Power grid risk prediction method, device, storage medium and computer equipment

Abstract

The power grid risk prediction method, device, storage medium and computer equipment provided by the present application, the method includes: when receiving a risk prediction instruction, obtaining a preset risk index set to determine risk index data corresponding to the risk index set; constructing a risk pre-judgment model according to the risk index data; wherein, the risk pre-judgment model aims at the lowest power grid security index, and takes wind farm power, photovoltaic power station power, fluctuating load power and the operating states of each transmission line under the N-1 fault scenario as a set of decision variables to be optimized; obtaining preset constraint conditions, solving the risk pre-judgment model, and obtaining at least one potential risk scenario. By taking the relevant data of new energy and uncertain factors such as load fluctuations as decision variables instead of probability modeling them, the data magnitude required for modeling can be reduced, the difficulty of constructing an accurate model is reduced, and thus the accuracy of power grid risk prediction is improved.

Description

Technical Field

[0001] This application relates to the technical field of risk assessment, and particularly to a power grid risk prediction method, device, storage medium, and computer device. Background Art

[0002] The large-scale grid connection of wind power and photovoltaic power has effectively alleviated the environmental pollution problems brought by traditional thermal power generation. However, at the same time, the problem of the accommodation of wind and light grid connection has become increasingly prominent. The high proportion of new energy grid connection has introduced great uncertainties into the power grid, resulting in problems such as increased difficulty in balancing power supply and demand, enhanced randomness of power grid power flow, and increased difficulty in risk control. Therefore, the importance of realizing flexible operation control of the power grid has become increasingly prominent. And how to improve the power grid's ability to identify and predict potential risk scenarios has become an urgent need for the operation of new regional power grids.

[0003] Currently, the assessment of traditional power systems mainly focuses on the stability of the power grid, that is, the ability of the power grid to maintain stability after a fault occurs. Especially for deterministic faults, such as "N-1" fault analysis, that is, to evaluate the stability ability of the power grid after all components independently fail in sequence. With the expansion of the scale and complexity of the power grid, the uncertainty of the power system is becoming more and more obvious, and the data volume involved in risk prediction is also getting larger and larger, resulting in the difficulty of effectively predicting the power grid risk by the established model, and the accuracy of power grid risk prediction is relatively low. Summary of the Invention

[0004] The purpose of this application aims to solve at least one of the above technical defects, especially the technical defect that with the expansion of the scale and complexity of the power grid in the prior art, the uncertainty of the power system is becoming more and more obvious, and the data volume involved in risk prediction is also getting larger and larger, resulting in the difficulty of effectively predicting the power grid risk by the established model, and the accuracy of power grid risk prediction is relatively low.

[0005] In a first aspect, this application provides a power grid risk prediction method, and the method includes:

[0006] When receiving a risk prediction instruction, obtain a preset risk index set;

[0007] Determine the risk index data corresponding to the risk index set;

[0008] Construct a risk prediction model according to the risk index data; wherein, the risk prediction model aims to minimize the power grid security index, and uses the wind farm power, photovoltaic power station power, fluctuating load power, and the operating states of each transmission line under the N-1 fault scenario as the decision variable set to be optimized;

[0009] Obtain the preset constraint conditions, and solve the risk prediction model according to the constraint conditions to obtain at least one potential risk scenario; wherein, the potential risk scenario includes data corresponding to the decision variable set.

[0010] In one embodiment, the solving the risk prediction model according to the constraint conditions includes:

[0011] Generate a particle swarm according to the constraint conditions and the risk prediction model, and initialize the initial position and initial velocity of each particle in the particle swarm;

[0012] Input the initial position of each particle in the particle swarm into the power flow calculation module respectively to obtain the safety index of the transmission line and the safety index of the transformer;

[0013] Determine the initial fitness of each particle according to the safety index of the transmission line, the safety index of the transformer and the risk prediction model;

[0014] Iteratively update the position and velocity of each particle in the particle swarm according to the preset update rules, the initial position, initial velocity and initial fitness of each particle;

[0015] When the number of iterative updates reaches the preset threshold, use the power flow calculation module and the risk prediction model to determine the fitness of the current position of each particle in the particle swarm;

[0016] Determine at least one target particle in the particle swarm according to the fitness of the current position of each particle in the particle swarm;

[0017] Determine at least one set of values corresponding to the decision variable set according to the current positions of the respective target particles to generate at least one potential risk scenario.

[0018] In one embodiment, the determining at least one target particle in the particle swarm according to the fitness of the current position of each particle in the particle swarm includes:

[0019] Obtain the preset target quantity; wherein, the target quantity is a positive integer greater than 0;

[0020] Sort each particle in the particle swarm according to the fitness of the current position of each particle;

[0021] Select the particles corresponding to the target quantity in the order of fitness from small to large, and determine the selected particles as target particles.

[0022] In one embodiment, the expression of the risk prediction model is:

[0023]

[0024] Wherein, S k represents the power grid security index under risk scenario k, N b is the set of transmission lines, is the upper limit of the power flow that transmission line i can carry, S k (i) is the apparent power of transmission line i under risk scenario k, N s is the set of transformers, is the upper limit of the power flow that transformer j can carry, S k (j) is the apparent power of transformer j under risk scenario k, η is the penalty weight, is the total active power load of the isolated nodes or isolated regions formed by the change of the power grid's network topology structure under risk scenario k, is the total active power load of the power grid.

[0025] In one embodiment, the constraint conditions include a first conditional constraint and a second conditional constraint; the first conditional constraint is:

[0026]

[0027] Wherein, P wGi is the active power of each wind turbine, P sGi is the active power of the photovoltaic power station, P Li is the active power of the load node, F tran,- (i) is the operating state of transmission line i in the N-1 fault scenario, P wGi,min 、P wGi,max are respectively the minimum and maximum values of the active power of each wind turbine, P sGi,min 、P sGi,max are respectively the minimum and maximum values of the active power of the photovoltaic power station, P Li,min 、P Li,max are respectively the minimum and maximum values of the active power of the load node, N wg is the set of wind turbines, N sg the set of photovoltaic power stations, N L is the set of load nodes, N tran,- is the set of transmission lines;

[0028] The second conditional constraint is:

[0029]

[0030] Wherein, P Gi 、Q Gi are respectively the active power and reactive power of the generator set, P Li 、QLi are the active power and reactive power of the load, respectively, V i is the voltage amplitude of node i, V j is the voltage amplitude of node j, θ ij is the phase angle difference between node i and node j, G ij and B ij are the real part and imaginary part of the admittance matrix element of the grid node, respectively, P i is the active power of transmission line i, Q i is the reactive power of transmission line i, S k (i) is the apparent power of transmission line i under risk scenario k.

[0031] In one embodiment, the determining the risk index data corresponding to the risk index set includes:

[0032] Obtaining grid parameter data;

[0033] According to each index item in the risk index set, determining the index data corresponding to each index item in the grid parameter data;

[0034] Determining the set of index data corresponding to each index item in the risk index set as the risk index data.

[0035] In one embodiment, the constructing a risk prediction model according to the risk index data includes:

[0036] Obtaining a preset target model;

[0037] Inputting the risk index data into the target model, and determining the target model after inputting the risk index data as the risk prediction model.

[0038] In a second aspect, the present application provides a grid risk prediction device, and the device includes:

[0039] An instruction receiving module, configured to obtain a preset risk index set when receiving a risk prediction instruction;

[0040] A data determining module, configured to determine risk index data corresponding to the risk index set;

[0041] A model constructing module, configured to construct a risk prediction model according to the risk index data; wherein, the risk prediction model aims at the lowest grid security index, and uses the wind farm power, photovoltaic power station power, fluctuating load power, and the operating states of each transmission line under the N-1 fault scenario as the decision variable set to be optimized;

[0042] A model solving module, configured to obtain preset constraint conditions, and solve the risk prediction model according to the constraint conditions to obtain at least one potential risk scenario; wherein, the potential risk scenario includes data corresponding to the decision variable set.

[0043] In a third aspect, the present application provides a storage medium storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to execute the steps of the power grid risk prediction method according to any one of the above embodiments.

[0044] In a fourth aspect, the present application provides a computer device, including: one or more processors, and a memory;

[0045] The memory stores computer-readable instructions, and when the one or more processors execute the computer-readable instructions, they execute the steps of the power grid risk prediction method according to any one of the above embodiments.

[0046] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

[0047] A power grid risk prediction method, device, storage medium and computer device provided by the present application, the method includes: when receiving a risk prediction instruction, obtaining a preset risk index set to determine risk index data corresponding to the risk index set; constructing a risk prediction model according to the risk index data; wherein, the risk prediction model aims to minimize the power grid security index, and uses wind farm power, photovoltaic power station power, fluctuating load power, and the operating states of each transmission line under the N-1 fault scenario as a decision variable set to be optimized; obtaining preset constraint conditions, and solving the risk prediction model according to the constraint conditions to obtain at least one potential risk scenario; wherein, the potential risk scenario includes data corresponding to the decision variable set. In this way, by using the relevant data of new energy and uncertain factors such as load fluctuations as decision variables instead of probability modeling them, the data volume required for modeling can be reduced, the difficulty of constructing an accurate model can be reduced, and thus the accuracy of power grid risk prediction can be improved. And because the requirement for data volume is small, the scalability of the risk prediction model is strong. Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1Flow schematic diagram of a power grid risk prediction method provided by an embodiment of the present application;

[0050] Figure 2 Flow schematic diagram of solving a risk prediction model according to constraint conditions provided by an embodiment of the present application;

[0051] Figure 3 Flow schematic diagram of determining at least one target particle in a particle swarm provided by an embodiment of the present application;

[0052] Figure 4 Operation diagram of an example system for power grid risk prediction provided by an embodiment of the present application;

[0053] Figure 5 Structure schematic diagram of a power grid risk prediction device provided by an embodiment of the present application;

[0054] Figure 6 Internal structure diagram of a computer device provided by an embodiment of the present application. Specific implementation manners

[0055] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0056] In one of the embodiments, the present application provides a power grid risk prediction method. The following embodiments will be described by taking the application of this method to a server as an example. It can be understood that the execution of the power grid risk prediction method can be a single server or a server cluster composed of multiple servers. The present application does not make specific limitations on this.

[0057] As Figure 1 shown, the present application provides a power grid risk prediction method, and the method includes:

[0058] Step S101: When receiving a risk prediction instruction, obtain a preset risk index set.

[0059] Among them, the risk index set refers to a set of indicators used to evaluate and monitor power grid risks.

[0060] In this step, when it is necessary to predict the operation risk of the power grid, the monitoring personnel can initiate a risk prediction instruction through the client. When the server receives this risk prediction instruction, it obtains the pre-set risk index set.

[0061] Specifically, the creation process of the risk index set may include:

[0062] (1) Define the safety index S of the transmission line k (N b ) and the safety index S of the transformer k (N s ). The expressions for the safety index of the transmission line and the safety index of the transformer can be expressed as follows:

[0063]

[0064]

[0065] In the formula, k represents the risk scenario number of the power grid under the current operation mode, N b is the set of transmission lines, is the upper limit of the power flow that the transmission line i can carry, S k (i) is the apparent power of the transmission line i under the risk scenario k, N s is the set of transformers, is the upper limit of the power flow that the transformer j can carry,

[0066] S k (j) is the apparent power of the transformer j under the risk scenario k.

[0067] It can be understood that the operation mode of the power grid corresponds one-to-one with the risk scenario. In other words, the risk scenarios corresponding to different operation modes of the power grid are also different.

[0068] (2) To evaluate the overall power flow safety and power supply capacity of the power grid, define the safety index S of the power grid k , which is used to reflect the overall safety of the power grid under the risk scenario k. Its expression can be expressed as follows:

[0069]

[0070] In the formula, S k (N b ) is the safety index of the transmission line, S k (N b ) is the safety index of the transformer, η is the penalty weight, is the total active load of the isolated nodes or isolated regions formed by the change of the grid topology structure of the power grid under the risk scenario k, is the total active load of the power grid.

[0071] According to the definitions in (1) and (2) above, construct the risk index set under the risk scenario k Risk index set The expression of can be expressed as follows:

[0072]

[0073] Wherein, S k is the safety index of the power grid, and S k (N b ) is the safety index of the transmission line,

[0074] S k (N b ) is the safety index of the transformer, is the total active load of the isolated nodes or isolated regions formed by the change of the grid topology structure of the power grid under the risk scenario k, is the total active load of the power grid.

[0075] It can be understood that from the above expressions, the risk index set can quantitatively reflect the comprehensive risk of the power grid, the overload risk of the transmission line, the overload risk of the transformer, and the load loss risk under the risk scenario k.

[0076] Step S102: Determine the risk index data corresponding to the risk index set.

[0077] Among them, the risk index data includes the index data corresponding to each index item in the risk index set.

[0078] In this step, after obtaining the risk index set, according to each index item in the risk index set, the data corresponding to each index item can be obtained in turn. When the data corresponding to each index item is obtained, the set of the data corresponding to each index item is determined as the risk index data. It can be understood that since the risk index set can quantify and reflect the risk of the power grid operation state, and reflects the overall safety of the power grid from two aspects of the power grid power flow margin and the isolated load ratio, therefore, obtaining the corresponding risk index data according to the risk index set can provide a representative data basis for subsequent modeling, and then improve the accuracy of the power grid risk prediction.

[0079] Step S103: Construct a risk prediction model according to the risk index data.

[0080] Among them, the risk prediction model aims at the lowest safety index of the power grid, and takes the wind farm power, the photovoltaic power station power, the fluctuating load power, and the operating states of each transmission line under the N-1 fault scenario as the decision variable set to be optimized.

[0081] It is understandable that the N - 1 fault scenario refers to the power grid fault scenario formed by simulating the fault mode of a single transmission line in the power grid, which conforms to the N - 1 criterion. The N - 1 criterion is used to ensure the reliability and stability of the power system. This criterion requires that in the normal operation state of the power grid, even if a fault or outage occurs in any one device (such as generators, transformers, transmission lines, etc.), the continuity of power supply can still be guaranteed. Among them, N represents the number of components in the system, and 1 represents the fault of any one device.

[0082] In this step, after the server obtains the risk index data, it can use the risk index data to construct a corresponding risk prediction model. The goal of the risk prediction model is to minimize the power grid security index to find the most dangerous potential risk scenarios for the power grid.

[0083] Step S104: Obtain the preset constraint conditions, and solve the risk prediction model according to the constraint conditions to obtain at least one potential risk scenario.

[0084] Among them, the potential risk scenario includes the data corresponding to the decision variable set.

[0085] In this step, when the risk prediction model is constructed, obtain the preset constraint conditions, and solve the risk prediction model based on the constraint conditions and the goal of the risk prediction model to obtain at least one potential risk scenario.

[0086] Specifically, since the wind farm power, photovoltaic power station power, and fluctuating load power in the decision variable set are continuous variables, while the operating states of each transmission line under the N - 1 fault scenario are discrete variables, solving the risk prediction model belongs to a mixed - integer optimization problem, and a heuristic optimization algorithm can be used for solving, such as: improved particle swarm optimization algorithm, ant colony algorithm, etc. This application does not make specific limitations on this.

[0087] It is understandable that by solving the risk prediction model, the specific values corresponding to each variable in the decision variable set can be obtained, and a risk scenario can be determined from the specific values corresponding to each variable in the decision variable set. The potential risk scenario refers to one or more relatively dangerous risk scenarios among all risk scenarios.

[0088] A power grid risk prediction method, device, storage medium and computer device provided by the present application. The method includes: when a risk prediction instruction is received, obtaining a preset risk index set to determine risk index data corresponding to the risk index set; constructing a risk prediction model according to the risk index data; wherein, the risk prediction model aims to minimize the power grid security index, and uses wind farm power, photovoltaic power station power, fluctuating load power, and the operating states of each transmission line under N-1 fault scenarios as a set of decision variables to be optimized; obtaining preset constraint conditions, and solving the risk prediction model according to the constraint conditions to obtain at least one potential risk scenario; wherein, the potential risk scenario includes data corresponding to the set of decision variables. In this way, by using relevant data of new energy and uncertain factors such as load fluctuations as decision variables instead of probability modeling for them, the data volume required for modeling can be reduced, the difficulty of constructing an accurate model can be lowered, and thus the accuracy of power grid risk prediction can be improved. And because the requirement for data volume is small, the scalability of the risk prediction model is relatively strong.

[0089] As Figure 2 shown, in one embodiment, solving the risk prediction model according to the constraint conditions includes:

[0090] Step S201: Generate a particle swarm according to the constraint conditions and the risk prediction model, and initialize the initial position and initial velocity of each particle in the particle swarm.

[0091] Wherein, the position of each particle in the particle swarm represents a feasible solution of the risk prediction model. A feasible solution includes the specific values of each variable in the set of decision variables corresponding to the risk prediction model.

[0092] In this step, a feasible solution space can be generated according to the risk prediction model and the constraint conditions, and then several feasible solutions can be randomly selected in the feasible solution space to generate a particle swarm. According to the constraint conditions, the upper and lower limits of each variable in the set of decision variables can be determined, and then the initial position of each particle in the particle swarm can be initialized according to the upper and lower limits of each variable in the set of decision variables. The initial velocity of each particle in the particle swarm can be set to 0 or randomly generated within a preset range, and the present application does not make specific restrictions on this.

[0093] Furthermore, initializing the initial position of each particle in the particle swarm according to the upper and lower limits of each variable in the set of decision variables can be achieved by randomly selecting within the range of the upper and lower limits of each variable in the set of decision variables to form a set of decision variables, or by presetting fixed values within the range of the upper and lower limits of each variable in the set of decision variables to form a set of decision variables.

[0094] Step S202: Input the initial positions of each particle in the particle swarm into the power flow calculation module respectively to obtain the safety index of the transmission line and the safety index of the transformer.

[0095] Among them, the power flow calculation module is used to calculate the voltage amplitude and phase angle of each node (bus) in the power system, as well as the power flow of each branch (branches include transmission lines and transformers). Power flow calculation can help analyze important parameters such as the stability of the power system, power distribution, and voltage quality. The safety index of the transmission line is used to measure and quantify the operation risk of the transmission line, and the safety index of the transformer is used to measure and quantify the operation risk of the transformer.

[0096] In this step, inputting the initial positions of each particle in the particle swarm into the power flow calculation module is equivalent to inputting the specific values of the decision variable set corresponding to each particle into the power flow calculation module. For a set of specific values of decision variables, the power flow calculation module can calculate the upper limit of the power flow and apparent power that each transmission line and each transformer can carry according to the specific values of this set of decision variables. Furthermore, according to the upper limit of the power flow and apparent power that each transmission line and each transformer can carry, determine the safety index of the transmission line and the safety index of the transformer.

[0097] Step S203: Determine the initial fitness of each particle according to the safety index of the transmission line, the safety index of the transformer, and the risk prediction model.

[0098] Among them, the initial fitness refers to the power grid safety index when the corresponding particle is at the initial position.

[0099] In this step, substitute the safety index of the transmission line and the safety index of the transformer into the risk prediction model to determine the corresponding power grid safety index, that is, the initial fitness.

[0100] Step S204: Iteratively update the positions and velocities of each particle in the particle swarm according to the preset update rule, the initial position, the initial velocity, and the initial fitness of each particle.

[0101] Among them, the update rule means that in each iterative update, each particle in the particle swarm searches for the current optimal solution. When the iteration ends, the local optimal solution of each particle in the particle swarm is obtained, and then the global optimal solution is determined according to the local optimal solution of each particle in the particle swarm.

[0102] It can be understood that for each particle in the particle swarm during each iterative update, according to the current velocity of the particle, the position to be moved is determined, and then the fitness of this position is calculated. If the preset condition is satisfied, the position of the particle is updated; otherwise, the position of the particle is not updated. During each iterative update, the velocity of each particle in the particle swarm can be updated, and the specific update method can be determined according to the selected optimization algorithm, which is not specifically limited in this application.

[0103] Specifically, during the iterative update of the positions and velocities of each particle in the particle swarm, when calculating the fitness corresponding to the position of the particle, a power flow calculation module is required, and the specific calculation process can refer to steps S202 to S203 and their corresponding descriptions.

[0104] Furthermore, the preset condition means that when this iteration is not the first iteration, to determine whether to update the particle position, it can be judged according to whether the fitness of the position to be moved is less than the fitness corresponding to the position in the previous iterative update. When this iteration is the first iteration, to determine whether to update the particle position, it can be judged according to whether the fitness of the position to be moved is less than the initial fitness of the particle.

[0105] Step S205: When the number of iterative updates reaches the preset threshold, use the power flow calculation module and the risk prediction model to determine the fitness of the current position of each particle in the particle swarm.

[0106] Among them, the preset threshold is an empirical value.

[0107] When the number of iterative updates reaches the preset threshold, the power flow calculation model and the risk prediction model can be used to determine the fitness corresponding to the current position of each particle in the particle swarm. It can be understood that at this time, the fitness corresponding to the current position of each particle is the minimum value of the fitness obtained by the corresponding particle in each round of iterative updates.

[0108] Step S206: According to the fitness of the current position of each particle in the particle swarm, determine at least one target particle in the particle swarm.

[0109] Among them, the fitness refers to the power grid security index of the risk prediction model at the corresponding position.

[0110] It can be understood that the number of target particles to be determined depends on the total number of the particle swarm and the needs of the monitoring personnel.

[0111] Step S207: According to the current positions of each target particle, determine at least one set of values corresponding to the decision variable set to generate at least one potential risk scenario.

[0112] In this step, according to the obtained values corresponding to the decision variable set, corresponding potential risk scenarios can be generated.

[0113] It can be understood that by using an optimization algorithm to solve the risk prediction model, potential risk scenarios that can minimize the power grid security index can be found to achieve the prediction of power grid risks. Moreover, uncertain factors such as wind farm power, PV power station power, fluctuating load power, and the operating states of each transmission line under N-1 fault scenarios are used as the decision variable set to be optimized. However, the method of using uncertain factors to establish a probability model requires collecting a large amount of data. Otherwise, it is easy to affect the accuracy of the established model, thereby affecting the accuracy of power grid risk prediction. In contrast, the interval optimization method adopted in this embodiment can reduce the data volume required for modeling, reduce the difficulty of constructing an accurate model, and thus improve the accuracy of power grid risk prediction. And due to the small requirement for data volume, the scalability of the risk prediction model is relatively strong.

[0114] As Figure 3 shown, in one embodiment, according to the fitness of the current position of each particle in the particle swarm, at least one target particle is determined in the particle swarm, including:

[0115] Step S301: Obtain a preset target number.

[0116] Among them, the target number is a positive integer greater than 0. The target number can be set and modified by the monitoring personnel or can also adopt the default setting value.

[0117] Step S302: Sort each particle in the particle swarm according to the fitness of the current position of each particle in the particle swarm.

[0118] Step S303: Select particles corresponding to the target number in ascending order of fitness, and determine the selected particles as target particles.

[0119] It can be understood that according to the set target number, the number of potential risk scenarios in the final solution result can be flexibly selected, thereby improving the flexibility of power grid risk prediction.

[0120] In one embodiment, the expression of the risk prediction model is:

[0121]

[0122] In the formula, S k represents the power grid security index under risk scenario k, N b is the set of transmission lines, is the upper limit of the power flow that transmission line i can carry, S k (i) is the apparent power of transmission line i under risk scenario k, Ns is a set of transformers, is the upper limit of the power flow that transformer j can carry, S k (j) is the apparent power of transformer j under risk scenario k, η is the penalty weight, is the total active power load of the isolated nodes or isolated regions formed by the change of the grid network topology under risk scenario k, is the total active power load of the power grid.

[0123] It can be understood that the change of the grid network topology may cause some nodes or regions to lose connection with other nodes or regions, forming isolated nodes or isolated regions. These isolated nodes or regions will not be able to exchange energy with other parts through transmission lines in the power system.

[0124] In one embodiment, the constraint conditions include a first condition constraint and a second condition constraint; the first condition constraint is:

[0125]

[0126] In the formula, P wGi is the active power of each wind turbine, P sGi is the active power of the photovoltaic power station, P Li is the active power of the load node, F tran,- (i) is the operating state of transmission line i in the N-1 fault scenario, P wGi,min 、P wGi,max are the minimum and maximum values of the active power of each wind turbine respectively, P sGi,min 、P sGi,max are the minimum and maximum values of the active power of the photovoltaic power station respectively, P Li,min 、P Li,max are the minimum and maximum values of the active power of the load node respectively, N wg is the set of wind turbines, N sg the set of photovoltaic power stations, N L is the set of load nodes, N tran,- is the set of transmission lines;

[0127] The second condition constraint is:

[0128]

[0129] In the formula, P Gi 、Q Gi are the active power and reactive power of the generator set respectively, P Li 、Q Li are the active power and reactive power of the load respectively, V i is the voltage amplitude of node i, V jis the voltage amplitude of node j, θ ij is the phase angle difference between node i and node j, G ij 、B ij are the real part and the imaginary part of the admittance matrix element of the grid network node respectively, P i is the active power of transmission line i, Q i is the reactive power of transmission line i, S k (i) is the apparent power of transmission line i under risk scenario k.

[0130] In one embodiment, determining risk index data corresponding to a risk index set includes:

[0131] Obtaining grid parameter data;

[0132] According to each index item in the risk index set, determining the index data corresponding to each index item in the grid parameter data;

[0133] Determining the set of index data corresponding to each index item in the risk index set as the risk index data.

[0134] In this embodiment, the risk index data corresponding to the risk index set can be determined by obtaining the grid parameter data, and then screening the data corresponding to each index item in the risk index set from the grid parameter data according to each index item in the risk index set.

[0135] Furthermore, for each index item in the risk index set, determining the data of this index item may include: searching for the data corresponding to this index item in the grid parameter data under various operation modes of the grid, and determining the found data as the data corresponding to this index item.

[0136] Specifically, the grid parameter data refers to the data recorded and stored on the operation conditions of the power system. It can be used to analyze and evaluate the performance, reliability, efficiency and security of the grid. The grid parameter data includes the data corresponding to each index item in the risk index set under various operation modes of the grid.

[0137] It can be understood that since the risk index set can quantify and reflect the risk of the grid operation state, and reflects the overall security of the grid from two aspects of the grid power flow margin and the proportion of isolated loads, therefore, obtaining the corresponding risk index data according to the risk index set can provide a representative data basis for subsequent modeling, and further improve the accuracy of grid risk prediction.

[0138] In one embodiment, constructing a risk prediction model according to the risk index data includes:

[0139] Obtaining a preset target model;

[0140] Input the risk index data into the target model, and determine the target model input with the risk index data as the risk prediction model.

[0141] The target model refers to a mathematical model pre-constructed for the optimization problem to be solved.

[0142] In this embodiment, by inputting the risk index data into the target model, the target model after data input is used as the risk prediction model.

[0143] In one example, as Figure 4 shown, Figure 4 is the operation diagram of the example system for power grid risk prediction provided by the embodiment of the present application. The example system includes two 110 kV subnetworks #A and #B. The black icons in the figure represent that they belong to subnetwork #A, and the white icons represent that they belong to subnetwork #B. Figure 4 In it, the numbers T, H, S, and W respectively represent substation, hydropower station, photovoltaic power station, and wind farm nodes. The dotted lines represent that the lines are in the disconnected state, and the black lines represent that the lines are in the operating state.

[0144] Under the normal operation mode, the tie line between subnetwork #A and subnetwork #B is in the disconnected state. The subnetworks operate independently of each other and are both in the open-loop operation mode; except for user station T#10, each station is equipped with a 110 kV automatic bus transfer device.

[0145] The risk sources of this example system are set as:

[0146] ① In terms of the power of photovoltaic power stations and wind farms: the prediction errors of all new energy stations, and the error limit is set to ±10%, including photovoltaic power stations S#1, S#2, S#3, S#4, and wind farm

[0147] W#1;

[0148] ② In terms of the power of fluctuating loads: the load prediction errors of large load substations, and the error limit is set to

[0149] ±5%, including substations T#1, T#3, T#4, T#9, T#10, T#15;

[0150] ③ In terms of the N-1 fault scenario: the fault set is set as all the transmission lines in operation.

[0151] Suppose the results obtained by solving this example system are shown in the following table:

[0152]

[0153] Among them, S k , S k (N b )、Sk (N s ) The meaning of can be referred to the description in the above embodiments. At this time, the risk sources of potential risk scenarios can be analyzed. Taking potential risk scenario 1 as an example, the risk index set of potential risk scenario 1 in this calculation example system can be expressed as follows:

[0154] (1.384, 0.310, -0.514, 0.107) T

[0155] It can be seen from the above expression that under potential risk scenario 1, the grid security index is 1.384, there is a risk of 31.0% over-limit for transmission lines, there is no over-limit risk for transformers, and there is at least a relative margin of 51.4%. There is a risk of losing 10.7% of the load in the grid.

[0156] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0157] Next, the grid risk prediction device provided by the embodiments of the present application will be described. The grid risk prediction device described below can be correspondingly referred to the grid risk prediction method described above.

[0158] As Figure 5 shown, the present application provides a grid risk prediction device 400, and the device includes:

[0159] An instruction receiving module 401, configured to obtain a preset risk index set when receiving a risk prediction instruction;

[0160] A data determination module 402, configured to determine risk index data corresponding to the risk index set;

[0161] A model construction module 403, configured to construct a risk prediction model according to the risk index data; wherein, the risk prediction model aims at the lowest grid security index, and uses the wind farm power, photovoltaic power station power, fluctuating load power, and the operating states of each transmission line under the N-1 fault scenario as the decision variable set to be optimized;

[0162] The model solving module 404 is configured to obtain preset constraint conditions and solve the risk prediction model according to the constraint conditions to obtain at least one potential risk scenario; wherein, the potential risk scenario includes data corresponding to the decision variable set.

[0163] In one embodiment, the model solving module includes:

[0164] The initialization sub-module is configured to generate a particle swarm according to the constraint conditions and the risk prediction model, and initialize the initial position and initial velocity of each particle in the particle swarm;

[0165] The power flow calculation sub-module is configured to input the initial position of each particle in the particle swarm into the power flow calculation module respectively to obtain the safety index of the transmission line and the safety index of the transformer;

[0166] The first fitness determination sub-module is configured to determine the initial fitness of each particle according to the safety index of the transmission line, the safety index of the transformer and the risk prediction model;

[0167] The iterative update sub-module is configured to iteratively update the position and velocity of each particle in the particle swarm according to the preset update rules, the initial position, the initial velocity and the initial fitness of each particle;

[0168] The second fitness determination sub-module is configured to, when the number of iterative updates reaches the preset threshold, determine the fitness of the current position of each particle in the particle swarm by using the power flow calculation module and the risk prediction model;

[0169] The target particle determination sub-module is configured to determine at least one target particle in the particle swarm according to the fitness of the current position of each particle in the particle swarm;

[0170] The scenario generation sub-module is configured to determine at least one set of values corresponding to the decision variable set according to the current positions of the respective target particles to generate at least one potential risk scenario.

[0171] In one embodiment, the target particle determination sub-module includes:

[0172] The quantity acquisition unit is configured to acquire a preset target quantity; wherein, the target quantity is a positive integer greater than 0;

[0173] The particle sorting unit is configured to sort each particle in the particle swarm according to the fitness of the current position of each particle in the particle swarm;

[0174] The target particle determination unit is configured to select the particles corresponding to the target quantity in ascending order of fitness and determine the selected particles as target particles.

[0175] In one embodiment, the data determination module includes:

[0176] A data acquisition sub-module for acquiring power grid parameter data;

[0177] An index data determination sub-module for determining, according to each index item in the risk index set, the index data corresponding to each index item in the power grid parameter data;

[0178] A data determination sub-module for determining the set of index data corresponding to each index item in the risk index set as the risk index data.

[0179] In one embodiment, the model construction module includes:

[0180] A model acquisition sub-module for acquiring a preset target model;

[0181] A model determination sub-module for inputting the risk index data into the target model and determining the target model after the input of the risk index data as the risk prediction model.

[0182] The division of each module in the above power grid risk prediction device is only for illustrative purposes. In other embodiments, the power grid risk prediction device can be divided into different modules as needed to complete all or part of the functions of the above power grid risk prediction device. Each module in the above power grid risk prediction device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0183] In one embodiment, the present application also provides a storage medium, in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, one or more processors are caused to execute the steps of the power grid risk prediction method as described in any one of the above embodiments.

[0184] In one embodiment, the present application also provides a computer device, in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, one or more processors are caused to execute the steps of the power grid risk prediction method as described in any one of the above embodiments.

[0185] Schematically, as Figure 6 shown, Figure 6 is a schematic internal structure diagram of a computer device provided by an embodiment of the present application. The computer device 500 can be provided as a server. Referring to Figure 6, the computer device 500 includes a processing component 502, which further includes one or more processors, and memory resources represented by a memory 501 for storing instructions executable by the processing component 502, such as application programs. The application programs stored in the memory 501 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 502 is configured to execute instructions to perform the power grid risk prediction method of any of the above embodiments.

[0186] The computer device 500 may further include a power supply component 503 configured to perform power management of the computer device 500, a wired or wireless network interface 504 configured to connect the computer device 500 to a network, and an input / output (I / O) interface 505. The computer device 500 may operate based on an operating system stored in the memory 501, such as Windows Server TM, Mac OS XTM, Unix TM, Linux TM, Free BSDTM, or the like.

[0187] Those skilled in the art can understand that Figure 6 the structure shown in

[0188] Finally, it should also be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the said element. In this text, the singular forms "a", "an" and "the" may also include the plural form, unless the context clearly dictates otherwise. It should also be understood that the terms "comprising / including" or "having" etc. specify the existence of the stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the existence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the related listed items.

[0189] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0190] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but rather will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting power grid risk, characterized in that: The method comprises: When receiving a risk prediction instruction, obtaining a preset risk indicator set; Determining risk indicator data corresponding to the risk indicator set; According to the risk indicator data, a risk prediction model is constructed; wherein the risk prediction model takes the lowest power grid security index as the goal, and takes the wind farm power, photovoltaic station power, fluctuating load power and the operating status of each transmission line under the N-1 fault scenario as the decision variable set to be optimized; Obtaining preset constraints, and solving the risk prediction model according to the constraints to obtain at least one potential risk scenario; wherein the potential risk scenario includes data corresponding to the decision variable set; The expression of the risk prediction model is: In the formula, S k represents the power grid security index under risk scenario k, N b is a collection of transmission lines, is the upper limit of the power flow that the transmission line i can carry, S k (i) is the apparent power of transmission line i under risk scenario k, N s For the transformer set, is the upper limit of the power flow that transformer j can carry, S k (j) is the apparent power of transformer j under risk scenario k, η is the penalty weight, is the total active load of isolated nodes or isolated areas caused by the change of grid topology structure under risk scenario k, is the total active load of the power grid; The constraint conditions include a first constraint and a second constraint; the first constraint condition is: Where P wGi is the active power of each wind turbine, P sGi is the active power of the photovoltaic power station, P Li is the active power of the load node, F tran,- (i) is the operating status of transmission line i in N-1 fault scenario, P wGi,min , P wGi,max are the minimum and maximum active power of each wind turbine, P sGi,min , P sGi,max are the minimum and maximum active power of the photovoltaic power station, P Li,min , P Li,max are the minimum and maximum active power of the load node, N wg is the set of wind turbines, N sg The collection of photovoltaic power plants, N L is the set of load nodes, N tran,- is a collection of transmission lines; The second condition constraint is: Where P Gi , Q Gi are the active power and reactive power of the generator set, Q Li is the reactive power of the load, V i is the voltage amplitude of node i, V j is the voltage amplitude at node j, θ ij is the phase angle difference between node i and node j, G ij , B ij are the real and imaginary parts of the admittance matrix elements of the grid nodes in the power grid, respectively. i is the active power of transmission line i, Q i is the reactive power of transmission line i, S k (i) is the apparent power of transmission line i under risk scenario k.

2. The power grid risk prediction method according to claim 1, characterized in that: Solving the risk prediction model according to the constraint conditions includes: Generate a particle swarm according to the constraint conditions and the risk prediction model, and initialize the initial position and initial velocity of each particle in the particle swarm; Inputting the initial position of each particle in the particle swarm into the power flow calculation module respectively to obtain the safety index of the transmission line and the safety index of the transformer; Determining the initial fitness of each particle according to the safety index of the transmission line, the safety index of the transformer and the risk prediction model; Iteratively updating the position and velocity of each particle in the particle swarm according to a preset update rule, an initial position, an initial velocity, and an initial fitness of each particle; When the number of iterative updates reaches a preset threshold, the fitness of the current position of each particle in the particle swarm is determined by using the power flow calculation module and the risk prediction model; Determining at least one target particle in the particle swarm according to the fitness of the current position of each particle in the particle swarm; According to the current position of each target particle, at least one set of values ​​corresponding to the decision variable set is determined to generate at least one potential risk scenario.

3. The power grid risk prediction method according to claim 2, characterized in that: The step of determining at least one target particle in the particle swarm according to the fitness of the current position of each particle in the particle swarm comprises: Obtain a preset target quantity; wherein the target quantity is a positive integer greater than 0; sorting each particle in the particle swarm according to the fitness of the current position of each particle in the particle swarm; According to the order of fitness from small to large, particles corresponding to the target number are selected, and the selected particles are determined as target particles.

4. The power grid risk prediction method according to claim 1, characterized in that: The determining of the risk indicator data corresponding to the risk indicator set includes: Obtain power grid parameter data; According to each indicator item in the risk indicator set, determining indicator data corresponding to each indicator item in the power grid parameter data; A set of indicator data corresponding to each indicator item in the risk indicator set is determined as risk indicator data.

5. The power grid risk prediction method according to claim 1, characterized in that: The step of constructing a risk prediction model based on the risk indicator data includes: Get the preset target model; The risk indicator data is input into the target model, and the target model after the risk indicator data is input is determined as a risk prediction model.

6. A power grid risk prediction device, characterized in that: The device comprises: An instruction receiving module, used to obtain a preset risk indicator set when receiving a risk prediction instruction; A data determination module, used to determine risk indicator data corresponding to the risk indicator set; A model building module is used to build a risk prediction model according to the risk indicator data; wherein the risk prediction model aims to minimize the power grid security index, and uses wind farm power, photovoltaic station power, fluctuating load power and the operating status of each transmission line under N-1 fault scenario as a set of decision variables to be optimized; A model solving module, used to obtain preset constraints, and solve the risk prediction model according to the constraints to obtain at least one potential risk scenario; wherein the potential risk scenario includes data corresponding to the decision variable set; The expression of the risk prediction model is: In the formula, S k represents the power grid security index under risk scenario k, N b is a collection of transmission lines, is the upper limit of the power flow that the transmission line i can carry, S k (i) is the apparent power of transmission line i under risk scenario k, N s For the transformer set, is the upper limit of the power flow that transformer j can carry, S k (j) is the apparent power of transformer j under risk scenario k, η is the penalty weight, is the total active load of isolated nodes or isolated areas caused by the change of grid topology structure under risk scenario k, is the total active load of the power grid; The constraint conditions include a first constraint and a second constraint; the first constraint condition is: Where P wGi is the active power of each wind turbine, P sGi is the active power of the photovoltaic power station, P Li is the active power of the load node, F tran,- (i) is the operating status of transmission line i in N-1 fault scenario, P wGi,min , P wGi,max are the minimum and maximum active power of each wind turbine, P sGi,min , P sGi,max are the minimum and maximum active power of the photovoltaic power station, P Li,min , P Li,max are the minimum and maximum active power of the load node, N wg is the set of wind turbines, N sg The collection of photovoltaic power plants, N L is the set of load nodes, N tran,- is a collection of transmission lines; The second condition constraint is: Where P Gi , Q Gi are the active power and reactive power of the generator set, Q Li is the reactive power of the load, V i is the voltage amplitude of node i, V j is the voltage amplitude at node j, θ ij is the phase angle difference between node i and node j, G ij , B ij are the real and imaginary parts of the admittance matrix elements of the grid nodes in the power grid, respectively. i is the active power of transmission line i, Q i is the reactive power of transmission line i, S k (i) is the apparent power of transmission line i under risk scenario k.

7. A storage medium, characterized in that: The storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the power grid risk prediction method as described in any one of claims 1 to 5.

8. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the power grid risk prediction method according to any one of claims 1 to 5 are performed.

Images