obtaining the target area can be extracted from the information of the link of matching the data transmission method of each target area; the above-mentioned data transmission abnormality deviation value refers to the difference processing of the data transmission abnormality factor and the data transmission abnormality threshold, and the ratio processing of the processing result with the data transmission abnormality threshold, and finally the data transmission abnormality deviation value is obtained, which represents the degree of deviation between the data transmission abnormality factor and the data transmission abnormality threshold; the above-mentioned data cleaning cycle refers to the overall time period for cleaning the received power data of each target area, and the specific length is determined by the actual data cleaning process; the above-mentioned adjustment and management of the data port transmission rate of the target area specifically refers to the adjustment and management of the data port transmission rate of the target area according to the target area. The data transmission abnormality deviation value of the target area during the data cleaning cycle is obtained, and the data transmission abnormality deviation value interval corresponding to the data transmission abnormality deviation value is queried from the management database, and the data port transmission rate adjustment value corresponding to the data transmission abnormality deviation value interval is extracted, and is accumulated with the existing data port transmission rate of the target area. The accumulated result is the adjusted data port transmission rate of the target area. For example, if the existing data port transmission rate is 500 megabits per second and the data port transmission rate adjustment value is +300 megabits per second, then the adjusted data port transmission rate is 800 megabits per second. The above-mentioned combined adjustment management of the data transmission link of the target area specifically refers to dual-link load balancing optimization based on real-time link The software-defined network controller dynamically adjusts the traffic ratio of the two physical links (such as optical fiber + wireless) based on the quality of the link (such as latency, packet loss rate, and bandwidth utilization). For example, when the optical fiber link utilization exceeds 70%, 30% of non-real-time data (such as device status logs) are automatically switched to the wireless link. The above-mentioned adjustment and management of the antenna transmission power of the target area specifically refers to querying the data transmission abnormality deviation value interval corresponding to the data transmission abnormality deviation value from the management database through the data transmission abnormality deviation value, extracting the antenna transmission power adjustment value corresponding to the data transmission abnormality deviation value interval, and adding it to the existing antenna transmission power of the target area. The accumulated result is the adjusted antenna transmission power of the target area.

[0037] It should be explained that, given the thermal design power limitations of RF front-end devices, when the adjusted antenna transmit power in the target area exceeds the maximum allowable transmit power of the RF front-end device, the power control unit will automatically lock the actual antenna transmit power at the maximum allowable transmit power in accordance with safety operating procedures.

[0038] Furthermore, the data transmission anomaly factor of each target area during the data cleaning cycle is specifically analyzed as follows: the data cleaning process parameters of the power data of each target area include the average overlap of the data curves of each target area during the data cleaning cycle, the data clock synchronization accuracy deviation value of each target area during the data cleaning cycle, and the data outlier space density of each target area during the data cleaning cycle; the above-mentioned average overlap of the data curves quantifies the average overlap of the curve shape of each data curve included in the power data of each target area before and after data cleaning, and calculates the original data of each data curve before cleaning through data processing software (such as Matrix Lab). The above-mentioned data clock synchronization accuracy deviation value refers to the cumulative sum of the absolute values of the instantaneous offsets of the clock sources of each data acquisition device relative to the unified reference time during the target monitoring period. This indicator comprehensively reflects the overall stability and error distribution characteristics of the clock synchronization of data acquisition devices in the target area by statistically summing the absolute values of the errors of all data acquisition devices at all sampling moments. The above-mentioned data outlier spatial density refers to the degree of aggregation of outliers in the multidimensional feature space, reflecting the local severity of data quality problems. High-density outlier areas may correspond to sensor failures or communication interference, which can be obtained from the data cleaning log.

[0039] By introducing the influence value, the influence of the normalized ratio between the average overlap of the data curve and the average overlap of the defined data curve on the data transmission anomaly factor, the influence of the normalized ratio between the average overlap of the defined data curve and the average overlap of the data curve on the data transmission anomaly factor, and the influence of the normalized ratio between the data clock synchronization accuracy deviation value and the defined data clock synchronization accuracy deviation value on the data transmission anomaly factor are quantified respectively. At the same time, the influence of the data transmission complexity index on the data transmission anomaly factor is introduced, and the influence degrees are integrated and summarized to obtain the data transmission anomaly factor. The data transmission anomaly factor of each target area during the data cleaning cycle represents the abnormal disturbance intensity introduced by the data transmission process of each target area during the data cleaning cycle. The specific expression is:

[0040]

[0041] Where, CL k is the data transmission anomaly factor of the kth target area during the data cleaning cycle, PL kis the abnormal data transmission component of the kth target area during the data cleaning period, GTP k is the data transmission complexity index of the kth target area, XQ k DT is the average overlap of the data curves of the kth target area during the data cleaning period. k is the data clock synchronization accuracy deviation value of the kth target area during the data cleaning cycle, KY k is the spatial density of data outliers in the kth target area during the data cleaning cycle, JXQ is the average overlap of the defined data curves preset in the management database, JDT is the defined data clock synchronization accuracy deviation value preset in the management database, JKY is the spatial density of defined data outliers preset in the management database, sa1 is the influence value corresponding to the data transmission complexity index preset in the management database, sa2 is the influence value corresponding to the average overlap of the data curves preset in the management database, sa3 is the influence value corresponding to the data clock synchronization accuracy deviation value preset in the management database, sa4 is the influence value corresponding to the spatial density of data outliers preset in the management database, k is the number of each target area, k = {1, 2, 3, ..., g}, and g is the total number of target areas.

[0042] The above-mentioned data transmission anomaly component refers to the summary result of the influence of the average overlap component of the data curve on the data transmission anomaly factor, the influence of the data clock synchronization accuracy deviation value component on the data transmission anomaly factor, and the influence of the data outlier spatial density component on the data transmission anomaly factor; the above-mentioned definition of the average overlap of the data curve indicates the minimum allowable value of the average overlap of the data curve; the above-mentioned definition of the data clock synchronization accuracy deviation value indicates the maximum allowable value of the data clock synchronization accuracy deviation value; the above-mentioned definition of the data outlier spatial density indicates the maximum allowable value of the data outlier spatial density.

[0043] The influence value corresponding to the above-mentioned data transmission complexity index is used to de-unitize the data transmission complexity index and represents the degree of influence of the unit value of the data transmission complexity index on the data transmission anomaly factor; the influence value corresponding to the above-mentioned data curve average overlap represents the degree of influence of the unit value of the data curve average overlap on the data transmission anomaly factor; the influence value corresponding to the above-mentioned data clock synchronization accuracy deviation value represents the degree of influence of the unit value of the data clock synchronization accuracy deviation value on the data transmission anomaly factor; the influence value corresponding to the above-mentioned data outlier spatial density represents the degree of influence of the unit value of the data outlier spatial density on the data transmission anomaly factor; the management database stores the correspondence between the data transmission complexity index, the average overlap of the data curve, the data clock synchronization accuracy deviation value, and the data outlier spatial density and their corresponding influence values. For example, when the data transmission complexity index, the average overlap of the data curve, the data clock synchronization accuracy deviation value, and the data outlier spatial density are input into the management database, the management database can match the influence value corresponding to the data transmission complexity index, the influence value corresponding to the average overlap of the data curve, the influence value corresponding to the data clock synchronization accuracy deviation value, and the influence value corresponding to the data outlier spatial density, and the value range is between 0 and 1.

[0044] It should be explained that the average overlap of the data curve reflects the consistency of data at different time points or between different data sources. When the overlap decreases, it means that the differences between the data increase, which may lead to an increase in the data transmission anomaly factor. At the same time, data inconsistency increases the increase in the data clock synchronization accuracy deviation value. The data clock synchronization accuracy deviation value measures the degree of synchronization of the clocks of each node in the data transmission system. The larger the deviation value, the higher the risk of timing disorder in data transmission, and the more outliers are removed, which further leads to a decrease in the average overlap of the data curve, which may cause an increase in the spatial density of data outliers. The spatial density of data outliers describes the distribution of outliers or extreme values in the dataset. A high density of outliers may indicate that there is a lot of noise or interference in the data transmission process, which will also increase the value of the data transmission anomaly factor. The data transmission complexity index comprehensively considers multiple aspects of data transmission. A higher data transmission complexity index may introduce more outliers during the data transmission process, resulting in more outliers being removed, further leading to a decrease in the average overlap of the data curve, an increase in the data clock synchronization accuracy deviation value, and an increase in the spatial density of data outliers, which directly or indirectly increases the level of the data transmission anomaly factor. Therefore, the parameters are interrelated and work together to affect the data transmission anomaly factor.

[0045] In a specific embodiment, the present invention monitors key parameters in the data cleaning process in real time, automatically calculates the data transmission anomaly factor and compares it with the data transmission anomaly threshold to form a preliminary adjustment judgment. For areas where the data transmission anomaly factor is higher than the data transmission anomaly threshold, a historical operation data verification mechanism is further introduced to eliminate the risk of misjudgment by comparing historical failure modes. This two-layer decision-making architecture can not only capture instantaneous anomalies in a timely manner, but also avoid excessive intervention.

[0046] Step 3: The knowledge graph receives the power data of each target area and updates the knowledge graph to determine whether to issue a data warning for each target area.

[0047] In a specific embodiment, the present invention achieves accurate early warning through a dual-threshold dynamic verification mechanism, which not only monitors the real-time operation abnormality index, but also conducts risk quantitative assessment in combination with historical tolerance margin values, introduces abnormal critical time point prediction, and can identify the time window of potential failure in advance, thereby transforming traditional passive response into active prevention and control.

[0048] Specifically, the determination of whether to issue a data warning for each target area is as follows: extracting the operation abnormality index of each target area in the first cycle from the knowledge graph and comparing it with the operation abnormality threshold; if the operation abnormality index of a target area in the first cycle is less than or equal to the operation abnormality threshold, it is determined that no data warning will be issued for the target area; the above-mentioned operation abnormality threshold represents the minimum value of the reasonable range of the operation abnormality index, which is extracted from the management database; the above-mentioned first cycle refers to the time period in which the knowledge graph receives the power data of each target area and updates the data, and the specific duration is obtained from the timestamp log of the knowledge graph.

[0049] If the operation anomaly index of a target area in the first cycle is greater than the operation anomaly threshold, the operation anomaly tolerance value of the target area is obtained from the data map, and the difference processing is performed on the operation anomaly index of the target area in the first cycle. The processing result is marked as the operation anomaly tolerance margin value of the target area in the first cycle. According to the operation anomaly tolerance margin value of the target area in the first cycle, the abnormal critical time point of the target area is matched from the management database, and compared with the reference time point stored in the management database. If the abnormal critical time point of the target area is after the reference time point, it is determined that no data warning will be issued for the target area. If the abnormal critical time point of the target area is before the reference time point or is at the reference time point, the target area is marked as an abnormal area, and a data warning is issued for the target area according to the abnormal critical time point of the target area; at the same time, a number of abnormal areas are counted, marked as each abnormal area, and The data map is updated and managed according to each abnormal area; the above-mentioned operation abnormality tolerance value represents the maximum value of the operation abnormality index that the target area can withstand, which is extracted from the management database. The operation abnormality tolerance value will automatically change according to the operating status of the target area, and the specific change process is formulated by the electrical engineer; the above-mentioned operation abnormality tolerance margin value represents the difference between the operation abnormality tolerance value and the operation abnormality index, and quantifies the safety margin of the electrical system of the target area when facing an operation abnormality; the above-mentioned abnormal critical time point refers to the time point when the target area is predicted to be unable to operate normally. The specific matching process is: the abnormal critical time point corresponding to each operation abnormality tolerance margin value interval is stored in the management database, and the operation abnormality tolerance margin value interval stored in the management database to which the operation abnormality tolerance margin value of the target area in the first cycle belongs is queried. The abnormal critical time point corresponding to the operation abnormality tolerance margin value interval is the abnormal critical time point of the target area;The above-mentioned reference time point refers to the time point preset by the electrical engineer. The time period between the end time point of the first cycle and the reference time point is the buffer time period of the target area. The DC transmission in the target area can be automatically adjusted so that it can recover to normal state without manual intervention, thereby avoiding the occurrence of abnormal conditions. This buffer time period provides a valuable "window period" for the automatic adjustment of the target area, so that when facing abnormal conditions, it can use its own adjustment mechanism to eliminate abnormal factors as much as possible to ensure the continuity and stability of DC transmission, aiming to maximize the self-regulation ability of DC transmission and improve the overall performance and safety of DC transmission. If the abnormal critical time point of the target area is after the reference time point, it is determined that no data warning will be issued for the target area because no manual intervention is required. It can also utilize its own regulation mechanism for adjustment. If the critical abnormal time point of the target area is before or at the reference time point, the target area is marked as an abnormal area. Because the target area's self-regulation mechanism cannot eliminate the abnormality in the target area at the critical abnormal time point, manual intervention is required for correction. In an example embodiment, a data warning is issued for the target area based on the critical abnormal time point. The specific warning content is: "Target area A123-Power-001 is expected to reach the abnormal operation threshold at [specific critical abnormal time point, such as "May 15, 2023 14:00"]. Currently, the main parameters of the power system in this area are as follows: the load rate has exceeded 90%, the insulation resistance value has dropped to the critical value within the safe range, and the current fluctuations are abnormally frequent."

[0050] Specifically, the operation abnormality index of each target area in the first cycle, the specific analysis process is: obtain the current abnormality rate of each target area in the first cycle, the average insulation resistance decrease rate of each target area in the first cycle, and the load growth rate of each target area in the first cycle; the above-mentioned current abnormality rate refers to the proportion of the time period in the current data of the collected target area that is higher than the rated current value of the target area to the total length of the entire first cycle; the above-mentioned average insulation resistance decrease rate refers to the difference processing of the average insulation resistance value of the target area in the historical monitoring cycle and the average insulation resistance value of the target area in the first cycle, and the ratio processing of the processing result with the average insulation resistance value of the target area in the historical monitoring cycle to obtain the average insulation resistance decrease rate; the above-mentioned load growth rate refers to the difference processing of the load amount of the target area in the historical monitoring cycle and the load amount of the target area in the first cycle, and the ratio processing of the processing result with the load amount of the target area in the historical monitoring cycle to obtain the load growth rate; wherein the current abnormality rate, average insulation resistance value and load amount can all be obtained from the knowledge graph.

[0051] According to the data transmission complexity index of each target area, the operation abnormality correction value of each target area is matched, which represents the numerical value of the correction degree of the operation abnormality index. The specific matching process is: the operation abnormality correction value corresponding to each data transmission complexity index interval is stored in the management database, and the data transmission complexity index interval stored in the management database to which the data transmission complexity index of each target area belongs is queried. The operation abnormality correction value corresponding to the data transmission complexity index interval stored in the management database to which the data transmission complexity index of each target area belongs is the operation abnormality correction value of each target area.

[0052] By introducing influence weights, the influence degree of the normalized ratio between the current abnormality rate and the defined current abnormality rate on the operation abnormality index, the influence degree of the normalized ratio between the average insulation resistance decrease rate and the defined average insulation resistance decrease rate on the operation abnormality index, and the influence degree of the normalized ratio between the load growth rate and the defined load growth rate on the operation abnormality index are quantified. The influence degrees are coupled and the coupling result is corrected using the operation abnormality correction value. At the same time, the influence degree of the data transmission abnormality factor on the operation abnormality index is quantified and coupled with the correction result for a second time to obtain the operation abnormality index. The operation abnormality index of each target area in the first cycle represents the degree of abnormality caused by the coupling of electrical characteristic offset, load change and data transmission interference in each target area in the first cycle. The specific expression is:

[0053] OAI k =CL k *tf1+X k *(QE k );

[0054]

[0055] Where, OAI k is the abnormal operation index of the kth target area in the first cycle, QE k is the abnormal operation component of the kth target area in the first cycle, CL k is the data transmission anomaly factor of the kth target area during the data cleaning cycle, ILG k is the current abnormality rate of the kth target area in the first cycle, RSG k is the average insulation resistance drop rate of the kth target area in the first cycle, ZFY kis the load growth rate of the kth target area in the first cycle, JILG is the defined current abnormality rate preset in the management database, JRSG is the defined insulation resistance average decrease rate preset in the management database, JZFY is the defined load growth rate preset in the management database, tf1 is the influence weight corresponding to the data transmission abnormality factor preset in the management database, tf2 is the influence weight corresponding to the current abnormality rate preset in the management database, tf3 is the influence weight corresponding to the insulation resistance average decrease rate preset in the management database, tf4 is the influence weight corresponding to the load growth rate preset in the management database, k is the number of each target area, k = {1, 2, 3, ..., g}, g is the total number of target areas, X k is the operational anomaly correction value of the kth target area.

[0056] The above-mentioned operation abnormality component represents the summary result of the influence of the current abnormality rate component on the operation abnormality index, the influence of the average insulation resistance decrease rate component on the operation abnormality index, and the influence of the load growth rate component on the operation abnormality index; the above-mentioned definition of the current abnormality rate represents the maximum allowable value of the current abnormality rate; the above-mentioned definition of the average insulation resistance decrease rate represents the maximum allowable value of the average insulation resistance decrease rate; the above-mentioned definition of the load growth rate represents the maximum allowable value of the load growth rate.

[0057] The influence weight corresponding to the above-mentioned data transmission abnormality factor is used to de-unitize the data transmission abnormality factor, indicating the degree of influence of the unit value of the data transmission abnormality factor on the operation abnormality index; the influence weight corresponding to the above-mentioned current abnormality rate indicates the degree of influence of the unit value of the current abnormality rate on the operation abnormality index; the influence weight corresponding to the above-mentioned average insulation resistance decrease rate indicates the degree of influence of the unit value of the average insulation resistance decrease rate on the operation abnormality index; the influence weight corresponding to the above-mentioned load growth rate indicates the degree of influence of the unit value of the load growth rate on the operation abnormality index; the management database stores the correspondence between the data transmission abnormality factor, current abnormality rate, average insulation resistance decrease rate and load growth rate and their corresponding influence weights. For example, the data transmission abnormality factor, current abnormality rate, average insulation resistance decrease rate and load growth rate are input into the management database, and the management database can match the influence weight corresponding to the data transmission abnormality factor, the influence weight corresponding to the current abnormality rate, the influence weight corresponding to the average insulation resistance decrease rate and the influence weight corresponding to the load growth rate, and the value range is between 0 and 1.

[0058] It needs to be explained that when data transmission is abnormal, it may cause the system's monitoring data of key parameters such as current, insulation resistance and load to be inaccurate or missing, thereby indirectly affecting the accurate assessment of the current anomaly rate, the average insulation resistance decrease rate and the load growth rate. Among them, the increase in the current anomaly rate often means that there are problems such as overload, short circuit or equipment aging in the DC transmission. These problems may further lead to a decrease in insulation resistance and increase the risk of DC transmission failure. At the same time, the continuous increase in the load growth rate reflects the continuous increase in demand for DC transmission. If the DC transmission capacity is not expanded or optimized in time, it may aggravate the current anomaly and insulation resistance decrease. Therefore, abnormal changes in these four parameters will increase the operation abnormality index of DC transmission and affect the stability and safety of DC transmission.

[0059] Furthermore, the data graph is updated and managed according to each abnormal area. The specific updating process is: obtaining the data analysis priority of each abnormal area, and increasing the data analysis priority of each abnormal area to the highest priority, and counting the number of data analysis priority increases; the above-mentioned data analysis priority refers to the priority of data analysis of each abnormal area determined when using the knowledge graph for data analysis. In an example embodiment, the data analysis priority can be divided into four levels. It should be explained that the number of data analysis priority increases is not necessarily equal to the total number of abnormal areas, because the data analysis priority of the abnormal area may already be the highest priority.

[0060] The operation anomaly index of each target area in the first cycle is sorted in ascending order, and the data analysis priority of the target area corresponding to the first rank is reduced to the corresponding lowest data analysis priority. The number of data analysis priority reductions is calculated until it is equal to the number of data analysis priority increases. It should be explained that only the data analysis priority of the target area corresponding to the operation anomaly index less than or equal to the operation anomaly threshold is downgraded. If the number of target areas corresponding to the operation anomaly index less than or equal to the operation anomaly threshold is less than the number of data analysis priority increases, it is only necessary to reduce the data analysis priority of all target areas corresponding to the operation anomaly index less than or equal to the operation anomaly threshold to the corresponding lowest data analysis priority, and there is no need to ensure that the number of data analysis priority reductions is equal to the number of data analysis priority increases; the lowest data analysis priority is specifically determined by the operation anomaly index of each target area in the first cycle. For example, according to the operation anomaly index of a target area in the first cycle, the lowest data analysis priority of the target area corresponding to the operation anomaly index is queried from the management database, thereby reducing the data analysis priority of the target area to the lowest data analysis priority.

[0061] In a specific embodiment, the present invention provides a knowledge graph-based DC transmission data management method, system, and device. By dividing a complex power grid into dynamically controllable target units, and combining real-time parameter acquisition with knowledge graph reasoning technology, the method realizes intelligent matching and optimization of data transmission modes. The method can accurately identify data characteristics of different regions, automatically select efficient transmission protocols, and effectively analyze noise data through embedded data cleaning analysis to ensure the reliability of DC transmission operation status analysis. At the same time, data quality indicators are monitored in real time, and a transmission strategy adjustment mechanism is dynamically triggered to form a closed-loop management of "acquisition-transmission-cleaning-feedback", which significantly enhances the data management flexibility of DC transmission regional operation and maintenance. The continuous updating of the knowledge graph further constructs a multi-dimensional early warning model, which can identify potential faults in advance and provide full-process intelligent protection for the safe and efficient operation of the DC transmission system.

[0062] Reference Figure 2 As shown, the second aspect of the present invention provides a direct current transmission data management system based on a knowledge graph, including: a transmission mode matching module, a data cleaning management module, a power data early warning module and a management database.

[0063] The management database is used to store parameters involved in the knowledge graph-based direct current transmission data management system.

[0064] The transmission mode matching module is connected to the data cleaning management module, the data cleaning management module is connected to the power data early warning module, and the transmission mode matching module, the data cleaning management module and the power data early warning module are all connected to the management database.

[0065] The transmission mode matching module is used to mark each DC transmission area as each target area, collect and analyze the transmission parameters of each target area, and match the data transmission mode of each target area.

[0066] The data cleaning management module is used to transmit the power data of each target area and perform data cleaning based on the data transmission method corresponding to each target area, while monitoring and analyzing the data cleaning process parameters of the power data of each target area to determine whether to adjust and manage the data transmission method of each target area.

[0067] The power data warning module is used to receive power data of each target area through the knowledge graph and update the knowledge graph to determine whether to issue a data warning for each target area.

[0068] A third aspect of the present invention provides a device that applies the direct current transmission data management method based on the knowledge graph, characterized in that it includes: a processor and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; when the processor is running, it calls a computer program from the non-volatile memory through the network interface and runs the computer program through the memory to execute the direct current transmission data management method based on the knowledge graph.

[0069] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A DC transmission data management method based on knowledge graph, characterized in that: include: Step 1: Mark each DC transmission area as a target area, collect and analyze the transmission parameters of each target area, and match the data transmission mode of each target area; Step 2: Based on the data transmission mode corresponding to each target area, transmit the power data of each target area and perform data cleaning. At the same time, monitor and analyze the data cleaning process parameters of the power data of each target area to determine whether to adjust the data transmission mode of each target area; Step 3: The knowledge graph receives the power data of each target area and updates the knowledge graph to determine whether to issue a data warning for each target area.

2. The knowledge graph-based DC transmission data management method according to claim 1, characterized in that: The data transmission mode of each target area is matched, and the specific matching process is as follows: By analyzing the transmission parameters of each target area, the data transmission complexity index of each target area is obtained; Comparing the data transmission complexity index of each target area with the data transmission complexity index reference interval, if the data transmission complexity index of a target area is greater than the maximum value of the data transmission complexity index reference interval, the data transmission mode of the target area is the first transmission mode; If the data transmission complexity index of a target area belongs to the data transmission complexity index reference interval, the data transmission mode of the target area is the second transmission mode; If the data transmission complexity index of a target area is less than the minimum value of the data transmission complexity index reference interval, the data transmission mode of the target area is the third transmission mode.

3. The knowledge graph-based DC transmission data management method according to claim 2, characterized in that: The data transmission complexity index of each target area, the specific data analysis process is as follows: The transmission parameters of each target area include a data transmission attenuation factor of each target area, a data transmission distance of each target area, and an average electromagnetic interference intensity of each target area; By introducing impact values, the influence of the normalized ratio between the data transmission attenuation factor and the defined data transmission attenuation factor on the data transmission complexity index, the influence of the normalized ratio between the data transmission distance and the defined data transmission distance on the data transmission complexity index, and the influence of the normalized ratio between the average electromagnetic interference intensity and the defined average electromagnetic interference intensity on the data transmission complexity index are quantified respectively. The influence degrees are summarized and aggregated to finally obtain the data transmission complexity index. The data transmission complexity index of each target area is used to quantify the complexity of the data transmission process of each target area.

4. The knowledge graph-based DC transmission data management method according to claim 1, characterized in that: The specific process of determining whether to adjust and manage the data transmission mode of each target area is as follows: By analyzing the data cleaning process parameters of the power data of each target area, the data transmission anomaly factor of each target area during the data cleaning cycle is obtained; Compare the data transmission anomaly factor of each target area during the data cleaning cycle with the data transmission anomaly threshold. If the data transmission anomaly factor of a target area during the data cleaning cycle is less than or equal to the data transmission anomaly threshold, it is determined that the data transmission mode of the target area will not be adjusted. If the data transmission anomaly factor of a target area in the data cleaning cycle is greater than the data transmission anomaly threshold, the operation anomaly index of the target area in the historical monitoring cycle is obtained and compared with the operation anomaly threshold. If the operation anomaly index of the target area in the historical monitoring cycle is less than or equal to the operation anomaly threshold, it is determined that the data transmission mode of the target area will not be adjusted and managed. If the operation anomaly index of the target area in the historical monitoring cycle is greater than the operation anomaly threshold, it is determined that the data transmission mode of the target area will be adjusted and managed. The specific adjustment management process is as follows: Obtaining a data transmission mode of the target area and a data transmission abnormality deviation value of the target area during a data cleaning period; if the data transmission mode of the target area is the first transmission mode, adjusting and managing a data port transmission rate of the target area according to the data transmission abnormality deviation value of the target area during the data cleaning period; If the data transmission mode of the target area is the second transmission mode, merging and adjusting the data transmission links of the target area; If the data transmission mode of the target area is the third transmission mode, the antenna transmission power of the target area is adjusted and managed according to the data transmission abnormality deviation value of the target area during the data cleaning period.

5. The knowledge graph-based DC transmission data management method according to claim 4 is characterized by: The specific analysis process of the data transmission anomaly factors of each target area during the data cleaning cycle is as follows: The data cleaning process parameters of the power data of each target area include the average overlap of the data curves of each target area during the data cleaning period, the data clock synchronization accuracy deviation value of each target area during the data cleaning period, and the data outlier spatial density of each target area during the data cleaning period; By introducing influence values, the influence of the normalized ratio between the average overlap of the data curve and the average overlap of the defined data curve on the data transmission anomaly factor, the influence of the normalized ratio between the average overlap of the defined data curve and the average overlap of the data curve on the data transmission anomaly factor, and the influence of the normalized ratio between the data clock synchronization accuracy deviation value and the defined data clock synchronization accuracy deviation value on the data transmission anomaly factor are quantified respectively. At the same time, the influence of the data transmission complexity index on the data transmission anomaly factor is introduced, and the influence degrees are integrated and summarized to obtain the data transmission anomaly factor. The data transmission anomaly factor of each target area during the data cleaning period represents the abnormal disturbance intensity introduced by the data transmission process of each target area during the data cleaning period.

6. The knowledge graph-based DC transmission data management method according to claim 1, characterized in that: The specific process of determining whether to issue a data warning for each target area is as follows: Extract the operation anomaly index of each target area in the first cycle from the knowledge graph and compare it with the operation anomaly threshold. If the operation anomaly index of a target area in the first cycle is less than or equal to the operation anomaly threshold, it is determined that no data warning will be issued for the target area; If the operation anomaly index of a target area in the first cycle is greater than the operation anomaly threshold, the operation anomaly tolerance value of the target area is obtained from the data map, and the difference processing is performed on the operation anomaly index of the target area in the first cycle. The processing result is marked as the operation anomaly tolerance margin value of the target area in the first cycle. According to the operation anomaly tolerance margin value of the target area in the first cycle, the abnormal critical time point of the target area is matched from the management database, and compared with the reference time point stored in the management database. If the abnormal critical time point of the target area is after the reference time point, it is determined that no data warning will be issued for the target area. If the abnormal critical time point of the target area is before the reference time point or is at the reference time point, the target area is marked as an abnormal area, and a data warning is issued for the target area according to the abnormal critical time point of the target area. At the same time, several abnormal areas are counted and marked as abnormal areas, and the data map is updated and managed according to each abnormal area.

7. The knowledge graph-based DC transmission data management method according to claim 6, characterized in that: The data map is updated and managed according to each abnormal area. The specific update process is as follows: Obtain the data analysis priority of each abnormal area, and increase the data analysis priority of each abnormal area to the highest priority, and the number of statistical data analysis priorities increased; The operation anomaly index of each target area in the first cycle is sorted in ascending order, and the data analysis priority of the target area corresponding to the first ranking is reduced, and the number of data analysis priorities is reduced until it is equal to the number of data analysis priorities increased.

8. The knowledge graph-based DC transmission data management method according to claim 7, characterized in that: The specific analysis process of the operation abnormality index of each target area in the first cycle is as follows: Obtaining the current abnormality rate of each target area in the first cycle, the average insulation resistance decrease rate of each target area in the first cycle, and the load growth rate of each target area in the first cycle; According to the data transmission complexity index of each target area, the operation abnormality correction value of each target area is matched; By introducing influence weights, the influence of the normalized ratio between the current abnormality rate and the defined current abnormality rate on the operation abnormality index, the influence of the normalized ratio between the average insulation resistance decrease rate and the defined average insulation resistance decrease rate on the operation abnormality index, and the influence of the normalized ratio between the load growth rate and the defined load growth rate on the operation abnormality index are quantified. The influence degrees are coupled and the coupling result is corrected using the operation abnormality correction value. At the same time, the influence of the data transmission abnormality factor on the operation abnormality index is quantified and coupled with the correction result for a second time to obtain the operation abnormality index. The operation abnormality index of each target area in the first cycle represents the degree of abnormality of each target area caused by electrical characteristic deviation, load change and data transmission interference coupling in the first cycle.

9. A system using the knowledge graph-based DC transmission data management method according to any one of claims 1 to 8, characterized in that: include: The transmission mode matching module is used to mark each DC transmission area as a target area, collect and analyze the transmission parameters of each target area, and match the data transmission mode of each target area; The data cleaning management module is used to transmit the power data of each target area based on the data transmission mode corresponding to each target area, and perform data cleaning. At the same time, it monitors and analyzes the data cleaning process parameters of the power data of each target area to determine whether to adjust the data transmission mode of each target area; The power data warning module is used to receive power data of each target area through the knowledge graph and update the knowledge graph to determine whether to issue a data warning for each target area.

10. A device using the knowledge graph-based DC transmission data management method according to any one of claims 1 to 8, characterized in that: include: Processor and memory and network interfaces connected to the processor; The network interface is connected to the non-volatile memory in the server; When running, the processor retrieves a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the method according to claims 1 to 8.

Images