Multi-level treatment method for real-time data of new energy station power generation equipment

Abstract

The invention discloses a multi-level governance method for real-time data of new energy station power generation equipment, and particularly relates to the field of power data governance, and the method comprises the steps: cooperatively generating an edge governance rule and a central processing logic according to a global data governance strategy, and transmitting the edge rule to an edge node; and meanwhile, the data quality is monitored in real time, and a result is fed back to dynamically adjust a global data governance strategy, so that closed-loop optimization of data governance is realized. According to the multi-level treatment method for the real-time data of the new energy station power generation equipment, an edge treatment rule set and a central processing logic set are generated through driving of a global data treatment strategy, and the strategy is dynamically adjusted based on third treatment data; the problem that the edge node processing rule and the central data processing logic lack collaboration and dynamic adaptation is effectively solved; by implementing cross-level timestamp synchronous calibration, secondary alignment processing of the center node on the multi-source heterogeneous data is avoided, and the equipment state evaluation precision is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power data governance. More specifically, the present invention relates to a multi-level governance method for real-time data of power generation equipment in new energy power stations. Background Art

[0002] With the rapid development of new energy power generation technology and the continuous expansion of the scale of power stations, it is particularly important to efficiently govern the real-time data of power generation equipment in new energy power stations. Traditional data processing in new energy power stations collects the original data generated by various equipment in the new energy power station through data acquisition terminals, and then aggregates and transmits it to the central data center for unified storage, cleaning, calculation, and analysis. However, the direct remote transmission of a large amount of original data has led to a huge bandwidth pressure on the communication network. The central data processing center needs to process heterogeneous, redundant, and even noisy original data from many power stations, resulting in an overloaded computing load.

[0003] To alleviate the problems of network congestion and central computing pressure in traditional new energy power station data processing technologies, an edge computing node is introduced as an improvement solution. By deploying intelligent gateways with local computing capabilities at the substation level, the original data is pre-screened and feature-compressed, reducing the data throughput of the central node, lowering the bandwidth requirements for the backbone communication network, and sharing part of the computing load of the central server.

[0004] However, in actual use, there are still some drawbacks. For example, there is a lack of an effective coordination and dynamic adaptation mechanism between the processing rules of the edge nodes and the central data processing logic, resulting in the difficulty of ensuring global optimality and consistency of the data quality after multi-level processing. The central node still needs to perform secondary alignment processing on multi-source heterogeneous data, and the time stamp synchronization deviation of cross-level data directly affects the accuracy of equipment status evaluation. The existing architecture lacks a closed-loop feedback mechanism for the data governance process, and the traceability of abnormal data still requires manual intervention, resulting in a long operation and maintenance response time. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a multi-level governance method for real-time data of power generation equipment in new energy power stations, through the following solutions to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A multi-level governance method for real-time data of power generation equipment in new energy power stations, comprising:

[0008] S1: According to a preset global data governance strategy, generate a mutually coordinated edge governance rule set and a central processing logic set, and send the edge governance rule set to the corresponding edge nodes of the new energy power station;

[0009] S2: The edge nodes of the new energy power station receive the edge governance rule set and perform a first governance operation on the raw data obtained in real time by the power generation equipment. The first governance operation includes at least data cleaning and format standardization to generate first-governed data;

[0010] S3: According to the central processing logic set, perform a second governance operation on the first-governed data received from the edge nodes. The second governance operation includes cross-level timestamp synchronization calibration and data fusion processing to generate second-governed data;

[0011] S4: Monitor in real time the data quality indicators during the first governance operation and the second governance operation, and compare the monitoring results with the preset quality thresholds to generate third-governed data including data quality assessment results and abnormal data traceability information;

[0012] S5: Based on the third-governed data, dynamically adjust the global data governance strategy, and accordingly update the edge governance rule set and the central processing logic set. According to the abnormal data traceability information, automatically trigger the preset abnormal data handling process.

[0013] Preferably, in S1, the preset global data governance strategy includes an equipment type hierarchical mapping table, a data quality target matrix, and network status perception rules.

[0014] Preferably, in S2, the first governance operation specifically includes:

[0015] Execute through a first data processing channel including at least a data cleaning channel and a format standardization channel;

[0016] Among them, the data cleaning channel, according to the device-level data cleaning rule library in the edge governance rule set, performs differential processing on the data of different power generation equipment types. The algorithms for the differential processing include at least one of a filtering algorithm based on a sliding window, a dynamic adjustment method for wavelet denoising coefficients, and a dynamic baseline correction algorithm under equipment start-stop conditions;

[0017] In addition, the format standardization channel, according to the format conversion template in the edge governance rule set, converts the data from the data cleaning channel into a predefined standard format and encapsulates it into a unified coding structure including device ID, high-precision timestamp, data value range, and quality flag bit.

[0018] Preferably, in S3, the second governance operation specifically includes:

[0019] Execute through a second data processing channel including at least a timing alignment calibration channel and a multi-source data fusion channel;

[0020] Among them, according to the cross - level timing alignment rules in the central processing logic, the timing alignment calibration channel constructs a transmission delay topology map for the coding structure of the first governance data and realizes data alignment by adopting a hybrid clock synchronization mechanism, and the hybrid clock synchronization mechanism includes at least one of the NTP protocol, the PTP protocol, and the Kalman filtering algorithm;

[0021] In addition, according to the multi - source data fusion algorithm chain in the central processing logic, the multi - source data fusion channel performs multi - source data fusion processing on the data from the timing alignment calibration channel and encapsulates it into the second governance data including quality assessment tags, processing metadata, and semantic association information.

[0022] Preferably, for S3, the metadata at least includes a clock compensation coefficient, a redundancy elimination identifier, and a knowledge graph inference path.

[0023] Preferably, for S3, the multi - source data fusion processing specifically includes:

[0024] Construct a spatio - temporal correlation weighted model based on the device topology correlation degree, where the correlation degree weight is calculated by an exponential decay function of the electrical distance, and is specifically expressed as:

[0025]

[0026] Among them, δ represents the slope factor, d max represents the maximum electrical distance between power generation device i and power generation device j, and d ij represents the electrical distance between power generation device i and power generation device j;

[0027] Adopt a clustering algorithm to implement redundant data elimination;

[0028] Construct a triple knowledge graph including device entities, operating states, and grid instructions, apply a graph neural network for semantic association analysis, and perform consistency verification of device operation logic.

[0029] Preferably, for S4, the abnormal data traceability information at least includes the power generation device ID, the data flow path, and the processing link time - axis information.

[0030] Preferably, for S5, the preset abnormal data handling process specifically includes:

[0031] For the abnormal data determined to be known according to the abnormal data traceability information, call the corresponding handling plan from the preset system database to perform automatic repair;

[0032] For the abnormal data identified as new according to the abnormal data traceability information, execute the preset general handling plan, evaluate the impact of the general handling plan, and select the plan with the best repair effect to execute;

[0033] In addition, for the case where it is determined to be a hardware-level fault according to the abnormal data traceability information, a device maintenance work order containing location information is automatically generated and synchronized to the operation and maintenance personnel.

[0034] Technical effects and advantages of the present invention:

[0035] 1. The present invention drives the generation of an edge governance rule set and a central processing logic set through a global data governance strategy, and dynamically adjusts the strategy based on the third governance data, effectively solving the problem of lack of coordination and dynamic adaptation between the edge node processing rules and the central data processing logic, ensuring that the data quality after multi-level processing reaches the global optimum and consistency, and improving the overall coordination of data governance;

[0036] 2. The present invention significantly reduces the timestamp synchronization deviation of cross-layer data by implementing cross-layer timestamp synchronization calibration, avoids the secondary alignment processing of multi-source heterogeneous data by the central node, and effectively improves the accuracy of device status assessment;

[0037] 3. The present invention generates the third governance data containing abnormal data traceability information, and realizes automatic repair and strategy adjustment in combination with the preset abnormal data handling process, greatly shortening the operation and maintenance response time and improving the automation level of data governance. Description of the Drawings

[0038] Figure 1 It is a step flow chart of a multi-level governance method for real-time data of power generation equipment in a new energy power station provided according to an embodiment of the present application. Detailed Embodiments

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a 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 those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0040] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. As used in the specification of the present application, the singular forms "a", "one", "the", "above-mentioned", "this" and "this one" are also intended to include the plural forms, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more of the listed items.

[0041] Hereinafter, the terms "first", "second", and "third" are for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first", "second", and "third" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0042] As shown in the attached Figure 1 A multi-level governance method for real-time data of power generation equipment in a new energy power station, including jointly generating edge governance rules and central processing logic according to a global data governance strategy, and sending the edge rules to edge nodes; at the same time, monitoring data quality in real time and feeding back the results for dynamically adjusting the global data governance strategy to achieve closed-loop optimization of data governance. The specific steps are as follows:

[0043] S1: Generate a mutually cooperative set of edge governance rules and a set of central processing logic according to a preset global data governance strategy, and send the set of edge governance rules to the corresponding edge nodes of the new energy power station.

[0044] Specifically, in S1, a collaborative governance architecture between the edge and the center is realized through a dynamic rule generation system driven by a pre-constructed global data governance strategy.

[0045] In a possible implementation manner, the preset global data governance strategy is dynamically generated by a cloud policy engine, including an equipment type classification mapping table, a data quality target matrix, and network status perception rules; the cloud policy engine generates a global data governance strategy based on the topological structure of the target new energy power station, the operation historical data of the power generation equipment, and the real-time network bandwidth status, specifically including: defining data sampling frequencies and accuracy requirements according to power generation equipment types to generate an equipment type classification mapping table, and the power generation equipment types include but are not limited to wind turbines, photovoltaic inverters, etc.; in this embodiment, the vibration data of a doubly-fed induction generator adopts a band-pass filtering threshold of 0.5Hz - 80Hz, and the current data of the photovoltaic inverter configures an outlier detection method with dynamic baseline adjustment; the data quality target matrix determines the dynamic weight allocation rules for integrity, consistency, and timeliness through the orthogonal test method; in this embodiment, when the network delay exceeds 50ms, the timeliness weight is automatically increased to 0.6; the network status perception rules collect the bandwidth utilization rate and transmission jitter value of each edge node in real time, and set the data cache window size of the edge node based on the network transmission jitter value threshold.

[0046] Further, the global data governance strategy is disassembled into an edge governance rule set and a central processing logic set through a decoupling algorithm. Among them, the edge rule set includes a device-level data cleaning rule library, a format conversion template, and a local caching strategy, and the central processing logic set constructs cross-level time series alignment rules and a multi-source data fusion algorithm chain.

[0047] It should be noted that the device-level data cleaning rule library in the edge rule set includes, but is not limited to, an outlier rejection algorithm based on a sliding window, a dynamic adjustment method for wavelet denoising coefficients, a dynamic baseline correction algorithm under device start-stop conditions, etc.; the format conversion template includes, but is not limited to, mapping rules from multiple protocols such as Modbus and IEC 61850 to the standard JSON Schema, defining a TLV encoding structure including device ID, high-precision timestamp, data value range, and quality flag bits, etc.; the local caching strategy includes, but is not limited to, a hierarchical storage mechanism based on data timeliness, a priority weighted queue management algorithm, a dynamic cache window adjustment rule triggered by network congestion status, etc.; the cross-level time series alignment rules in the central processing logic set adopt a hybrid clock synchronization mechanism of NTP and PTP. By embedding a hierarchical transmission path mark in the data packet, the transmission path mark includes node ID, transmission hop count, and estimated delay, and the Kalman filter algorithm is applied to compensate for network jitter, so as to control the clock deviation across three-level nodes within ±10 ms; the multi-source data fusion algorithm chain includes, but is not limited to, a spatio-temporal correlation weighting algorithm based on device topology correlation, a redundant data elimination algorithm, a cross-region semantic association analysis algorithm based on a knowledge graph, etc.

[0048] In this embodiment, the digital twin model of the target new energy power station is accessed, the device connection relationship in the topological structure is parsed, and device metadata is associated, including the rated power of the doubly-fed induction generator and the MPPT curve characteristics of the photovoltaic inverter; at the same time, based on the original data stream with a sampling period of 10 ms stored in the historical operation database in the past 6 months, the device type feature pattern is extracted; through the probe program deployed on the edge node, the round-trip delay and jitter value of each communication link are collected in real time. When it is monitored that the network jitter value of the edge node exceeds 15 ms for 5 consecutive sampling periods, the decay factor β in the data cache window calculation formula is dynamically adjusted from 0.8 to 0.5, where the data cache window W dc The calculation formula is specifically expressed as:

[0049] W dc = α×(1―RTT / 100)+β×J

[0050] Among them, α and β respectively represent the attenuation factors of round-trip delay and jitter value, RTT represents round-trip delay, and J represents jitter value; the decoupling algorithm adopts a hierarchical decision tree algorithm, and splits the global data governance strategy into a wind turbine dedicated rule branch and a photovoltaic dedicated rule branch according to the device type classification mapping table. For the wind turbine branch, a vibration data processing rule set is extracted, and the vibration data processing rule set includes three-level wavelet denoising and peak detection based on a 3-second sliding window; for the photovoltaic branch, a dynamic baseline model of current data is generated.

[0051] S2: The edge node of the new energy power station receives the edge governance rule set, and performs a first governance operation on the original data obtained in real time by the power generation equipment. The first governance operation at least includes data cleaning and format standardization, and generates first-governed data.

[0052] Specifically, in S2, the edge node of the new energy power station receives the edge governance rule set sent from the cloud through a preset encrypted communication channel, and at the same time, through the data acquisition interface, obtains the original data stream from each power generation equipment in the new energy power station in real time. After receiving the edge governance rule set and obtaining the original data, the edge node processes the original data according to the edge governance rule set to perform the first governance operation to obtain the first-governed data, and the first-governed data is the data after the edge node of the new energy power station performs the first governance operation on the original data.

[0053] In a possible implementation manner, the first governance operation is executed through a first data processing channel that at least includes a data cleaning channel and a format standardization channel;

[0054] It should be noted that in the data cleaning channel, the edge node retrieves the device-level data cleaning rule library in the edge rule set, and implements differential processing of problems such as noise, outliers, and drift in the original data for different power generation equipment types;

[0055] In this embodiment, a sliding window-based filtering algorithm is applied to the wind turbine vibration data. The window size is dynamically adjusted between 20 and 50 sampling points according to the dynamic characteristics of the data, the step size is fixed at 5 sampling points, and in combination with the dynamic adjustment method of wavelet denoising coefficients, the db4 wavelet basis is selected, and the decomposition level is automatically selected between 3 and 5 layers according to the real-time signal-to-noise ratio. The denoising threshold DT is calculated by the formula, and is specifically expressed as:

[0056]

[0057] Among them, σ represents the estimated value of the noise standard deviation, and N is the length of the signal sequence;

[0058] For the current data of the PV inverter, a dynamic baseline correction algorithm is enabled under the start-stop conditions of the device. The baseline adjustment period is adaptively set according to the power change rate, with a period not greater than 1 second under fast-changing conditions and not greater than 10 seconds under steady-state conditions. At the same time, outlier detection is performed in combination with a threshold that dynamically floats according to ±3σ standard deviation;

[0059] In the format standardization channel, the edge node converts the data passing through the data cleaning channel into a predefined standard format according to the format conversion template in the edge governance rule set, and encapsulates it into a unified coding structure including device ID, high-precision timestamp, data value range, and quality flag bits;

[0060] In this embodiment, for Modbus RTU protocol data, the register address is mapped to a semantic label, the data sampling rate is set to 10Hz, and the value is normalized by a coefficient of 0.001; for IEC 61850 MMS messages, it is parsed into a device status tree structure, the timestamp accuracy reaches 1 millisecond, and a 4-bit encoding quality flag bit is used; for CAN bus data, the frame ID is parsed into a device operation instruction set, achieving a data compression rate of not less than 70%, and the original check bits are retained; all standardized data are encapsulated into a unified TLV coding structure.

[0061] In addition, in specific cases, when the network connection between the edge node and the central layer is unstable or data needs to be temporarily stored according to the preset edge governance rule set, the data processing pipeline will also include a local cache channel. In the local cache channel, the edge node implements hierarchical storage management according to the local cache policy in the edge governance rule set;

[0062] In this embodiment, the real-time data buffer adopts a circular buffer structure, and the dynamic window is adjusted to monitor the network round-trip delay with the central layer in real time every 200 milliseconds. Once the detected round-trip delay value exceeds 50 milliseconds, the cache window size for data transmission is automatically reduced by 20% to 40% to adapt to network congestion.

[0063] S3: According to the central processing logic set, perform a second governance operation on the first governance data received from the edge node. The second governance operation includes cross-layer timestamp synchronization calibration and data fusion processing to generate second governance data;

[0064] Specifically, in S3, the central node performs a second governance operation on the first governance data transmitted by each edge node according to the central processing logic set.

[0065] In a possible implementation manner, the second governance operation is performed through a second data processing channel that at least includes a timing alignment calibration channel and a multi-source data fusion channel;

[0066] It should be noted that in the timing alignment and calibration channel, the encoding structure in the first governance data is parsed according to the cross-level timing alignment rules in the central processing logic, a transmission delay topology map is constructed, and a hybrid clock synchronization mechanism is used to achieve high-precision alignment of the data. The transmission delay topology map is a manifestation form combining delay data and transmission paths. The hybrid clock synchronization mechanism includes at least one of the NTP protocol, the PTP protocol, and the Kalman filter algorithm;

[0067] In this embodiment, the NTP protocol is used to achieve preliminary clock synchronization at the millisecond level, ensuring that the error range is controlled within ±50 ms; the PTP protocol is introduced, and the hardware timestamp is used to record the time of the first governance data entering and leaving the edge node, regional node, and central processing node, achieving microsecond-level clock fine synchronization; according to the transmission delay topology map, a state space model of the Kalman filter algorithm is constructed to achieve timing compensation, the compensation coefficient is dynamically adjusted according to the transmission hop count, and the sliding window is used to statistically calculate the network jitter variance, dynamically updating the parameters of the Kalman filter, so as to control the timestamp deviation of the aligned data within ±10 ms;

[0068] Further, the state space model constructed based on the Kalman filter algorithm is specifically expressed as:

[0069]

[0070] Among them, represents the state vector at the k-th moment, including the delay information at the k-th moment, A represents the clock drift coefficient matrix, B represents the network delay weight matrix, and u k represents the network perturbation, and w k represents Gaussian white noise.

[0071] In the multi-source data fusion channel, according to the multi-source data fusion algorithm chain in the central processing logic, the data from the timing alignment and calibration channel is subjected to multi-source data fusion processing, and is encapsulated into the second governance data including quality assessment labels, processing metadata, and semantic association information. Among them, the metadata at least includes clock compensation coefficients, redundancy elimination identifiers, and knowledge graph inference paths.

[0072] Further, the multi-source data fusion processing includes: constructing a spatio-temporal correlation weighted model based on the device topology correlation degree, where the correlation degree weight is calculated by the exponential decay function of the electrical distance; using a clustering algorithm to eliminate redundant data, and the dynamic density parameter is dynamically set according to the data distribution mean and standard deviation; constructing a triple knowledge graph including device entities, operating states, and grid instructions, applying a graph neural network for semantic association analysis, and performing consistency verification of the device operation logic.

[0073] Furthermore, a device topology correlation matrix is constructed, and the electrical distance d between power generation device i and power generation device j ij is calculated as follows:

[0074] d ij = α d × L l + β d × |V i ― V j |

[0075] where L l represents the line length between power generation device i and power generation device j, V i and V j represent the voltages of power generation device i and power generation device j respectively, and α d , β d represent empirical coefficients respectively, which are used to balance the weights of line length and node voltage difference in the calculation of electrical distance. In this embodiment, α d = 0.6, β d = 0.4;

[0076] The calculation formula for the correlation weight w ij between power generation device i and power generation device j is as follows:

[0077]

[0078] where δ represents the slope factor, which takes a value of 0.5 in this embodiment, d max represents the maximum electrical distance between power generation device i and power generation device j, and d ij represents the electrical distance between power generation device i and power generation device j;

[0079] In this embodiment, an improved DBSCAN clustering algorithm is adopted, the dynamic density parameter is set, and for the data reported repeatedly within the preset time window, the sample with the highest confidence is retained; a triple knowledge graph including device entities, operating states, and grid commands is constructed, and a graph neural network is applied for state inference. By comparing the real-time data with the graph logic rules, when contradictions are found, the quality flag bit is triggered to be updated.

[0080] S4: Monitor the data quality indicators during the first governance operation and the second governance operation in real time, and compare the monitoring results with the preset quality threshold to generate the third governance data including the data quality evaluation result and the abnormal data traceability information;

[0081] Specifically, in S4, for the first governance operation performed at the edge layer, the system deploys lightweight quality probes that collect three core data quality indicators in real time. The data quality indicators include integrity indicators, accuracy indicators, and consistency indicators. For the second governance operation performed at the central layer, a hierarchical quality assessment mechanism is implemented. For the data quality assessment results that do not meet the quality assessment mechanism, abnormal data records with confidence annotations are generated.

[0082] In this embodiment, the integrity indicator is evaluated by verifying the missing rate of data fields, the proportion of null values, and the volatility of the data collection cycle. Verification is performed based on a preset rule library reflecting the physical characteristics of the device, and the data is predicted using a long short-term memory network model, and the deviation rate between the actual value and the predicted value is calculated to evaluate the accuracy of the data. The distributed time window algorithm is used to verify the consistency between the data of multiple devices with logical relevance within the same substation.

[0083] In a possible implementation manner, the hierarchical quality assessment mechanism includes: in the time series alignment and calibration channel, an NTP enhanced clock synchronization service is deployed to continuously monitor the time offset between each edge node and the central node, and it is required that the offset be controlled within a preset offset. In this embodiment, the preset offset is set to ±10 milliseconds. If synchronization failure or deviation exceeding the limit is detected, a resynchronization process with precise time scale compensation is automatically triggered to restore clock accuracy; in the multi-source data fusion channel, by constructing a metadata mapping model based on a knowledge graph, the pattern matching degree between the first governance data from different sources and initially governed is calculated in real time, and it is required that the score is not lower than the preset pattern matching degree. In this embodiment, the preset pattern matching degree is set to 0.85; at the same time, the semantic consistency is calculated, and it is required that the similarity score is not lower than the preset similarity score. In this embodiment, the preset similarity score is set to 0.9.

[0084] In a possible implementation manner, generating the third governance data includes: using the sliding window statistical technique to integrate the monitored data to generate a quality matrix of quantization indicators. The quality matrix of quantization indicators includes but is not limited to: field filling rate, number of rule violations, time series continuity score, data freshness, etc.; if any indicator in the quality matrix exceeds the preset threshold, the response mechanism is activated.

[0085] It should be noted that the response mechanism includes: automatically marking the abnormal data segment and generating a traceability information including the ID of the power generation device, the data flow path, and the time axis information of the processing link; locating the specific link causing the quality problem; generating a structured quality report, the content covering the severity level of the abnormality, the visual heat map of the problem impact range, and the specific repair suggestion plan.

[0086] S5: Dynamically adjust the global data governance strategy based on the third governance data, and accordingly update the edge governance rule set and the central processing logic set. Automatically trigger a preset abnormal data handling process according to the abnormal data traceability information.

[0087] Specifically, in S5, conduct a trial run on selected partial edge nodes based on the quality matrix and traceability information in the third governance data. Compare the difference in data governance efficiency between the repaired proposed solution in the third governance data and the original operating data governance efficiency. When the data governance efficiency reaches the preset target and operates stably, batch distribute the updated edge governance rule set and central processing logic set to all nodes through the differential upgrade protocol.

[0088] In a possible implementation manner, the preset abnormal data handling process includes: judging known abnormal data according to the traceability information in S4, and calling the corresponding handling solution from the preset system database to perform automatic repair; in this embodiment, for the detected timestamp out-of-step abnormality, automatically execute the operation process of "time scale compensation - data resampling - historical window repair"; when identifying new abnormal data according to the traceability information in S4, in the operating environment of the virtualized new energy power station, execute the preset general abnormal handling solution, evaluate the potential impact paths of the general abnormal handling solution on data quality and system stability, and select the solution with the least expected negative impact and the best repair effect for actual execution; if the traceability information in S4 points to a hardware-level fault, automatically generate an equipment maintenance work order containing accurate three-dimensional positioning coordinates and synchronize it to the power station operation and maintenance personnel in real time.

[0089] Secondly: In the attached drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments of the present disclosure are involved. Other structures can refer to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0090] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A multi - level governance method for real - time data of power generation equipment in a new energy power station, characterized in that, Including: S1: Generate a mutually cooperative edge governance rule set and a central processing logic set according to a preset global data governance strategy, and send the edge governance rule set to the corresponding new energy power station edge nodes; S2: The new energy power station edge nodes receive the edge governance rule set and perform a first governance operation on the raw data obtained in real time by the power generation equipment. The first governance operation at least includes data cleaning and format standardization to generate first-governed data; S3: According to the central processing logic set, perform a second governance operation on the first-governed data received from the edge nodes. The second governance operation includes cross-layer timestamp synchronization calibration and data fusion processing to generate second-governed data; S4: Real-time monitor the data quality indicators in the process of the first governance operation and the second governance operation, and compare the monitoring results with the preset quality thresholds to generate third-governed data including data quality assessment results and abnormal data traceability information; S5: Dynamically adjust the global data governance strategy based on the third-governed data, and accordingly update the edge governance rule set and the central processing logic set. According to the abnormal data traceability information, automatically trigger a preset abnormal data handling process.

2. The multi-level governance method for real-time data of power generation equipment in a new energy power station according to claim 1, wherein: In S1, the preset global data governance strategy includes an equipment type hierarchical mapping table, a data quality target matrix, and network status perception rules.

3. A multi-level governance method for real-time data of power generation equipment in a new energy power station according to claim 1, characterized in that: In S2, the first governance operation specifically includes: Execute through a first data processing channel that at least includes a data cleaning channel and a format standardization channel; Among them, the data cleaning channel implements differential processing according to the device-level data cleaning rule library in the edge governance rule set for data of different power generation equipment types. The algorithms for the differential processing include at least one of a sliding window-based filtering algorithm, a wavelet denoising coefficient dynamic adjustment method, and a dynamic baseline correction algorithm under device start-stop conditions; And, the format standardization channel converts the data from the data cleaning channel into a predefined standard format according to the format conversion template in the edge governance rule set and encapsulates it into a unified coding structure including device ID, high-precision timestamp, data value range, and quality flag bits.

4. A multi-level governance method for real-time data of power generation equipment in a new energy power station according to claim 1, characterized in that: In S3, the second governance operation specifically includes: Execute through a second data processing channel that at least includes a timing alignment calibration channel and a multi-source data fusion channel; Among them, the timing alignment calibration channel constructs a transmission delay topology map according to the cross-layer timing alignment rules in the central processing logic set for the coding structure of the first-governed data and uses a hybrid clock synchronization mechanism to achieve data alignment. The hybrid clock synchronization mechanism includes at least one of the NTP protocol, the PTP protocol, and the Kalman filtering algorithm; And, the multi-source data fusion channel performs multi-source data fusion processing on the data from the timing alignment calibration channel according to the multi-source data fusion algorithm chain in the central processing logic set and encapsulates it into second-governed data including quality assessment tags, processing metadata, and semantic association information.

5. A multi-level governance method for real-time data of power generation equipment in a new energy power station according to claim 4, characterized in that: In S3, the metadata at least includes a clock compensation coefficient, a redundancy elimination identifier, and a knowledge graph inference path.

6. The multi-level governance method for real-time data of power generation equipment in a new energy power station according to claim 1, characterized in that: S3, multi-source data fusion processing, specifically including: Construct a spatio-temporal correlation weighted model based on the device topology correlation degree, where the correlation degree weight is calculated by the exponential decay function of the electrical distance, specifically expressed as: where δ is expressed as the slope factor, d max is expressed as the maximum electrical distance between power generation equipment i and power generation equipment j, d ij is expressed as the electrical distance between power generation equipment i and power generation equipment j; Adopt a clustering algorithm to implement redundant data elimination; Construct a triple knowledge graph containing device entities, operating states, and grid instructions, apply graph neural networks for semantic association analysis, and perform consistency verification of device operation logic.

7. A multi-level governance method for real-time data of power generation equipment in a new energy power station according to claim 1, characterized in that: In S4, the abnormal data traceability information at least includes the power generation equipment ID, data flow path, and processing link time axis information.

8. A multi-level governance method for real-time data of power generation equipment in a new energy power station according to claim 1, characterized in that: S5, a preset abnormal data handling process, specifically including: For the abnormal data determined to be known according to the abnormal data traceability information, call the corresponding handling solution from the preset system database to perform automatic repair; For the abnormal data identified as new according to the abnormal data traceability information, execute the preset general handling solution, evaluate the impact of the general handling solution, and select the solution with the best repair effect to execute; And, for the case determined to be a hardware-level fault according to the abnormal data traceability information, automatically generate a device maintenance work order containing location information and synchronize it to the operation and maintenance personnel.

Images