Vector machine-based comprehensive security risk assessment method for new energy power system

Abstract

The application discloses a kind of new energy power system comprehensive security risk assessment methods based on vector machine, according to equipment type, equipment type division is carried out to entire new energy power system;Combining new energy power system historical working data, the correlation model of different operation scenes of power system multi-type equipment is constructed;Using correlation model, the multi-service scene sample set of different type equipment is calculated;For each type equipment, each service scene is randomly assigned a kind of basic operating environment of new energy power system, and the comprehensive security risk index of new energy power system under corresponding basic operating environment is obtained;Based on multi-service scene sample set, using kernel support vector machine algorithm, the comprehensive security risk assessment model of new energy power system is established and trained;Based on comprehensive security risk assessment model, the comprehensive operation security risk of new energy power system is evaluated.The application avoids complicated mathematical modeling, and improves new energy utilization benefit.

Description

Technical Field

[0001] The present invention relates to the technical field of risk assessment of new energy power systems, and in particular discloses a vector machine-based comprehensive security risk assessment method for new energy power systems. Background Art

[0002] Currently, more and more power grids are replacing traditional fossil fuels with clean energy sources like wind and solar. With the rapid growth of installed capacity and grid-connected capacity of various renewable energy sources, such as wind and solar, uncertainty in power output is increasing, and the complexity of power grid structures is increasing. With interconnected grids at all levels, the number of power system components is increasing, and the grid is gradually moving towards long-distance, high-capacity transmission. This source-grid-load uncertainty poses a significant challenge to the safe and stable operation, system regulation, and planning of these new power systems. This also serves as a warning for strengthening research on power grid security, conducting comprehensive and timely security assessments, and controlling operational and maintenance risks.

[0003] Based on this, the present invention proposes a new energy power system comprehensive security risk assessment method based on vector machine. Summary of the Invention

[0004] The present invention provides a new energy power system comprehensive security risk assessment method based on vector machines, aiming to solve at least one defect existing in the above-mentioned prior art.

[0005] The present invention relates to a new energy power system comprehensive security risk assessment method based on a vector machine, comprising the following steps:

[0006] Divide the entire new energy power system into equipment types based on equipment types;

[0007] Combined with the historical operating data of the new energy power system, a correlation model for different operating scenarios of multiple types of equipment in the power system is constructed;

[0008] Using the correlation model, we calculated and obtained a sample set of multiple business scenarios for different types of equipment.

[0009] Randomly assign a basic operating environment of a new energy power system to each business scenario of each type of equipment, and obtain the comprehensive security risk index of the new energy power system under the corresponding basic operating environment;

[0010] Based on a multi-business scenario sample set, a comprehensive security risk assessment model for the new energy power system is established and trained using the kernel support vector machine algorithm;

[0011] Evaluate the comprehensive operational safety risks of new energy power systems based on a comprehensive safety risk assessment model;

[0012] Based on the comprehensive operational safety risk assessment results, provide new energy power system operation and maintenance decision-making recommendations.

[0013] Furthermore, the steps of classifying the entire new energy power system into equipment types according to equipment types include:

[0014] Construct the network topology of the new energy power system. The network topology is expressed as follows: , where N represents different nodes in the topology, and L represents different lines in the topology;

[0015] On this basis, the efficiency concentration of each node is calculated. The efficiency concentration of each node is calculated using the following formula:

[0016]

[0017] in, represents the efficiency concentration of node i, represents the power consumption of node i, represents the power consumption of node j, Represents the topological nodes that are adjacent to node i and connected to each other.

[0018] Furthermore, in the step of dividing the entire new energy power system into equipment types according to the equipment types, the DBSCAN clustering algorithm is used to classify the different equipment types of the new energy power system. The objective function of the DBSCAN clustering algorithm is defined as:

[0019]

[0020] in, Represents the clustering objective function, C represents the cluster center matrix, N represents the number of nodes, CLU represents the number of clusters, represents the degree of node i’s belonging to device type j, The square representing the center point of the device type;

[0021] The distance function of the DBSCAN clustering algorithm is:

[0022]

[0023]

[0024] in, represents the efficiency concentration of node i, represents the efficiency concentration of node j, For arrive The cross entropy of , i.e. the objective function; For arrive The relative entropy of , that is, KL divergence; represents the expected value of effectiveness concentration;

[0025] After that, all node data are marked as unprocessed, and a point that has not been marked is randomly selected to calculate the radius of the point. All neighbor points within, that is, cross entropy All nodes of is a custom radius; if the number of neighbor nodes of the point is not less than 10, mark the point as a core point; create a new cluster for the core point, and add it and its neighbor points to the cluster; if the number of neighbors of the point is less than 10, mark it as a noise point; for each core point in the new cluster, find its All neighbor nodes in the cluster are marked as processed and added to the current cluster. If the neighbor node has no less than 10 neighbor nodes, it is marked as a core point and its neighbor nodes are searched. Repeat the above steps until all nodes are marked as processed and nodes that are not classified into any cluster are noise points. Finally, output all cluster information.

[0026] Furthermore, in the step of constructing a correlation model for different operating scenarios of multiple types of equipment in the power system in combination with the historical operating data of the new energy power system, the joint probability distribution of the multidimensional random variables is decomposed into a two-dimensional Archimedean Copulas function including two random variables based on the historical operating data of the new energy power system. Considering the random variables of different equipment types in multiple business scenarios, the probability density function is expressed as:

[0027]

[0028] in, is the probability density function, Represents the expansion parameter, when the marginal distribution of the random variable and When independent of each other, The value is 0, otherwise it is 1; is the marginal distribution of variable x, is the marginal distribution of variable y.

[0029] Furthermore, the steps of calculating and obtaining a multi-service scenario sample set for different types of devices using the correlation model include:

[0030] Using the Monte Carlo sampling method, M samples are drawn from different business scenarios of different device types. Different samples correspond to different business scenarios. For each device type i, M uniformly distributed random samples are generated. , the value range is an integer between 1 and 9, representing 9 different business scenarios. Different random samples represent the marginal distribution of business scenarios of this type of device.

[0031] Based on the established Archimedean Copulas model, all samples of each device type are converted into business scenario samples of that device type. , all business scenario samples of this device type constitute the business scenario sample set of this device type; among them, represents the device type, and j represents the sample number of the corresponding device type;

[0032] Specifically, for each sample , using the inverse Archimedean Copulas transform, we get a two-dimensional random variable:

[0033]

[0034] Substituting into the Archimedean Copulas function, we get:

[0035]

[0036] in, is the Copulas function of variables i, j, represents the cross entropy of the inverse function of the marginal distribution, is the Archimedean Copulas function of variables i, j, Represents extended parameters;

[0037] Then, based on the marginal distribution of business scenarios for each device type, we obtain the following business scenario samples:

[0038] in, For business scenario samples, is the inverse transformation function of the marginal distribution of device type i.

[0039] Furthermore, the steps of randomly assigning a basic operating environment of a new energy power system to each business scenario of each type of equipment and obtaining a comprehensive security risk index of the new energy power system under the corresponding basic operating environment include:

[0040] Use random number generation algorithm to obtain random equipment load status , Equipment flow status , and the combined wind and solar power output of the equipment Parameters, ensure that the values ​​of the three state variables are within a reasonable range;

[0041] According to the equipment load status , Equipment flow status , and the combined wind and solar power output of the equipment Parameters, three indicators are selected for evaluation: equipment load loss risk, power flow over-limit risk, and wind and solar power abandonment risk;

[0042] The risk of equipment losing load is expressed as:

[0043]

[0044] in, Represents the risk value of equipment losing load, Represents the total working hours, Represents the equipment load status The probability of Is the equipment load status The severity of the load loss consequence under NL is the load shedding amount at the load node;

[0045] The risk of power flow exceeding the limit is expressed as:

[0046]

[0047] in, Represents the risk of over-limit trend, Represents the total working hours, Indicates the device power flow status The probability of Indicates the device power flow status The severity of the consequences of the current exceeding the limit under Represents the number of lines, represents the overcurrent power of overcurrent line i, represents the rated maximum overcurrent power of overcurrent circuit i;

[0048] The risk of wind and solar curtailment is expressed as:

[0049]

[0050] in, represents the risk probability of wind and solar power abandonment, Represents the combined wind and solar power output status of the device The severity of the consequences of wind and solar power curtailment under Represents the total amount of wind and solar power curtailment, Represents the total operating time of new energy equipment;

[0051] Finally, the equipment load status , Equipment flow status , and the combined wind and solar power output of the equipment The weighted average of the three indicators is used to obtain the operating risk value of new energy power equipment:

[0052]

[0053] in Energy and power equipment operation risk value, Take 0.8, Take 2.0, Take 1.0; sum the operating risk values ​​of all equipment in the new energy power system to obtain the comprehensive safety risk index of the new energy power system ; Construct a training sample set based on the acquired historical operation data, comprehensive security risk indicators and corresponding business scenarios.

[0054] Furthermore, based on the multi-business scenario sample set, the steps of establishing and training the comprehensive security risk assessment model of the new energy power system using the kernel support vector machine algorithm include:

[0055] The kernel support vector machine is used to construct a comprehensive security risk assessment model for the new energy power system. The kernel support vector machine algorithm is used to construct the risk assessment model. The kernel support vector machine algorithm uses the weighted average of the linear kernel function, polynomial kernel function, radial basis function kernel function, sigmoid kernel function, cosine similarity kernel function and Laplace kernel function as the final kernel function. , its actual expression is:

[0056]

[0057]

[0058]

[0059]

[0060]

[0061]

[0062]

[0063] in, represents the linear kernel function, represents the polynomial kernel function, represents the radial basis function kernel function, represents the Sigmoid kernel function, represents the cosine similarity kernel function, represents the Laplace kernel function; represents the scaling factor, r is the bias matrix, and d represents the actual order of the polynomial kernel function. 、 、 、 、 and Represent the weights of each kernel function respectively; represents the first data set, represents the second data set; Represents the transpose operation of a vector;

[0064] The business scenarios of the training sample set and the historical operation data of the new energy power system are used as the input training data of the kernel support vector machine model to calculate the corresponding comprehensive security risk index of the new energy power system. As output training data;

[0065] Initialize the model's hidden layer weights and biases, and convert the input training data into hidden layer outputs through the final kernel function.

[0066] Furthermore, based on the comprehensive safety risk assessment model, the steps for assessing the comprehensive operational safety risk of the new energy power system include:

[0067] Collect business scenarios of Y types of equipment, load node load shedding, line rated maximum overcurrent power and total wind and solar curtailment, input them into the input end of the kernel support vector machine model, and obtain the comprehensive security risk index of the new energy power system from the output end , according to the corresponding relationship between risk value and risk level, determine the comprehensive security risk level of the new energy power system, among which, Represents no risk, Represents low risk, Represents medium risk, Represents high risk, Represents a serious risk.

[0068] Furthermore, based on the comprehensive operational safety risk assessment results, the steps for providing new energy power system operation and maintenance decision-making recommendations include:

[0069] If the safety assessment level of the new energy power system is no risk or low risk, it will operate according to the current system status; if the safety assessment level of the new energy power system is medium risk or high risk, the operation and maintenance process of the new energy power system will be readjusted. By adjusting the power system operation and maintenance process, it can output appropriate power to meet the actual load needs while avoiding the possibility of current over-limit. At the same time, the combined output of wind and solar energy will be appropriately reduced.

[0070] The beneficial effects achieved by the present invention are:

[0071] The present invention provides a new energy power system comprehensive security risk assessment method based on a vector machine, which divides the entire new energy power system into equipment types according to equipment types; combines historical working data of the new energy power system to construct a correlation model of different operating scenarios of multiple types of equipment in the power system; uses the correlation model to calculate a multi-business scenario sample set of different types of equipment; randomly assigns a basic operating environment of the new energy power system to each business scenario of each type of equipment, and obtains a comprehensive security risk index of the new energy power system under the corresponding basic operating environment; based on the multi-business scenario sample set, uses a kernel support vector machine algorithm to establish and train a comprehensive security risk assessment model of the new energy power system; based on the comprehensive security risk assessment model, evaluates the comprehensive operational safety risk of the new energy power system; and provides new energy power system operation and maintenance decision-making recommendations based on the evaluation results of the comprehensive operational safety risk. Compared with the prior art, the present invention has the following beneficial effects:

[0072] (1) The kernel support vector machine used in the present invention is similar to other neural networks in that it does not rely on the complex relationship between parameters and outputs, but relies on the continuous change of weights to closely associate parameters with outputs, avoiding tedious mathematical modeling.

[0073] (2) The present invention has high generalization and can maintain high calculation accuracy while reducing some input parameters. The operation and maintenance decision-making suggestions of the present invention are beneficial to the protection of the new energy power grid system, thereby improving the efficiency of new energy utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a flow chart of an embodiment of a method for comprehensive security risk assessment of a new energy power system based on a vector machine according to the present invention. DETAILED DESCRIPTION

[0075] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0076] like Figure 1 As shown, the first embodiment of the present invention proposes a new energy power system comprehensive security risk assessment method based on a vector machine, comprising the following steps:

[0077] Step S100: classify the entire new energy power system into equipment types according to the equipment types.

[0078] Step S200: Combine historical operating data of the new energy power system to construct a correlation model for different operating scenarios of multiple types of equipment in the power system.

[0079] Step S300: Use the correlation model to calculate and obtain a multi-service scenario sample set of different types of equipment.

[0080] Step S400: randomly assign a basic operating environment of a new energy power system to each business scenario of each type of equipment, and obtain a comprehensive security risk index of the new energy power system under the corresponding basic operating environment.

[0081] Step S500: Based on a multi-business scenario sample set, a comprehensive security risk assessment model for the new energy power system is established and trained using a kernel support vector machine algorithm.

[0082] Step S600: Evaluate the comprehensive operational safety risk of the new energy power system based on the comprehensive safety risk assessment model.

[0083] Step S700: Providing new energy power system operation and maintenance decision-making recommendations based on the comprehensive operational safety risk assessment results.

[0084] Further, see Figure 1 In the embodiment of the present invention, the method for comprehensive security risk assessment of new energy power system based on vector machine is proposed. Step S100 includes:

[0085] Step S110: construct the network topology of the new energy power system. The network topology is expressed as , where N represents different nodes in the topology and L represents different lines in the topology.

[0086] Step S120: On this basis, calculate the efficiency concentration of each node. The efficiency concentration of each node is calculated using the following formula:

[0087] (1)

[0088] In formula (1), represents the efficiency concentration of node i, represents the power consumption of node i, represents the power consumption of node j, Represents the topological nodes that are adjacent to node i and connected to each other.

[0089] Preferably, see Figure 1 In the vector machine-based comprehensive security risk assessment method for a new energy power system proposed in this embodiment, in step S100, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm is used to classify different types of equipment in the new energy power system. The objective function of the DBSCAN clustering algorithm is defined as:

[0090] (2)

[0091] In formula (2), Represents the clustering objective function, C represents the cluster center matrix, N represents the number of nodes, CLU represents the number of clusters, represents the degree of node i’s belonging to device type j, Represents the square of the center point of the device type.

[0092] The distance function of the DBSCAN clustering algorithm is:

[0093]

[0094] (3)

[0095] In formula (3), represents the efficiency concentration of node i, represents the efficiency concentration of node j, For arrive The cross entropy of , i.e. the objective function; For arrive The relative entropy of , that is, KL divergence; Represents the expected value of efficiency concentration.

[0096] After that, all node data are marked as unprocessed, and a point that has not been marked is randomly selected to calculate the radius of the point. All neighbor points within, that is, cross entropy All nodes of is a custom radius; if the number of neighbor nodes of the point is not less than 10, mark the point as a core point; create a new cluster for the core point, and add it and its neighbor points to the cluster; if the number of neighbors of the point is less than 10, mark it as a noise point; for each core point in the new cluster, find its All neighbor nodes in the cluster are marked as processed and added to the current cluster. If the neighbor node has no less than 10 neighbor nodes, it is marked as a core point and its neighbor nodes are searched. Repeat the above steps until all nodes are marked as processed and nodes that are not classified into any cluster are noise points. Finally, output all cluster information.

[0097] Further, see Figure 1In the integrated security risk assessment method for a new energy power system based on a vector machine proposed in this embodiment, in step S200, based on the historical operating data of the new energy power system, the joint probability distribution of multidimensional random variables is decomposed into a two-dimensional Archimedean Copulas function consisting of two random variables. Considering the random variables of different equipment types in multiple business scenarios, the probability density function can be expressed as:

[0098] (4)

[0099] In formula (4), is the probability density function, Represents the expansion parameter, when the marginal distribution of the random variable and When independent of each other, The value is 0, otherwise it is 1; is the marginal distribution of variable x, is the marginal distribution of variable y.

[0100] Preferably, see Figure 1 In the embodiment of the present invention, the method for comprehensive security risk assessment of new energy power system based on vector machine is proposed. Step S300 includes:

[0101] Step S310: Using the Monte Carlo sampling method, M samples are extracted for different business scenarios of different device types, and different samples correspond to different business scenarios; for each device type i, a number of M uniformly distributed random samples are generated. , the value range is an integer between 1 and 9, representing 9 different business scenarios. Different random samples each represent the marginal distribution of business scenarios of this type of device.

[0102] Step S320: Based on the established Archimedean Copulas model, all samples of each device type are converted into business scenario samples of the device type. , all business scenario samples of this device type constitute the business scenario sample set of this device type; among them, represents the device type, and j represents the sample number corresponding to the device type.

[0103] Specifically, for each sample , using the inverse Archimedean Copulas transform, we get a two-dimensional random variable:

[0104] (5)

[0105] Substituting into the Archimedean Copulas function, we get:

[0106] (6)

[0107] In formulas (5) and (6), is the Copulas function of variables i, j; represents the cross entropy of the inverse function of the marginal distribution, is the Archimedean Copulas function of variables i, j; Represents extended parameters.

[0108] Then, based on the marginal distribution of business scenarios for each device type, we obtain the following business scenario samples: (7)

[0109] In formula (7), For business scenario samples, is the inverse transformation function of the marginal distribution of device type i.

[0110] Further, see Figure 1 In the embodiment of the present invention, the method for comprehensive security risk assessment of new energy power system based on vector machine is proposed. Step S400 includes:

[0111] Step S410: Use a random number generation algorithm to obtain random device load status , Equipment flow status , and the combined wind and solar power output of the equipment Parameters to ensure that the values ​​of the three state variables are within a reasonable range.

[0112] Equipment load status For example, using Represents the distribution process of equipment load status, where and Respectively represent the minimum and maximum values ​​of the equipment load status; Represents a random number uniformly distributed between 0 and 1; Represents the generated equipment load status. Using the same method, generate the equipment flow status and the combined wind and solar power output of the equipment .

[0113] Step S420: According to the equipment load status , Equipment flow status , and the combined wind and solar power output of the equipment Parameters, three indicators are selected for evaluation: equipment load loss risk, power flow over-limit risk and wind and solar power abandonment risk.

[0114] The equipment load loss risk is the probability that the available power generation capacity of the equipment is less than or equal to a certain constant load demand. The equipment load loss risk can be expressed as:

[0115] (8)

[0116] In formula (8), Represents the risk value of equipment losing load, Represents the total working hours, Represents the equipment load status The probability of Is the equipment load status The severity of the load loss consequences under load conditions, NL represents the load shedding amount at the load node.

[0117] The power flow over-limit risk is the risk that the bus voltage, branch current, or power supplying equipment exceeds the rated value, causing line overload and resulting in equipment damage and power outage. The power flow over-limit risk can be expressed as:

[0118] (9)

[0119] In formula (9), Represents the risk of over-limit trend, Represents the total working hours, Indicates the device power flow status The probability of Indicates the device power flow status The severity of the consequences of the current exceeding the limit under Represents the number of lines, represents the overcurrent power of overcurrent line i, Represents the rated maximum overcurrent power of overcurrent circuit i.

[0120] The risk of wind and solar curtailment is caused by the combined output of wind and solar energy from a device exceeding the grid's capacity, resulting in the waste of wind and solar resources. The risk of wind and solar curtailment can be expressed as:

[0121] (10)

[0122] In formula (10), represents the risk probability of wind and solar power abandonment, Represents the combined wind and solar power output status of the device The severity of the consequences of wind and solar power curtailment under Represents the total amount of wind and solar power curtailment, Represents the total operating time of new energy equipment.

[0123] Step S430: Check the equipment load status , Equipment flow status , and the combined wind and solar power output of the equipment The weighted average of the three indicators is used to obtain the operating risk value of new energy power equipment:

[0124] (11)

[0125] In formula (11) Energy and power equipment operation risk value, Take 0.8, Take 2.0, Take 1.0; sum the operating risk values ​​of all equipment in the new energy power system to obtain the comprehensive safety risk index of the new energy power system ; Construct a training sample set based on the acquired historical operation data, comprehensive security risk indicators and corresponding business scenarios.

[0126] Preferably, see Figure 1 In the method for comprehensive security risk assessment of a new energy power system based on a vector machine proposed in this embodiment, step S500 includes:

[0127] Step S510: Use kernel support vector machine to build a comprehensive security risk assessment model for new energy power system, wherein the risk assessment model is built using kernel support vector machine algorithm, wherein the kernel support vector machine algorithm uses the weighted average of linear kernel function, polynomial kernel function, radial basis function kernel function, sigmoid kernel function, cosine similarity kernel function and Laplace kernel function as the final kernel function , its actual expression is:

[0128]

[0129] (13)

[0130] (14)

[0131] (15)

[0132] (16)

[0133] (17)

[0134] (18)

[0135] In formulas (12)~(18), represents the linear kernel function, represents the polynomial kernel function, represents the radial basis function kernel function, represents the Sigmoid kernel function, represents the cosine similarity kernel function, represents the Laplace kernel function; represents the scaling factor, r is the bias matrix, and d represents the actual order of the polynomial kernel function. 、 、 、 、 and Represent the weights of each kernel function respectively; represents the first data set, represents the second data set; Represents the transpose operation of a vector.

[0136] Step S520: Use the business scenarios of the training sample set and the historical operation data of the new energy power system as the input training data of the kernel support vector machine model to calculate the corresponding comprehensive security risk index of the new energy power system. As output training data.

[0137] Step S530: Initialize the model hidden layer weights and biases, and convert the input training data into hidden layer outputs through the final kernel function.

[0138] The weights between the hidden layer and the output layer are solved using the Moore-Penrose pseudo-inverse algorithm, which is a commonly used algorithm for calculating weights and will not be described here.

[0139] Further, see Figure 1 In the comprehensive security risk assessment method for a new energy power system based on a support vector machine proposed in this embodiment, in step S600, the business scenarios of Y types of equipment, the load shedding amount of load nodes, the rated maximum overcurrent power of the line, and the total amount of wind and solar power curtailment are collected and input into the input end of the core support vector machine model, and the comprehensive security risk index of the new energy power system is obtained from the output end. , according to the corresponding relationship between risk value and risk level, determine the comprehensive security risk level of the new energy power system, among which, Represents no risk, Represents low risk, Represents medium risk, Represents high risk, Represents a serious risk.

[0140] Preferably, see Figure 1In the vector machine-based comprehensive security risk assessment method for a new energy power system proposed in this embodiment, in step S700, if the security assessment level of the new energy power system is no risk or low risk, the system operates according to the current system state; if the security assessment level of the new energy power system is medium risk or high risk, the operation and maintenance process of the new energy power system is readjusted. By adjusting the power system operation and maintenance process, the system outputs appropriate power, meeting actual load requirements while avoiding the possibility of power flow exceeding the limit. At the same time, the combined output of wind and solar energy is appropriately reduced to avoid the waste of renewable energy, ultimately achieving efficient and reliable power generation at the lowest cost. In addition, when a risk occurs, power system dispatchers can dynamically adjust the weights of various risk indicators based on actual conditions, thereby achieving risk control under different risk states.

[0141] This embodiment provides a comprehensive security risk assessment method for a new energy power system based on a vector machine. Compared with the existing technology, the entire new energy power system is divided into equipment types according to equipment types; a correlation model of different operating scenarios of multiple types of equipment in the power system is constructed in combination with historical working data of the new energy power system; a multi-business scenario sample set of different types of equipment is calculated using the correlation model; a basic operating environment of the new energy power system is randomly assigned to each business scenario of each type of equipment, and a comprehensive security risk index of the new energy power system under the corresponding basic operating environment is obtained; based on the multi-business scenario sample set, a kernel support vector machine algorithm is used to establish and train a comprehensive security risk assessment model for the new energy power system; based on the comprehensive security risk assessment model, the comprehensive operational safety risk of the new energy power system is assessed; and based on the assessment results of the comprehensive operational safety risk, a new energy power system operation and maintenance decision recommendation is provided. Compared with the existing technology, the beneficial effects achieved by this embodiment are as follows:

[0142] (1) The kernel support vector machine used in this embodiment is similar to other neural networks in that it does not rely on the complex relationship between parameters and outputs, but relies on the continuous change of weights to closely associate parameters with outputs, avoiding tedious mathematical modeling.

[0143] (2) This embodiment has high generalization and can maintain high calculation accuracy while reducing some input parameters. The operation and maintenance decision-making suggestions of the present invention are beneficial to the protection of the new energy power grid system, thereby improving the efficiency of new energy utilization.

[0144] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic inventive concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the invention. Thus, the present invention is intended to include such changes and modifications as fall within the scope of the claims and their equivalents.

Claims

1. A comprehensive security risk assessment method for new energy power systems based on vector machines, characterized in that: The following steps are involved: Divide the entire new energy power system into equipment types based on equipment types; Combined with the historical operating data of the new energy power system, a correlation model for different operating scenarios of multiple types of equipment in the power system is constructed; Using the correlation model, a sample set of multiple business scenarios of different types of devices is calculated; Randomly assign a basic operating environment of a new energy power system to each business scenario of each type of equipment, and obtain the comprehensive security risk index of the new energy power system under the corresponding basic operating environment; Based on the multi-business scenario sample set, a comprehensive security risk assessment model for the new energy power system is established and trained using a kernel support vector machine algorithm; Based on the comprehensive safety risk assessment model, the comprehensive operational safety risk of the new energy power system is assessed; Provide decision-making recommendations on the operation and maintenance of new energy power systems based on the comprehensive operational safety risk assessment results; In the step of dividing the entire new energy power system into equipment types according to equipment types, the DBSCAN clustering algorithm is used to classify different equipment types of the new energy power system. The objective function of the DBSCAN clustering algorithm is defined as: in, Represents the clustering objective function, C represents the cluster center matrix, N represents the number of nodes, CLU represents the number of clusters, represents the degree of node i’s belonging to device type j, represents the efficiency concentration of node i, The square representing the center point of the device type; The distance function of the DBSCAN clustering algorithm is: in, represents the efficiency concentration of node i, represents the efficiency concentration of node j, For arrive The cross entropy of , i.e. the objective function; For arrive The relative entropy of , that is, KL divergence; represents the expected value of effectiveness concentration; After that, all node data are marked as unprocessed, and a point that has not been marked is randomly selected to calculate the radius of the point. All neighbor points within, that is, cross entropy All nodes of is a custom radius; if the number of neighbor nodes of the point is not less than 10, mark the point as a core point; create a new cluster for the core point, and add it and its neighbor points to the cluster; if the number of neighbors of the point is less than 10, mark it as a noise point; for each core point in the new cluster, find its All neighbor nodes in the cluster are marked as processed and added to the current cluster. If the neighbor node has no less than 10 neighbor nodes, it is marked as a core point and its neighbor nodes are searched. Repeat the above steps until all nodes are marked as processed and nodes that are not classified into any cluster are noise points. Finally, output all cluster information.

2. The vector machine-based comprehensive security risk assessment method for new energy power systems according to claim 1, characterized in that: The step of classifying the entire new energy power system into equipment types according to equipment types includes: Construct the network topology of the new energy power system. The network topology is expressed as follows: , where N represents different nodes in the topology, and L represents different lines in the topology; On this basis, the efficiency concentration of each node is calculated. The efficiency concentration of each node is calculated using the following formula: in, represents the efficiency concentration of node i, represents the power consumption of node i, represents the power consumption of node j, Represents the topological nodes that are adjacent to node i and connected to each other.

3. The vector machine-based comprehensive security risk assessment method for new energy power systems according to claim 1, characterized in that: In the step of constructing a correlation model for different operating scenarios of multiple types of equipment in the power system in combination with the historical operating data of the new energy power system, the joint probability distribution of the multidimensional random variables is decomposed into a two-dimensional Archimedean Copulas function including two random variables based on the historical operating data of the new energy power system. Considering the random variables of different equipment types in multiple business scenarios, the probability density function is expressed as: in, is the probability density function, Represents the expansion parameter, when the marginal distribution of the random variable and When independent of each other, The value is 0, otherwise it is 1; is the marginal distribution of variable x, is the marginal distribution of variable y.

4. The method for comprehensive security risk assessment of new energy power systems based on vector machines according to claim 1, characterized in that: The step of calculating and obtaining a multi-service scenario sample set of different types of devices using the correlation model includes: Using the Monte Carlo sampling method, M samples are drawn from different business scenarios of different device types. Different samples correspond to different business scenarios. For each device type i, M uniformly distributed random samples are generated. , the value range is an integer between 1 and 9, representing 9 different business scenarios. Different random samples represent the marginal distribution of business scenarios of this type of device. Based on the established Archimedean Copulas model, all samples of each device type are converted into business scenario samples of that device type. , all business scenario samples of this device type constitute the business scenario sample set of this device type; among them, represents the device type, and j represents the sample number of the corresponding device type; Specifically, for each sample , using the inverse Archimedean Copulas transform, we get a two-dimensional random variable: Substituting into the Archimedean Copulas function, we get: in, is the Copulas function of variables i, j; represents the cross entropy of the inverse function of the marginal distribution, is the Archimedean Copulas function of variables i, j, Represents extended parameters; Then, based on the marginal distribution of business scenarios for each device type, we obtain the following business scenario samples: in, For business scenario samples, is the inverse transformation function of the marginal distribution of device type i.

5. The vector machine-based comprehensive security risk assessment method for new energy power systems according to claim 1, characterized in that: The steps of randomly assigning a basic operating environment of the new energy power system to each business scenario of each type of equipment and obtaining a comprehensive security risk index of the new energy power system under the corresponding basic operating environment include: Use random number generation algorithm to obtain random equipment load status , Equipment flow status , and the combined wind and solar power output of the equipment Parameters, ensure that the values ​​of the three state variables are within a reasonable range; According to the equipment load status , Equipment flow status , and the combined wind and solar power output of the equipment Parameters, three indicators are selected for evaluation: equipment load loss risk, power flow over-limit risk, and wind and solar power abandonment risk; The equipment load loss risk is expressed as: in, Represents the risk value of equipment losing load, Represents the total working hours, Represents the equipment load status The probability of Is the equipment load status The severity of the load loss consequence under NL is the load shedding amount at the load node; The risk of power flow exceeding the limit is expressed as: in, Represents the risk of over-limit trend, Represents the total working hours, Indicates the device power flow status The probability of Indicates the device power flow status The severity of the consequences of the current exceeding the limit under Represents the number of lines, represents the overcurrent power of overcurrent line i, represents the rated maximum overcurrent power of overcurrent circuit i; The risk of wind and solar power curtailment is expressed as: in, represents the risk probability of wind and solar power abandonment, Represents the combined wind and solar power output status of the device The severity of the consequences of wind and solar power curtailment under Represents the total amount of wind and solar power curtailment, Represents the total operating time of new energy equipment; Finally, the equipment load status , Equipment flow status , and the combined wind and solar power output of the equipment The weighted average of the three indicators is used to obtain the operating risk value of new energy power equipment: in, New energy power equipment operation risk value, Take 0.8, Take 2.0, Take 1.0; sum the operating risk values ​​of all equipment in the new energy power system to obtain the comprehensive safety risk index of the new energy power system ; Construct a training sample set based on the acquired historical operation data, comprehensive security risk indicators and corresponding business scenarios.

6. The vector machine-based comprehensive security risk assessment method for new energy power systems according to claim 1, characterized in that: The step of establishing and training a comprehensive security risk assessment model for a new energy power system based on the multi-business scenario sample set using a kernel support vector machine algorithm includes: The kernel support vector machine is used to construct a comprehensive security risk assessment model for the new energy power system. The kernel support vector machine algorithm is used to construct the risk assessment model. The kernel support vector machine algorithm uses the weighted average of the linear kernel function, polynomial kernel function, radial basis function kernel function, sigmoid kernel function, cosine similarity kernel function and Laplace kernel function as the final kernel function. , its actual expression is: in, represents the linear kernel function, represents the polynomial kernel function, represents the radial basis function kernel function, represents the Sigmoid kernel function, represents the cosine similarity kernel function, represents the Laplace kernel function, represents the scaling factor, r is the bias matrix, and d represents the actual order of the polynomial kernel function. 、 、 、 、 and Represent the weights of each kernel function respectively; represents the first data set, represents the second data set; Represents the transpose operation of a vector; The business scenarios of the training sample set and the historical operation data of the new energy power system are used as the input training data of the kernel support vector machine model to calculate the corresponding comprehensive security risk index of the new energy power system. As output training data; Initialize the model hidden layer weights and biases, and convert the input training data into hidden layer outputs through the final kernel function.

7. The vector machine-based comprehensive security risk assessment method for new energy power systems according to claim 6, characterized in that: In the step of evaluating the comprehensive operational safety risk of the new energy power system based on the comprehensive safety risk assessment model, the business scenarios of Y types of equipment, the load shedding amount of load nodes, the rated maximum overcurrent power of the line and the total amount of wind and solar power curtailment are collected and input into the input end of the kernel support vector machine model, and the comprehensive safety risk index of the new energy power system is obtained from the output end. , according to the corresponding relationship between risk value and risk level, determine the comprehensive security risk level of the new energy power system, among which, Represents no risk, Represents low risk, Represents medium risk, Represents high risk, Represents a serious risk.

8. The vector machine-based comprehensive security risk assessment method for new energy power systems according to claim 7, characterized in that: In the step of providing operation and maintenance decision recommendations for the new energy power system based on the comprehensive operation safety risk assessment results, if the safety assessment level of the new energy power system is no risk or low risk, the system is operated according to the current system state; if the safety assessment level of the new energy power system is medium risk or high risk, the operation and maintenance process of the new energy power system is readjusted. By adjusting the power system operation and maintenance process, the system outputs appropriate power, meets the actual load needs, avoids the possibility of power flow exceeding the limit, and appropriately reduces the combined output of wind and solar energy.

Images