Reliability evaluation method and device for power distribution network containing multiple types of distributed energy

Abstract

The invention provides a reliability evaluation method for a power distribution network containing multi-type distributed energy, and the method comprises the steps: determining a relation between disaster intensity and a power distribution network element fault, describing an incidence relation between a disaster intensity feature and an element fault rate through a random forest model, and generating a disaster fault data set of the power distribution network through a sampling method; carrying out post-disaster load recovery and line repair in a post-disaster recovery stage of the power distribution network, establishing a fault recovery model, solving the fault recovery model to obtain a load node power supply state of the power distribution network, and calculating a reliability index of the power system according to the power supply state; according to the method provided by the invention, the reliability of the novel power system actually containing the multi-type distributed resources is evaluated, and a basis and a reference are provided for long-term planning operation of a power grid.

Description

Technical Field

[0001] The present invention relates to a distribution network performance evaluation technology, and in particular to a distribution network reliability evaluation method and device containing multiple types of distributed energy sources. Background Art

[0002] Distributed energy resources (DERs), as a typical application of renewable energy, are an important way to build a new "clean, low-carbon, safe and efficient" power system. At present, it is necessary to promote the development of distributed renewable energy and promote multi-energy synergy and comprehensive cascade utilization of energy in the field of terminal energy consumption. Microgrids (MGs), as localized small-scale power systems with enhanced control capabilities, are regarded as an effective solution to integrate and coordinate different types of distributed energy resources (e.g., diesel generators, wind turbines, photovoltaics, energy storage, etc.) to enhance the resilience of distribution networks. The access of microgrids can improve the comprehensive utilization efficiency of energy. However, the access of microgrids makes the traditional distribution system an active distribution system with a more flexible operation mode, which brings many challenges to reliability assessment.

[0003] First, the output power of intermittent renewable energy in microgrids has significant uncertainty characteristics; second, new reliability assessment algorithms need to be developed to reflect changes in operating modes; in addition, the fault state of the distribution system will also cause the operating state of the microgrid to switch, affecting its operating reliability. Summary of the invention

[0004] Based on this, the present invention aims to propose a reliability assessment method and device for a distribution network containing multiple types of distributed energy sources, using a random forest model to describe the relationship between disaster intensity and component failure rate in the power grid, based on which a data set of component failures after a disaster is generated, and the data set is used as input for post-disaster load recovery and line repair, and a power grid recovery optimization model is established, thereby solving the power supply status of the load nodes of the power system under various fault scales, and calculating the reliability index of the power system based on this.

[0005] In a first aspect, the present invention provides a method for evaluating the reliability of a distribution network containing multiple types of distributed energy resources, comprising:

[0006] The random forest algorithm is used to describe the relationship between disaster intensity and power grid component failure rate, and a disaster failure classification model is obtained;

[0007] Generate disaster failure data set using sampling method based on disaster failure classification model;

[0008] The disaster fault data set is used as the input of the distribution network for load recovery, and a post-disaster fault recovery model and its constraints are established;

[0009] Solve the post-disaster fault recovery model based on the constraint conditions to obtain the power supply status value of the load node corresponding to each disaster fault data;

[0010] The power supply load of the distribution network is calculated according to the power supply status value of the load node, and the reliability evaluation result of the distribution network is obtained based on the power supply load.

[0011] Furthermore, the random forest algorithm is used to describe the relationship between disaster intensity and power grid component failure rate, and the disaster failure classification model is obtained, including:

[0012] Define disaster types and intensity characteristics;

[0013] Obtain component failure rates corresponding to each disaster type and intensity characteristic, and generate a training sample set;

[0014] The training sample set is input into the random forest model for training to obtain the disaster fault classification model.

[0015] Furthermore, the sampling method includes a non-sequential Monte Carlo sampling method.

[0016] Furthermore, the disaster fault data set is generated using a sampling method based on the disaster fault classification model, including:

[0017] Get a random number uniformly distributed in the space [0,1] , the state of the component when an extreme disaster occurs is expressed as follows:

[0018]

[0019] in, represents the probability of failure, Indicates the i-th component in the disaster scene Fault, Indicates Components in disaster scenarios Medium Normal;

[0020] Repeat the sampling N times, record the number of faulty components corresponding to each sampling, and calculate the average number of faulty components corresponding to the same disaster intensity to obtain the component failure scale corresponding to each disaster intensity.

[0021] Furthermore, the post-disaster recovery model and its constraints include:

[0022] The following post-disaster fault recovery model is established with the goal of minimizing cost and power loss load:

[0023]

[0024] in, represents the weighted power loss load, represents the switching operation cost during fault recovery, represents the cost of mobilizing distributed resources. represents the cost of purchasing electricity, Indicates the total number of time intervals representing the fault period; Represents the total number of nodes in the network; Represents the length of each time interval during the fault period; Represents the power loss of node i in time period t; is the load weight of node i; is a 0-1 optimization variable, which indicates the switch state of the branch starting from node i and ending at node j during the fault recovery period t; Indicates that the switch is closed; Indicates the total number of branches in the network; represents the output power of distributed power generation at node i during period t; It means that node i buys power from the substation during period t;

[0025] The constraints include distributed new energy operation constraints, V2G reverse charging constraints, load constraints, post-disaster repair and dispatch constraints, dynamic interconnected microgrid topology constraints, and power flow constraints.

[0026] Furthermore, establishing a post-disaster recovery model includes:

[0027] The weighted power loss load, switch operation cost during fault recovery, distributed resource mobilization cost, and power purchase cost are weighted to obtain the following final post-disaster fault recovery model:

[0028]

[0029] in, represents the load shedding cost; represents the cost of switch operation; represents the cost of DER electricity generation; It represents the cost of the distribution network purchasing electricity from the upper level.

[0030] Furthermore, the power supply load of the distribution network is calculated according to the power supply state value of the load node, and the reliability evaluation result of the distribution network obtained based on the power supply load includes:

[0031] Calculate the power supply load of the distribution network according to the power supply status value of the load node and draw the power supply performance curve of the distribution network;

[0032] Based on the drawn distribution network power supply performance curve, the ratio of the integral from the time the disaster occurs to the time the system recovers to the expected state to the integral of the expected power supply load curve is calculated, and this ratio is recorded as the distribution network reliability assessment result.

[0033] In a second aspect, the present invention provides a distribution network reliability assessment device containing multiple types of distributed energy sources, comprising:

[0034] A fault classification module is configured to use a random forest algorithm to describe the relationship between the disaster intensity and the failure rate of the power grid components to obtain a disaster fault classification model;

[0035] A data sampling module is configured to generate a disaster fault data set using a sampling method based on a disaster fault classification model;

[0036] A fault recovery modeling module is configured to use the disaster fault data set as input of the distribution network for load recovery and establish a post-disaster fault recovery model and its constraints;

[0037] A model solving module is configured to solve a post-disaster fault recovery model based on constraint conditions to obtain a power supply state value of a load node corresponding to each disaster fault data;

[0038] The evaluation module is configured to calculate the power supply load of the distribution network according to the power supply status value of the load node, and obtain the reliability evaluation result of the distribution network based on the power supply load.

[0039] In a third aspect, the present invention provides an electronic device comprising a memory storing computer executable instructions and a processor, wherein when the computer executable instructions are executed by the processor, the device executes each step of the method for assessing the reliability of a distribution network containing multiple types of distributed energy provided in the first aspect.

[0040] In a fourth aspect, the present invention provides a readable storage medium storing a computer executable program, which, when executed, can implement the various steps of the distribution network reliability assessment method containing multiple types of distributed energy provided in the first aspect.

[0041] It can be seen from the above technical solutions that the present invention has the following beneficial effects:

[0042] The present invention provides a reliability assessment method for a distribution network containing multiple types of distributed energy sources, determines the relationship between disaster intensity and distribution network component failures, uses a random forest model to describe the correlation between disaster intensity characteristics and component failure rates, and generates a disaster failure data set for the distribution network through a sampling method; in the post-disaster recovery phase of the distribution network, post-disaster load recovery and line repair are performed, a fault recovery model is established, and the power supply status of the load nodes of the distribution network is obtained by solving the model, and the reliability index of the power system is calculated accordingly. The method provided by the present invention realizes the assessment of the reliability of a new power system that actually contains multiple types of distributed resources, and provides a basis and reference for the long-term planning and operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0044] Figure 1 It is a flow chart of a reliability assessment method for a distribution network containing multiple types of distributed energy provided by an embodiment of the present invention;

[0045] Figure 2 is a diagram showing the principle of training a random forest model provided by an embodiment of the present invention;

[0046] Figure 3 is a schematic diagram of a decision tree generation process provided by an embodiment of the present invention;

[0047] Figure 4 is a diagram of the RBTS bus4 system architecture provided by an embodiment of the present invention;

[0048] Figure 5 It is a structural diagram of a distribution network reliability assessment device containing multiple types of distributed energy sources provided by an embodiment of the present invention;

[0049] Figure 6 This is a diagram of the electronic device architecture provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] 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.

[0051] See also Figure 1 An embodiment of the present invention provides a method for evaluating the reliability of a distribution network containing multiple types of distributed energy resources, comprising the following steps:

[0052] Step S110. Use the random forest algorithm to describe the relationship between disaster intensity and power grid component failure rate, and obtain a disaster failure classification model.

[0053] Specifically, this step includes the following processes:

[0054] Step S111. Define disaster type and intensity characteristics.

[0055] In this step, the disaster intensity and intensity characteristics can be defined first, such as typhoon wind speed, radius, earthquake intensity, flood water level, etc. In addition, the properties of each component in the distribution network can be obtained first, such as the type, location, age, load rate, etc. of equipment such as transformers and transmission lines.

[0056] Step S112: Obtain component failure rates corresponding to various disaster types and intensity characteristics, and generate a training sample set.

[0057] In this step, the data are grouped according to disaster type and intensity range, and the failure rate of power grid components in each group is calculated. This failure rate can be obtained by dividing the number of failures by the total number of samples in the group.

[0058] Step S113: Input the training sample set into the random forest model for training to obtain a disaster fault classification model.

[0059] Specifically, the random forest algorithm is an integrated machine learning algorithm composed of multiple base decision trees. It uses the Bootstrap resampling method to randomly extract k training set samples from the original sample to generate a decision tree, and then collects the results of k decision trees to obtain the prediction results by voting (the dependent variable is a categorical variable) or averaging (the dependent variable is a continuous variable). The principle is as follows: Figure 2 shown.

[0060] Step S120: Generate a disaster fault data set using a sampling method based on the disaster fault classification model.

[0061] Specifically, using the trained disaster fault classification model, samples of disaster intensity and grid component characteristics can be generated through Monte Carlo sampling or other sampling methods, and fault conditions can be predicted based on the model. Among them, different disaster types (such as typhoons, floods, earthquakes, etc.) can be randomly selected for disaster types, and the distribution of disaster intensity can be obtained from historical data, or a certain distribution (such as normal distribution, uniform distribution, etc.) can be set for disaster intensity.

[0062] According to the defined feature distribution, a set of data on disaster type, intensity, and component attributes is generated as input features. In this step, the sample data can be generated using the sampling method, and the generated disaster and component samples are input into the previously trained classification model to predict the failure probability or failure condition of each sample. The prediction results can be represented by binary values, for example, 0 represents a normal power grid and 1 represents a power grid failure. The generated sample data and the prediction results are combined to obtain the disaster failure data set.

[0063] Step S130: Use the disaster fault data set as the input of the distribution network to perform load recovery, and establish a post-disaster fault recovery model and its constraints.

[0064] Specifically, after a disaster (such as a typhoon, earthquake, etc.) occurs, components in the distribution network may fail, causing power outages. We need to use the disaster fault dataset to predict the affected components and plan load restoration to minimize power outage time and ensure priority restoration of critical loads. Typically, the goals of post-disaster load restoration include minimizing the total restoration time, maximizing the amount of load restoration, or prioritizing the restoration of critical loads.

[0065] Post-disaster load recovery can be described using an optimization model that takes into account the repair time of different components, network topology, and load demand. The goal of the model is to optimize the load recovery process, such as reducing power outage time, reducing recovery costs, and satisfying a series of constraints, which may include network topology constraints, power balance constraints, component repair time constraints, load priority constraints, power generation capacity constraints, disaster impact constraints, etc.

[0066] Step S140: Solve the post-disaster fault recovery model based on the constraint conditions to obtain the power supply status value of the load node corresponding to each disaster fault data.

[0067] In this step, post-disaster fault recovery can be modeled as an optimization problem. The decision variables used include whether the load node has restored power (power supply status value) and the restoration order of the grid elements. A suitable solver (such as the mixed integer linear programming solver MILP) is used to solve the problem and obtain the power supply status of the load node.

[0068] Step S150: Calculate the power supply load of the distribution network according to the power supply status value of the load node, and obtain the reliability evaluation result of the distribution network based on the power supply load.

[0069] In a further embodiment, step S110 includes the following process:

[0070] A random forest is k trees A collection of is the M-dimensional feature vector of the disaster. For regression prediction, the set will produce k results , the final prediction is the average of all tree predictions.

[0071] Therefore, the initial random forest model is trained based on the training sample set. ,in The feature vector representing the disaster, Indicates the component failure rate that may be caused by a disaster.

[0072] The process of implementing the random forest regression algorithm is as follows:

[0073] The sample size of the original data is n. The Bootstrap resampling method is used to randomly select k sampling sets from the original sample to generate k decision trees. The sample capacity of each sampling set is the same as that of the original data set. The samples that are not selected in each sampling constitute k out-of-bag data (OOB), which are used as test samples for random forest.

[0074] For each node of each decision tree, m feature variables are randomly selected from all M feature variables as candidate branch feature variables, and then the optimal branch is selected according to the optimal branching rule. At the same time, the overfitting problem that may be caused by excessive growth of the tree is prevented by limiting the depth of the tree.

[0075] The process of generating a decision tree is as follows: Figure 3 As shown, taking its root node as an example, each node includes four items of disaster information.

[0076] Among them, "moving speed (km / h) 31.5" represents the selected characteristic variable and the division value of the variable;

[0077] The mse representation is as follows: Based on the partition point 31.5, the data set can be divided into two subsets , the number of samples in each subset is , and the calculation formula of mse is as follows:

[0078]

[0079] samples indicates the number of samples contained in the node, and value indicates the predicted failure rate value of the data set falling in the node.

[0080] In a further embodiment, the sampling method includes a non-sequential Monte Carlo sampling method, and generating a disaster fault data set using the sampling method based on the disaster fault classification model includes the following steps:

[0081] Get a random number uniformly distributed in the space [0,1] , the state of the component when an extreme disaster occurs is expressed as follows:

[0082]

[0083] in, represents the probability of failure, Indicates the i-th component in the disaster scene Fault, Indicates Components in disaster scenarios Medium Normal;

[0084] Repeat the sampling N times, record the number of faulty components corresponding to each sampling, and calculate the average number of faulty components corresponding to the same disaster intensity to obtain the component failure scale corresponding to each disaster intensity.

[0085] In a further embodiment, steps S130-S140 include the following steps:

[0086] During the post-disaster system recovery phase, based on the perceived line fault conditions, issues such as V2G reverse charging, distributed resource coordination, dispatch of repair teams, flexible load management, network reconstruction, and the formation of dynamic interconnected microgrids are considered to optimize the dispatch position of the repair team, the output of distributed resources, the power supply range and interconnection status of each microgrid, and to carry out rapid post-disaster load recovery and line repair.

[0087] This embodiment establishes the following post-disaster fault recovery model with the goal of minimizing cost and power failure load:

[0088]

[0089] in, represents the weighted power loss load, represents the switching operation cost during fault recovery, represents the cost of mobilizing distributed resources. represents the cost of purchasing electricity, Indicates the total number of time intervals representing the fault period; Represents the total number of nodes in the network; Represents the length of each time interval during the fault period; Represents the power loss of node i in time period t; is the load weight of node i; is a 0-1 optimization variable, which indicates the switch state of the branch starting from node i and ending at node j during the fault recovery period t; Indicates that the switch is closed; Indicates the total number of branches in the network; represents the output power of distributed power generation at node i during period t; It means that node i buys electricity from the substation during period t.

[0090] The constraints include distributed new energy operation constraints, V2G reverse charging constraints, load constraints, post-disaster repair and dispatch constraints, dynamic interconnected microgrid topology constraints, and power flow constraints.

[0091] In a further embodiment, weighted calculation is performed on each optimization target in the above model to obtain the following final post-disaster fault recovery model:

[0092]

[0093] in, represents the load shedding cost; represents the cost of switch operation; represents the cost of DER electricity generation; It represents the cost of the distribution network purchasing electricity from the upper level.

[0094] In a further embodiment, the constraints of the post-disaster fault recovery model include:

[0095] (1) Various types of DER operation constraints

[0096] For nodes connected to distributed renewable energy, the following constraints must be met:

[0097]

[0098] in, is the set of nodes connected to DREs; and are the active and reactive outputs of DREs at node i at time t, respectively; and are the minimum and maximum active outputs of DREs at node i at time t, respectively; and are the minimum reactive power output and maximum reactive power output of DREs at node i at time t, respectively.

[0099] For nodes connected to energy storage, the following constraints are met:

[0100]

[0101] Where: A collection of nodes connected to energy storage; is the charge state of the energy storage at node i at time t; is the maximum value of the energy storage charge state at node i; and are the charging power and discharging power of the energy storage at node i at time t respectively; and They represent the maximum charging and discharging power of the energy storage device connected to the i-node respectively; and are charging efficiency and discharging efficiency respectively; and are 0-1 decision variables for the charging and discharging states of the energy storage at node i at time t, respectively.

[0102] (2) V2G reverse charging constraints

[0103]

[0104] In the formula, Represents a collection of V2G stations; is the actual power of the i-th V2G station at time t; and are the maximum and minimum outputs of the ith V2G station, respectively. V2G stands for vehicle to grid, which refers to plug-in electric vehicles, such as battery electric vehicles (BEV), plug-in hybrid electric vehicles (PHEV) or hydrogen fuel cell vehicles (FCEV), which can communicate with the transmission network and provide demand response services, such as delivering electricity back to the grid or adjusting the charging speed according to the electricity price.

[0105] (3) Load constraints

[0106]

[0107] In the formula, and They represent the set of curtailable loads and the set of non-curtailable loads respectively; and represents the active and reactive load shedding of node i at time t; and They represent the active power and reactive power requirements of node i at time t respectively; Indicates the switching situation of the load that cannot be cut at time t, Indicates load shedding, Indicates that load is connected.

[0108] (4) Emergency repair scheduling constraints

[0109]

[0110] In the formula, F represents the set of all fault lines; The time required to repair a line.

[0111] (5) Dynamically interconnected microgrid topology constraints

[0112]

[0113] In the formula, is a matrix with 0-1 variables. The number of rows corresponds to the total number of fault intervals, and the number of columns corresponds to the sum of the number of DERs with droop control and the number of substations. It indicates that at time t, an island region exists with the q power source point as the dominant node; is a three-dimensional space composed of 0-1 variables. Indicates that node i at time t is a node in island q. The above formula shows that each node belongs to a unique island, and the island may be an island with multiple droop control DERs formed by the interconnection of multiple microgrids. At the same time, the above formula ensures that there are no isolated nodes in each island and that each power dominant node is always located in its corresponding island partition.

[0114] In order to meet the radial topology constraints of the distribution network, the virtual power flow method is used to constrain:

[0115]

[0116] In the formula, is the virtual output of the dominant node in region q at time t; is the virtual power on the line from node i to node j in region q at time t; is the virtual load of node i. The above formula ensures the connectivity of each island area.

[0117] (6) Power flow constraints

[0118] According to the DistFlow model, the node power balance, node voltage and branch current constraints can be expressed as:

[0119]

[0120] In the formula, and They represent the active power and reactive power transmitted by branch (i, j) at time t respectively; and are the resistance and reactance of branch (i, j); is the square of the branch current modulus at time t; is the square of the voltage modulus of node i at time t; is the maximum capacity of the line transmission; M is a large constant. The quadratic equality constraint causes the model to be non-convex, and a second-order cone relaxation is required:

[0121]

[0122] In addition, since the voltage term is introduced in the droop control constraint ,and , which can be approximated by piecewise linearization.

[0123] The commercial solver CPLEX is used to solve the mixed integer second-order cone model established above, and the dynamic microgrid area division and interconnection status, line switch status and output of each distributed resource at different times during the fault recovery period are obtained.

[0124] Based on the above constraint solving post-disaster fault recovery model, the power supply status of the load nodes is solved when a disaster of a certain intensity causes Nk faults in the nodes and edges in the power system, and then the distribution network reliability index is calculated according to the definition of distribution network reliability index.

[0125] Specifically, the power supply load of the distribution network is calculated according to the power supply status value of the load node, and the power supply performance curve of the distribution network is drawn; based on the drawn power supply performance curve of the distribution network, the ratio of the integral from the time the disaster occurs to the time the system recovers to the expected state to the integral of the expected power supply load curve is calculated, and the ratio is recorded as the distribution network reliability assessment result.

[0126] The effect of the present invention is illustrated below by using an evaluation example of a RBTS bus4 distribution network system.

[0127] like Figure 4 As shown in the figure, it shows the RBTS bus4 system without considering distributed resources. Assuming the fault duration is 4 hours, when a certain disaster scenario causes the failure of components 1, 32, and 36, the reliability index value of the RBTS bus4 distribution system is 0.922; when the disaster scenario causes the failure of components 1, 42, and 83, the reliability index value of the distribution system is 0.943. Therefore, components 32 and 36 are more important than components 42 and 83.

[0128] At the same time, by traversing all N-3, N-4 and N-5 order faults, and obtaining the system performance indicators under each fault scenario, and finally averaging them, the reliability indicators of the RBTS bus4 system when facing 3rd order, 4th order and 5th order faults are obtained. The results are shown in Table 1 below.

[0129]

[0130] In order to compare the resilience of distribution systems with different topologies, the resilience indicators of RBTS bus2 and RBTS bus4 systems are summarized as shown in Table 2 below.

[0131]

[0132] From this, we can see that under the same disaster intensity, the stronger the network strength of the distribution system (reflected in more energy supply paths from the power source to the load), the stronger the system's ability to respond to small-probability-high-loss disturbance events, and the higher the reliability of the distribution system. Under the same network strength, the greater the disaster intensity faced by the distribution system, the greater the impact of the disaster on the distribution system, and the weaker the reliability of the distribution system.

[0133] In order to illustrate the impact of considering distributed resources on the reliability of the distribution network, distributed resources are added to some nodes in RBTS bus4, as shown in Tables 3 and 4 below, where Table 3 shows the output parameters of multiple types of distributed resources, and Table 4 shows the parameters of energy storage and V2G sites.

[0134]

[0135]

[0136] Table 5 below shows the comparison of system reliability indicators with and without considering distributed resources.

[0137]

[0138] It can be seen from Table 5 that, since distributed resources are taken into account for power supply restoration support after a disaster, the system's active defense capability is enhanced, and the reliability level under the influence of disasters can be significantly improved. The present invention provides a systematic evaluation method for reliability evaluation of distribution network disaster defense and provides an objective reference for defense strategies.

[0139] The above embodiments provide a method for evaluating the reliability of a distribution network containing multiple types of distributed energy sources, determine the relationship between disaster intensity and distribution network component failures, use a random forest model to describe the correlation between disaster intensity characteristics and component failure rates, and generate a disaster failure data set for the distribution network through a sampling method; perform post-disaster load recovery and line repair in the post-disaster recovery phase of the distribution network, establish a fault recovery model, solve it to obtain the power supply status of the load nodes of the distribution network, and calculate the reliability index of the power system based on this. The method provided by the present invention realizes the evaluation of the reliability of a new power system that actually contains multiple types of distributed resources, and provides a basis and reference for the long-term planning and operation of the power grid.

[0140] The above method disclosed can be implemented by using various forms of equipment, so the present invention also discloses a device corresponding to the above method, and specific embodiments are given below for detailed description.

[0141] like Figure 5 As shown, an embodiment of the present invention provides a distribution network reliability assessment device containing multiple types of distributed energy sources, including:

[0142] The fault classification module 501 is configured to use a random forest algorithm to describe the relationship between the disaster intensity and the failure rate of the power grid components to obtain a disaster fault classification model;

[0143] A data sampling module 502 is configured to generate a disaster fault data set using a sampling method based on a disaster fault classification model;

[0144] The fault recovery modeling module 503 is configured to use the disaster fault data set as the input of the distribution network for load recovery and establish a post-disaster fault recovery model and its constraints;

[0145] The model solving module 504 is configured to solve the post-disaster fault recovery model based on the constraint conditions to obtain the power supply state value of the load node corresponding to each disaster fault data;

[0146] The evaluation module 505 is configured to calculate the power supply load of the distribution network according to the power supply status value of the load node, and obtain the reliability evaluation result of the distribution network based on the power supply load.

[0147] The implementation principle and technical effects of the device provided in the embodiments of the present application are the same as those of the aforementioned method embodiments. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiments.

[0148] The methods and related devices mentioned in the above embodiments are described with reference to the method flow charts and / or structural diagrams provided in the embodiments of the present application. Specifically, each process and / or block in the method flow charts and / or structural diagrams, as well as the combination of processes and / or blocks in the flow charts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the process. Figure 1 A process or multiple processes and / or structures Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 Schematic diagram of one or more processes and / or structures Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A flow or multiple flows and / or structures illustrate the steps of the functions specified in one block or multiple blocks.

[0149] The following embodiments are described by taking the method applied to a computer device as an example. It can be understood that the computer device can be any device with computing and processing functions, and can be but not limited to a server or a personal laptop computer, etc. In one embodiment, the computer device can be an application server, and the application server can be a server for running an application to be tested.

[0150] See also Figure 6 , which shows a hardware block diagram of an electronic device, the electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0151] like Figure 6 As shown, the electronic device includes: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

[0152] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;

[0153] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0154] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory;

[0155] Among them, the memory stores a program, and the processor can call the program stored in the memory, and the program is used to: implement each processing flow of the aforementioned distribution network reliability assessment solution containing multiple types of distributed energy.

[0156] An embodiment of the present invention also provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements the various processing flows of the distribution network reliability assessment solution containing multiple types of distributed energy provided in the above embodiment and / or any possible implementation method in combination with the embodiment.

[0157] The above-mentioned embodiments have described the present invention in particular detail with respect to possible scenarios, and those skilled in the art will recognize that the present invention can be practiced through other embodiments. The specific naming of components, the capitalization of terms, attributes, data structures, or any other programming or structural aspects are not mandatory or important, and the mechanisms or features of the present invention may have different names, forms, or procedures. The system may be implemented by a combination of hardware and software (as described), entirely by hardware elements, or entirely by software elements. The specific division of functions between the various system components described herein is exemplary only and not mandatory; on the contrary, the functions performed by a single system component may be performed by multiple components, or the functions performed by multiple components may be performed by a single component.

[0158] Those skilled in the art should understand that the various steps of the above disclosed method can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented with program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the embodiments of the present invention are not limited to any specific combination of hardware and software.

[0159] These computing device executable programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors, and these computing programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0160] Certain aspects of the present invention include process steps and instructions described herein in the form of algorithms. It should be noted that the process steps and instructions of the present invention can be implemented in software, firmware and / or hardware, and when implemented by software, it can be downloaded, stored on different platforms used by various operating systems and operated from the platforms.

[0161] Those skilled in the art will understand that the structures shown in the accompanying drawings are merely block diagrams of partial structures related to the scheme of the present application, and do not constitute a limitation on the terminal device to which the scheme of the present application is applied. The specific terminal device may include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

[0162] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "possible design" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0163] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A reliability assessment method for distribution networks containing multiple types of distributed energy resources. It is characterized in that include: The random forest algorithm is used to describe the relationship between disaster intensity and power grid component failure rate, and a disaster failure classification model is obtained; Generate a disaster fault data set using a sampling method based on the disaster fault classification model; The disaster fault data set is used as the input of the distribution network to perform load recovery, and a post-disaster fault recovery model and its constraint conditions are established; Solving the post-disaster fault recovery model based on the constraint conditions to obtain the power supply status value of the load node corresponding to each disaster fault data; The power supply load of the distribution network is calculated according to the power supply status value of the load node, and the reliability evaluation result of the distribution network is obtained based on the power supply load.

2. The method according to claim 1, It is characterized in that The random forest algorithm is used to describe the relationship between the disaster intensity and the failure rate of the power grid components, and the disaster failure classification model is obtained, including: Define disaster types and intensity characteristics; Obtain component failure rates corresponding to each disaster type and intensity characteristic, and generate a training sample set; The training sample set is input into the random forest model for training to obtain the disaster fault classification model.

3. The method according to claim 1, It is characterized in that The sampling method includes a non-sequential Monte Carlo sampling method.

4. The method according to claim 3, It is characterized in that The method of generating a disaster fault data set using a sampling method based on a disaster fault classification model includes: Get a random number uniformly distributed in the space [0,1] , the state of the component when an extreme disaster occurs is expressed as follows: in, represents the probability of failure, Indicates the i-th component in the disaster scene Fault, Indicates Components in disaster scenarios Medium Normal; Repeat the sampling N times, record the number of faulty components corresponding to each sampling, and calculate the average number of faulty components corresponding to the same disaster intensity to obtain the component failure scale corresponding to each disaster intensity.

5. The method according to claim 1, It is characterized in that The establishment of the post-disaster fault recovery model and its constraints include: The following post-disaster fault recovery model is established with the goal of minimizing cost and power loss load: in, represents the weighted power loss load, represents the switching operation cost during fault recovery, represents the cost of mobilizing distributed resources. represents the cost of purchasing electricity, Indicates the total number of time intervals representing the fault period; Represents the total number of nodes in the network; Represents the length of each time interval during the fault period; Represents the power loss of node i in time period t; is the load weight of node i; is a 0-1 optimization variable, which indicates the switch state of the branch starting from node i and ending at node j during the fault recovery period t. Indicates that the switch is closed; Indicates the total number of branches in the network; represents the output power of distributed power generation at node i during period t; It means that node i buys power from the substation during period t; The constraints include distributed new energy operation constraints, V2G reverse charging constraints, load constraints, post-disaster repair and dispatch constraints, dynamic interconnected microgrid topology constraints, and power flow constraints.

6. The method according to claim 5, It is characterized in that The establishment of a post-disaster fault recovery model includes: The weighted power loss load, the switch operation cost during the fault recovery process, the cost of mobilizing distributed resource output, and the power purchase cost are weighted to obtain the following final post-disaster fault recovery model: in, represents the load shedding cost; represents the cost of switch operation; represents the cost of DER electricity generation; It represents the cost of the distribution network purchasing electricity from the upper level.

7. The method according to claim 1, It is characterized in that The calculating the power supply load of the distribution network according to the power supply state value of the load node, and obtaining the reliability evaluation result of the distribution network based on the power supply load includes: Calculate the power supply load of the distribution network according to the power supply status value of the load node, and draw a power supply performance curve of the distribution network; Based on the drawn distribution network power supply performance curve, the ratio of the integral from the time when the disaster occurs to the time when the system recovers to the expected state to the integral of the expected power supply load curve is calculated, and the ratio is recorded as the distribution network reliability assessment result.

8. A reliability assessment device for a distribution network containing multiple types of distributed energy. It is characterized in that include: A fault classification module is configured to use a random forest algorithm to describe the relationship between the disaster intensity and the failure rate of the power grid components to obtain a disaster fault classification model; A data sampling module is configured to generate a disaster fault data set using a sampling method based on a disaster fault classification model; A fault recovery modeling module is configured to use the disaster fault data set as input of the distribution network for load recovery and establish a post-disaster fault recovery model and its constraints; A model solving module is configured to solve a post-disaster fault recovery model based on constraint conditions to obtain a power supply state value of a load node corresponding to each disaster fault data; The evaluation module is configured to calculate the power supply load of the distribution network according to the power supply status value of the load node, and obtain the reliability evaluation result of the distribution network based on the power supply load.

9. An electronic device, It is characterized in that The device comprises a memory storing computer executable instructions and a processor. When the computer executable instructions are executed by the processor, the device executes the reliability assessment method for a distribution network containing multiple types of distributed energy sources as described in any one of claims 1 to 7.

10. A readable storage medium, It is characterized in that A computer executable program is stored, and when the program is executed, the reliability assessment method for a distribution network containing multiple types of distributed energy sources as described in any one of claims 1 to 7 can be implemented.

Images