Electric power topology system based on graph database

Abstract

The invention relates to the technical field of power systems, in particular to a power topology system based on a graph database, which comprises a data transmission platform for acquiring real-time data of power equipment through a monitoring system and preprocessing and transmitting the real-time data based on a message queue system and a stream processing platform; when the method is used, the accuracy and timeliness of data are ensured, reliable data support is provided for subsequent topology updating and fault analysis, the overall efficiency of the system is improved, the updating efficiency of the database is improved, it is ensured that topology information reflects the real-time state of the system, and the real-time performance of the system is improved. The method is beneficial to reducing delay and errors, provides visual data for a user to deeply analyze power network topology, optimize scheduling and operate and maintain decisions, is beneficial to improving the safety and reliability of a power system, recognizes potential faults of equipment in advance, and reduces sudden faults.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a power topology system based on a graph database. Background Art

[0002] Power topology is an important basis for power system planning, design and operation. By rationally selecting and optimizing the topology structure, the reliability, stability and economy of power supply can be significantly improved.

[0003] The patent application number is CN201610703694.4. The specification states that “a method for rapid topological analysis of a power network based on a graph database comprises the following steps: numbering nodes, switches and branches in a power network wiring diagram; defining relevant variables of electrical equipment in the power network, and describing the terminal numbers of power components to form a topological matrix; establishing a Neo4j-CIM model, and mapping the power topological matrix to the Neo4j-CIM model; performing topological analysis on the power network, forming a power network topological diagram, and realizing visualization. The present invention establishes a standard and open power system information model, which promotes interoperability. ", reducing production and maintenance costs, and greatly improving the speed and accuracy of power network topology analysis". Although the above technology accelerates the topology analysis process through the graph database, it has the advantages of meeting real-time requirements and improving system accuracy. However, the status of equipment and topology in the power system will change frequently. When the topology update delay is high or an error occurs, the topological relationship in the graph database will not be updated in time, and the current status of the power system cannot be reflected in real time, thus affecting real-time scheduling decisions. In addition, topology update errors will cause the status of the power network to present an inaccurate model, affecting the accuracy of the scheduling algorithm, and further affecting the reliability and efficiency of the power system.

[0004] In summary, developing a power topology system based on graph database is still a key issue that needs to be urgently solved in the field of power system technology. Summary of the invention

[0005] The purpose of the present invention is to solve the problem in the prior art that although the above-mentioned technology accelerates the process of topology analysis through the graph database, it has the advantages of meeting real-time requirements and improving system accuracy, but the status of equipment and topology in the power system will change frequently. When the delay in topology update is high or an error occurs, the topological relationship in the graph database will not be updated in time, and the current status of the power system cannot be reflected in real time, thereby affecting real-time scheduling decisions. In addition, topology update errors will cause the status of the power network to present an inaccurate model, affecting the accuracy of the scheduling algorithm, and further affecting the reliability and efficiency of the power system.

[0006] To achieve the above object, the present invention provides a power topology system based on a graph database, comprising:

[0007] The data transmission platform collects real-time data of power equipment through the monitoring system, and pre-processes and transmits the real-time data based on the message queue system and the stream processing platform;

[0008] A graph database synchronization mechanism, based on a real-time synchronization mechanism, updates the nodes, edges and relationships of the graph database in real time according to the real-time data to obtain topology update information;

[0009] A real-time visualization module, based on a visualization tool and according to the topology update information, displays the updated power topology map in real time;

[0010] The analysis and optimization module predicts the fault risk of the power system status based on the real-time data and topology update information.

[0011] Furthermore, the data transmission platform includes:

[0012] Real-time data is obtained by collecting status data of power equipment such as switches, transformers, generators and lines through the monitoring system, and the real-time data is passed to the downstream using the message queue system. The stream processing platform uses the stream processing engine to pre-process and clean the real-time data.

[0013] Furthermore, the graph database synchronization mechanism includes:

[0014] The real-time synchronization mechanism generates update events after acquiring the change data of the power equipment through the stream processing platform. The graph database adds, deletes, updates and generates topology graphs for nodes, edges and relationships according to the update events through the incremental update and optimized query mechanism to obtain topology update information.

[0015] Furthermore, the real-time visualization module includes:

[0016] Based on the topology update information continuously obtained from the graph database synchronization mechanism and the real-time data of the data transmission platform, it is converted into graph data and compatible with visualization tools such as Gephi.js. Update requests are sent regularly, such as every 2 minutes. The graph database synchronization mechanism and the data transmission platform return the latest topology update information and real-time data to update the power topology map in real time.

[0017] Furthermore, the analysis and optimization module includes:

[0018] After analyzing the real-time data and topology update information as training data, a dynamic model of the power system is constructed. The dynamic model of the power system is used to predict the fault risk based on the set threshold. The threshold setting is based on historical data and the normal operating range of the equipment. The real-time data of the power equipment, such as temperature, voltage, power, vibration and temperature rise, are analyzed. After the predicted data is obtained, it is displayed in real time with the cooperation of the real-time visualization module.

[0019] Furthermore, the data synchronization platform operation process includes:

[0020] The monitoring system collects the status data of power equipment such as switches, transformers, generators and lines in real time to obtain real-time data. After the data is collected, each piece of data is marked by the timestamp t. The formula is expressed as: Q t ={M t , N t , B t , V t , C t}, where Q t represents the real-time data collected at time t, C t is the device status, V t is the frequency, B t is the power, N t is the current, M t is the voltage, and the message queue system is used to pass real-time data to the downstream. The transmission formula of the message queue system is: WE(Q t )→Stream Procing Platform, where WE(Q t ) represents the real-time data transmitted by the message queue. After the real-time data enters the stream processing platform, it must first be preprocessed. The preprocessing includes denoising, missing value filling, and outlier detection. After preprocessing, the real-time data is passed to the graph database.

[0021] Furthermore, the operation process of the graph database synchronization mechanism includes:

[0022] After the real-time synchronization mechanism obtains the change data of the power equipment through the stream processing platform, when the change of the equipment status exceeds the set threshold, an update event is generated. The graph database adds, deletes, updates and generates topology graphs for nodes, edges and relationships according to the update event through the incremental update and optimized query mechanism to obtain topology update information and update events: in is the threshold of the device r state change. The threshold is provided by the rated value, design parameters or manufacturer of each power device according to the predefined normal operating parameter range of each power device. The set of update events generated by the stream processing platform can be expressed as: Each update event It is based on the output of the device r state change detection function, and the incremental update formula is:

[0023] ΔU(t″)=[Δi nodes (t″), Δo edges (t″), Δp edges (t″)], where ΔU(t″) represents the change of the power system topology at time t″, Δi nodes (t″) represents the change of the node in the power system topology diagram at time t″, Δo edges (t″) represents the change of the edge in the power system topology graph at time t″, Δp edges (t″) represents the change in the additional attributes of the edge in the power system topology graph at time t″, such as current, voltage, etc. The update operation formula is: ΔU new (t″)=U old (t″)∪ΔU(t″), where U new (t″) represents the updated power system topology at time t″, U old (t″) represents the power system topology before time t″, ΔU(t″) represents the topology change that occurs at time t″, ∪ represents the union operation of the set, and the optimization query mechanism formula is: Among them I opt (t″) is the optimal query strategy, Cost read，s Is for reading, Cost write，s is the cost of a write operation,

[0024] is an optimization operator that selects the query strategy q to minimize the objective function. is a summation symbol representing the sum of all s from 1 to A.

[0025] Furthermore, the real-time visualization module operation process includes:

[0026] According to the topology update information continuously obtained from the graph database synchronization mechanism and the real-time data of the data transmission platform, it is converted into graph data and compatible with visualization tools such as Gephi.js, and update requests are sent regularly, such as every 2 minutes. The graph database synchronization mechanism and the data transmission platform return the latest topology update information and real-time data to perform real-time updates of the power topology map. The real-time update formula is: in represents the updated node i set, represents the current node i set, Δd i The part that represents the state change of the node. represents the jth edge in the updated edge set, represents the jth edge in the current edge set, Δf jRepresents the state change part of the edge, and the update process formula is:

[0027] where g updated represents the updated graph, H updated represents the updated node set, J updated represents the updated edge set, H updated Represents the node set after real-time update. Indicates the new state of the nth device node, J updated represents the edge set after real-time synchronization, Represents the updated status of the n′th edge.

[0028] Furthermore, the analysis and optimization module operation process includes:

[0029] After analyzing the real-time data and topology update information as training data, a power system dynamic model is constructed. The power system dynamic model is based on a machine learning algorithm. The power system dynamic model formula is: i′ =∫(L i′ ,Z i′ ,X i′ ,C i′ ,V i′ ), where k i′ is the failure risk prediction value of the equipment, ∫(·) represents the trained prediction model, and L i′ is the temperature of device i′, Z i′ is the voltage of device i′, X i′ is the power of device i′, C i′ is the vibration of device i′, V i′ is the temperature rise of device i′, based on the set threshold value using the power system dynamic model. The threshold value is set based on historical data such as the normal operating range of device i′, such as: L i′ ∈[L min ,L max ], where L min is the lower threshold of the equipment operation status, L max is the upper threshold of the equipment operation status, L i′ represents the state quantity of the device at time i′, [L min ,L max ] is a closed interval representing the normal working range of the equipment. The threshold is automatically adjusted according to the operating age and usage of the equipment i′ based on the performance degradation model: The adjustment factor is the factor adjusted according to the equipment degradation model.

[0030] Furthermore, the analysis and optimization module operation process includes:

[0031] Analyze the real-time data of power equipment such as temperature, voltage, power, vibration and temperature rise to predict fault risk. The fault risk prediction formula is: Risk i′ =B(L i′ ,Z i′ ,X i′ ,C i′ ,V i′ ), where Risk i′ represents the failure risk of equipment i′, B(·) represents the failure prediction function based on real-time data, and L i′ is the temperature of device i′, Z i′ is the voltage of device i′, X i′ is the power of device i′, C i′ is the vibration of device i′, V i′ It is the temperature rise of equipment i′. After the predicted data is obtained, it is displayed in real time with the cooperation of the real-time visualization module.

[0032] Beneficial Effects

[0033] Compared with the known public technology, the technical solution provided by the present invention has the following advantages:

[0034] Beneficial effects:

[0035] When used, the present invention is conducive to ensuring the accuracy and timeliness of data, providing reliable data support for subsequent topology updates and fault analysis, improving the overall efficiency of the system, improving the efficiency of database updates, ensuring that topology information reflects the real-time status of the system, and reducing delays and errors. At the same time, it provides users with intuitive data for in-depth analysis of power network topology, optimized scheduling and operation and maintenance decisions, which is conducive to improving the safety and reliability of the power system, identifying potential equipment failures in advance, and reducing the occurrence of sudden failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a system diagram of a power topology system based on a graph database according to the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but includes other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] The present invention is further described in detail with reference to the accompanying drawings:

[0040] Example:

[0041] like Figure 1 As shown, the present invention provides a power topology system based on a graph database, including: a data transmission platform, which collects real-time data of power equipment through a monitoring system, and pre-processes and transmits the real-time data based on a message queue system and a stream processing platform;

[0042] Furthermore, the data transmission platform includes:

[0043] The monitoring system collects the status data of power equipment such as switches, transformers, generators and lines in real time to obtain real-time data, and uses the message queue system to transmit the real-time data to the downstream. The stream processing platform uses the stream processing engine to pre-process and clean the real-time data;

[0044] Furthermore, the data synchronization platform operation process includes:

[0045] The monitoring system collects the status data of power equipment such as switches, transformers, generators and lines in real time to obtain real-time data. After the data is collected, each piece of data is marked by the timestamp t. The formula is expressed as: Q t ={M t , N t , B t , V t , C t}, where Q t represents the real-time data collected at time t, C t is the device status, V t is the frequency, B t is the power, N t is the current, M t is the voltage, and the message queue system is used to pass real-time data to the downstream. The transmission formula of the message queue system is: WE(Q t)→Stream Procing Platform, where WE(Q t ) represents the real-time data transmitted by the message queue. After entering the stream processing platform, the real-time data needs to be preprocessed first. The preprocessing includes denoising, missing value filling and outlier detection. After preprocessing, the real-time data is passed to the graph database;

[0046] Specifically, the data transmission platform collects real-time data of power equipment through the monitoring system, adds a timestamp to each piece of data, and uses the message queue system to pass this data to the stream processing platform. The stream processing platform is responsible for data preprocessing, including denoising, missing value filling, and outlier detection. Finally, the processed data is passed to the graph database, which helps to ensure the accuracy and timeliness of the data, provide reliable data support for subsequent topology updates and fault analysis, and improve the overall efficiency of the system.

[0047] A graph database synchronization mechanism, based on a real-time synchronization mechanism, updates the nodes, edges and relationships of the graph database in real time according to the real-time data to obtain topology update information;

[0048] Furthermore, the graph database synchronization mechanism includes:

[0049] The real-time synchronization mechanism obtains the change data of the power equipment through the stream processing platform and generates update events. The graph database adds, deletes, updates and generates topology graphs for nodes, edges and relationships according to the update events through the incremental update and optimized query mechanism to obtain topology update information.

[0050] Furthermore, the operation process of the graph database synchronization mechanism includes:

[0051] After the real-time synchronization mechanism obtains the change data of the power equipment through the stream processing platform, when the change of the equipment status exceeds the set threshold, an update event is generated. The graph database adds, deletes, updates and generates topology graphs for nodes, edges and relationships according to the update event through the incremental update and optimized query mechanism to obtain topology update information and update events: in is the threshold of the device r state change. The threshold is provided by the rated value, design parameters or manufacturer of each power device according to the predefined normal operating parameter range of each power device. The set of update events generated by the stream processing platform can be expressed as: Each update event It is based on the output of the device r state change detection function, and the incremental update formula is:

[0052] ΔU(t″)=[Δi nodes (t″), Δo edges (t″), Δp edges(t″)], where ΔU(t″) represents the change of the power system topology at time t″, Δi nodes (t″) represents the change of the node in the power system topology diagram at time t″, Δo edges (t″) represents the change of the edge in the power system topology graph at time t″, Δp edges (t″) represents the change in the additional attributes of the edge in the power system topology graph at time t″, such as current, voltage, etc. The update operation formula is: ΔU new (t″)=U old (t″)∪ΔU(t″), where U new (t″) represents the updated power system topology at time t″, U old (t″) represents the power system topology before time t″, ΔU(t″) represents the topology change that occurs at time t″, ∪ represents the union operation of the set, and the optimization query mechanism formula is: Among them I opt (t″) is the optimal query strategy, Cost read，s Is for reading, Cost write，s is the cost of a write operation,

[0053] is an optimization operator that selects the query strategy q to minimize the objective function. is a summation symbol representing the sum of all s from 1 to A;

[0054] Specifically, the graph database synchronization mechanism obtains the change data of power equipment through a real-time synchronization mechanism and generates update events according to the set thresholds. The graph database uses the incremental update mechanism to add, delete, and update the power system topology based on the update events, thereby updating the topology information in real time. At the same time, the optimized query mechanism is used to reduce the query cost and detect device status changes based on the set thresholds to ensure that only important changes are included in the system update, avoiding unnecessary noise and misoperation, which is beneficial to improving the database update efficiency and ensuring that the topology information reflects the real-time status of the system.

[0055] A real-time visualization module, based on a visualization tool and according to the topology update information, displays the updated power topology map in real time;

[0056] Furthermore, the real-time visualization module includes:

[0057] Based on the topology update information continuously obtained from the graph database synchronization mechanism and the real-time data of the data transmission platform, it is converted into graph data and compatible with visualization tools such as Gephi.js. Update requests are sent regularly, such as every 2 minutes. The graph database synchronization mechanism and the data transmission platform return the latest topology update information and real-time data to update the power topology map in real time.

[0058] Furthermore, the real-time visualization module operation process includes:

[0059] According to the topology update information continuously obtained from the graph database synchronization mechanism and the real-time data of the data transmission platform, it is converted into graph data and compatible with visualization tools such as Gephi.js, and update requests are sent regularly, such as every 2 minutes. The graph database synchronization mechanism and the data transmission platform return the latest topology update information and real-time data to perform real-time updates of the power topology map. The real-time update formula is: in represents the updated node i set, represents the current node i set, Δd i The part that represents the state change of the node. represents the jth edge in the updated edge set, represents the jth edge in the current edge set, Δf j Represents the state change part of the edge, and the update process formula is:

[0060] where g updated represents the updated graph, H updated represents the updated node set, J updated represents the updated edge set, H updated Represents the node set after real-time update. Indicates the new state of the nth device node, J updated represents the edge set after real-time synchronization, Represents the update status of the n′th edge;

[0061] Specifically, the real-time visualization module obtains the latest topology information and equipment status data from the graph database synchronization mechanism and data transmission platform every 2 minutes, and updates it into graphic data in real time. It is compatible with the Gephi.js visualization tool, and finally displays the power topology map to timely reflect the changes in the status of power equipment, so that the displayed information is the latest, which is conducive to reducing delays and errors, and at the same time provides users with intuitive data for in-depth analysis of power network topology, optimized scheduling and operation and maintenance decisions.

[0062] An analysis and optimization module predicts the fault risk of the power system state based on the real-time data and topology update information;

[0063] Furthermore, the analysis and optimization module includes:

[0064] After analyzing the real-time data and topology update information as training data, a power system dynamic model is constructed, and the power system dynamic model is used to analyze the real-time data of the power equipment such as temperature, voltage, power, vibration and temperature rise to predict the risk of failure based on the set threshold value. After the predicted data is obtained, it is displayed in real time with the cooperation of the real-time visualization module;

[0065] Furthermore, the analysis and optimization module operation process includes:

[0066] After analyzing the real-time data and topology update information as training data, a power system dynamic model is constructed. The power system dynamic model is based on a machine learning algorithm. The power system dynamic model formula is: ′ =∫(Li ′ ,Zi ′ ,Xi ′ ,Ci ′ ,Vi ′ ), where k i′ is the failure risk prediction value of the equipment, ∫(·) represents the trained prediction model, and L i′ is the temperature of device i′, Z i′ is the voltage of device i′, X i′ is the power of device i′, C i′ is the vibration of device i′, V i′ is the temperature rise of device i′, based on the set threshold value using the power system dynamic model. The threshold value is set based on historical data such as the normal operating range of device i′, such as: L i′ ∈[L min ,L max ], where L min is the lower threshold of the equipment operation status, L max is the upper threshold of the equipment operation status, L i′ represents the state quantity of the device at time i′, [L min ,L max ] is a closed interval representing the normal working range of the equipment. The threshold is automatically adjusted according to the operating age and usage of the equipment i′ based on the performance degradation model: The adjustment factor is the factor adjusted according to the equipment degradation model.

[0067] Furthermore, the analysis and optimization module operation process includes:

[0068] Analyze the real-time data of power equipment such as temperature, voltage, power, vibration and temperature rise to predict fault risk. The fault risk prediction formula is: Risk i′ =B(L i′ ,Z i′ ,Xi′ ,C i′ ,V i′ ), where Risk i′ represents the failure risk of equipment i′, B(·) represents the failure prediction function based on real-time data, and L i′ is the temperature of device i′, Z i′ is the voltage of device i′, X i′ is the power of device i′, C i′ is the vibration of device i′, V i′ is the temperature rise of equipment i′. After the predicted data is obtained, it is displayed in real time with the cooperation of the real-time visualization module;

[0069] Specifically, based on the processed real-time data and topology update information, a dynamic model of the power system is constructed through a machine learning algorithm. In order to effectively identify fault risks, thresholds are set according to the normal operating range of the equipment. The thresholds are set based on historical data and the normal operating status range of the equipment, and are dynamically adjusted according to the operating years and usage of the equipment. Based on the dynamic model of the power system and the set thresholds, the system analyzes the real-time data of the power equipment and predicts fault risks. Once the system predicts a fault risk, it will promptly update the power system topology map and display the latest status through a real-time visualization module, which is conducive to improving the safety and reliability of the power system, identifying potential equipment failures in advance, and reducing the occurrence of sudden failures.

[0070] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power topology system based on a graph database, characterized in that: include: The data transmission platform collects real-time data of power equipment through the monitoring system, and pre-processes and transmits the real-time data based on the message queue system and the stream processing platform; A graph database synchronization mechanism, based on a real-time synchronization mechanism, updates the nodes, edges and relationships of the graph database in real time according to the real-time data to obtain topology update information; A real-time visualization module, based on a visualization tool and according to the topology update information, displays the updated power topology map in real time; The analysis and optimization module predicts the fault risk of the power system status based on the real-time data and topology update information.

2. According to claim 1, a power topology system based on a graph database is characterized in that: The data transmission platform includes: Real-time data is obtained by collecting status data of power equipment such as switches, transformers, generators and lines through the monitoring system, and the real-time data is passed to the downstream using the message queue system. The stream processing platform uses the stream processing engine to pre-process and clean the real-time data.

3. The power topology system based on graph database according to claim 2, characterized in that: The graph database synchronization mechanism includes: The real-time synchronization mechanism generates update events after acquiring the change data of the power equipment through the stream processing platform. The graph database adds, deletes, updates and generates topology graphs for nodes, edges and relationships according to the update events through the incremental update and optimized query mechanism to obtain topology update information.

4. The power topology system based on graph database according to claim 3 is characterized in that: Real-time visualization modules include: Based on the topology update information continuously obtained from the graph database synchronization mechanism and the real-time data of the data transmission platform, it is converted into graph data and compatible with visualization tools such as Gephi.js. Update requests are sent regularly, such as every 2 minutes. The graph database synchronization mechanism and the data transmission platform return the latest topology update information and real-time data to update the power topology map in real time.

5. The power topology system based on graph database according to claim 4, characterized in that: The analysis and optimization modules include: After analyzing the real-time data and topology update information as training data, a dynamic model of the power system is constructed. The dynamic model of the power system is used to predict the fault risk based on the set threshold. The threshold setting is based on historical data and the normal operating range of the equipment. The real-time data of the power equipment, such as temperature, voltage, power, vibration and temperature rise, are analyzed. After the predicted data is obtained, it is displayed in real time with the cooperation of the real-time visualization module.

6. The power topology system based on graph database according to claim 5, characterized in that: The data synchronization platform operation process includes: The monitoring system collects the status data of power equipment such as switches, transformers, generators and lines in real time to obtain real-time data. After the data is collected, each piece of data is marked by the timestamp t. The formula is expressed as: Q t ={M t , N t , B t , V t , C t }, where Q t represents the real-time data collected at time t, C t is the device status, V t is the frequency, B t is the power, N t is the current, M t is the voltage, and the message queue system is used to pass real-time data to the downstream. The transmission formula of the message queue system is: WE(Q t )→Stream Procing Platform, where WE(Q t ) represents the real-time data transmitted by the message queue. After the real-time data enters the stream processing platform, it must first be preprocessed. The preprocessing includes denoising, missing value filling, and outlier detection. After preprocessing, the real-time data is passed to the graph database.

7. The power topology system based on graph database according to claim 6, characterized in that: The operation process of the graph database synchronization mechanism includes: After the real-time synchronization mechanism obtains the change data of the power equipment through the stream processing platform, when the change of the equipment status exceeds the set threshold, an update event is generated. The graph database adds, deletes, updates and generates topology graphs for nodes, edges and relationships according to the update event through the incremental update and optimized query mechanism to obtain topology update information and update events: in is the threshold of the device r state change. The threshold is provided by the rated value, design parameters or manufacturer of each power device according to the predefined normal operating parameter range of each power device. The set of update events generated by the stream processing platform can be expressed as: Each update event It is based on the output of the device r state change detection function, and the incremental update formula is: Where ΔU(t″) represents the change of the power system topology at time t″, Δi nodes (t″) represents the change of the node in the power system topology diagram at time t″, Δo edges (t″) represents the change of the edge in the power system topology graph at time t″, Δp edges (t″) represents the change in the additional attributes of the edge in the power system topology graph at time t″, such as current, voltage, etc. The update operation formula is: ΔU new (t″)=U old (t″)∪ΔU(t″), where U new (t″) represents the updated power system topology at time t″, U old (t″) represents the power system topology before time t″, ΔU(t″) represents the topology change that occurs at time t″, ∪ represents the union operation of the set, and the optimization query mechanism formula is: Among them I opt (t″) is the optimal query strategy, Cost read，s Is for reading, Cost write，s is the cost of a write operation, is an optimization operator that selects the query strategy q to minimize the objective function. is a summation symbol representing the sum of all s from 1 to A.

8. The power topology system based on graph database according to claim 7, characterized in that: The real-time visualization module operation process includes: According to the topology update information continuously obtained from the graph database synchronization mechanism and the real-time data of the data transmission platform, it is converted into graph data and compatible with visualization tools such as Gephi.js, and update requests are sent regularly, such as every 2 minutes. The graph database synchronization mechanism and the data transmission platform return the latest topology update information and real-time data to perform real-time updates of the power topology map. The real-time update formula is: in represents the updated node i set, represents the current node i set, Δd i The part that represents the state change of the node. represents the jth edge in the updated edge set, represents the jth edge in the current edge set, Δf j Represents the state change part of the edge, and the update process formula is: where g updated represents the updated graph, H updated represents the updated node set, J updated represents the updated edge set, H updated Represents the node set after real-time update. Indicates the new state of the nth device node, J updated represents the edge set after real-time synchronization, Represents the updated status of the n′th edge.

9. The power topology system based on graph database according to claim 8, characterized in that: The operation process of the analysis and optimization module includes: After analyzing the real-time data and topology update information as training data, a power system dynamic model is constructed. The power system dynamic model is based on a machine learning algorithm. The power system dynamic model formula is: i′ =∫(L i′ ,Z i′ ,X i′ ,C i′ ,V i′ ), where k i′ is the failure risk prediction value of the equipment, ∫(·) represents the trained prediction model, and L i′ is the temperature of device i′, Z i′ is the voltage of device i′, X i′ is the power of device i′, C i′ is the vibration of device i′, V i′ is the temperature rise of device i′, based on the set threshold value using the power system dynamic model. The threshold value is set based on historical data such as the normal operating range of device i′, such as: L i′ ∈[L min ,L max ], where L min is the lower threshold of the equipment operation status, L max is the upper threshold of the equipment operation status, L i′ represents the state quantity of the device at time i′, [L min ,L max ] is a closed interval representing the normal working range of the equipment. The threshold is automatically adjusted according to the operating age and usage of the equipment i′ based on the performance degradation model: The adjustment factor is the factor adjusted according to the equipment degradation model.

10. The power topology system based on graph database according to claim 9, characterized in that: The operation process of the analysis and optimization module includes: Analyze the real-time data of power equipment such as temperature, voltage, power, vibration and temperature rise to predict fault risk. The fault risk prediction formula is: Risk i′ =B(L i′ ,Z i′ ,X i′ ,C i′ ,V i′ ), where Risk i′ represents the failure risk of equipment i′, B(·) represents the failure prediction function based on real-time data, and L i′ is the temperature of device i′, Z i′ is the voltage of device i′, X i′ is the power of device i′, C i′ is the vibration of device i′, V i′ It is the temperature rise of equipment i′. After the predicted data is obtained, it is displayed in real time with the cooperation of the real-time visualization module.

Images