Power distribution network dispatching method, system, device, medium and product based on multi-element resource cooperation

Abstract

The present application relates to the technical field of power distribution network, disclose a kind of multi-element resource coordination's power distribution network scheduling method, system, equipment, medium and product, the present application determines the typical failure scenario of power distribution network by collecting the operation failure data of each element of power distribution network under typhoon weather scene, and with the minimum load loss of power distribution network, the minimum total cost of scheduling and the shortest recovery time of key load minimization as multi-optimization goal, simultaneously consider load loss rate, economic cost, key load recovery time, give consideration to economic efficiency-resilience-time multi-dimensional balance, by the balanced operation state of power distribution network and EV charging station, determine the constraint condition of multi-optimization goal, to ensure the operation reliability of power distribution network and EV charging station, by constructing power distribution network scheduling optimization model, and carry out optimization solution, obtain power distribution network scheduling optimization scheme, to realize the real-time scheduling of multi-element flexibility resource, improve the reliability of power distribution network scheduling.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution networks, and in particular to a multi-element resource coordinated power distribution network scheduling method, system, device, medium and product. BACKGROUND

[0002] In recent years, the frequent occurrence of extreme weather events (such as typhoons, heavy rains, etc.) has put higher requirements on the stable operation of power distribution networks. At the same time, the increasing penetration of renewable energy generation (such as distributed photovoltaic, wind power, etc.) has further increased the uncertainty and complexity of power grid operation. Extreme weather conditions such as typhoons not only pose a threat to traditional transmission lines and substations, but also seriously affect the normal operation of distributed energy devices, thereby exacerbating the vulnerability of power distribution networks in disaster scenarios.

[0003] Although traditional numerical prediction, statistical models and some machine learning methods can reflect the macro characteristics of typhoons and disasters to some extent, there are still deficiencies in capturing the spatio-temporal characteristics of typhoons, predicting disaster evolution and evaluating the impact of disasters on power grid elements (such as transmission lines, substations, photovoltaic systems). At the same time, with the popularity of flexible resources such as distributed energy, energy storage devices, mobile energy storage and electric vehicles, how to fully coordinate these multi-element resources in disaster scheduling to achieve a balance between economy, resilience and timeliness has become an important research direction for current power grid scheduling and restoration.

[0004] In existing power distribution network scheduling, real-time scheduling of multi-element flexible resources (such as electric vehicles (EV), energy storage, mobile energy storage) cannot achieve efficient distributed coordination and real-time scheduling, and the reliability of the scheduling is poor. SUMMARY

[0005] Therefore, the present application provides a multi-element resource coordinated power distribution network scheduling method, system, device, medium and product, which solves the technical problem that real-time scheduling of multi-element flexible resources cannot achieve efficient distributed coordination and real-time scheduling, and the reliability of the scheduling is poor.

[0006] The first aspect of the present application provides a multi-element resource coordinated power distribution network scheduling method, comprising:

[0007] Collecting operation failure data of each element of the power distribution network in a typhoon weather scenario, and determining a typical failure scenario of the power distribution network according to the operation failure data;

[0008] Minimizing load loss, minimizing total scheduling cost and minimizing key load recovery time of the power distribution network as multi-optimization objectives;

[0009] According to the balanced operation state of the power distribution network and the EV charging station, a constraint condition of the multiple optimization objectives is determined;

[0010] According to the multiple optimization objectives and the constraint condition, a power distribution network dispatching optimization model is constructed.

[0011] According to the typical fault scenario, the power distribution network dispatching optimization model is optimized and solved to obtain a power distribution network dispatching optimization scheme under the typical fault scenario.

[0012] Preferably, the operation fault data includes line fault probability and photovoltaic unit fault probability.

[0013] The operation fault data of each element of the power distribution network under the typhoon weather scenario is collected, and according to the operation fault data, a typical fault scenario of the power distribution network is determined, including:

[0014] According to the historical typhoon wind speed, a pre-trained typhoon time-varying prediction model is used for prediction to obtain a typhoon predicted wind speed at a current prediction moment.

[0015] A line fault probability model and a photovoltaic unit fault probability model are respectively constructed, and according to the line fault probability model and the photovoltaic unit fault probability model, the line fault probability and the photovoltaic unit fault probability are determined in combination with the typhoon predicted wind speed.

[0016] According to the line fault probability and the photovoltaic unit fault probability, a plurality of fault scenarios are generated by Monte Carlo sampling.

[0017] From a plurality of the fault scenarios, a fault scenario corresponding to an entropy value with the maximum line fault probability and photovoltaic unit fault probability is screened out to determine the typical fault scenario of the power distribution network.

[0018] Preferably, the method further includes:

[0019] Typhoon historical sample time series data is collected, and the typhoon historical sample time series data is extracted through a convolutional neural network to obtain space-time features.

[0020] The space-time features are input into a long short-term memory network to process the time sequence relationship in the space-time features to obtain a typhoon time-varying prediction model.

[0021] Preferably, the objective function corresponding to the multiple optimization objectives is:

[0022]

[0023] In the formula, is a weighted load loss rate, is a total dispatching cost, is a key load recovery time. , , All are weighting coefficients;

[0024] in,

[0025] In the formula, Let be the active power lost at node n at time t. Let be the active power demand of node n at time t. The load importance weight for node n, The total number of time periods in the scheduling cycle. This represents the total number of nodes in the distribution network.

[0026]

[0027] In the formula, for EV scheduling cost at any given moment; for The cost of energy storage dispatch at any given moment; for The cost of scheduling photovoltaic units at any given time; The incentive cost for charging stations;

[0028] in,

[0029] In the formula, The unit discharge loss cost of the battery in the EV charging station. For nodes A collection of EV charging stations for Time Node The active power output of the EV charging station q;

[0030]

[0031] In the formula, The unit scheduling cost for MESS; for Time Node The active power output by MESS. For unit distance scheduling cost, For scheduling distance; m represents the number of users participating in the scheduling; m is the index of the users participating in the scheduling.

[0032]

[0033] In the formula, The unit power output operation and maintenance cost of photovoltaic units; for Time Node active power of the PV output;

[0034] wherein,

[0035]

[0036] wherein, active power of the EV charging station at the node at the time t, base incentive price; incentive price adjustment coefficient; active power of all EV charging stations at the node at the time t,

[0037]

[0038] wherein, unit time cost of critical node delay recovery; critical load node set; time length of power outage of the node n.

[0039] Preferably, the constraint conditions include power grid operation constraints and EV charging station scheduling constraints; wherein the power grid operation constraints include topology constraints, node power balance constraints, node voltage relaxation constraints, line transmission power limit constraints, node voltage limit constraints, node load loss limit constraints and PV operation limit constraints;

[0040] the EV charging station scheduling constraints include road network-power grid coupling constraints, EV power limit constraints participating in scheduling, user discharge response rate constraints under the incentive price, balance constraints of the user discharge response rate under the incentive price and the output of the EV charging station, EV charging and discharging power limit constraints, EV power limit constraints and MESS scheduling limit constraints;

[0041] wherein, the road network-power grid coupling constraint is used to constrain the EV to arrive at the designated location for charging and discharging in time during the scheduling process;

[0042] the EV power limit constraint participating in scheduling is used to ensure that the EV has power not lower than a preset threshold at the end of the scheduling;

[0043] the user discharge response rate constraint under the incentive price is used to constrain the user discharge response rate under different incentive prices according to the sensitivity of the user to the incentive price;

[0044] the balance constraint of the user discharge response rate under the incentive price and the output of the EV charging station is used to constrain to ensure that the output of the EV charging station matches the user's discharge demand. ​

[0045] Preferably, the optimization solution of the power distribution network scheduling optimization model under the typical fault scenario is obtained by optimizing the power distribution network scheduling optimization model according to the typical fault scenario, comprising:

[0046] a plurality of power distribution network scheduling candidate schemes satisfying the constraint condition are randomly generated, and the plurality of power distribution network scheduling candidate schemes are used to initialize a population;

[0047] the individuals in the initialized population are non-dominantly sorted, and the crowding distance is calculated;

[0048] the fitness value of each individual is determined according to the objective function corresponding to the multi-optimization objective;

[0049] According to the fitness value and the crowding distance, the individuals with a fitness value greater than a preset fitness threshold and a crowding distance greater than a preset crowding distance threshold are selected to form a new population;

[0050] The new population is subjected to cross and mutation operations to generate new offspring individuals;

[0051] The new offspring individuals and the parent individuals are combined to form a new population, and the non-dominant sorting of the individuals in the initialized population and the calculation of the crowding distance are repeated until the iteration termination condition is met;

[0052] The optimal individual is selected from the final population as the optimal solution of the power distribution network scheduling optimization model, and the power distribution network scheduling optimization scheme under the typical fault scenario is obtained.

[0053] In a second aspect, the present application provides a multi-element resource coordinated power distribution network scheduling system, comprising:

[0054] A fault scenario determination module is configured to collect operation failure data of each element of a power distribution network under a typhoon weather scenario, and determine a typical fault scenario of the power distribution network according to the operation failure data;

[0055] An optimization objective determination module is configured to minimize the load loss, minimize the total scheduling cost, and minimize the key load recovery time of the power distribution network as multi-optimization objectives;

[0056] A constraint determination module is configured to determine the constraint condition of the multi-optimization objective according to the balanced operation state of the power distribution network and the EV charging station;

[0057] A model construction module is configured to construct a power distribution network scheduling optimization model according to the multi-optimization objective and the constraint condition;

[0058] The scheduling optimization module is configured to perform optimization solution on the power distribution network scheduling optimization model according to the typical fault scenario, so as to obtain a power distribution network scheduling optimization scheme under the typical fault scenario.

[0059] In a third aspect, the present application provides an electronic device, which comprises a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the power distribution network scheduling method with multi-element resource coordination as described in the first aspect.

[0060] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed to implement the steps of the power distribution network scheduling method with multi-element resource coordination as described in the first aspect.

[0061] In a fifth aspect, the present application provides a computer program product, which comprises a computer program stored on a non-transitory computer readable storage medium, and the computer program comprises program instructions, wherein when the program instructions are executed by a computer, the computer executes the steps of the power distribution network scheduling method with multi-element resource coordination as described in the first aspect.

[0062] From the above technical solutions, it can be seen that the present application determines the typical fault scenario of the power distribution network by collecting the operation failure data of each element of the power distribution network under the typhoon weather scenario, and takes the minimization of the load loss, the minimization of the total scheduling cost and the minimization of the key load recovery time as the multi-optimization target, considers the load loss rate, the economic cost and the key load recovery time at the same time, balances the economy-resilience-time multi-dimension, determines the constraint condition of the multi-optimization target according to the balanced operation state of the power distribution network and the EV charging station, so as to ensure the operation reliability of the power distribution network and the EV charging station, constructs the power distribution network scheduling optimization model through the multi-optimization target and the constraint condition, and performs optimization solution to obtain the power distribution network scheduling optimization scheme, so as to realize the real-time scheduling of the multi-element flexible resource, and realize the efficient distributed coordination and real-time scheduling, thereby improving the reliability of the power distribution network scheduling. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0064] Figure 1 An application environment diagram of the power distribution network scheduling method with multi-element resource coordination provided by the embodiments of the present application is shown in the figure.

[0065] Figure 2 A flow chart of a multi-element resource cooperative power distribution network scheduling method provided for an embodiment of the present application;

[0066] Figure 3 A structural schematic diagram of a multi-element resource cooperative power distribution network scheduling system provided for an embodiment of the present application;

[0067] Figure 4 A structural schematic diagram of an electronic device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0068] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative work fall within the scope of protection of the present application.

[0069] The multi-element resource cooperative power distribution network scheduling method provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 . The terminal 101 communicates with the server 102 through a network. The data storage system can store data required to be processed by the server 102. The data storage system can be integrated on the server 102, or placed on a cloud or other network server. The terminal 101 or the server 102 collects operation failure data of each element of the power distribution network under a typhoon weather scenario, determines a typical failure scenario of the power distribution network according to the operation failure data, takes minimization of load loss of the power distribution network, minimization of total scheduling cost and minimization of key load recovery time as multi-optimization objectives, determines constraint conditions of the multi-optimization objectives according to balanced operation states of the power distribution network and the EV charging station, constructs a power distribution network scheduling optimization model according to the multi-optimization objectives and the constraint conditions, and obtains a power distribution network scheduling optimization scheme under the typical failure scenario by optimizing and solving the power distribution network scheduling optimization model.

[0070] The terminal 101 can be, but is not limited to, various personal computers, notebook computers, smart phones and tablet computers, etc.

[0071] The server 102 can be a stand-alone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0072] As shown in Figure 2 , the present application provides a multi-element resource cooperative power distribution network scheduling method. The method is applied inFigure 1 The terminal 101 or the server 102 in the system 100 is taken as an example for illustration, including the following steps S1 to S5. Wherein:

[0073] Step S1, collecting operation failure data of each element of the power distribution network in a typhoon weather scenario, and determining a typical failure scenario of the power distribution network according to the operation failure data.

[0074] Wherein, the element of the power distribution network refers to various devices and components in the power distribution network, including but not limited to transformers, switching devices, lines, capacitors, reactors, photovoltaic (PV) and the like. By collecting the operation failure data of these elements in the typhoon weather, the operation state and possible failure conditions of the power distribution network under extreme weather conditions can be comprehensively understood. The operation failure data includes but is not limited to the failure probability of the element, etc., and the typical failure scenario most likely to occur of the power distribution network under the typhoon weather can be determined.

[0075] The typical failure scenario refers to the most representative and most likely to occur failure condition of the power distribution network under the typhoon weather, which is analyzed according to the operation failure data of each element.

[0076] Step S2, taking minimization of load loss, minimization of total scheduling cost and minimization of key load recovery time of the power distribution network as multi-optimization objectives.

[0077] After the typical failure scenario is determined, the target of optimization scheduling needs to be determined. In this embodiment, the minimization of load loss, the minimization of total scheduling cost and the minimization of key load recovery time of the power distribution network are taken as multi-optimization objectives, so as to realize the optimization of scheduling of the power distribution network.

[0078] Wherein, the minimization of load loss refers to reducing the load outage time and outage range as much as possible and improving the power supply reliability under the premise of ensuring the safe and stable operation of the power grid; the minimization of total scheduling cost refers to reducing the cost generated in the scheduling process as much as possible under the premise of meeting the load demand and power grid safety constraints, including EV scheduling cost, energy storage scheduling cost, photovoltaic unit scheduling cost and charging station incentive cost, etc.; the minimization of key load recovery time refers to restoring the power supply of key load as soon as possible and reducing the impact on society and economy when a failure occurs.

[0079] Specifically, the objective function corresponding to the multi-optimization objective is:

[0080]

[0081] In the formula, is a weighted load loss rate, is a total scheduling cost, is a key load recovery time; , , All are weighting coefficients; among them, .

[0082] in,

[0083] In the formula, Let be the active power lost at node n at time t. Let be the active power demand of node n at time t. The load importance weight for node n, The total number of time periods in the scheduling cycle. This represents the total number of nodes in the distribution network.

[0084]

[0085] In the formula, for EV scheduling cost at any given moment; for The cost of energy storage dispatch at any given moment; for The cost of scheduling photovoltaic units at any given time; The incentive cost for charging stations;

[0086] in,

[0087] In the formula, The unit discharge loss cost of the battery in the EV charging station. For nodes A collection of EV charging stations for Time Node The active power output of the EV charging station q;

[0088]

[0089] In the formula, The unit scheduling cost for MESS; for Time Node The active power output by MESS. For unit distance scheduling cost, For scheduling distance; m represents the number of users participating in the scheduling; m is the index of the users participating in the scheduling.

[0090]

[0091] In the formula, The unit power output operation and maintenance cost of photovoltaic units; for Time Node active power at the PV output;

[0092] wherein,

[0093]

[0094] wherein, active power at the node at the dynamic incentive price, at the basic incentive price; is an incentive price adjustment coefficient; wherein, is dynamically adjusted according to the load loss, for dynamically increasing the incentive price according to the load loss rate; is active power at the node at the moment.

[0095]

[0096] wherein, is the unit time cost of the critical node delay recovery; is the critical load node set; is the duration from power outage to power restoration of the node n.

[0097] Step S3, according to the balanced operation state of the distribution network and the EV charging station, determine the constraint condition of the multi-optimization target.

[0098] Wherein, the constraint condition of the multi-optimization target is to consider the balanced operation state of the distribution network and the EV charging station, and to ensure that the operation state of the distribution network after dispatching is safe and reliable. The balance constraint of the EV charging station is to ensure that the charging and discharging behavior of the EV charging station can meet the demand of the power grid during the dispatching process, while not affecting the normal use of the EV. These constraint conditions jointly constitute the boundary conditions of the distribution network dispatching optimization problem, ensuring that the optimization scheme is feasible and effective in actual application.

[0099] Specifically, the constraint conditions include grid operation constraints and EV charging station dispatching constraints; wherein, the grid operation constraints include topology constraints, node power balance constraints, node voltage relaxation constraints, line transmission power limit constraints, node voltage limit constraints, node load loss limit constraints and PV operation limit constraints.

[0100] The topology constraint is that the connection relationship between elements in the power distribution network remains unchanged in the dispatching process, ensuring the stability of the power grid structure. The node power balance constraint is that the sum of the injected power and the outflow power of each node at any time is zero, ensuring the power balance of the power grid. The node voltage relaxation constraint is a certain relaxation of the node voltage to adapt to the voltage fluctuation of the power grid in the dispatching process. The line transmission power limit constraint is that the transmission power of each line cannot exceed its maximum transmission capacity, preventing line overload. The node voltage limit constraint is that the voltage of each node must be within the specified range to ensure stable operation of the power grid. The node load loss limit constraint limits the load loss that may occur in the dispatching process of the node, ensuring the power supply of critical loads. The PV operation limit constraint is that the output of the photovoltaic unit in the dispatching process cannot exceed its maximum output, preventing photovoltaic unit overload.

[0101] The topology constraint (radial operation) is:

[0102]

[0103]

[0104]

[0105]

[0106] In the formula, is the branch state; , are the power virtual flow directions, respectively; is the actual power flow direction same as the default flow direction, is the actual power flow direction opposite to the default flow direction; is the set of all nodes in the island network; is the set of backup island power nodes; is the set of all branches connected to node i; is the set of all branches with node i as a subnode.

[0107] The node power balance constraint is:

[0108]

[0109] In the formula, , are the downstream node set and upstream node set of node , respectively; , are the line on at Active and reactive power flowing through at all times; , They are respectively Timetable Above Active and reactive power flowing through at all times; for Time Node Active power injected into the upstream power grid. for Time Node The reactive power output of the EV charging station; for Time Node The reactive power output of MESS; for Time Node The reactive power output of the PV unit; for Time Node The reactive power demand at the location; for Time Node The reactive power lost at the point.

[0110] The node voltage relaxation constraint is:

[0111]

[0112] In the formula, , They are respectively Time Node and nodes The voltage value; This is the rated voltage value; It is a very large constant; for Timetable The fault status; , The lines are respectively The resistance and reactance on it.

[0113] The line transmission power limit constraints and node voltage limit constraints are as follows:

[0114]

[0115] In the formula, For the line Maximum transmission power; , They are nodes The upper and lower limits of the voltage.

[0116] The node load loss constraint is:

[0117]

[0118] The PV operation constraint is:

[0119]

[0120] wherein, , are the theoretical active power and reactive power maximum values of the PV at the nodes

[0121] The EV charging station scheduling constraint is to consider the EV travel characteristics, describe the EV scheduling behavior before the disaster by using the trip chain theory, obtain the EV space-time distribution state and the current power, and ensure that the charging and discharging behavior of the EV charging station can meet the demand of the power grid in the scheduling process, and will not affect the normal use of the EV.

[0122] The EV charging station scheduling constraint includes the road network-power grid coupling constraint, the EV power limit constraint participating in scheduling, the user discharge response rate constraint under the incentive price, the balance constraint of the user discharge response rate under the incentive price and the output of the EV charging station, the EV charging and discharging power limit constraint, the EV power limit constraint and the MESS scheduling limit constraint.

[0123] The road network-power grid coupling constraint is used to constrain the EV to arrive at the designated location for charging and discharging in time during the scheduling process.

[0124] The EV power limit constraint participating in scheduling is used to ensure that the EV power is not lower than the preset threshold at the end of the scheduling.

[0125] The user discharge response rate constraint under the incentive price is used to constrain the user discharge response rate under different incentive prices according to the sensitivity of the user to the incentive price.

[0126] The balance constraint of the user discharge response rate under the incentive price and the output of the EV charging station is used to constrain the output of the EV charging station to match the discharge demand of the user.

[0127] ​The charging and discharging power limits for EVs ensure that their power output during charging and discharging does not exceed the maximum power that the charging station and the EV itself can withstand, preventing equipment overload and damage. The energy limit limits for EVs ensure that their energy level remains within a certain range during dispatching, neither too high nor too low, to guarantee normal EV operation. The MESS dispatching limits, on the other hand, are constraints imposed on the dispatching of microgrid energy storage systems (MESS), ensuring that the charging and discharging behavior of the MESS during dispatching meets grid demands while guaranteeing the safe operation and energy storage efficiency of the MESS. These constraints collectively constitute the boundary conditions of the EV charging station dispatching optimization problem, ensuring that the optimization scheme is feasible and effective in practical applications.

[0128] Specifically, the road network-power grid coupling constraints are:

[0129]

[0130]

[0131] In the formula, This is the set of edges for the road network and the power grid; This is the set of coupling points between the road network and the power grid. For the set of road network nodes; A set of power grid nodes; For the first road network One node; For the first power grid One node; It indicates the connection relationship between the road network and the power grid.

[0132] The process of constructing the EV power limit constraints participating in the scheduling is as follows:

[0133] Travel chain modeling: A user's travel chain is described by state variables such as origin, destination, path, and time.

[0134]

[0135] In the formula, A set of state variables for a segment of a trip in a travel chain; This is the starting point of this leg of the journey; This is the end point of this leg of the journey; For the driving route; This refers to the departure time; Arrival time; This refers to the travel time. The duration of the stop.

[0136] Consider the first The segment travel time can be calculated as:

[0137]

[0138]

[0139]

[0140] wherein, The segment travel time; The segment travel length; The segment travel average speed; The segment travel arrival time; The segment travel departure time.

[0141] Considering the travel willingness of EV users:

[0142]

[0143] wherein, is the travel willingness index, is the travel willingness coefficient under disaster ( ); is the total number of EVs in the region.

[0144] The travel time is subject to normal distribution, and the real-time state of EVs can be modeled:

[0145]

[0146] wherein, is the real-time state set of each EV at time t; is the travel time of each EV at time t; is the current power of each EV at time t; is the nearest EV charging station to the current location. EVs participating in power supply restoration need to meet the power constraint:

[0147]

[0148]

[0149] wherein, is the rated discharge power of the EV charging station; is the fault repair time, for example, is set to 4h.

[0150] ​​​The construction process of the user's discharge response rate constraint under the incentive price is as follows:

[0151] Based on the theory of consumer psychology, the user's discharge response rate and the incentive price show a segmented linear relationship:

[0152] The upper boundary function is:

[0153]

[0154] In the formula, is the upper limit of the user m's discharge response rate in the ideal scenario; is the incentive price (yuan / kWh); is the minimum incentive price threshold at which the user m starts to respond in the ideal scenario; is the maximum incentive price threshold at which the user m's response rate reaches saturation in the ideal scenario; is the maximum response rate of the user m under the ideal scenario when the incentive price reaches .

[0155] The lower boundary function is:

[0156]

[0157] In the formula, is the upper limit of the user m's discharge response rate in the conservative scenario; is the minimum incentive price threshold at which the user m starts to respond in the conservative scenario; is the maximum incentive price threshold at which the user m's response rate reaches saturation in the conservative scenario; is the maximum response rate of the user m under the conservative scenario when the incentive price reaches .

[0158] The user's discharge response rate constraint under the incentive price is:

[0159]

[0160] In the formula, is the actual discharge response rate of the user m under the incentive price, which is subject to a uniform distribution; is the uniform distribution symbol, indicating that the actual response rate randomly fluctuates between the upper and lower boundaries.

[0161] The balance constraint of the user's discharge response rate under the incentive price and the output of the EV charging station is determined by the relationship between the response rate and the output of the EV charging station, and is obtained as:

[0162] In the formula, is the number of EVs that meet the power requirements at the node . Discharge power of a single EV.

[0163] The charge-discharge power limit constraint of the EV is:

[0164]

[0165] wherein, , are respectively the charge-discharge power of the EV at the moment t; , are respectively the upper limits of the charge-discharge power of the EV; , are respectively the charge-discharge states of the EV at the moment t;

[0166] The state of charge limit constraint of the EV is:

[0167]

[0168] wherein, is the state of charge of the EV at the moment t; , are respectively the upper and lower limits of the state of charge of the EV; is the charge-discharge efficiency of the EV.

[0169] The MESS scheduling limit constraint is:

[0170]

[0171]

[0172] wherein, is the MESS state at the node n, indicates that the node has allocated MESS, indicates that the node has not allocated MESS; , are respectively the upper limits of the active power and reactive power of the MESS output. Step S4: constructing a power distribution network scheduling optimization model according to the multi-optimization objectives and the constraint conditions.

[0173] Step S5: performing optimization and solution on the power distribution network scheduling optimization model according to the typical fault scenarios, to obtain a power distribution network scheduling optimization scheme under the typical fault scenarios.

[0174]

[0175] ​​​​​​​​It should be noted that the embodiment of the present application determines the typical fault scene of the power distribution network by collecting the operation fault data of each element of the power distribution network in the typhoon weather scene, and takes the minimization of the load loss of the power distribution network, the minimization of the total cost of scheduling and the minimization of the recovery time of the key load as the multi-optimization target, considers the load loss rate, economic cost and key load recovery time at the same time, balances the economy-resilience-time multi-dimensional balance, determines the constraint condition of the multi-optimization target according to the balanced operation state of the power distribution network and the EV charging station, so as to ensure the operation reliability of the power distribution network and the EV charging station, constructs the power distribution network scheduling optimization model through the multi-optimization target and the constraint condition, and performs optimization and solution to obtain the power distribution network scheduling optimization scheme, so as to realize the real-time scheduling of the multi-element flexible resource, and realize efficient distributed coordination and real-time scheduling, and improve the reliability of the power distribution network scheduling.

[0176] In some embodiments, the operation fault data includes line fault probability and photovoltaic unit fault probability;

[0177] Collecting operation fault data of each element of the power distribution network in the typhoon weather scene, determining the typical fault scene of the power distribution network according to the operation fault data, including:

[0178] Step S101, according to the historical typhoon wind speed, the typhoon time-varying prediction model is predicted by pre-training to obtain the typhoon predicted wind speed at the current prediction time.

[0179] Wherein, the training process of the typhoon time-varying prediction model is:

[0180] Step S1011, collect typhoon historical sample time series data, and extract space-time features of typhoon historical sample time series data through convolutional neural network.

[0181] Wherein, the space-time features include typhoon wind speed, typhoon moving path, typhoon intensity change and typhoon influence range and other key information.

[0182] Wherein, the space-time features of the typhoon historical sample time series data are extracted based on the multi-scale three-dimensional convolutional neural network (3D Convolutional Neural Network, 3DNN) to form the space-time correlation of atmospheric parameters in the typhoon formation process. The output value calculation process of the (x, y, z) position of the i-th layer j-th feature map:

[0183]

[0184] In the formula, is the activation value of the i-th layer j-th feature map at position (x, y, z); k is the traversal of all input feature maps (channel dimension) of the i-th layer, , wherein is the​ the number of feature maps of the layer; is a nonlinear activation function; p, q, r are the offsets of the three-dimensional convolution kernel in the longitude, latitude, and pressure layer dimensions, respectively, , , wherein is the size of the convolution kernel; is the weight of the jth convolution kernel of the ith layer on the kth input feature map at position (p, q, r); is the value of the kth input feature map of the ith layer at position ; is the value of the kth input feature map of the ith layer at position ;

[0185] Parallel multi-scale convolution: three different sizes of convolution kernels (3x3x3, 5x5x5, 7x7x7) are used in parallel to extract features, capturing local details, mesoscale structures, and global environmental fields, respectively, to obtain:

[0186]

[0187] wherein is the channel dimension concatenation, which concatenates multiple feature maps in the channel dimension to fuse information of different scales; is the multi-scale feature map, which is obtained by concatenating the outputs of 3x3, 5x5, and 7x7 convolutions (64x3=192 channels); is the 3x3x3 convolution kernel parameter, with input channel N and output channel 64; is the 5x5x5 convolution kernel parameter, with input channel N and output channel 64; is the 7x7x7 convolution kernel parameter, with input channel N and output channel 64.

[0188] Spatial attention weight generation:

[0189]

[0190] wherein is the global average pooling, which compresses each channel of the feature map into a scalar; is the spatial attention weight, which is generated by global average pooling and a fully connected layer; , is the fully connected layer parameter for attention weight generation.

[0191] wherein

[0192] wherein is the weighted feature map, i.e., the spatiotemporal feature.

[0193] Step S1012, inputting the spatiotemporal features into a long short-term memory network to process the time sequence relationship in the spatiotemporal features, to obtain a typhoon time-varying prediction model.

[0194] In the formula, the spatiotemporal features extracted based on the 3DCNN are used to predict the future typhoon formation and intensity. The output prediction formula is:

[0195]

[0196] In the formula, is the hidden state of the current time step, containing historical time sequence information; W is a weight matrix, and b is a bias term, which are learned through training; is an output mapping.

[0197] The state update formula of the long short-term memory network (LSTM) is:

[0198]

[0199] In the formula, is the feature after attention enhancement; is the hidden state of the previous time step; is the memory unit of the previous time step, storing long-term dependence information; is the updated hidden state and memory unit, which is passed to the next time step.

[0200] The prediction model obtained by combining the 3DCNN-LSTM is:

[0201]

[0202] In the formula, is the typhoon time-varying feature at the historical moment , and the dimension is , is the latitude and longitude grid resolution, L is the number of pressure layers, and N is the number of atmospheric variables (wind speed, temperature, humidity).

[0203] Step S102, respectively constructing a line fault probability model and a photovoltaic unit fault probability model, and determining the line fault probability and the photovoltaic unit fault probability according to the line fault probability model and the photovoltaic unit fault probability model, in combination with the typhoon predicted wind speed.

[0204] In the formula, the typhoon disaster mainly causes strong force on the conductor and the tower of the transmission line, resulting in line breakage between the towers. The line fault of the distribution network under extreme weather is modeled, the distribution network is grid processed, and is divided into equilateral grids according to the latitude and longitude. It is assumed that the typhoon intensity suffered by each grid is consistent.

[0205] This application's embodiments use typhoon-predicted wind speeds combined with line vulnerability curves to obtain line... In the The failure rate within each grid area is used to obtain the failure probability of the entire line.

[0206] The line fault probability model is as follows:

[0207]

[0208] In the formula, For the first Typhoon wind speeds within each grid area; The maximum wind speed that the power distribution network lines can withstand; This is an empirical coefficient; for Timetable In the The probability of failure within each grid area; for Timetable The total probability of failure.

[0209] The photovoltaic unit failure probability model is as follows:

[0210]

[0211] In the formula, for Time of the first The failure probability of a PV unit; The failure probability of PV under normal conditions; for Time of the first The angle between the PV and the wind direction; for Time of the first Wind speed at the location of the PV unit; and These are the upper and lower limits of wind speed when the PV system fails; The wind direction change sensitivity coefficient, This represents the rate of change of wind direction.

[0212] Step S103: Based on the line fault probability and the photovoltaic unit fault probability, generate multiple fault scenarios by sampling using the Monte Carlo method.

[0213] The Monte Carlo method is a random simulation method based on probability statistics, and the solution of a complex problem is approximately calculated through a large number of random sampling. In the embodiments of the present application, the Monte Carlo method is used to generate a plurality of possible fault scenarios according to the joint distribution of the line fault probability and the photovoltaic unit fault probability, and each scenario contains specific line and photovoltaic unit fault conditions. These fault scenarios are used to simulate the actual operation of the distribution network in typhoon weather, so as to comprehensively evaluate the operation risk of the distribution network.

[0214] Step S104, filtering out the fault scenario corresponding to the maximum entropy value of the line fault probability and the photovoltaic unit fault probability from the plurality of fault scenarios to determine the typical fault scenario of the distribution network.

[0215] Among them, by extracting N possible initial fault times from the plurality of fault scenarios, N possible fault scenarios are constructed to establish a set composed of N system information entropy values, and the probability distribution thereof is fitted, wherein the system information entropy value with the maximum occurrence probability represents the most possible distribution network fault scenario, and therefore a certain extreme fault scenario corresponding to the value is selected as the typical fault scenario. The calculation of the entropy value is as follows:

[0216]

[0217] In the formula, W is the entropy value, is the line set of the distribution network; is the photovoltaic set of the distribution network; and are the fault states of the line and the photovoltaic unit (1 for fault, otherwise 0).

[0218] In some embodiments, according to the typical fault scenario, the distribution network dispatching optimization model is optimized and solved to obtain a distribution network dispatching optimization scheme under the typical fault scenario, including:

[0219] Step S501, randomly generating a plurality of distribution network dispatching candidate schemes satisfying the constraint condition, and initializing a population by using the plurality of distribution network dispatching candidate schemes;

[0220] Step S502, non-dominant sorting of individuals in the initialized population, and calculation of crowding distance;

[0221] Step S503, determining the fitness value of each individual according to the objective function corresponding to the multi-optimization objective;

[0222] Step S504, selecting individuals with a fitness value greater than a preset fitness threshold and a crowding distance greater than a preset crowding threshold to form a new population according to the fitness value and the crowding distance;

[0223] The calculation of the crowding distance is performed by comparing the density of other individuals around the individual. The smaller the density, the fewer solutions around the individual, and the greater the crowding distance of the individual, which is more likely to be retained in the optimization process. The individual with a better fitness value is selected by non-dominated sorting, and the crowding distance is considered to avoid premature convergence and maintain the diversity of the population. In each iteration, new solutions are generated by genetic algorithm operations such as crossover and mutation, and the global optimal solution is constantly approached.

[0224] Step S505, performing crossover and mutation operations on the new population to generate new offspring individuals;

[0225] Step S506, merging the new offspring individuals with the parent individuals to form a new population, and repeating the non-dominated sorting of the individuals in the initialized population and the calculation of the crowding distance until the iteration termination condition is met.

[0226] Step S507, selecting the optimal individual from the final population as the optimal solution of the distribution network scheduling optimization model to obtain the distribution network scheduling optimization scheme under the typical fault scenario.

[0227] The distribution network scheduling optimization scheme includes the active power demand of each node, the active power output of the EV charging station at the node, the active power output of the MESS at the node, the active power output of the PV at the node, the dynamic incentive price, and the set of key load nodes.

[0228] It can be understood that the embodiments of the present application use the third generation non-dominated sorting genetic algorithm (NSGA-III) to optimize and solve the distribution network scheduling optimization model. After obtaining the distribution network scheduling optimization scheme, the improved alternating direction multiplier (ADMM) algorithm is used for distributed solving to coordinate the real-time power distribution of EV, energy storage, mobile energy storage, and photovoltaic resources, and to meet the total power balance and the operation constraints of each device. ADMM solves local subproblems and coordinates global variables to ensure the consistency and convergence of the decisions of each subsystem. Specifically, the global power distribution problem is divided into optimization problems of EV, MESS, and PV, dual variables are introduced to coordinate the power constraints between subsystems, and through local optimization of EV, MESS, and PV, the optimal solution is converged through global coordination.

[0229] Based on the same inventive concept, the embodiments of the present application also provide a multi-resource cooperative distribution network scheduling system for implementing the multi-resource cooperative distribution network scheduling method described above.

[0230] The implementation scheme for solving the problem provided by the system is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more power distribution network scheduling system embodiments of the multi-element resource coordination provided below can refer to the limitations of the multi-element resource coordination power distribution network scheduling method described above, which will not be repeated here.

[0231] As Figure 3 shown, the embodiment of the present application provides a multi-element resource coordinated power distribution network scheduling system, comprising:

[0232] A fault scenario determination module 100 is configured to collect operation failure data of each element of the power distribution network under a typhoon weather scenario, and determine a typical fault scenario of the power distribution network according to the operation failure data;

[0233] An optimization target determination module 200 is configured to take minimization of load loss, minimization of total scheduling cost, and minimization of key load recovery time of the power distribution network as multi-optimization targets;

[0234] A constraint determination module 300 is configured to determine constraint conditions of the multi-optimization targets according to balanced operation states of the power distribution network and the EV charging station;

[0235] A model construction module 400 is configured to construct a power distribution network scheduling optimization model according to the multi-optimization targets and the constraint conditions;

[0236] A scheduling optimization module 500 is configured to perform optimization and solution on the power distribution network scheduling optimization model according to the typical fault scenario, and obtain a power distribution network scheduling optimization scheme under the typical fault scenario.

[0237] In some embodiments, the operation failure data includes line failure probability and photovoltaic unit failure probability;

[0238] The fault scenario determination module 100 is configured to:

[0239] According to historical typhoon wind speed, a pre-trained typhoon time-varying prediction model is used for prediction to obtain a predicted typhoon wind speed at a current prediction time;

[0240] A line failure probability model and a photovoltaic unit failure probability model are respectively constructed, and the line failure probability and the photovoltaic unit failure probability are determined according to the line failure probability model and the photovoltaic unit failure probability model in combination with the predicted typhoon wind speed;

[0241] According to the line failure probability and the photovoltaic unit failure probability, a plurality of fault scenarios are generated by Monte Carlo sampling;

[0242] From the plurality of fault scenarios, a fault scenario corresponding to an entropy value with the maximum line failure probability and photovoltaic unit failure probability is screened out, and a typical fault scenario of the power distribution network is determined.

[0243] In some embodiments, the system further includes: a prediction model building module, used for:

[0244] Collect historical time-series data of typhoons and extract spatiotemporal features from the historical time-series data of typhoons through a convolutional neural network;

[0245] The spatiotemporal features are input into a long short-term memory network to process the time series relationships in the spatiotemporal features, thus obtaining a typhoon time-varying prediction model.

[0246] In some embodiments, the objective function corresponding to multiple optimization objectives is:

[0247]

[0248] In the formula, For weighted load loss rate, For the total scheduling cost, For critical load recovery time; , , All are weighting coefficients;

[0249] in,

[0250] In the formula, Let be the active power lost at node n at time t. Let be the active power demand of node n at time t. The load importance weight for node n, The total number of time periods in the scheduling cycle. This represents the total number of nodes in the distribution network.

[0251]

[0252] In the formula, for EV scheduling cost at any given moment; for The cost of energy storage dispatch at any given moment; for The cost of scheduling photovoltaic units at any given time; The incentive cost for charging stations;

[0253] in,

[0254] In the formula, The unit discharge loss cost of the battery in an EV charging station. For nodes A collection of EV charging stations for Time Node The active power output of the EV charging station q;

[0255]

[0256] wherein, is the MESS unit dispatching cost; is the active power output at time node , is the unit distance dispatching cost, is the dispatching distance; is the number of users participating in dispatching; m is the index of users participating in dispatching;

[0257]

[0258] wherein, is the unit output operation and maintenance cost of the photovoltaic unit; is the active power output at time node ,

[0259] wherein,

[0260]

[0261] wherein, is the dynamic incentive price of node , is the basic incentive price; is the incentive price adjustment coefficient; is the active power output at time node ,

[0262]

[0263] wherein, is the unit time cost of delay recovery of the key node; is the set of key load nodes; is the time length from power outage to power restoration of node n.

[0264] In some embodiments, the constraint conditions include power grid operation constraints and EV charging station dispatching constraints; wherein the power grid operation constraints include topology constraints, node power balance constraints, node voltage relaxation constraints, line transmission power limit constraints, node voltage limit constraints, node load loss limit constraints, and PV operation limit constraints;

[0265] The EV charging station scheduling constraints include a road network-power grid coupling constraint, an EV power limit constraint, a user discharge response rate constraint under an incentive price, a balance constraint between the user discharge response rate under the incentive price and the output of the EV charging station, an EV charging and discharging power limit constraint, an EV power limit constraint, and a MESS scheduling limit constraint.

[0266] The road network-power grid coupling constraint is used to constrain the EV to arrive at a designated location in time for charging and discharging during the scheduling process.

[0267] The EV power limit constraint is used to ensure that the EV has a power that is not lower than a preset threshold at the end of the scheduling.

[0268] The user discharge response rate constraint under the incentive price is used to determine the user discharge response rate under different incentive prices according to the sensitivity of the user to the incentive price.

[0269] The balance constraint between the user discharge response rate under the incentive price and the output of the EV charging station is used to ensure that the output of the EV charging station matches the user discharge demand.

[0270] In some embodiments, the scheduling optimization module 500 is configured to:

[0271] randomly generate a plurality of power distribution network scheduling candidate schemes that satisfy the constraint conditions, and initialize a population using the plurality of power distribution network scheduling candidate schemes;

[0272] non-dominantly sort the individuals in the initialized population, and calculate the crowding distance;

[0273] determine the fitness value of each individual according to the objective function corresponding to the multi-optimization objective;

[0274] select individuals with a fitness value greater than a preset fitness threshold and a crowding distance greater than a preset crowding distance threshold to form a new population according to the fitness value and the crowding distance;

[0275] perform a crossover and mutation operation on the new population to generate new offspring individuals;

[0276] merge the new offspring individuals and the parent individuals to form a new population, and repeatedly perform non-dominant sorting on the individuals in the initialized population and calculate the crowding distance until an iteration termination condition is met;

[0277] select an optimal individual from the final population as an optimal solution of the power distribution network scheduling optimization model to obtain a power distribution network scheduling optimization scheme under a typical fault scenario.

[0278] As Figure 4As shown, the embodiment of the present application provides an electronic device, the electronic device 10 includes a memory 20 and a processor 30, the memory 20 stores a computer program, the computer program is executed by the processor 30, so that the processor 30 executes the steps of the power distribution network scheduling method of the multi-element resource coordination in the above embodiment.

[0279] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed to realize the steps of the power distribution network scheduling method of the multi-element resource coordination in the above embodiment.

[0280] The embodiment of the present application provides a computer program product, the computer program product includes a computer program stored on a non-transitory computer readable storage medium, the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the steps of the power distribution network scheduling method of the multi-element resource coordination described in the above embodiment.

[0281] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-mentioned system, electronic device, computer storage medium and computer program product can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0282] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to include only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0283] It should be understood that, although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other sequences. Moreover, as described above, at least some of the steps in the flowcharts involved in the above embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of the steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least some of the other steps or steps or stages in other steps.

[0284] In several embodiments provided by the present application, it should be understood that the disclosed system, electronic device, computer storage medium, computer program product and method can be implemented in other ways. For example, the above-described device embodiments are only schematic. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or in other forms.

[0285] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0286] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0287] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium, includes a plurality of instructions for executing all or part of the steps of the method described in various embodiments of the present application by a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (English full name: Read-Only Memory, English abbreviation: ROM), a random access memory (English full name: Random Access Memory, English abbreviation: RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0288] The above embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A power distribution network scheduling method based on multi-element resource coordination, characterized in that, The method comprises the following steps: collecting operation failure data of each element of the power distribution network in a typhoon weather scenario, and determining a typical failure scenario of the power distribution network according to the operation failure data; minimizing load loss, minimizing total scheduling cost and minimizing key load recovery time of the power distribution network as multi-optimization objectives; a target function corresponding to the multi-optimization objectives is: ； In the formula, is the weighted load loss rate, is the total cost of scheduling, is the key load recovery time; , , are weight coefficients; ； In the formula, is the EV scheduling cost at the moment; is the energy storage scheduling cost at the moment; is the photovoltaic scheduling cost at the moment; is the charging station incentive cost of is the total number of scheduling periods. wherein ; wherein, is the battery unit discharging loss cost of EV charging station q, is the set of EV charging stations of node is the set of EV charging stations of node is the active power output of EV charging station q at time node is the active power output of EV charging station q at time node is the active power output of EV charging station q at time node is the total number of distribution network nodes; ； wherein, is the MESS unit dispatch cost; is the is the time node is the active power output at the MESS, is the unit distance dispatch cost, is the dispatch distance; is the number of users participating in the dispatch; m is the participating user index; ； In the formula, is the unit operation and maintenance cost of the photovoltaic unit; is time node active power at the PV output; wherein ; ； In the formula, is the dynamic incentive electricity price of the node , is the basic incentive electricity price; is the incentive electricity price adjustment coefficient; is the active power output of all EV charging stations at the node at the moment t; is the active power loss of the node n at the moment t, is the active power demand of the node n at the moment t; determining constraint conditions of the multi-optimization objectives according to the balanced operation state of the power distribution network and the EV charging station; constructing a power distribution network scheduling optimization model according to the multi-optimization objectives and the constraint conditions; obtaining a power distribution network scheduling optimization scheme in the typical failure scenario by optimizing and solving the power distribution network scheduling optimization model according to the typical failure scenario.

2. The power distribution network scheduling method of claim 1, wherein, The operation failure data includes line failure probability and photovoltaic unit failure probability; The method for determining the typical failure scenario of the power distribution network according to the operation failure data of each element of the power distribution network in a typhoon weather scenario comprises the following steps: predicting a typhoon predicted wind speed at a current prediction time according to a historical typhoon wind speed through a pre-trained typhoon time-varying prediction model; constructing a line failure probability model and a photovoltaic unit failure probability model respectively, and determining line failure probability and photovoltaic unit failure probability according to the line failure probability model and the photovoltaic unit failure probability model in combination with the typhoon predicted wind speed; generating a plurality of failure scenarios by sampling through a Monte Carlo method according to the line failure probability and the photovoltaic unit failure probability; determining the typical failure scenario of the power distribution network by screening a failure scenario corresponding to an entropy value with the maximum line failure probability and photovoltaic unit failure probability from the plurality of failure scenarios.

3. The method of claim 1, wherein, The method further comprises the following steps: collecting typhoon historical sample time series data, and extracting space-time features of the typhoon historical sample time series data through a convolutional neural network; inputting the space-time features into a long short-term memory network to process time sequence relationships in the space-time features, and obtaining a typhoon time-varying prediction model.

4. The power distribution network scheduling method of multi-element resource coordination according to claim 1, wherein ； In the formula, is the load importance weight of node n; ； wherein is the unit time cost for critical node delay recovery; is the set of critical load nodes; is the duration of time for node n from power outage to power restoration.

5. The power grid dispatching method of claim 1-4, wherein, the constraint conditions include power grid operation constraints and EV charging station scheduling constraints; wherein the power grid operation constraints include topology constraints, node power balance constraints, node voltage relaxation constraints, line transmission power limit constraints, node voltage limit constraints, node load loss limit constraints and PV operation limit constraints; the EV charging station scheduling constraints include road network-power grid coupling constraints, EV power limit constraints participating in scheduling, user discharge response rate constraints under an incentive electricity price, balance constraints between the user discharge response rate under the incentive electricity price and the EV charging station output, EV charging and discharging power limit constraints, EV power limit constraints and MESS scheduling limit constraints; the road network-power grid coupling constraints are used to constrain the EV to reach the designated location for charging and discharging in time during the scheduling process; the EV power limit constraints participating in scheduling are used to ensure that the EV power is not lower than a preset threshold at the end of the scheduling; The discharge response rate of the user under the incentive price constraint is used to constrain the sensitivity of the user to the incentive price, and determine the discharge response rate of the user under different incentive prices; The balance constraint of the discharge response rate of the user under the incentive price and the output of the EV charging station is used to ensure that the output of the EV charging station matches the discharge demand of the user.

6. The power distribution network scheduling method of claim 5, wherein, The optimization solution of the power distribution network scheduling optimization model under the typical fault scenario is obtained by optimizing the power distribution network scheduling optimization model according to the typical fault scenario, including: A plurality of power distribution network scheduling candidate schemes satisfying the constraint condition are randomly generated, and a population is initialized by using the plurality of power distribution network scheduling candidate schemes; Individuals in the initialized population are non-dominantly sorted, and a crowding distance is calculated; The fitness value of each individual is determined according to the objective function corresponding to the multiple optimization objectives; According to the fitness value and the crowding distance, individuals with a fitness value greater than a preset fitness threshold and a crowding distance greater than a preset crowding distance threshold are selected to form a new population; New offspring individuals are generated by performing crossover and mutation operations on the new population; The new offspring individuals and the parent individuals are combined to form a new population, and the non-dominant sorting of the individuals in the initialized population and the calculation of the crowding distance are repeated until the iteration termination condition is met; The optimal individual is selected from the final population as the optimal solution of the power distribution network scheduling optimization model, and the power distribution network scheduling optimization scheme under the typical fault scenario is obtained.

7. A power distribution network dispatching system with multi-element resource coordination, characterized in that, It includes: A fault scenario determination module is configured to collect operation fault data of each element of a power distribution network in a typhoon weather scenario, and determine a typical fault scenario of the power distribution network according to the operation fault data; An optimization objective determination module is configured to take the minimization of load loss, the minimization of total scheduling cost, and the minimization of key load recovery time of the power distribution network as multiple optimization objectives; The objective function corresponding to the multiple optimization objectives is: ； In the formula, is the weighted load loss rate, is the total cost of scheduling, is the key load recovery time; , , are weight coefficients; ； In the formula, is the EV dispatching cost at the moment; is the energy storage dispatching cost at the moment; is the photovoltaic unit dispatching cost at the moment; is the charging station incentive cost of wherein ; wherein, is the battery unit discharging loss cost of EV charging station q, is the set of EV charging stations of node is the set of EV charging stations of node is the active power output of EV charging station q at time node is the active power output of EV charging station q at time node is the active power output of EV charging station q at time node is the total number of distribution network nodes; ； wherein, is the MESS unit dispatch cost; is time node active power output at MESS, is the unit distance dispatch cost, is the dispatch distance; is the number of users participating in dispatch; m is the index of users participating in dispatch; ； In the formula, is the unit operation and maintenance cost of the photovoltaic unit; is time node active power at the PV output; wherein ; ； In the formula, For nodes Dynamic incentive electricity prices, Based on incentive electricity prices; To incentivize the electricity price adjustment coefficient; for Time Node The active power output of all EV charging stations; Let be the active power lost at node n at time t. Let be the active power demand of node n at time t; A constraint determination module is configured to determine constraint conditions of the multiple optimization objectives according to a balanced operation state of the power distribution network and an EV charging station; A model construction module is configured to construct a power distribution network scheduling optimization model according to the multiple optimization objectives and the constraint conditions; A scheduling optimization module is configured to optimize and solve the power distribution network scheduling optimization model according to the typical fault scenario, and obtain a power distribution network scheduling optimization scheme under the typical fault scenario.

8. An electronic device, comprising: The electronic device includes a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the multi-resource coordinated power distribution network scheduling method of any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed to implement the steps of the multi-resource coordinated power distribution network scheduling method of any one of claims 1-6.

10. A computer program product, characterised in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the steps of the multi-resource coordinated power distribution network scheduling method of any one of claims 1-6.

Images