Graph database construction method and system based on electric power data

Abstract

The invention provides a graph database construction method and system based on electric power data. The method comprises the following steps: taking an electric power dispatching center, power generation equipment, electric power equipment and electric power users as graph nodes; establishing a node edge between the power dispatching center and the corresponding power generation equipment, and establishing a first node edge according to a cooperative relationship between the power generation equipment under the power dispatching center to obtain a first sub-graph; establishing a node edge between the target power generation equipment and the corresponding power equipment, establishing a second node edge according to the association degree between the power equipment under the target power generation equipment, and constructing a second sub-graph; establishing a node edge between the target power equipment and the corresponding power user, establishing a third node edge according to the similarity degree between the power users under the target power equipment, and constructing a third sub-graph; and constructing a graph database of the power dispatching center according to the first sub-graph, the second sub-graph and the third sub-graph of the power dispatching center. The stability and reliability of data processing of the whole power system are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for constructing a graph database based on power data. Background Art

[0002] In the operation and management of power systems, the effective organization and utilization of power data is crucial. With the acceleration of power informatization, a large amount of power data is collected and stored.

[0003] The existing methods for building power databases are mainly based on the traditional relational database model. The relational database model is relatively fixed and has poor adaptability to the ever-changing business needs and data structures in the power system. For example, when the power network is upgraded, new types of power equipment are added, or the connection relationship between equipment is changed, the table structure of the database needs to be complexly modified, which can easily introduce data inconsistency errors. Secondly, there are extensive connections between power data, such as the electrical connection relationship between equipment and equipment, the power supply relationship between equipment and users, etc. Querying these related data in a relational database often requires multi-table join operations. As the amount of data increases, the performance of this multi-table join operation will drop sharply, resulting in a long query response time. Furthermore, relational databases are not scalable enough for the storage and management of large-scale power data. When power data grows exponentially, relational databases face challenges in hardware resource expansion and data distribution processing, and are prone to system bottlenecks.

[0004] Therefore, the existing power database construction methods are difficult to efficiently handle the complexity, dynamics and large scale of power data, affecting the stability and reliability of data processing in the entire power system. Summary of the invention

[0005] The present invention provides a method and system for constructing a graph database based on power data, so as to efficiently process the complexity, dynamics and large scale of power data and improve the stability and reliability of data processing in the entire power system.

[0006] In a first aspect, the present invention provides a method for constructing a graph database based on power data, comprising:

[0007] Collect the power generation equipment, power equipment and power users under the power dispatching center in the power system, and use the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center as graph nodes;

[0008] Establishing a node edge between the power dispatching center and its corresponding power generation equipment, and establishing a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center, to obtain a first subgraph;

[0009] Establishing a node edge between a target power generation device and its corresponding electric power device, and establishing a second node edge according to the degree of association between the electric power devices under the target power generation device, to construct a second subgraph; the target power generation device is any power generation device in the electric power dispatching center;

[0010] Establishing a node edge between a target power device and its corresponding power user, and establishing a third node edge according to the similarity between the power users under the target power device, to construct a third subgraph; the target power device is any power device of the target power generation device;

[0011] A graph database of the electric power dispatching center is constructed according to the first subgraph, the second subgraph and the third subgraph of the electric power dispatching center.

[0012] According to the method for constructing a graph database based on power data provided by an embodiment of the present invention, the first node edge is established according to the collaborative relationship between power generation equipment under the power dispatching center to obtain a first subgraph, including:

[0013] Obtain the power generation power of any two power generation equipment under the power dispatching center at the target time within the preset observation time period, the most recent start-stop time interval of any two power generation equipment, and the regulation rate of any two power generation equipment;

[0014] Calculate the synergy coefficient between any two power generation equipment according to the power generation of any two power generation equipment at the target time, the most recent start-stop time interval and the regulation rate;

[0015] If the synergy relationship coefficient between any two power generation devices is greater than or equal to a preset synergy relationship threshold, a first node edge between any two power generation devices is established to obtain the first subgraph.

[0016] According to the method for constructing a graph database based on power data provided by an embodiment of the present invention, the calculation formula for the synergy relationship coefficient between any two power generation devices is as follows:

[0017]

[0018] Among them, S GG (g i ,g j ) represents the synergy coefficient between the i-th power generation equipment and the j-th power generation equipment, gi represents the i-th power generation equipment, g j represents the jth power generation equipment, T represents the preset observation time period, t represents the target time, represents the power generation of the i-th power generation equipment at the target time, represents the power generation of the jth power generation equipment at the target time, T represents the time interval between the most recent start and stop of the i-th power generation equipment and the j-th power generation equipment. max Indicates the preset maximum time interval reference value, represents the regulation rate of the i-th power generation equipment, represents the regulation rate of the jth power generation equipment, Q max Indicates the preset maximum value of the regulation rate.

[0019] According to the method for constructing a graph database based on power data provided by an embodiment of the present invention, a second node edge is established according to the degree of association between the power equipment under the target power generation equipment to construct a second subgraph, including:

[0020] Obtaining the number of power transmission paths and electrical connections jointly participated by any two power devices under the target power generation device, as well as the current values ​​of the electrical connections associated with any two power devices at the target time within a preset observation time period, and the influence coefficient of a failure of one of the two power devices on the other power device;

[0021] Calculate the correlation coefficient between any two power devices according to the number of power transmission paths and electrical connections in which any two power devices participate, the current value on the electrical connection associated with any two power devices, and the influence coefficient between any two power devices;

[0022] If the correlation coefficient between any two power devices is greater than or equal to a preset correlation threshold, a second node edge between the any two power devices is established to construct the second subgraph.

[0023] According to the method for constructing a graph database based on power data provided by an embodiment of the present invention, the calculation formula for the correlation coefficient between any two power devices is as follows:

[0024]

[0025] ω1+ω2=1;

[0026] Among them, S EE (e i , e j ) represents the correlation coefficient between the i-th power equipment and the j-th power equipment, e i represents the ith power device, e j represents the jth power device, N common (e i , e j ) represents the number of power transmission paths in which the ith power device and the jth power device participate together, N total represents the maximum reference number of power transmission paths, Mcommon (e i , e j ) represents the number of electrical connections that the ith power device and the jth power device participate in, M total represents the maximum reference number of electrical connections, T represents the preset observation time period, t represents the target time, represents the current value of the electrical connection between the i-th power device and the j-th power device at the target time, I max Indicates the preset maximum current reference value, F represents the influence coefficient of the i-th power equipment failure on the j-th power equipment. amx represents the preset maximum influence reference coefficient, e represents the base of the exponential function, and ω1 and ω2 represent the preset weight values.

[0027] According to the method for constructing a graph database based on power data provided by an embodiment of the present invention, a third node edge is established according to the similarity between power users under the target power equipment to construct a third subgraph, including:

[0028] Obtaining the power consumption of any two power users under the target power equipment at a target time within a preset observation time period, and the power consumption of any two power users within a preset time period;

[0029] Calculate the similarity coefficient between any two electricity users based on their electricity consumption at the target time and their electricity consumption within a preset time period;

[0030] If the similarity coefficient between any two power users is greater than or equal to a preset similarity threshold, a third node edge between the any two power users is established to construct the third subgraph.

[0031] According to the graph database construction method based on power data provided by an embodiment of the present invention, the calculation formula of the similarity coefficient between any two power users is as follows:

[0032]

[0033] Among them, S UU (u i ,u j ) represents the similarity coefficient between the ith power user and the jth power user, u i represents the i-th electricity user, u j represents the jth power user, T represents the preset observation time period, t represents the target time, represents the power consumption of the ith power user at the target time, represents the power consumption of the jth power user at the target time, represents the power factor of the power consumed by the ith power user at the target time, represents the power factor of the jth power user at the target time, represents the power consumption of the ith power user in the preset time period, represents the power consumption of the ith power user in a preset time period, log() represents a logarithmic function, and λ1 and λ2 represent preset weight factors.

[0034] According to the method for constructing a graph database based on power data provided by an embodiment of the present invention, after constructing the graph database of the power dispatching center according to the first subgraph, the second subgraph and the third subgraph of the power dispatching center, the method further includes:

[0035] According to the jurisdiction area information and dispatching strategy information of each power dispatching center, a graph index between power dispatching centers is established;

[0036] A graph database of the power system is constructed based on the graph indexes between the power dispatching centers and the graph database of each power dispatching center.

[0037] In a second aspect, the present invention further provides a graph database construction system based on power data, which is applied to the graph database construction method based on power data as described in the first aspect, and the graph database construction system based on power data includes:

[0038] A collection module is used to collect the power generation equipment, power equipment and power users under the power dispatching center in the power system, and the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center are used as graph nodes;

[0039] A first subgraph construction module is used to establish a node edge between the power dispatching center and its corresponding power generation equipment, and to establish a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center to obtain a first subgraph;

[0040] A second subgraph construction module is used to establish a node edge between a target power generation device and its corresponding electric power device, and to establish a second node edge according to the degree of association between the electric power devices under the target power generation device, so as to construct a second subgraph; the target power generation device is any power generation device in the electric power dispatching center;

[0041] A third subgraph construction module is used to establish a node edge between a target power device and its corresponding power user, and to establish a third node edge according to the similarity between the power users under the target power device, so as to construct a third subgraph; the target power device is any power device of the target power generation device;

[0042] The graph database construction module is used to construct a graph database of the power dispatching center based on the first subgraph, the second subgraph and the third subgraph of the power dispatching center.

[0043] In a third aspect, the present invention further provides an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing any of the above-mentioned methods for constructing a graph database based on power data.

[0044] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, wherein a computer software program is stored in the storage medium, and when the computer software program is executed by a processor, the method for constructing a graph database based on power data as described in any one of the above is implemented.

[0045] In a fifth aspect, the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above methods for constructing a graph database based on power data.

[0046] The method for constructing a graph database based on power data provided by the embodiment of the present invention establishes a database of the power system by means of a graph model. The nodes and edges of the graph model can be flexibly defined and expanded. When the power system changes, it is only necessary to add the corresponding nodes and edges in the graph model, without modifying the complex table structure like a relational database. Secondly, since the graph database directly stores the association relationship of power data in the form of nodes and edges, there is no need to perform complex multi-table connection operations when querying. It is only necessary to start from the node representing the power dispatching center and traverse along the edges to quickly obtain the nodes of all relevant power users, which greatly reduces the query time complexity. Furthermore, the graph database is constructed by multiple subgraphs, so it can be understood that large-scale power data is distributed to multiple storage nodes or computing units. When the number of power users increases significantly and the amount of data exceeds the processing capacity of the original system, the graph partitioning algorithm is used to redistribute the graph data to the newly added storage nodes, and each storage node is responsible for processing a part of the subgraph data, thereby avoiding the occurrence of system bottlenecks. Therefore, the embodiment of the present invention realizes efficient processing of the complexity, dynamics and large-scale nature of power data, and improves the stability and reliability of data processing of the entire power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flowchart of a method for constructing a graph database based on power data provided by an embodiment of the present invention;

[0048] Figure 2 is a schematic diagram of a first sub-graph provided by an embodiment of the present invention;

[0049] Figure 3 is a schematic diagram of a second sub-graph provided by an embodiment of the present invention;

[0050] Figure 4 is a schematic diagram of a second sub-graph provided by an embodiment of the present invention;

[0051] Figure 5 is a schematic diagram of a graph database of a power system provided by an embodiment of the present invention;

[0052] Figure 6 It is a structural diagram of a graph database construction system based on power data provided by an embodiment of the present invention;

[0053] Figure 7 An embodiment diagram of an electronic device provided by an embodiment of the present invention;

[0054] Figure 8 An embodiment diagram of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0056] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0057] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0058] Optional, see Figure 1 As shown, Figure 1It is a flow chart of the method for constructing a graph database based on power data provided by the present invention. In the embodiment of the present invention, the execution subject of the method for constructing a graph database based on power data is a database construction system. Therefore, the method for constructing a graph database based on power data includes:

[0059] Step 10, collect the power generation equipment, power equipment and power users under the power dispatching center in the power system, and use the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center as graph nodes.

[0060] Optionally, the database construction system is connected to the power system, so it can interface with the monitoring system, management information system (MIS), etc. of the power dispatching center of the power system to obtain the data source within the jurisdiction of each power dispatching center. The data source includes power generation equipment information, such as relevant parameters, location, operating status, etc. of thermal power generating units, hydropower generating units, wind power generating units, etc.; power equipment information, such as specifications, connection relationships, real-time flow data, etc. of substations, transmission lines, distribution equipment, etc.; and power user information, such as the power consumption scale, power consumption characteristics, and location of different types of users.

[0061] Furthermore, the database construction system extracts the power dispatching center, as well as the power generation equipment, power equipment and power users under the power dispatching center from the data source, wherein the power equipment includes substation equipment and transmission equipment, and the power users include industrial users and residential users.

[0062] Furthermore, the database construction system defines the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center as graph nodes. Each graph node has a unique identifier and contains corresponding attribute information, such as the user number, power consumption, power consumption time and other attribute information of the power user. Among them, the power dispatching center set of the power system can be expressed as C = {c1, c2, ..., c s}, c s represents the sth power dispatching center. The set of power generation equipment under each power dispatching center can be expressed as G = {g1, g2, ..., g n}, g n represents the nth power generation equipment. The set of power equipment under each power generation equipment can be expressed as E = {e1, e2, ..., e m},e m represents the mth power device. The set of power users under each power device can be expressed as U = {u1, u2, ..., u k},u k represents the kth electricity user.

[0063] Step 20, establish a node edge between the power dispatching center and its corresponding power generation equipment, and establish a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center to obtain a first subgraph.

[0064] It should be noted that the graph in the embodiment of the present invention is an unweighted graph. Therefore, if there is an edge between two nodes, the default value of the edge between the nodes is 1.

[0065] Optionally, for each power dispatch center c i , determine each power dispatch center c i and its corresponding power generation equipment g i The connection relationship between them can be determined based on the communication link and the dispatch instruction issuing channel. If there is an effective connection so that the power dispatch center c i Can be used for power generation equipment i To conduct dispatching control, a power dispatching center c i and power generation equipment i The node edges between them. Among them, the connection relationship can be expressed by a function as f CE (c i , g i ), whose values ​​are:

[0066]

[0067] When f CE (c i , g i )=1, build slave node c i To node g i Node edge.

[0068] Furthermore, the database construction system establishes a first node edge according to the collaborative relationship between any two power generation devices under the power dispatching center to obtain a first subgraph, as specifically described in steps 201 to 203 .

[0069] Step 30: establish a node edge between the target power generation equipment and its corresponding electric power equipment, and establish a second node edge according to the degree of association between the electric power equipment under the target power generation equipment to construct a second subgraph.

[0070] Optionally, for each power generation device, from the perspective of power flow, it is determined whether the electric energy generated by the power generation device is transmitted, converted, etc. through a specific power device. i The generated electricity is sent to the power equipment through a specific transmission line. i , then build a power generation equipment g i With power equipment i The node edges between them. Among them, the connection relationship can be expressed by a function as fCE (g i , e i ), whose values ​​are:

[0071]

[0072] When f CE (g i , e i )=1, construct slave node g i To node e i Node edge.

[0073] Furthermore, the database construction system establishes a second node edge according to the degree of association between any two power equipment under the target power generation equipment, and constructs a second subgraph, as described in steps 301 to 303 .

[0074] Step 40: establish a node edge between the target power device and its corresponding power user, and establish a third node edge according to the similarity between the power users under the target power device to construct a third subgraph.

[0075] Optionally, for each power device, it is determined whether the power device directly or indirectly supplies power to the power user according to the power distribution relationship. i For residential users i Power supply, then establish power equipment e i With residential users i The node edges between them. Among them, the connection relationship can be expressed by a function as f CE (e i ,u i ), whose values ​​are:

[0076]

[0077] When f CE (e i ,u i )=1, construct the slave node e i To node u i Node edge.

[0078] Furthermore, the database construction system establishes a third node edge according to the similarity between any two power users under the target power equipment, and constructs a third subgraph, as described in steps 401 to 403 .

[0079] Step 50: construct a graph database of the electric power dispatching center according to the first subgraph, the second subgraph and the third subgraph of the electric power dispatching center.

[0080] Furthermore, for each power dispatching center, the database construction system integrates the first subgraph, the second subgraph and the third subgraph constructed by each power dispatching center, that is, taking each power dispatching center as the core, all relevant power generation equipment, power equipment and power users and their edge relationships are brought together, and a suitable graph database management system (such as Neo4j) is used to store the graph structure information, and finally a complete graph database for each power dispatching center is formed.

[0081] It should be noted that in a graph database, each node and edge can be associated with corresponding attributes (such as real-time parameters of equipment, detailed information of users, etc.), which facilitates subsequent queries, analysis, and applications based on graph algorithms (such as the shortest path algorithm for finding the optimal recovery path during troubleshooting, and the community discovery algorithm for analyzing different closely related user groups).

[0082] The embodiment of the present invention establishes a database of the power system by means of a graph model. The nodes and edges of the graph model can be flexibly defined and expanded. When the power system changes, it is only necessary to add the corresponding nodes and edges to the graph model, without modifying the complex table structure like a relational database. Secondly, since the graph database directly stores the association relationship of power data in the form of nodes and edges, there is no need to perform complex multi-table connection operations when querying. It is only necessary to start from the node representing the power dispatching center and traverse along the edges to quickly obtain the nodes of all relevant power users, which greatly reduces the query time complexity. Furthermore, the graph database is constructed by multiple subgraphs, so it can be understood as distributing large-scale power data to multiple storage nodes or computing units. When the number of power users increases significantly and the amount of data exceeds the processing capacity of the original system, the graph partitioning algorithm is used to redistribute the graph data to the newly added storage nodes. Each storage node is responsible for processing a part of the subgraph data, thereby avoiding the occurrence of system bottlenecks. Therefore, the embodiment of the present invention realizes efficient processing of the complexity, dynamics and large scale of power data, and improves the stability and reliability of data processing of the entire power system.

[0083] In one embodiment, the description of steps 201 to 203 is as follows:

[0084] Step 201, obtaining the power generation power of any two power generation devices under the power dispatching center at the target time within the preset observation time period, the most recent start-stop time interval of any two power generation devices, and the regulation rate of any two power generation devices.

[0085] Among them, the coordinated relationship between power generation equipment can be considered from multiple dimensions, such as the complementarity of power generation (for example, the power coordination between hydropower and thermal power in the dry season and the flood season), and the coordination of start and stop times (different types of units can reasonably arrange the start and stop sequence according to the peak and valley periods of electricity consumption).

[0086] Therefore, the database construction system obtains the power generation power of any two power generation equipment under the power dispatching center at the target time within the preset observation time period, the most recent start and stop time interval of any two power generation equipment, and the regulation rate of any two power generation equipment, where the preset observation time period is such as the past day, the past week, etc.

[0087] Step 202, calculating the coordination relationship coefficient between any two power generation devices according to the power generation power of the any two power generation devices at the target time, the most recent start-stop time interval and the regulation rate.

[0088] Furthermore, the database construction system calculates the synergy coefficient between any two power generation devices according to the power generation of any two power generation devices at the target time, the most recent start-stop time interval, and the regulation rate. The calculation formula of the synergy coefficient between any two power generation devices is as follows:

[0089]

[0090] Among them, S GG (g i , g j ) represents the synergy coefficient between the i-th power generation equipment and the j-th power generation equipment, g i represents the i-th power generation equipment, g j represents the jth power generation equipment, T represents the preset observation time period, t represents the target time, represents the power generation of the i-th power generation equipment at the target time, represents the power generation of the jth power generation equipment at the target time, T represents the time interval between the most recent start and stop of the i-th power generation equipment and the j-th power generation equipment. max Indicates the preset maximum time interval reference value, represents the regulation rate of the ith power generation equipment, Q gj represents the regulation rate of the jth power generation equipment, Q max Indicates the preset maximum value of the regulation rate.

[0091] Step 203: If the synergy relationship coefficient between any two power generation devices is greater than or equal to a preset synergy relationship threshold, a first node edge between any two power generation devices is established to obtain a first subgraph.

[0092] Furthermore, if the synergy relationship coefficient between any two power generation devices is greater than or equal to a preset synergy relationship threshold, the database construction system establishes a first node edge between any two power generation devices to obtain a first subgraph, wherein the preset synergy relationship threshold θ GG According to the actual setting.

[0093] Therefore, it can be understood that if the synergy coefficient S between the i-th power generation equipment and the j-th power generation equipment is GG (g i , g j )≥θ GG , then create a slave node g in the graph i To node g j Node edge.

[0094] In one embodiment, the power dispatching center 1 has power generation equipment 1, power generation equipment 2, power generation equipment 3, power generation equipment 4, power generation equipment 5 and power generation equipment 6, and all power generation equipment are effectively connected to the power dispatching center 1. The synergy relationship coefficient between power generation equipment 1 and power generation equipment 5, the synergy relationship coefficient between power generation equipment 2 and power generation equipment 6, and the synergy relationship coefficient between power generation equipment 3 and power generation equipment 4 are all greater than the preset synergy relationship threshold. Therefore, the first subgraph constructed is as follows Figure 2 shown.

[0095] The embodiment of the present invention constructs a first subgraph to provide a data basis for the subsequent construction of a graph database, so that the complexity, dynamics and large-scale nature of power data can be efficiently processed through the graph database, thereby improving the stability and reliability of data processing in the entire power system.

[0096] In one embodiment, the description of steps 301 to 303 is as follows:

[0097] Step 301, obtain the number of power transmission paths and the number of electrical connections jointly participated by any two power devices under the target power generation device, as well as the current values ​​on the electrical connections associated with any two power devices at the target time within a preset observation time period, and the influence coefficient of one power device of any two power devices on the other power device when a power device fails.

[0098] The degree of correlation between power equipment can take into account factors such as electrical connection tightness and the scope of impact of equipment failure. For example, adjacent towers on the same transmission line and different electrical compartment equipment in the same substation have a high degree of correlation.

[0099] Therefore, the database construction system obtains the number of power transmission paths and the number of electrical connections jointly participated by any two power devices under the target power generation device, as well as the current values ​​on the electrical connections associated with any two power devices at the target time within a preset observation time period, and the impact coefficient of one power device on the other power device when a power device among any two power devices fails.

[0100] In one embodiment, the specific process of obtaining the influence coefficient is as follows:

[0101] First, the power equipmenti and power equipment j Perform failure mode analysis.

[0102] The failure modes of power equipment can be divided into short circuit failure, open circuit failure, performance degradation caused by equipment aging, etc. The failure modes of different types of equipment are also different. For example, for transmission lines (which belong to power equipment), short circuit failures may be caused by lightning strikes, tree branches touching, etc.; for transformers, it may be winding short circuit, iron core failure, etc. List the power equipment e i The set of all possible failure modes F i ={f i1 , f i2 , ..., f in}, f in Indicates electrical equipment i The nth failure mode of the power equipment e j The set of all possible failure modes F j ={f j1 , f j2 , ..., f jm}, f jm Indicates electrical equipment j The mth failure mode of .

[0103] Further, the analysis from the power equipment i Failure occurs to affect power equipment j The possible propagation paths of the power system need to be considered, including the connection relationship between transmission lines, substations and other equipment.

[0104] Construct the topology matrix X of the power system, where the element x in the topology matrix X pq Indicates whether there is a direct electrical connection between power equipment p and power equipment q (if so, x pq =1; otherwise, x pq =0). By searching the topology matrix, the power equipment e i Set out and find all possible power equipment e j The path set Q ij ={q1, q2, ..., q k}, where path q l ={e l1 , e l2 , ..., e ln}, indicating that from the power equipment e i After a series of electrical equipment l1 , e l2 , ..., e ln Reaching power equipment j .

[0105] Furthermore, for each propagation path q l ∈Q ij , when the power equipment i When a fault occurs, the power flow changes of each device on the path are calculated according to the power flow calculation method. The power flow calculation can be based on the node voltage equation and branch power equation of the power system, as follows:

[0106] Assume that the node admittance matrix of the power system is Y, the node voltage vector is V, and the branch power vector is S. For normal operation, the equations I = YV and S = VI are satisfied. * , where I represents the node injection current vector and I * Represents the conjugate vector of I. When the power device e i A fault occurs (assuming it is a short circuit fault with a short circuit impedance of Z f ), modify the node admittance matrix Y to Y * The specific modification method depends on the fault type and location, and the node voltage vector V is recalculated. * and branch power vector S * Furthermore, the calculation of the power equipment e i The change of power flow ΔS ej , for example, for transmission line equipment, in, Indicates the branch power after the fault, S ej Indicates normal branch power.

[0107] Furthermore, reliability indicators are used to quantify the impact of failures. Commonly used reliability indicators include lack of power probability (LOLP) and expected short supply voltage (EENS).

[0108] Therefore, the calculation of the power equipment e i The reliability index R1 of the power system during normal operation, for example, is obtained by performing a large number of random state sampling on the power system through methods such as Monte Carlo simulation, calculating the power supply situation under each state, and obtaining the reliability index statistically. i When a fault occurs, the reliability index R2 of the power system is recalculated, and the change in the reliability index ΔR = |R2-R1| is calculated.

[0109] According to the power equipment i The position and role of the power system, the reliability index change is distributed to the power equipment j Get the power equipment j The reliability impact For example, if the electrical equipment j It is a key transmission line, which contributes more to the reliability index and has a greater impact on the distribution.

[0110] Furthermore, the power equipment is evaluated by combining the changes in power flow and reliability indicators. i When a fault occurs, the power equipment j The degree of influence The details are as follows:

[0111] Assume that the weight of power flow change is μ1, the weight of reliability index change is μ2, and μ1+μ2=1, then the impact degree is It can be expressed as:

[0112]

[0113] in, Indicates electrical equipment j The maximum allowable branch power is used to normalize the power flow variation.

[0114] Step 302, calculate the correlation coefficient between any two power devices based on the number of power transmission paths and electrical connections jointly participated by any two power devices, the current values ​​on the electrical connections associated with any two power devices, and the influence coefficient between any two power devices.

[0115] Furthermore, the database construction system calculates the correlation coefficient between any two power devices according to the number of power transmission paths and the number of electrical connections in which any two power devices participate, the current value on the electrical connection associated with any two power devices, and the influence coefficient between any two power devices. The calculation formula of the correlation coefficient between any two power devices is as follows:

[0116]

[0117] ω1+ω2=1;

[0118] Among them, S EE (e i , e j ) represents the correlation coefficient between the i-th power equipment and the j-th power equipment, e i represents the ith power device, e j represents the jth power device, N common (e i , e j ) represents the number of power transmission paths in which the ith power device and the jth power device participate together, N total represents the maximum reference number of power transmission paths, M common (e i , e j) represents the number of electrical connections that the ith power device and the jth power device participate in, M total represents the maximum reference number of electrical connections, T represents the preset observation time period, t represents the target time, represents the current value of the electrical connection between the i-th power device and the j-th power device at the target time, I max Indicates the preset maximum current reference value, F represents the influence coefficient of the i-th power equipment failure on the j-th power equipment. amx represents the preset maximum influence reference coefficient, e represents the base of the exponential function, and ω1 and ω2 represent the preset weight values.

[0119] Step 303: If the correlation coefficient between any two power devices is greater than or equal to a preset correlation threshold, a second node edge between the any two power devices is established to construct a second subgraph.

[0120] Furthermore, if the correlation coefficient between any two power devices is greater than or equal to a preset correlation threshold, the database construction system establishes a second node edge between any two power devices and constructs a second subgraph, wherein the preset correlation threshold θ EE According to the actual setting.

[0121] Therefore, it can be understood that if the correlation coefficient S between the i-th power equipment and the j-th power equipment is EE (e i , e j )≥θ EE , then create a slave node e in the graph i To node e j Node edge.

[0122] In one embodiment, power generation device 1 includes power device 1, power device 2, power device 3, power device 4, power device 5 and power device 6, and electric energy can flow from target power generation device 1 to all power devices. The correlation coefficient between power device 1 and power device 3, the correlation coefficient between power device 2 and power device 4, and the correlation coefficient between power device 5 and power device 6 are all greater than a preset correlation threshold. Therefore, the second subgraph constructed is as follows: Figure 3 shown.

[0123] The embodiment of the present invention constructs a second subgraph to provide a data basis for the subsequent construction of a graph database, so that the complexity, dynamics and large-scale nature of power data can be efficiently processed through the graph database, thereby improving the stability and reliability of data processing in the entire power system.

[0124] In one embodiment, the description of steps 401 to 403 is as follows:

[0125] Step 401, obtaining the power consumption of any two power users under the target power equipment at the target time within the preset observation time period, and the power consumption of any two power users within the preset time period.

[0126] Among them, the similarity between power users can be measured from the perspectives of power consumption behavior (power consumption time distribution, power factor, etc.), power consumption scale (daily power consumption, monthly power consumption, etc.). Therefore, the database construction system obtains the power consumption of any two power users under the target power equipment at the target time within the preset observation time period, and the power consumption of any two power users within the preset time period.

[0127] Step 402: Calculate the similarity coefficient between any two power users based on the power consumption of the two power users at the target time and the power consumption within a preset time period.

[0128] Furthermore, the database construction system calculates the similarity coefficient between any two power users according to the power consumption of any two power users at the target time and the power consumption in the preset time period, wherein the calculation formula of the similarity coefficient between any two power users is as follows:

[0129]

[0130] Among them, S UU (u i ,u j ) represents the similarity coefficient between the ith power user and the jth power user, u i represents the i-th electricity user, u j represents the jth power user, T represents the preset observation time period, t represents the target time, represents the power consumption of the ith power user at the target time, represents the power consumption of the jth power user at the target time, represents the power factor of the power consumed by the ith power user at the target time, represents the power factor of the jth power user at the target time, represents the power consumption of the ith power user in the preset time period, represents the power consumption of the ith power user in a preset time period, log() represents a logarithmic function, and λ1 and λ2 represent preset weight factors.

[0131] Step 403: If the similarity coefficient between any two power users is greater than or equal to a preset similarity threshold, a third node edge is established between the any two power users to construct a third subgraph.

[0132] Furthermore, if the similarity coefficient between any two power users is greater than or equal to a preset similarity threshold, the database construction system establishes a third node edge between any two power users to construct the third subgraph, wherein the preset similarity threshold θ UU According to the actual setting.

[0133] Therefore, it can be understood that if the similarity coefficient S between the i-th power user and the j-th power user is UU (u i ,u j )≥θ UU , then in the graph, we create a slave node u i To node u j Node edge.

[0134] In one embodiment, there are power users 1, 2, 3, 4, 5 and 6 under power equipment 1. Power equipment 1 can supply power to all power users. The similarity coefficient between power user 1 and power user 2, the similarity coefficient between power user 1 and power user 5, the similarity coefficient between power user 1 and power user 6, the similarity coefficient between power user 2 and power user 4, the similarity coefficient between power user 2 and power user 6, the similarity coefficient between power user 3 and power user 4, and the similarity coefficient between power user 3 and power user 5 are all greater than a preset similarity threshold. The third subgraph constructed is as follows: Figure 4 shown.

[0135] The embodiment of the present invention constructs a third subgraph to provide a data basis for the subsequent construction of a graph database, so that the complexity, dynamics and large-scale nature of power data can be efficiently processed through the graph database, thereby improving the stability and reliability of data processing in the entire power system.

[0136] In one embodiment, after the graph database of each power dispatching center is constructed, it is necessary to construct the graph database of the power system based on the graph databases of all power dispatching centers, as follows:

[0137] Step 60: Establish a graph index between power dispatch centers based on the jurisdiction area information and dispatch strategy information of each power dispatch center.

[0138] Specifically, the database construction system obtains the jurisdiction information of each power dispatching center, and the jurisdiction information includes jurisdiction range description information, voltage level coverage information and jurisdiction distribution information. The jurisdiction range description information includes the geographical area range, such as which cities, districts and counties are covered, longitude and latitude boundaries, etc. Voltage level coverage information such as being mainly responsible for 110kV and above voltage level power grid dispatching, or including specific low-voltage distribution network areas, etc. Jurisdiction distribution information such as the approximate distribution of power generation, transmission, and electricity users under its jurisdiction. In one embodiment, the set of power dispatching centers of the power system can be expressed as C={c1, c2, ..., c s},c s represents the sth power dispatching center. For each power dispatching center, its jurisdiction information is quantified, for example, the geographic area coverage vector is defined as O i = {O i1 , O i2 , ..., O in}, where O ij It can represent the coverage in a certain geographical dimension (such as a region divided by a grid with a certain precision) (the value can be 0 or 1, indicating no coverage or coverage); the voltage level coverage vector V i = {v i1 , v i2 , ..., v im},v ik Indicates whether the corresponding voltage level is covered.

[0139] Furthermore, the database construction system obtains the dispatching strategy information of each power dispatching center. The dispatching strategy information includes power generation plan allocation strategy (how different power dispatching centers arrange the power generation power, start and stop time, etc. of power generation equipment according to the load forecast in their own area), fault emergency handling strategy (when facing power grid failure, how to coordinate with adjacent power dispatching centers to perform load transfer, fault isolation and other operations), and power mutual assistance strategy (rules for power support between different power dispatching centers during peak and valley periods).

[0140] Furthermore, the database construction system extracts and quantifies the dispatching strategies. For example, for the power generation plan allocation strategy, the strategy difference measurement function S is defined. P (c i , c j ), the calculation formula is as follows:

[0141]

[0142] Among them, T represents the planning period, G ij Indicates that it is in the power dispatching center c i and power dispatch centerj The collection of power generation equipment in the surrounding areas of the jurisdiction, and They represent the power generation equipment g in the power dispatching center c i and power dispatch center j The power generation plan is scheduled at the time t. Indicates the maximum power generation of the power generation equipment; ω g It represents the weight coefficient of power generation equipment g in the overall strategy consideration, which can be set according to factors such as power generation capacity and importance.

[0143] For the fault emergency handling strategy, define the fault coordination function S F (c i , c j ), the calculation formula is as follows:

[0144]

[0145] in, In the face of multiple preset fault scenarios, the power dispatch center c i and power dispatch center j The number of scenarios that can be effectively handled collaboratively (e.g., through reasonable load transfer, power restoration, etc.); represents the total number of preset fault scenarios, and α1 represents the weight coefficient of the number of scenarios; In the critical fault simulation, the power dispatch center c i and power dispatch center j The time difference in initiating effective emergency response measures; represents the maximum allowable time difference reference value, β1 represents the time difference weight coefficient, E ij Indicates that it involves the power dispatch center c i and power dispatch center j Coordinate the collection of key power equipment within the region; and They represent the power equipment e in the power dispatching center c in the case of a fault. i and power dispatch center j The current change can be estimated through power flow calculation, etc. max represents the maximum current change of the reference; γ represents the current change weight coefficient, α1+β1+γ=1.

[0146] For the electric energy mutual assistance strategy, define the electric energy mutual assistance correlation function S E (c i , c j ), the calculation formula is as follows:

[0147]

[0148] Among them, T peak Represents the peak and valley time periods of electricity consumption. Indicates that at time t, the power dispatching center c i and power dispatch center j The expected mutual energy between the two (positive value indicates that the power dispatch center c i Flow to the power dispatch center c j , negative value is opposite); E max represents the set maximum mutual aid power reference value, α2 represents the mutual aid power weight coefficient; It means that after a long period of time, the power dispatch center c i and power dispatch center j The difference in the change of the power balance state (measured by the surplus or deficit of power), represents the maximum balance difference value of the reference; β2 represents the power balance weight coefficient, α2+β2=1.

[0149] Furthermore, the database construction system calculates the power dispatch center c i and power dispatch center j The degree of correlation between D (c i , c j ), the specific calculation formula is as follows:

[0150]

[0151] Among them, O i ·O j Represents vector O i and vector O j The inner product of |O i | and |O j | respectively represent vector O i and vector O j The modulus of ; ε1, ε2, ε3, ε4 represent weight coefficients, ε1+ε2+ε3+ε4=1.

[0152] If the power dispatching center c i and power dispatch center j The degree of correlation between E (c i , c j ) is greater than the correlation threshold θ D , the database construction system establishes the power dispatching center c i and power dispatch center j The node edges between them, node edges, power dispatching center c i and power dispatch center j Constitute the graph index.

[0153] Step 70, constructing a graph database of the power system based on the graph indexes between the power dispatching centers and the graph database of each power dispatching center.

[0154] Furthermore, the database construction system uses the established graph index between power dispatch centers as a framework to integrate the graph database of each power dispatch center (such as the graph database containing power generation equipment, power equipment, power users and the complex relationships between them built in the previous step). i and power dispatch center j edge).

[0155] It should be noted that in the graph database of the integrated power system, not only the power dispatching center c represented by this edge is retained i and the associated information of the power dispatching center cj (reflected by the above comprehensive correlation, etc.), and the power dispatching center cj i and power dispatch center j The relevant cross-regional connection information in the graph database is sorted and associated. For example, if the power dispatch center c i In the graph database, there is a power generation device g connected to a transmission line (power equipment) e, and the transmission line is associated with the power equipment in the jurisdiction through a cross-regional contact line. j The power system diagram database needs to reflect the connection relationship of power equipment across dispatching centers.

[0156] Furthermore, in the constructed graph database of the power system, it is necessary to improve the structure of the graph. For example, according to the hierarchical and partitioning characteristics of the actual power system (such as provincial dispatching, municipal dispatching and other different levels and different geographical divisions), the nodes and edges should be reasonably classified and labeled to facilitate subsequent query and analysis operations.

[0157] At the same time, more attribute information needs to be associated with the nodes and edges in the graph. For example, for the power dispatching center nodes, in addition to the above-mentioned jurisdiction area and dispatching strategy related attributes, its historical dispatching operation records, personnel configuration and other information can also be associated; for power generation equipment nodes, the equipment's full life cycle maintenance records, real-time operation status monitoring data, etc. can be associated; for edges (whether they are edges between dispatching centers or edges between internal devices), attributes such as power transmission limits and reliability assessment values ​​can be associated.

[0158] Continuing with the above embodiment, the degree of association between the power dispatching center 1 and the power dispatching center 2 in the power system is greater than the association threshold. Therefore, the graph database of the power system is as follows: Figure 5 shown.

[0159] The embodiment of the present invention constructs a graph database of the power system based on the graph database of the power dispatching center, so that the complexity, dynamics and large scale of power data can be efficiently processed through the graph database of the power system, thereby improving the stability and reliability of data processing of the entire power system.

[0160] Furthermore, the graph database construction system based on power data provided by the present invention is described below. The graph database construction system based on power data described below and the graph database construction method based on power data described above can refer to each other.

[0161] Optional, see Figure 6 , Figure 6 It is a structural diagram of a graph database construction system based on power data provided by the present invention, and the graph database construction system based on power data includes:

[0162] The collection module 610 is used to collect the power generation equipment, power equipment and power users under the power dispatching center in the power system, and use the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center as graph nodes;

[0163] A first subgraph construction module 620 is used to establish a node edge between the power dispatching center and its corresponding power generation equipment, and to establish a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center to obtain a first subgraph;

[0164] The second subgraph construction module 630 is used to establish a node edge between the target power generation equipment and its corresponding power equipment, and to establish a second node edge according to the degree of association between the power equipment under the target power generation equipment, so as to construct a second subgraph; the target power generation equipment is any power generation equipment in the power dispatching center;

[0165] The third subgraph construction module 640 is used to establish a node edge between the target power device and its corresponding power user, and to establish a third node edge according to the similarity between the power users under the target power device, so as to construct a third subgraph; the target power device is any power device of the target power generation device;

[0166] The graph database construction module 650 is used to construct a graph database of the electric power dispatching center according to the first subgraph, the second subgraph and the third subgraph of the electric power dispatching center.

[0167] The embodiment of the present invention establishes a database of the power system by means of a graph model. The nodes and edges of the graph model can be flexibly defined and expanded. When the power system changes, it is only necessary to add the corresponding nodes and edges to the graph model, without modifying the complex table structure like a relational database. Secondly, since the graph database directly stores the association relationship of power data in the form of nodes and edges, there is no need to perform complex multi-table connection operations when querying. It is only necessary to start from the node representing the power dispatching center and traverse along the edges to quickly obtain the nodes of all relevant power users, which greatly reduces the query time complexity. Furthermore, the graph database is constructed by multiple subgraphs, so it can be understood as distributing large-scale power data to multiple storage nodes or computing units. When the number of power users increases significantly and the amount of data exceeds the processing capacity of the original system, the graph partitioning algorithm is used to redistribute the graph data to the newly added storage nodes. Each storage node is responsible for processing a part of the subgraph data, thereby avoiding the occurrence of system bottlenecks. Therefore, the embodiment of the present invention realizes efficient processing of the complexity, dynamics and large scale of power data, and improves the stability and reliability of data processing of the entire power system.

[0168] See also Figure 7 , Figure 7 FIG. 1 is an embodiment diagram of an electronic device provided by an embodiment of the present invention. Figure 7 As shown, an embodiment of the present invention provides an electronic device 700, including a memory 710, a processor 720, and a computer program 711 stored in the memory 710 and executable on the processor 720. When the processor 720 executes the computer program 711, the following steps are implemented:

[0169] Collect the power generation equipment, power equipment and power users under the power dispatching center in the power system, and use the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center as graph nodes;

[0170] Establishing a node edge between the power dispatching center and its corresponding power generation equipment, and establishing a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center, to obtain a first subgraph;

[0171] Establishing a node edge between the target power generation equipment and its corresponding electric power equipment, and establishing a second node edge according to the degree of association between the electric power equipment under the target power generation equipment, to construct a second subgraph; the target power generation equipment is any power generation equipment in the electric power dispatching center;

[0172] Establishing a node edge between the target power equipment and its corresponding power user, and establishing a third node edge according to the similarity between the power users under the target power equipment, to construct a third subgraph; the target power equipment is any power equipment of the target power generation equipment;

[0173] A graph database of the electric power dispatching center is constructed according to the first subgraph, the second subgraph and the third subgraph of the electric power dispatching center.

[0174] See also Figure 8 , Figure 8 Detailed description of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. Figure 8 As shown, this embodiment provides a computer-readable storage medium 800, on which a computer program 711 is stored. When the computer program 711 is executed by a processor, the following steps are implemented:

[0175] Collect the power generation equipment, power equipment and power users under the power dispatching center in the power system, and use the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center as graph nodes;

[0176] Establishing a node edge between the power dispatching center and its corresponding power generation equipment, and establishing a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center, to obtain a first subgraph;

[0177] Establishing a node edge between the target power generation equipment and its corresponding electric power equipment, and establishing a second node edge according to the degree of association between the electric power equipment under the target power generation equipment, to construct a second subgraph; the target power generation equipment is any power generation equipment in the electric power dispatching center;

[0178] Establishing a node edge between the target power equipment and its corresponding power user, and establishing a third node edge according to the similarity between the power users under the target power equipment, to construct a third subgraph; the target power equipment is any power equipment of the target power generation equipment;

[0179] A graph database of the electric power dispatching center is constructed according to the first subgraph, the second subgraph and the third subgraph of the electric power dispatching center.

[0180] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the method for constructing a graph database based on power data provided by the above methods, the method includes:

[0181] Collect the power generation equipment, power equipment and power users under the power dispatching center in the power system, and use the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center as graph nodes;

[0182] Establishing a node edge between the power dispatching center and its corresponding power generation equipment, and establishing a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center, to obtain a first subgraph;

[0183] Establishing a node edge between the target power generation equipment and its corresponding electric power equipment, and establishing a second node edge according to the degree of association between the electric power equipment under the target power generation equipment, to construct a second subgraph; the target power generation equipment is any power generation equipment in the electric power dispatching center;

[0184] Establishing a node edge between the target power equipment and its corresponding power user, and establishing a third node edge according to the similarity between the power users under the target power equipment, to construct a third subgraph; the target power equipment is any power equipment of the target power generation equipment;

[0185] A graph database of the electric power dispatching center is constructed according to the first subgraph, the second subgraph and the third subgraph of the electric power dispatching center.

[0186] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0187] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0188] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a graph database based on power data, characterized in that: include: Collect the power generation equipment, power equipment and power users under the power dispatching center in the power system, and use the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center as graph nodes; Establishing a node edge between the power dispatching center and its corresponding power generation equipment, and establishing a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center, to obtain a first subgraph; Establishing a node edge between a target power generation device and its corresponding electric power device, and establishing a second node edge according to the degree of association between the electric power devices under the target power generation device, to construct a second subgraph; the target power generation device is any power generation device in the electric power dispatching center; Establishing a node edge between a target power device and its corresponding power user, and establishing a third node edge according to the similarity between the power users under the target power device, to construct a third subgraph; The target power equipment is any power equipment of the target power generation equipment; A graph database of the electric power dispatching center is constructed according to the first subgraph, the second subgraph and the third subgraph of the electric power dispatching center.

2. The method for constructing a graph database based on power data according to claim 1, characterized in that: The step of establishing a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center to obtain a first subgraph includes: Obtain the power generation power of any two power generation equipment under the power dispatching center at the target time within the preset observation time period, the most recent start-stop time interval of any two power generation equipment, and the regulation rate of any two power generation equipment; Calculate the synergy coefficient between any two power generation equipment according to the power generation of any two power generation equipment at the target time, the most recent start-stop time interval and the regulation rate; If the synergy relationship coefficient between any two power generation devices is greater than or equal to a preset synergy relationship threshold, a first node edge between any two power generation devices is established to obtain the first subgraph.

3. The method for constructing a graph database based on power data according to claim 2, characterized in that: The calculation formula of the synergy coefficient between any two power generation equipment is as follows: Among them, S GG (g i ,g j ) represents the synergy coefficient between the i-th power generation equipment and the j-th power generation equipment, g i represents the i-th power generation equipment, g j represents the jth power generation equipment, T represents the preset observation time period, t represents the target time, represents the power generation of the i-th power generation equipment at the target time, represents the power generation of the jth power generation equipment at the target time, T represents the time interval between the most recent start and stop of the i-th power generation equipment and the j-th power generation equipment. max Indicates the preset maximum time interval reference value, represents the regulation rate of the i-th power generation equipment, represents the regulation rate of the jth power generation equipment, Q max Indicates the preset maximum value of the regulation rate.

4. The method for constructing a graph database based on power data according to claim 1, characterized in that: The step of establishing a second node edge according to the degree of association between the power equipment under the target power generation equipment and constructing a second subgraph includes: Obtaining the number of power transmission paths and electrical connections jointly participated by any two power devices under the target power generation device, as well as the current values ​​of the electrical connections associated with any two power devices at the target time within a preset observation time period, and the influence coefficient of a failure of one of the two power devices on the other power device; Calculate the correlation coefficient between any two power devices according to the number of power transmission paths and electrical connections in which any two power devices participate, the current value on the electrical connection associated with any two power devices, and the influence coefficient between any two power devices; If the correlation coefficient between any two power devices is greater than or equal to a preset correlation threshold, a second node edge between the any two power devices is established to construct the second subgraph.

5. The method for constructing a graph database based on power data according to claim 4, characterized in that: The calculation formula of the correlation coefficient between any two power devices is as follows: ω1+ω2=1; Among them, S EE (e i ,e j ) represents the correlation coefficient between the i-th power equipment and the j-th power equipment, e i represents the ith power device, e j represents the jth power device, N common (e i ,e j ) represents the number of power transmission paths in which the ith power device and the jth power device participate together, N total represents the maximum reference number of power transmission paths, M common (e i ,e j ) represents the number of electrical connections in which the ith power device and the jth power device participate, M total represents the maximum reference number of electrical connections, T represents the preset observation time period, t represents the target time, represents the current value of the electrical connection between the i-th power device and the j-th power device at the target time, I max Indicates the preset maximum current reference value, F represents the influence coefficient of the i-th power equipment failure on the j-th power equipment. amx represents the preset maximum influence reference coefficient, e represents the base of the exponential function, and ω1 and ω2 represent the preset weight values.

6. The method for constructing a graph database based on power data according to claim 1, characterized in that: The step of establishing a third node edge according to the similarity between the power users under the target power equipment and constructing a third subgraph includes: Obtaining the power consumption of any two power users under the target power equipment at a target time within a preset observation time period, and the power consumption of any two power users within a preset time period; Calculate the similarity coefficient between any two electricity users based on their electricity consumption at the target time and their electricity consumption within a preset time period; If the similarity coefficient between any two power users is greater than or equal to a preset similarity threshold, a third node edge between the any two power users is established to construct the third subgraph.

7. The method for constructing a graph database based on power data according to claim 6, characterized in that: The calculation formula of the similarity coefficient between any two electricity users is as follows: Among them, S UU (u i ,u j ) represents the similarity coefficient between the ith power user and the jth power user, u i represents the i-th electricity user, u j represents the jth power user, T represents the preset observation time period, t represents the target time, represents the power consumption of the ith power user at the target time, represents the power consumption of the jth power user at the target time, represents the power factor of the power consumed by the ith power user at the target time, represents the power factor of the jth power user at the target time, represents the power consumption of the ith power user in the preset time period, represents the power consumption of the ith power user in a preset time period, log() represents a logarithmic function, and λ1 and λ2 represent preset weight factors.

8. The method for constructing a graph database based on power data according to any one of claims 1 to 7, characterized in that: After constructing the graph database of the power dispatching center according to the first subgraph, the second subgraph and the third subgraph of the power dispatching center, the method further includes: According to the jurisdiction area information and dispatching strategy information of each power dispatching center, a graph index between power dispatching centers is established; A graph database of the power system is constructed based on the graph indexes between the power dispatching centers and the graph database of each power dispatching center.

9. A graph database construction system based on power data, characterized in that: Applied to the method for constructing a graph database based on power data according to any one of claims 1 to 8, the graph database construction system based on power data comprises: A collection module is used to collect the power generation equipment, power equipment and power users under the power dispatching center in the power system, and the power dispatching center, the power generation equipment, power equipment and power users under the power dispatching center are used as graph nodes; A first subgraph construction module is used to establish a node edge between the power dispatching center and its corresponding power generation equipment, and to establish a first node edge according to the collaborative relationship between the power generation equipment under the power dispatching center to obtain a first subgraph; A second subgraph construction module is used to establish a node edge between a target power generation device and its corresponding electric power device, and to establish a second node edge according to the degree of association between the electric power devices under the target power generation device, so as to construct a second subgraph; the target power generation device is any power generation device in the electric power dispatching center; A third subgraph construction module is used to establish a node edge between a target power device and its corresponding power user, and to establish a third node edge according to the similarity between the power users under the target power device, so as to construct a third subgraph; the target power device is any power device of the target power generation device; The graph database construction module is used to construct a graph database of the power dispatching center based on the first subgraph, the second subgraph and the third subgraph of the power dispatching center.

10. A non-transitory computer-readable storage medium having a computer software program stored therein, characterized in that: When the computer software program is executed by a processor, the method for constructing a graph database based on power data as described in any one of claims 1 to 8 is implemented.

Images