Energy power data asset assessment method based on artificial intelligence

Abstract

The invention relates to an artificial intelligence-based energy power data asset assessment method. The method comprises the following steps of S1, acquiring multi-source heterogeneous data of an energy power industry; s2, constructing a database based on a time sequence database and distributed storage, and storing multi-source heterogeneous data; s3, constructing an energy knowledge graph according to the multi-source heterogeneous data; s4, constructing a multi-dimensional value evaluation model, and quantifying the economic benefit, the quality index, the use condition and the potential mining capability of the data assets; and S5, establishing a dynamic monitoring system, and performing real-time evaluation on the full life cycle value of the data assets based on the multi-dimensional value evaluation model and the energy knowledge graph. According to the invention, the utilization efficiency of energy data assets is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of data management, and particularly to an artificial intelligence-based method for evaluating the assets of energy and power data. Background Art

[0002] With the rapid development of the energy Internet and smart grids, the energy and power industry is facing the challenges of the rapid growth of massive data and diverse demands. There are multiple data sources in the energy system, including on-site equipment operation data, SCADA (Supervisory Control and Data Acquisition) system data, historical record data, as well as market transaction data and external environment data (such as meteorological information and policy dynamics). These data types exhibit the characteristics of multi-source heterogeneity, temporal dynamics, and complex correlation, making traditional data management and value evaluation techniques difficult to meet current requirements.

[0003] On the one hand, the integration and processing of multi-source heterogeneous data are difficult, and there are problems such as semantic inconsistency, different formats, and quality differences among data, resulting in low data utilization. On the other hand, traditional data evaluation methods usually only focus on a single dimension (such as efficiency or quality), and cannot comprehensively quantify the comprehensive value of data in terms of economic benefits, quality indicators, scenario adaptation, and potential mining. In addition, due to the strong time sensitivity and dynamic change characteristics of data in the energy and power system, it is difficult to grasp the full life cycle performance of data assets in a timely manner solely relying on static analysis means, and it is even more impossible to discover data problems in real time or optimize potentially high-value data. Summary of the Invention

[0004] In order to solve the above problems, the purpose of the present invention is to provide an artificial intelligence-based method for evaluating the assets of energy and power data, which can not only evaluate the full life cycle value of data in real time, but also provide automated problem repair and optimization suggestions, thereby significantly improving the utilization efficiency of energy data assets.

[0005] To achieve the above object, the present invention adopts the following technical solutions: An artificial intelligence-based method for evaluating the assets of energy and power data, comprising the following steps: S1: Obtain multi-source heterogeneous data in the energy and power industry, including on-site equipment data, SCADA system data, historical record data, market and external data; S2: Build a database based on a time series database and distributed storage to store multi-source heterogeneous data; S3: According to the multi-source heterogeneous data, build an energy knowledge graph, model equipment associations, energy process chains, and market change information as a knowledge graph to provide context-enhanced information; S4: Build a multi-dimensional value evaluation model to quantify the economic benefits, quality indicators, usage, and potential mining capabilities of data assets; S5: Establish a dynamic monitoring system to conduct real-time evaluation on the value of the entire life cycle of data assets based on the multi-dimensional value evaluation model and the energy knowledge graph.

[0006] Furthermore, the on-site device data includes sensor data, smart meters, and relay protection device data; the SCADA system data includes power grid dispatching, equipment operation status, and accident alarm data; the market and external data includes electricity market prices, load forecasting data, policy documents, climate, and environmental data; the historical record data includes historical electricity consumption behaviors and equipment operation and maintenance logs.

[0007] Furthermore, the database adopts a hierarchical storage design for hot and cold data. The time-series database is used to store high-frequency and real-time time-series data; the distributed storage is used to store large-scale and low-frequency accessed historical data; In the time-series database, data is partitioned according to time and device ID; In the distributed storage, data is partitioned and stored according to time and type; The built-in compression algorithm of the time-series database is adopted for time-series data to save storage space; Hot data, that is, the data in the time-series database, is regularly migrated to the distributed storage, and the automated migration process is implemented through Apache Nifi.

[0008] Furthermore, the energy knowledge graph is as follows: Let the node set V = {v1, v2, …, v i ,..., v n}, where v i is the i-th entity, and the number of entities is n. The node types include: device node v device , market node v market , process node v process , and external environment node v env ; The edges represent the relationships between entities, including the connection relationships between devices, the sequential relationships of process chains, and the influence relationships between market dynamics and device operations. Define the edge set as E: ; where e m =(v a , v b , r) represents the relationship r connecting entities v a and v b ; The relationship classification of the edges: the connection relationship between devices r connect ; the sequential relationship of the process chain r process ; the relationship between the market and the device r market ; the relationship between the environment and the processenv ; The attributes of relationship r include: transmission capacity C, time attribute T, and directivity attribute D; The energy knowledge graph is modeled by a directed attributed graph G: ; where V is the set of nodes in the graph; E is the set of edges in the graph; A V is the set of attributes of the nodes; A E is the set of attributes of the edges; The directed attributed graph G includes the following subgraphs: The device association subgraph G device , corresponding to the physical connections and logical relationships between devices: ; where V device represents device nodes, E connect represents the physical connection relationships between devices; A device represents the attributes of device nodes, A connect represents the attributes of the physical connections between devices; The energy process chain subgraph G process , modeling the links of energy flow: ; where E process represents the sequence of processes, A flow represents the power values of the participating nodes in the links; A process represents the attributes of the process nodes; V process represents the process nodes; The market change subgraph G market , representing the association between market rules, price fluctuations, and the physical system: ; where V market represents market nodes; E market represents the association relationship between market changes and device operations; A price is the characteristic factor of market price changes; A policy is the set of policy attributes; The meteorological impact subgraph G env , representing the association between meteorology and device operations: ; where V env is the external environment node; E impact represents the impact relationship of meteorological conditions on devices or processes; A weather is the set of gas attributes; A env is the set of environmental impact attributes; The energy process chain path is inferred through the path in the figure: ;

[0009] Among them, P is the path; v j represents node j; v k represents node k; e ij represents node v i and v j 's edge; e jk represents node v j and v k 's edge; The path weight W p is expressed as the rated power loss of each link in the process: ;

[0010] Among them, f loss is defined as the function used to calculate the power loss between devices.

[0011] Furthermore, the multi-dimensional value evaluation model G P , specifically as follows: ; Among them: G eco is the economic benefit sub-model; G qual is the quality index sub-model; G util is the usage situation sub-model; G pot is the potential mining ability sub-model; is the weighting model; The economic benefit sub-model is specifically: ;

[0012] Among them, E rev , E cost , E fit are the revenue increase, cost savings, and key scenario matching degree respectively; R t represents the revenue brought by data support in scenario t; , are the costs before and after the optimization of the th data respectively; , are the scenario contribution data volume and the total data volume respectively; w1, w2, w3 are weight coefficients; T is the total number of scenarios; is the total data volume; The quality index sub-model is specifically:

[0013] Among them, Q acc 、Q comp 、Q cons are data accuracy, data integrity, and data consistency respectively; is the th measured value; is the predicted value; is the amount of missing data; is the amount of data that is time or logically consistent; w4, w5, w6 are weight coefficients; The usage situation sub-model is specifically:

[0014] Among them, U freq 、U scen 、U depth are access frequency, scenario coverage, and usage depth respectively; is the total number of accesses; is the evaluation period; is the number of usage scenarios; is the total number of supported scenarios; is the number of data fields utilized; is the number of available data fields; w7, w8, w9 are weight coefficients; The potential mining ability sub-model, ; Among them, P ext 、P reuse 、P market are scalability, reuse value, and reuse value respectively; w 10 、w 11 、w 12 are weight coefficients.

[0015] Furthermore, the dynamic monitoring system includes a data stream collection and storage module, a model evaluation and calculation module, a knowledge graph collaboration module, and a feedback optimization module; The data stream collection and storage module accesses data sources through Apache Kafka or Flink, including device operation status, market fluctuation information, energy process chain monitoring information, and meteorological data; and performs preliminary cleaning and verification; The model evaluation and calculation module uses a multi-dimensional value evaluation model to evaluate the value of data, and performs value calculation and analysis through a periodic and event-triggered mechanism; dynamically calls the knowledge graph to assist in inferring and calculating values; The knowledge graph collaboration module derives the intrinsic value or problems of data through the association relationships between entity nodes, obtains the nodes that need to be repaired or optimized, and corrects or optimizes the data.

[0016] Furthermore, the intrinsic value or problems of the data are deduced through the association relationships between entity nodes, as follows: The intrinsic value or problems of a node are deduced through the association relationships and attribute weights between nodes. For a target node v i , its intrinsic value V value (v i ) is deduced through the influence of its neighbor nodes: ; where w(v i, v j ) is the relationship weight between node v i and v j ; is the attribute value of neighbor node v j ; represents the neighbor nodes of v i ; If there are abnormal problems with the target node v i , the problems of the target node v i are deduced through the association relationships of its neighbor nodes : ; where is the attribute difference function, used to judge the abnormal difference between the attributes of node v i and v j ; The node association weight is dynamically adjusted according to the time attribute and the transmission capacity C : ; where is the initial weight; is the time-related weight function; is the transmission capacity-related weight function.

[0017] Furthermore, the nodes that need to be repaired or optimized are obtained, and the data is corrected or optimized, as follows: For the missing data or abnormal problems of nodes, neighbor nodes are used for data inference and repair: ; where A fixed (v i ) is the repaired attribute value; Transmission path optimization, based on the sub-diagram of the energy process chain Gprocess , find the optimal path to minimize power loss : ; where P loss (e) is the power loss value on edge e; Node load balancing, for nodes with transmission load higher than the threshold, reallocate the power flow: ; where P surplus (v j ) is the remaining power that the neighbor node v j can reallocate to v i ; P redistribute (v i ) is the power flow that node v i can regain through neighbor nodes.

[0018] The present invention has the following beneficial effects: 1. The present invention can not only perform real-time evaluation on the full life cycle value of data, but also provide automated problem repair and optimization suggestions, thus significantly improving the utilization efficiency of energy data assets; 2. The present invention constructs an energy knowledge graph based on multi-source heterogeneous data. Through the device association sub-graph, energy process chain sub-graph, market change sub-graph, and meteorological impact sub-graph, it can comprehensively model the complex relationships of device connections, energy process chains, market dynamics, and environmental impacts in the energy system, providing support for the optimization and analysis of the energy system; 3. The multi-dimensional value evaluation model of the present invention provides a comprehensive value quantification method for data assets in the energy and power industry by combining four dimensions of economic benefits, data quality, usage, and potential mining ability; and by combining the multi-dimensional value evaluation model with the energy knowledge graph, the dynamic monitoring mechanism realizes real-time value evaluation of the entire life cycle of data assets, and uses the reasoning ability of the knowledge graph to assist in evaluation and repair, which will further improve the accuracy, real-time performance, and potential value mining ability of data. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is the flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0020] The following further describes the present invention in detail with reference to the attached Figure 1 drawings and specific embodiments: An artificial intelligence-based method for evaluating energy and power data assets includes the following steps: S1: Obtain multi-source heterogeneous data in the energy and power industry, including on-site equipment data, SCADA system data, historical record data, market and external data; S2: Build a database based on a time-series database and distributed storage to store multi-source heterogeneous data; S3: Build an energy knowledge graph according to the multi-source heterogeneous data, model equipment associations, energy process chains, and market change information as a knowledge graph to provide context-enhanced information; S4: Build a multi-dimensional value evaluation model to quantify the economic benefits, quality indicators, usage, and potential mining capabilities of data assets; S5: Establish a dynamic monitoring system to perform real-time evaluation of the full-life cycle value of data assets based on the multi-dimensional value evaluation model and the energy knowledge graph.

[0021] In this embodiment, the on-site equipment data includes sensor data (such as voltage, current, frequency, etc.), smart meters, and relay protection device data; the SCADA system data includes power grid dispatching, equipment operation status, and accident alarm data; the market and external data includes electricity market prices, load forecasting data, policy documents, climate, and environmental data; the historical record data includes electricity consumption behavior history and equipment operation and maintenance logs.

[0022] In this embodiment, the database adopts a cold and hot data hierarchical storage design. The time-series database is used to store high-frequency and real-time time-series data (such as sensor data and load curves); the distributed storage is used to store large-scale and low-frequency accessed historical data (such as equipment operation logs and policy documents); In the time-series database, the data is partitioned according to time and device ID; In the distributed storage, the data is partitioned and stored according to time and type (such as by year and device type in directories); The built-in compression algorithm of the time-series database is used for time-series data to save storage space; Regularly migrate the hot data, that is, the data in the time-series database, to the distributed storage, and implement an automated migration process through Apache Nifi.

[0023] In this embodiment, the energy knowledge graph is as follows: Let the nodes V = {v1, v2,..., v i ,..., v n}, where v i is the i-th entity, the number of entities is n, and the node types include: Equipment node v device : Power generation equipment, power transmission equipment, power consumption equipment, etc.; Market node v market: Electricity market prices, policy rules, load forecasting results; Process node v process : Process links indicating the energy flow direction; External environment node v env : Meteorological data (such as temperature, wind speed) and other environmental impact factors; Edges represent the relationships between entities, including the connection relationships between devices, the sequential relationships in the process chain, the impact relationships between market dynamics and device operations. Define the edge set as E: ; Where e m =(v a , v b , r) represents the relationship r connecting entities v a and v b ; Edge relationship classification: Connection relationship r between devices connect : Such as "relay protection device connects to transformer"; Sequential relationship r in the process chain process : Such as "transmission equipment belongs to a specific power grid area"; Relationship r between market and device market : Such as "market price fluctuations affect device load"; Relationship r between environment and process env : Such as "temperature changes affect transmission power"; The attributes of relationship r include: transmission capacity C, such as the power transmission capacity between devices; time attribute T indicating the time when the relationship occurs (such as seasonal or real-time impact); directional attribute D, for example, the energy flow direction; The energy knowledge graph is modeled by a directed attributed graph G: ; Where, V: the set of nodes in the graph; E: the set of edges in the graph; A V The set of attributes of nodes; A E The set of attributes of edges; The directed attributed graph G includes the following subgraphs: Device association subgraph G device , corresponding to the physical connections and logical relationships between devices: ; Where, V device represents device nodes, E connect represents device physical connection relationships; A device represents device node attributes, A connect represents the attributes of device physical connections; Sub - diagram G of the energy process chain process , modeling the link of energy flow: ; Among them, E process represents the sequence of the process, and A flow represents the power value of the participating nodes in the link; A process represents the attribute of the process node; V process represents the process node; Sub - diagram G of market changes market , representing the association between market rules, price fluctuations and the physical system: ; Among them, V market represents the market node; E market represents the association relationship between market changes and equipment operation; A price is the characteristic factor of market price change; A policy policy attribute set; Sub - diagram G of meteorological influence env , representing the association between meteorology and equipment operation: ; Among them, V env is the external environment node; E impact represents the influence relationship of meteorological conditions on equipment or process; A weather is the gas attribute set; A env environmental impact attribute set; The energy process chain path is inferred through the paths in the diagram: ; Among them, P is the path; v j represents node j; v k represents node k; e ij represents the edge between node v i and v j ; e jk represents the edge between node v j and v k ; Path weight W p represents the rated power loss of each link in the process: ; Among them, f loss is defined as the function used to calculate power loss between devices.

[0024] In this embodiment, the multi - dimensional value evaluation model G P , is specifically as follows: ; Among them: G eco is the economic benefit sub - model; G qual is the quality index sub - model; G util is the usage situation sub - model; G pot is the potential mining ability sub - model; is the weighted model; The economic benefit sub - model is specifically:

[0025] Among them, E rev , E cost , E fit are the revenue increase, cost savings and key scenario matching degree respectively; R t represents the revenue brought by data support in scenario t; , are the costs before and after the optimization of the th data respectively; , are the amount of scenario - contributing data and the total amount of data respectively; w1, w2, w3 are weight coefficients; T is the total number of scenarios; is the total amount of data; The quality index sub - model is specifically:

[0026] Among them, Q acc , Q comp , Q cons are data accuracy, data integrity and data consistency respectively; is the th measured value; is the predicted value; is the amount of missing data; is the amount of data with time or logical consistency; w4, w5, w6 are weight coefficients; The usage situation sub - model is specifically:

[0027]

[0028] Among them, U freq , U scen , U depth are access frequency, scenario coverage and usage depth respectively; is the total number of accesses; is the evaluation period; is the number of usage scenarios; is the total number of supportable scenarios; is the number of data fields utilized; is the number of data available fields; w7, w8, and w9 are weight coefficients; The potential mining ability sub-model

[0029] Among them, P ext , P reuse , P market are scalability, reuse value, and reuse value respectively; w 10 , w 11 , w 12 are weight coefficients.

[0030] In this embodiment, the dynamic monitoring system includes a data stream collection and storage module, a model evaluation and calculation module, a knowledge graph collaboration module, and a feedback optimization module; The data stream collection and storage module accesses data sources through Apache Kafka / Flink, including device operating status, market fluctuation information, energy process chain monitoring information, and meteorological data; and performs preliminary cleaning and verification; The model evaluation and calculation module uses a multi-dimensional value evaluation model to evaluate the value of data, and performs value calculation and analysis through a periodic and event-triggered mechanism; dynamically calls the knowledge graph to assist in inferring and calculating values; The knowledge graph collaboration module deduces the intrinsic value or problems of data through the association relationships between entity nodes, obtains the nodes that need to be repaired or optimized, and corrects or optimizes the data.

[0031] In this embodiment, the intrinsic value or problems of data are deduced through the association relationships between entity nodes, as follows: The intrinsic value or problems of a node are deduced through the association relationships and attribute weights between nodes. For a target node v i , its intrinsic value V value (v i ) is deduced through the influence of neighbor nodes: ;

[0032] Among them, w(v i, v j ) is the relationship weight between node v i and v j ; is the attribute value of neighbor node v j ; represents the neighbor nodes of v i ; If there are abnormal problems with the target node v i , the target node v is deduced through the association relationships of neighbor nodesi problem : ; Among them, is an attribute difference function used to judge the abnormal difference between the attributes of nodes v i and v j ; Dynamically adjust the node association weight according to the time attribute and the transmission capacity C: : ; Among them, is the initial weight; is a time-related weight function; is a transmission capacity-related weight function.

[0033] In this embodiment, nodes that need to be repaired or optimized are obtained, and the data is corrected or optimized as follows: For the missing data or abnormal problems of nodes, use neighbor nodes for data inference and repair: ; Among them, A fixed (v i ) is the repaired attribute value; Transmission path optimization, based on the sub-graph of the energy process chain G process , find the optimal path to minimize power loss : ; Among them, P loss (e) is the power loss value on edge e; Node load balancing, for nodes with a transmission load higher than the threshold, reallocate the power flow: ; Among them, P surplus (v j ) is the remaining power that the neighbor node v j can reallocate to v i ; P redistribute (v i ) is the power flow that node v i can regain through neighbor nodes; Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0034] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0035] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0036] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0037] As described above, it is only the preferred embodiments of the present invention, and the present invention is not limited to other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the technical solution content of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An artificial intelligence-based method for evaluating the assets of energy and power data, characterized in that It includes the following steps: S1: Obtain multi-source heterogeneous data in the energy and power industry, including on-site equipment data, SCADA system data, historical record data, market and external data; S2: Build a database based on a time-series database and distributed storage to store multi-source heterogeneous data; S3: Build an energy knowledge graph according to the multi-source heterogeneous data, model equipment associations, energy process chains, and market change information as a knowledge graph to provide context-enhanced information; S4: Build a multi-dimensional value evaluation model to quantify the economic benefits, quality indicators, usage, and potential mining capabilities of data assets; S5: Establish a dynamic monitoring system to perform real-time evaluation of the full life cycle value of data assets based on the multi-dimensional value evaluation model and the energy knowledge graph.

2. The method for evaluating the assets of energy and power data based on artificial intelligence according to claim 1, wherein The on-site equipment data includes sensor data, smart meters, and relay protection device data; the SCADA system data includes power grid dispatching, equipment operation status, and accident alarm data; the market and external data includes electricity market prices, load forecasting data, policy documents, climate, and environmental data; the historical record data includes historical electricity consumption behavior and equipment operation and maintenance logs.

3. The method for evaluating the assets of energy and power data based on artificial intelligence according to claim 1, wherein, The database adopts a hot and cold data hierarchical storage design. The time-series database is used to store high-frequency and real-time time-series data; the distributed storage is used to store large-scale and low-frequency accessed historical data; In the time-series database, data is partitioned according to time and device ID; In the distributed storage, data is partitioned and stored according to time and type; The built-in compression algorithm of the time-series database is used for time-series data to save storage space; Hot data, that is, the data in the time-series database, is regularly migrated to the distributed storage, and the automated migration process is implemented through Apache Nifi.

4. The method for evaluating the assets of energy and power data based on artificial intelligence according to claim 1, wherein The energy knowledge graph is as follows: Let the set of nodes be \(V = \{v_1, v_2, \ldots, v i , \ldots, v n \}\), where \(v i \) is the \(i\)-th entity, the number of entities is \(n\), and the node types include: device node \(v device \), market node \(v market \), process node \(v process \), external environment node \(v env \); Edges represent the relationships between entities, including the connection relationships between devices, the sequential relationships of process chains, and the impact relationships between market dynamics and equipment operations. Define the edge set as E: E = {e1, e2, …, e m,... , e M}; where e m =(v a ,v b ,r) represents the relationship r connecting entities v a and v b ; Relationship classification of edges: Connection relationship r between devices connect ; Sequential relationship r of process chains process ; Relationship r between market and devices market ; Relationship r between environment and processes env ; The attributes of the relationship r include: transmission capacity C, time attribute T, and directionality attribute D; The energy knowledge graph is modeled through a directed attributed graph G: G=(V,E,A V ,A E ); Among them, V: the set of nodes in the graph; E: the set of edges in the graph; A V the set of attributes of the nodes; A E Set of edge attributes; The directed attributed graph G includes the following subgraphs: Device Association Subgraph G device , the physical connections and logical relationships between corresponding devices: G device =(V device ,E connect ,A device ,A connect ); Among them, V device represents the device node, and E connect represents the physical connection relationship of the devices; A device represents the device node attributes, and A connect represents the attributes of the physical connection of the devices; Sub-diagram G of the energy process chain process , modeling the links of energy flow: G process =(V process ,E process ,A process ,A flow ); Among them, E process represents the sequence of the process, A flow represents the power value of the participating nodes in the link; A process represents the attribute of the process node; V process represents the process node; Market change sub - graph G market , indicating the association between market rules, price fluctuations and physical systems: G market = (V market , E market , A price , A policy ); Among them, V market represents a market node; E market represents the correlation between market changes and equipment operation; A price is the characteristic factor of market price change; A policy is the set of policy attributes; Meteorological influence sub - figure G env , indicating the association between meteorology and equipment operation: G env =(V env ,E impact ,A weather ,A env ); Among them, V env is an external environmental node; E impact represents the influence relationship of meteorological conditions on equipment or processes; A weather is a set of gas attributes; A env Set of environmental impact attributes; The energy process chain path is inferred through the path in the graph; ； Among them, P is the path; v j represents node j; v k represents node k; e ij represents node v i and v j 's edge; e jk represents node v j and v k 's edge; Path weight W p Expressed as the rated power loss for each link in the process: ； where f loss is defined as a function for calculating power loss in the equipment room.

5. The method for evaluating the assets of energy and power data based on artificial intelligence according to claim 1, wherein The multi-dimensional value evaluation model G P , is specifically as follows: G P = f(G eco , G qual , G util , G pot ); Among them: G eco is the economic benefit sub-model; G qual is the quality index sub-model; G util is the usage situation sub-model; G pot is the potential mining capacity sub-model; is the weighted model; The economic benefit sub-model is specifically: G eco = w1E rev + w2E cost + w3E fit ; ； ； ； Among them, E rev , E cost , E fit are the revenue increase, cost savings, and key scenario matching degree respectively; R t represents the revenue brought by data support in scenario t; , are the costs before and after the optimization of the th data respectively; , are the scenario contribution data volume and the total data volume respectively; w1, w2, and w3 are weight coefficients; T is the total number of scenarios; is the total data volume; The quality indicator sub-model is specifically: G qual = w4Q acc + w5Q comp + w6Q cons ; ； ； ； Among them, Q acc , Q comp , Q cons are data accuracy, data integrity, and data consistency respectively; is the th measured value; is the predicted value; is the amount of missing data; is the amount of data that is time or logically consistent; w4, w5, w6 are weighting coefficients; The usage sub-model is specifically: G util =w7U freq +w8U scen +w9U depth ; ； Among them, U freq , U scen , U depth are the access frequency, scenario coverage, and usage depth respectively; is the total number of accesses; is the evaluation period; is the number of usage scenarios; is the total number of supported scenarios; is the number of data fields utilized; is the number of available data fields; w7, w8, w9 are weight coefficients; The potential mining ability sub-model G pot = w 10 P ext + w 11 P reuse + w 12 P market ; Among them, P ext , P reuse , P market are extensibility, reuse value, and reuse value respectively; w 10 , w 11 , w 12 are weight coefficients.

6. The method for evaluating the assets of energy and power data based on artificial intelligence according to claim 5, wherein The dynamic monitoring system includes a data stream collection and storage module, a model evaluation and calculation module, a knowledge graph collaboration module, and a feedback optimization module; The data stream collection and storage module accesses data sources through Apache Kafka or Flink, including equipment operation status, market fluctuation information, energy process chain monitoring information, and meteorological data; And perform preliminary cleaning and verification; The model evaluation and calculation module uses the multi-dimensional value evaluation model to evaluate the value of data, and performs value calculation and analysis through periodic and event-triggered mechanisms; dynamically calls the knowledge graph to assist in realizing the inference calculation of values; The knowledge graph collaboration module derives the intrinsic value or problems of data through the association relationships between entity nodes, obtains the nodes that need to be repaired or optimized, and corrects or optimizes the data.

7. The method for evaluating the assets of energy and power data based on artificial intelligence according to claim 6, wherein The derivation of the intrinsic value or problems of data through the association relationships between entity nodes is as follows: Derive the intrinsic value or problem of a node based on the association relationship and attribute weights between nodes, for a target node v i , whose intrinsic value V value (v i ) is derived through the influence of neighbor nodes: ; Among them, w(v i, v j ) is the relationship weight between nodes v i and v j ; is the attribute value of neighbor node v j ; represents the neighbor nodes of v i ; If the target node v i has an abnormal problem, deduce the problem of the target node v i through the association relationship of neighbor nodes : ； Among them, is an attribute difference function used to judge the abnormal difference between the attributes of node v i and v j ; Adjust the node association weight dynamically according to the time attribute and the transmission capacity C : ； Among them, w0(v i , v j ) is the initial weight; is the time-related weight function; f C (C) is the transmission capacity-related weight function.

8. The method for evaluating energy and power data assets based on artificial intelligence according to claim 7, wherein The obtaining of the nodes that need to be repaired or optimized and the correction or optimization of the data are as follows: For the missing data or abnormal problems of nodes, neighbor nodes are used for data inference and repair: ； Among them, A fixed (v i ) is the repaired attribute value; Transmission path optimization, based on the sub-diagram G of the energy process chain process , find the optimal path to minimize power loss :[[]]END]] ； Among them, P loss (e) is the power loss value on edge e; Node load balancing. For nodes with a transmission load higher than the threshold, the power flow is reallocated: ； Among them, P surplus (v j ) is the remaining power that can be reassigned to neighbor node v j ; P i (v redistribute ) is the power flow that node v i can regain through neighbor nodes. i ​

Images