Intelligent power grid planning coordination evaluation method

Abstract

The invention provides a smart power grid planning coordination evaluation method, which relates to the technical field of smart power grids and comprises the following steps: collecting power grid structure data, power operation data and external environment data related to a power grid; forming a power grid structure database based on the power grid structure data, the power operation data and the external environment data; extracting features of any data in the power grid structure database; constructing a coordination evaluation model based on topological feature information, operation feature information and environment feature information of the power grid; inputting data obtained by data acquisition into a coordination evaluation model to obtain an evaluation result; and generating an evaluation decision suggestion according to the evaluation result. According to the method, power grid structure, operation and external environment data are comprehensively collected, a multi-agent, a complex network and a fuzzy logic theory are fused to construct a model, topology, operation and environment characteristics are accurately extracted, key nodes are accurately identified, load distribution is optimized, a scientific basis is provided for planning operation, and the reliability and the overall performance of a power grid are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to a smart grid planning coordination evaluation method. Background Art

[0002] With the advancement of smart grid construction, the coordination of its planning is crucial to ensure the stable and efficient operation of the power grid.

[0003] However, traditional evaluation methods often have limitations. Some evaluation methods only focus on a single factor, such as focusing only on the grid structure and ignoring the impact of operating data and the external environment, or only analyzing the power operation status without combining the actual physical structure and external conditions of the grid. This one-sidedness lacks full consideration of the complex relationship between the grid structure, operating status and external environment, making it difficult to evaluate the coordination of smart grid planning. Therefore, there is an urgent need for an evaluation method that comprehensively considers multiple factors to improve the quality and effectiveness of smart grid planning.

[0004] Therefore, it is necessary to provide a smart grid planning coordination evaluation method to solve the above technical problems. Summary of the invention

[0005] The present invention provides a smart grid planning coordination evaluation method, which solves the problems raised in the background technology.

[0006] In order to solve the above technical problems, the present invention provides a smart grid planning coordination evaluation method, comprising the following steps: S1, collecting grid structure data, power operation data and external environment data related to the grid; forming a grid structure database based on the grid structure data, power operation data and external environment data; S2, extract the features of any data in the power grid structure database: S21, extracting topological feature information based on power grid structure data; S22, extracting operation characteristic information based on the power operation data; S23, extracting environmental feature information based on external environmental data; S3, building a coordination evaluation model based on the topological characteristic information, operation characteristic information, and environmental characteristic information of the power grid; S4, inputting the data obtained from data collection into the coordination evaluation model to obtain evaluation results; and generating evaluation decision recommendations based on the evaluation results.

[0007] Preferably, based on step S1, the grid structure data, power operation data and external environment data related to the grid are collected, specifically: The grid structure data specifically refers to the connection relationship between each node in the grid, including the topological structure information of substations, transmission lines, and distribution lines; the power operation data specifically refers to the voltage, current, and power of each node in the grid; the external environment data specifically refers to meteorological data, geographical data, and socio-economic data related to grid operation.

[0008] Preferably, based on step S3, the specific steps of constructing the coordination evaluation model are: S31, adopts a multi-agent system initialization evaluation model, regards each node in the power grid as an agent, and each agent has its own state information and behavior rules; the state information includes voltage, active power, and reactive power, and the behavior rules include power regulation strategy, fault response mechanism and cooperation rules; S32, design a message queue-based communication protocol between intelligent agents to achieve information interaction, and adopt a distributed collaborative control algorithm, specifically a consensus algorithm: Interaction between agents, where xi(t) represents the state variable of agent number i at time t, Ni represents the neighbor set of agent number i, and aij represents the connection weight between agents number i and j; S33, introduces complex network theory, regards the power grid as a complex network, and constructs a complex network model of the power grid. Specifically, each node in the power grid is regarded as a node in the complex network, and the transmission lines and distribution lines connecting the nodes are regarded as edges; S34, using the node index in the complex network model to calculate the structural characteristic index of the power grid; the structural characteristic index includes the node degree value, clustering coefficient, node betweenness centrality, edge betweenness centrality, key nodes or key lines of the node; S35, performing robustness and vulnerability analysis on a complex network model of the power grid to obtain coordination evaluation information; the coordination evaluation information includes a connectivity index, a power transmission capacity index, a connectivity difference and a power transmission difference and corresponding time integrals and coordination evaluation values; S36, integrates fuzzy logic and uses fuzzy logic to process fuzzy information in the evaluation process; establishes a fuzzy rule base and uses the extracted feature data as fuzzy input; for each fuzzy input and output variable, determines the appropriate fuzzy set and membership function, and the membership function is used to describe the boundary and degree of fuzziness of each fuzzy set; inputs the fuzzified topological characteristics, operation characteristics and environmental impact characteristics data into the fuzzy rule base, and performs reasoning calculations through the fuzzy reasoning engine to obtain the fuzzy evaluation results of the coordination of power grid planning.

[0009] Preferably, when integrating fuzzy logic to construct an evaluation model, a quantum fuzzy logic algorithm is used, and the superposition state and entanglement characteristics of quantum bits are used to process fuzzy information; the quantum fuzzy logic algorithm specifically quantizes the fuzzy input through quantum gate operations, and then performs reasoning operations based on quantum fuzzy rules, and finally obtains a fuzzy evaluation result of the coordination of power grid planning.

[0010] Preferably, the acquisition logic of the connection weight aij is: Identify the electrical distance and line impedance between any set of adjacent agents; Set the monitoring time zone, calculate the mean and standard deviation of the line impedance in the monitoring time zone to obtain the impedance mean and impedance fluctuation value; The line impedance, impedance mean value and impedance fluctuation value are weightedly calculated to obtain the line impedance impact value; The electrical distance and line impedance influence values ​​are weighted and calculated to obtain the connection weight aij.

[0011] Preferably, the collection time interval of the power operation data is dynamically adjusted according to the power grid load fluctuation, specifically: Set a real-time load monitoring cycle, calculate the load change rate of the power grid in each real-time load monitoring cycle and mark it as a load change value; Set the collection time interval frequency group, including normal time interval frequency and first-level time interval frequency; If the load change value is within the preset reasonable load change range, it is determined that the load change is within a reasonable range, and the power operation data is collected using a normal time interval frequency; If the load change value is not within the preset reasonable load change range, it is determined to be a period of large load change, and the power operation data is collected using the first-level time interval frequency.

[0012] Preferably, based on step S33, the structural characteristic index of the power grid is calculated using the node index in the complex network model, specifically: Identify the number of edges connected to the node and mark it as the node degree value; Count the frequencies of nodes with different degree values ​​and get the node degree distribution; Calculate the clustering coefficient of each node, the formula is expressed as: ; Where j represents the index of the node, Cj represents the clustering coefficient of node j, ej represents the number of edges actually existing between the neighboring nodes of node i, and kj represents the node degree value of node j; Calculate the node betweenness centrality and edge betweenness centrality of any node and line respectively; the calculation formula of node betweenness centrality is: ; The calculation formula of edge betweenness centrality is: ; Set the betweenness centrality threshold, compare the node betweenness centrality and edge betweenness centrality of the node or line with their corresponding betweenness centrality threshold. If the node betweenness centrality and edge betweenness centrality are greater than their corresponding betweenness centrality threshold, mark the node or line as a key node or key line.

[0013] Preferably, based on step S34, a robustness and vulnerability analysis is performed on the complex network model of the power grid, specifically: Identify the fault scenarios and disturbances currently being simulated; Calculate the number of nodes contained in the largest connected subgraph in the power grid after a fault or disturbance in a complex network model Total number of nodes The ratio is marked as the connectivity index H, and the formula is: ; Calculate the actual power delivered by the grid after a fault or disturbance in complex network models Transmit power during normal operation The ratio of is marked as the power transmission capability index G, and the formula is expressed as: ; Set the expected values ​​corresponding to the connectivity index and the power transmission capacity index, and calculate the connectivity difference LH and the power transmission difference LG by taking the difference between the power transmission capacity index and the power transmission capacity index and the corresponding expected values; The concept of time integration is introduced to evaluate the changes in the connectivity difference LH and the power transfer difference LG, specifically: set up is the function of connectivity difference changing with time, is the function of the power transmission capacity difference changing with time, t0 is the start time of the fault or disturbance, and t1 is the end time of the observation; the time integral of the connectivity difference is calculated, and the formula is expressed as: ; Calculate the time integral of the power transfer difference, the formula is expressed as: ; The time integral of the connectivity difference and the power transfer difference is weighted to obtain the coordination evaluation value E, which is expressed as ; Wherein, w1 and w2 represent the weights corresponding to the time integrals of the connectivity difference and the power transfer difference, respectively; the connectivity index, the power transmission capacity index, the connectivity difference and the power transfer difference and the corresponding time integral and coordination evaluation value are marked as coordination evaluation information; The coordination of the power grid in the simulation scenario or disturbance is judged based on the coordination evaluation information, specifically: A coordination evaluation threshold is set. If the coordination evaluation value is less than the coordination evaluation threshold, it indicates that the power grid has good coordination in the simulation scenario or disturbance. If the coordination evaluation value is greater than or equal to the coordination evaluation threshold, it indicates that the power grid has weak coordination. In this case, the redundant lines at the corresponding positions of the key nodes and key lines in the power grid are identified and enabled in sequence. The coordination of the power grid after the redundant lines are enabled in sequence is evaluated to obtain a comprehensive coordination evaluation value; when the comprehensive coordination evaluation value is greater than its preset comprehensive coordination evaluation threshold, it means that the enabled redundant lines are sufficient to supplement the weak coordination of the power grid.

[0014] Preferably, the coordination of the power grid after the redundant lines are enabled in sequence is evaluated, specifically: The coordination evaluation value of the power grid after the redundant line is enabled is calculated by difference with the coordination evaluation value before the activation to obtain the evaluation change value; the coordination evaluation value of the power grid after the redundant line is enabled is calculated by difference with the coordination evaluation threshold to obtain the coordination evaluation difference; the coordination evaluation value of the power grid after the redundant line is enabled is calculated by difference with the coordination evaluation threshold to obtain the coordination threshold difference; the coordination evaluation difference and the coordination threshold difference are weighted to obtain the coordination evaluation value; The co-evaluation values ​​after activating the redundant lines of different key nodes or key lines are traversed in turn, and the mean and standard deviation of the co-evaluation values ​​after activating the redundant lines of different key nodes or key lines are calculated to obtain the co-evaluation mean and the co-evaluation fluctuation value; the co-evaluation value, the co-evaluation mean and the co-evaluation fluctuation value are weightedly calculated to obtain the co-evaluation comprehensive value.

[0015] Compared with the related art, the smart grid planning coordination evaluation method provided by the present invention has the following beneficial effects: 1. The present invention comprehensively collects data on the structure, operation and external environment of the power grid, integrates multi-agent, complex network and fuzzy logic theory to build a model, accurately extracts topology, operation and environmental characteristics, accurately identifies key nodes, optimizes load distribution, provides a scientific basis for planning and operation, and effectively improves the reliability and overall performance of the power grid.

[0016] 2. The present invention adjusts the operation data collection interval according to load fluctuations, updates the power grid information in a timely manner, and re-evaluates the coordination regularly, so as to effectively respond to changes in the power grid structure, operation status and external environment, ensure that the power grid is always in the optimal coordination state, and enhance the flexibility and adaptability of the power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A method flow chart of a smart grid planning coordination evaluation method provided by the present invention. DETAILED DESCRIPTION

[0018] 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. The singular forms of "class", "group" and "the" used in this disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0020] It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0021] Please refer to Figure 1 A smart grid planning coordination evaluation method includes the following steps: S1, collecting grid structure data, power operation data and external environment data related to the grid; forming a grid structure database based on the grid structure data, power operation data and external environment data; S2, extract the features of any data in the power grid structure database: S21, extracting topological feature information based on power grid structure data; S22, extracting operation characteristic information based on the power operation data; S23, extracting environmental feature information based on external environmental data; It should be noted that the feature extraction in steps S21-S23 is an existing mature technology, so it is not described in detail in this application; S3, building a coordination evaluation model based on the topological characteristic information, operation characteristic information, and environmental characteristic information of the power grid; S4, inputting the data obtained from data collection into the coordination evaluation model to obtain evaluation results; and generating evaluation decision recommendations based on the evaluation results.

[0022] In this application, based on step S1, the grid structure data, power operation data and external environment data related to the grid are collected, specifically: The grid structure data specifically refers to the connection relationship between each node in the grid, including the topological structure information of substations, transmission lines, and distribution lines; the power operation data specifically refers to the voltage, current, and power of each node in the grid; the external environment data specifically refers to the meteorological data, geographic data, and socio-economic data related to the operation of the grid.

[0023] In this application, based on step S3, the specific steps of constructing the coordination evaluation model are: S31, adopts a multi-agent system initialization evaluation model, regards each node in the power grid as an agent, and each agent has its own state information and behavior rules; the state information includes voltage, active power, and reactive power, and the behavior rules include power regulation strategy, fault response mechanism and cooperation rules; The specific process of setting behavioral rules is as follows: Power regulation strategy: Obtaining the load change value of the power grid , compare the load change value with its change threshold. If the load change value is greater than its change threshold, a power regulation strategy is generated; the power regulation strategy is used to adjust the load according to the dynamic adjustment coefficient. The output power of the control agent and the dynamic adjustment coefficient are calculated as follows: ;in, represents the power regulation factor (determined according to the characteristics of the power grid and the response capability of the equipment), represents the rated power of the agent numbered i; Fault response mechanism: collect the state information of the intelligent body, calculate the difference between any parameter in the state information and its preset reference value to obtain the state parameter difference value; Set the state monitoring time zone, calculate the mean and standard deviation of the state difference values ​​of the parameters in the state information of the intelligent agent to obtain the state difference mean and state difference discrete value; The state parameter difference value, state parameter difference mean value, and state parameter difference discrete value of the agent are weighted to obtain the state parameter influence value; the state parameter influence values ​​of all parameters in the state information of the agent are weighted to obtain the fault assessment value; a fault assessment threshold is set, and if the fault assessment value is greater than its fault assessment threshold, a fault response mechanism is generated; the fault response mechanism is used to trigger the sending of a fault signal to the agent adjacent to the agent and cut off the line between the agent and the adjacent agent; Collaboration rules: Get the load change value of the agent; set the overload change threshold, compare the load change value of the agent with its overload change threshold, and generate the agent's collaboration rules if the load change value is greater than or equal to its overload change threshold; the collaboration rules are used to trigger the collaborative evaluation analysis of adjacent agents, specifically: The electrical distance, line impedance and load change value between adjacent intelligent agents corresponding to the collaborative rule of the generated intelligent agent are obtained; the electrical distance, line impedance and load change value are weightedly calculated to obtain the collaborative value; Arrange the adjacent agents corresponding to the collaboration rules of the generated agents in the order of the collaboration values ​​to obtain the adjacent agent collaboration list; Select a set number of adjacent agents in the adjacent agent collaboration list in order of size as collaborative load agents; Analyze the load transfer power of the collaborative load agent, specifically: Obtain the load change value corresponding to the collaboration rule of the generated intelligent agent, and calculate the difference between the load change value and the conventional load change value preset by the intelligent agent to obtain the load excess difference; The total synergy value is obtained by summing up the synergy values ​​of a set number of synergy load agents; the ratio between the synergy value of each synergy load agent and the total synergy value is marked as a synergy allocation coefficient; and the excess of the agent is allocated to each synergy load agent according to the synergy allocation coefficient; S32, design a message queue-based communication protocol between intelligent agents to achieve information interaction, and adopt a distributed collaborative control algorithm, specifically a consensus algorithm: Interaction between agents, where xi(t) represents the state variable of agent number i at time t, Ni represents the neighbor set of agent number i, and aij represents the connection weight between agents number i and j; S33, introduces complex network theory, regards the power grid as a complex network, and constructs a complex network model of the power grid. Specifically, each node in the power grid is regarded as a node in the complex network, and the transmission lines and distribution lines connecting the nodes are regarded as edges; S34, using the node index in the complex network model to calculate the structural characteristic index of the power grid; the structural characteristic index includes the node degree value, clustering coefficient, node betweenness centrality, edge betweenness centrality, key nodes or key lines of the node; S35, performing robustness and vulnerability analysis on a complex network model of the power grid to obtain coordination evaluation information; the coordination evaluation information includes a connectivity index, a power transmission capacity index, a connectivity difference and a power transmission difference and corresponding time integrals and coordination evaluation values; S36, integrates fuzzy logic and uses fuzzy logic to process fuzzy information in the evaluation process; establishes a fuzzy rule base and uses the extracted feature data as fuzzy input; for each fuzzy input and output variable, determines the appropriate fuzzy set and membership function. The division of the fuzzy set should be reasonably determined based on the actual value range and characteristics of the variable, and the membership function is used to describe the boundary and degree of fuzziness of each fuzzy set; inputs the fuzzified topological characteristics, operating characteristics and environmental impact characteristics data into the fuzzy rule base, and performs reasoning calculations through the fuzzy inference engine to obtain the fuzzy evaluation results of the coordination of the power grid planning; the fuzzy inference engine adopts the Mamdani reasoning method or the TS reasoning method.

[0024] In this application, when integrating fuzzy logic to construct an evaluation model, a quantum fuzzy logic algorithm is used to process fuzzy information using the superposition state and entanglement characteristics of quantum bits; the quantum fuzzy logic algorithm specifically quantizes the fuzzy input through quantum gate operations, and then performs reasoning operations based on quantum fuzzy rules, and finally obtains a fuzzy evaluation result of the coordination of power grid planning.

[0025] In this application, the logic for obtaining the connection weight aij is: Identify the electrical distance and line impedance between any set of adjacent agents; Set the monitoring time zone, calculate the mean and standard deviation of the line impedance in the monitoring time zone to obtain the impedance mean and impedance fluctuation value; The line impedance, impedance mean value and impedance fluctuation value are weightedly calculated to obtain the line impedance impact value; The electrical distance and line impedance influence values ​​are weighted and calculated to obtain the connection weight aij.

[0026] In this application, the time interval for collecting power operation data is dynamically adjusted according to the fluctuation of power grid load, specifically: Set the real-time load monitoring cycle, calculate the load change rate of the power grid in each real-time load monitoring cycle and mark it as the load change value , the formula is: ;in, It is represented as the load value at the current time t, Indicates the previous real-time load monitoring cycle The load value at the moment; Set the collection time interval frequency group, including normal time interval frequency and first-level time interval frequency. It should be noted that the normal time interval frequency is smaller than the first-level time interval frequency; If the load change value is within the preset reasonable load change range, it is determined that the load change is within a reasonable range, and the power operation data is collected using a normal time interval frequency; If the load change value is not within the preset reasonable load change range, it is determined to be a period of large load change, and the power operation data is collected using the first-level time interval frequency.

[0027] In this application, based on step S33, the structural characteristic index of the power grid is calculated using the node index in the complex network model, specifically: Identify the number of edges connected to the node and mark it as the node degree value; Count the frequencies of nodes with different degree values ​​and get the node degree distribution; Calculate the clustering coefficient of each node, the formula is expressed as: ; Where j represents the index of the node, Cj represents the clustering coefficient of node j, ej represents the number of edges actually existing between the neighboring nodes of node i, and kj represents the node degree value of node j; Calculate the node betweenness centrality and edge betweenness centrality of any node and line respectively; the calculation formula of node betweenness centrality is: ; The calculation formula of edge betweenness centrality is: ; Set the betweenness centrality threshold, compare the node betweenness centrality and edge betweenness centrality of the node or line with their corresponding betweenness centrality threshold. If the node betweenness centrality and edge betweenness centrality are greater than their corresponding betweenness centrality threshold, mark the node or line as a key node or key line.

[0028] In this application, based on step S34, the complex network model of the power grid is analyzed for robustness and vulnerability, specifically: Identify the currently simulated fault scenarios and disturbance conditions, including fault scenarios such as line short circuits and node failures, and disturbance conditions such as load mutations and meteorological disaster impacts; Calculate the number of nodes contained in the largest connected subgraph in the power grid after a fault or disturbance in a complex network model Total number of nodes The ratio is marked as the connectivity index H, and the formula is: ; Calculate the actual power delivered by the grid after a fault or disturbance in complex network models Transmit power during normal operation The ratio of is marked as the power transmission capability index G, and the formula is expressed as: ; Set the expected values ​​corresponding to the connectivity index and the power transmission capacity index, and calculate the connectivity difference LH and the power transmission difference LG by taking the difference between the power transmission capacity index and the power transmission capacity index and the corresponding expected values; The concept of time integration is introduced to evaluate the changes in the connectivity difference LH and the power transfer difference LG, specifically: set up is the function of connectivity difference changing with time, is the function of the power transmission capacity difference changing with time, t0 is the start time of the fault or disturbance, and t1 is the end time of the observation; the time integral of the connectivity difference is calculated, and the formula is expressed as: ; Calculate the time integral of the power transfer difference, the formula is expressed as: ; The time integral of the connectivity difference and the power transfer difference is weighted to obtain the coordination evaluation value E, which is expressed as ; Wherein, w1 and w2 represent the weights corresponding to the time integrals of the connectivity difference and the power transfer difference, respectively; the connectivity index, the power transmission capacity index, the connectivity difference and the power transfer difference and the corresponding time integral and coordination evaluation value are marked as coordination evaluation information; The coordination of the power grid in the simulation scenario or disturbance is judged based on the coordination evaluation information, specifically: A coordination evaluation threshold is set. If the coordination evaluation value is less than the coordination evaluation threshold, it indicates that the power grid has good coordination in the simulation scenario or disturbance. If the coordination evaluation value is greater than or equal to the coordination evaluation threshold, it indicates that the power grid has weak coordination. In this case, the redundant lines at the corresponding positions of the key nodes and key lines in the power grid are identified and enabled in sequence. The coordination of the power grid after the redundant lines are enabled in sequence is evaluated to obtain a comprehensive coordination evaluation value; when the comprehensive coordination evaluation value is greater than its preset comprehensive coordination evaluation threshold, it means that the enabled redundant lines are sufficient to supplement the weak coordination of the power grid.

[0029] In this application, the coordination of the power grid after the redundant lines are enabled in sequence is evaluated, specifically: The coordination evaluation value of the power grid after the redundant line is enabled is calculated by difference with the coordination evaluation value before the activation to obtain the evaluation change value; the coordination evaluation value of the power grid after the redundant line is enabled is calculated by difference with the coordination evaluation threshold to obtain the coordination evaluation difference; the coordination evaluation value of the power grid after the redundant line is enabled is calculated by difference with the coordination evaluation threshold to obtain the coordination threshold difference; the coordination evaluation difference and the coordination threshold difference are weighted to obtain the coordination evaluation value; The co-evaluation values ​​after activating the redundant lines of different key nodes or key lines are traversed in turn, and the mean and standard deviation of the co-evaluation values ​​after activating the redundant lines of different key nodes or key lines are calculated to obtain the co-evaluation mean and the co-evaluation fluctuation value; the co-evaluation value, the co-evaluation mean and the co-evaluation fluctuation value are weightedly calculated to obtain the co-evaluation comprehensive value.

[0030] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0031] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A smart grid planning coordination evaluation method, characterized in that: The following steps are involved: S1, collecting grid structure data, power operation data and external environment data related to the grid; forming a grid structure database based on the grid structure data, power operation data and external environment data; S2, extract the features of any data in the power grid structure database: S21, extracting topological feature information based on power grid structure data; S22, extracting operation characteristic information based on the power operation data; S23, extracting environmental feature information based on external environmental data; S3, building a coordination evaluation model based on the topological characteristic information, operation characteristic information, and environmental characteristic information of the power grid; S4, inputting the data obtained from data collection into the coordination evaluation model to obtain evaluation results; and generating evaluation decision recommendations based on the evaluation results.

2. A smart grid planning coordination evaluation method according to claim 1, characterized in that: Based on step S1, the grid structure data, power operation data and external environment data related to the grid are collected, specifically: The grid structure data specifically refers to the connection relationship between each node in the grid, including the topological structure information of substations, transmission lines, and distribution lines; the power operation data specifically refers to the voltage, current, and power of each node in the grid; the external environment data specifically refers to meteorological data, geographical data, and socio-economic data related to grid operation.

3. A smart grid planning coordination evaluation method according to claim 1, characterized in that: Based on step S3, the specific steps of constructing the coordination evaluation model are: S31, uses a multi-agent system to initialize the evaluation model, treating each node in the power grid as an agent, each agent has its own matching state information and behavior rules; The status information includes voltage, active power, and reactive power, and the behavior rules include power regulation strategy, fault response mechanism, and collaboration rules; S32, design a message queue-based communication protocol between intelligent agents to achieve information interaction, and adopt a distributed collaborative control algorithm, specifically a consensus algorithm: Interaction between agents, where xi(t) represents the state variable of agent number i at time t, Ni represents the neighbor set of agent number i, and aij represents the connection weight between agents number i and j; S33, introduces complex network theory, regards the power grid as a complex network, and constructs a complex network model of the power grid. Specifically, each node in the power grid is regarded as a node in the complex network, and the transmission lines and distribution lines connecting the nodes are regarded as edges; S34, using the node index in the complex network model to calculate the structural characteristic index of the power grid; the structural characteristic index includes the node degree value, clustering coefficient, node betweenness centrality, edge betweenness centrality, key nodes or key lines of the node; S35, performing robustness and vulnerability analysis on a complex network model of the power grid to obtain coordination evaluation information; the coordination evaluation information includes a connectivity index, a power transmission capacity index, a connectivity difference and a power transmission difference and corresponding time integrals and coordination evaluation values; S36, integrates fuzzy logic and uses fuzzy logic to process fuzzy information in the evaluation process; establishes a fuzzy rule base and uses the extracted feature data as fuzzy input; for each fuzzy input and output variable, determines the appropriate fuzzy set and membership function, and the membership function is used to describe the boundary and degree of fuzziness of each fuzzy set; inputs the fuzzified topological characteristics, operation characteristics and environmental impact characteristics data into the fuzzy rule base, and performs reasoning calculations through the fuzzy reasoning engine to obtain the fuzzy evaluation results of the coordination of power grid planning.

4. A smart grid planning coordination evaluation method according to claim 3, characterized in that: When integrating fuzzy logic to construct an evaluation model, a quantum fuzzy logic algorithm is used to process fuzzy information using the superposition state and entanglement characteristics of quantum bits; the quantum fuzzy logic algorithm specifically quantizes the fuzzy input through quantum gate operations, and then performs reasoning operations based on quantum fuzzy rules, and finally obtains a fuzzy evaluation result of the coordination of power grid planning.

5. A smart grid planning coordination evaluation method according to claim 3, characterized in that: The acquisition logic of the connection weight aij is: Identify the electrical distance and line impedance between any set of adjacent agents; Set the monitoring time zone, calculate the mean and standard deviation of the line impedance in the monitoring time zone to obtain the impedance mean and impedance fluctuation value; The line impedance, impedance mean value and impedance fluctuation value are weightedly calculated to obtain the line impedance impact value; The electrical distance and line impedance influence values ​​are weighted and calculated to obtain the connection weight aij.

6. A smart grid planning coordination evaluation method according to claim 1, characterized in that: The time interval for collecting the power operation data is dynamically adjusted according to the power grid load fluctuation, specifically: Set a real-time load monitoring cycle, calculate the load change rate of the power grid in each real-time load monitoring cycle and mark it as a load change value; Set the collection time interval frequency group, including normal time interval frequency and first-level time interval frequency; If the load change value is within the preset reasonable load change range, it is determined that the load change is within a reasonable range, and the power operation data is collected using a normal time interval frequency; If the load change value is not within the preset reasonable load change range, it is determined to be a period of large load change, and the power operation data is collected using the first-level time interval frequency.

7. A smart grid planning coordination evaluation method according to claim 3, characterized in that: Based on step S33, the structural characteristic index of the power grid is calculated using the node index in the complex network model, specifically: Identify the number of edges connected to the node and mark it as the node degree value; Count the frequencies of nodes with different degree values ​​and get the node degree distribution; Calculate the clustering coefficient of each node, the formula is expressed as: ; Where j represents the index of the node, Cj represents the clustering coefficient of node j, ej represents the number of edges actually existing between the neighboring nodes of node i, and kj represents the node degree value of node j; Calculate the node betweenness centrality and edge betweenness centrality of any node and line respectively; the calculation formula of node betweenness centrality is: ; The calculation formula of edge betweenness centrality is: ; Set the betweenness centrality threshold, compare the node betweenness centrality and edge betweenness centrality of the node or line with their corresponding betweenness centrality threshold. If the node betweenness centrality and edge betweenness centrality are greater than their corresponding betweenness centrality threshold, mark the node or line as a key node or key line.

8. A smart grid planning coordination evaluation method according to claim 3, characterized in that: Based on step S34, the complex network model of the power grid is analyzed for robustness and vulnerability, specifically: Identify the fault scenarios and disturbances currently being simulated; Calculate the number of nodes contained in the largest connected subgraph in the power grid after a fault or disturbance in a complex network model Total number of nodes The ratio is marked as the connectivity index H, and the formula is: ; Calculate the actual power delivered by the grid after a fault or disturbance in complex network models Transmit power during normal operation The ratio of is marked as the power transmission capability index G, and the formula is expressed as: ; Set the expected values ​​corresponding to the connectivity index and the power transmission capacity index, and calculate the connectivity difference LH and the power transmission difference LG by taking the difference between the power transmission capacity index and the power transmission capacity index and the corresponding expected values; The concept of time integration is introduced to evaluate the changes in the connectivity difference LH and the power transfer difference LG, specifically: set up is the function of connectivity difference changing with time, is the function of the power transfer capability difference changing with time, t0 is the start time of the fault or disturbance, and t1 is the end time of the observation; The time integral of the connected difference is calculated as follows: ; The time integral of the power transfer difference is calculated as: ; The time integral of the connectivity difference and the power transfer difference is weighted to obtain the coordination evaluation value E, which is expressed as ; Wherein, w1 and w2 represent the weights corresponding to the time integrals of the connectivity difference and the power transfer difference, respectively; the connectivity index, the power transmission capacity index, the connectivity difference and the power transfer difference and the corresponding time integral and coordination evaluation value are marked as coordination evaluation information; The coordination of the power grid in the simulation scenario or disturbance is judged based on the coordination evaluation information, specifically: A coordination evaluation threshold is set. If the coordination evaluation value is less than the coordination evaluation threshold, it indicates that the power grid has good coordination in the simulation scenario or disturbance. If the coordination evaluation value is greater than or equal to the coordination evaluation threshold, it indicates that the power grid has weak coordination. In this case, the redundant lines at the corresponding positions of the key nodes and key lines in the power grid are identified and enabled in sequence. The coordination of the power grid after the redundant lines are enabled in sequence is evaluated to obtain a comprehensive coordination evaluation value; when the comprehensive coordination evaluation value is greater than its preset comprehensive coordination evaluation threshold, it means that the enabled redundant lines are sufficient to supplement the weak coordination of the power grid.

9. A smart grid planning coordination evaluation method according to claim 8, characterized in that: Evaluate the coordination of the power grid after enabling redundant lines in sequence, specifically: The coordination evaluation value of the power grid after the redundant line is enabled is calculated by difference with the coordination evaluation value before the activation to obtain the evaluation change value; the coordination evaluation value of the power grid after the redundant line is enabled is calculated by difference with the coordination evaluation threshold to obtain the coordination evaluation difference; the coordination evaluation value of the power grid after the redundant line is enabled is calculated by difference with the coordination evaluation threshold to obtain the coordination threshold difference; the coordination evaluation difference and the coordination threshold difference are weighted to obtain the coordination evaluation value; The co-evaluation values ​​after activating the redundant lines of different key nodes or key lines are traversed in turn, and the mean and standard deviation of the co-evaluation values ​​after activating the redundant lines of different key nodes or key lines are calculated to obtain the co-evaluation mean and the co-evaluation fluctuation value; the co-evaluation value, the co-evaluation mean and the co-evaluation fluctuation value are weightedly calculated to obtain the co-evaluation comprehensive value.

Images