A method and device for quickly restoring power supply of a distribution network

Abstract

The present invention discloses a method and device for quickly restoring power supply of a distribution network, and the method includes: obtaining historical data of a photovoltaic power station, various meteorological data, information on factors affecting photovoltaic output, and information on factors affecting load changes; establishing a photovoltaic output prediction model and a load prediction model according to the historical data of the photovoltaic power station, various meteorological data, information on factors affecting photovoltaic output, and information on factors affecting load changes; formulating a power supply restoration strategy based on the photovoltaic output prediction model and the load prediction model in combination with the time dimension; traversing fault-prone locations based on the photovoltaic output prediction model, the load prediction model, and the power supply restoration strategy, establishing a power supply restoration plan library; when a fault occurs in the distribution network, calling a power supply restoration plan based on the fault information to quickly restore power. The present invention shortens the power outage time and provides a guarantee for the stable operation of the power grid by providing a power supply restoration method based on the time-varying photovoltaic output and load.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply restoration, and in particular to a method and device for quickly restoring power supply of a distribution network. Background Art

[0002] The distribution network is the link in the power system that is directly connected to users and distributes electric energy to users. The reliability of its operation is closely related to the rise and fall of the national economy and the well-being of the people. When a fault occurs, quickly and to the greatest extent possible, restoring power supply, shortening or even eliminating the perception of power outage time on the user side, and improving the reliability of the distribution network have become one of the important tasks of power grid construction and maintenance. With the construction and development of the distribution network, the penetration rate of distributed power sources represented by photovoltaics in the distribution network continues to increase, and it becomes possible for them to provide short-term power supply support during power supply restoration. However, the output of distributed power sources is uncertain, which is very likely to cause secondary load shedding of the restored load, making it difficult for traditional power supply restoration strategies to meet the requirements.

[0003] Although the existing technology takes into account the randomness of photovoltaic output, it is only described with a specific model or from a probabilistic statistical perspective, and does not reflect the randomness of photovoltaic output in the time dimension - the impact of time-varying nature on power supply restoration issues; on the other hand, since the restoration plan of the existing technology is calculated and formulated after the fault, when the complexity of the network increases, the power outage time in the power-off area will be extended due to the extension of calculation time, resulting in a decrease in the reliability of the distribution network at a macro level.

[0004] Therefore, in order to ensure the stable operation of the power grid and solve the technical problem that the existing traditional power supply restoration methods are difficult to quickly restore power supply, it is urgent to construct a fast power supply restoration method. Summary of the invention

[0005] The present invention provides a method and device for quickly restoring power supply of a distribution network, which solves the technical problem that the existing traditional power supply restoration method is difficult to quickly restore power supply.

[0006] In a first aspect, the present invention provides a method for quickly restoring power supply, comprising:

[0007] Obtain historical data of photovoltaic power stations in the target distribution network, various meteorological data, information on factors affecting photovoltaic output and factors affecting load changes;

[0008] Establishing a photovoltaic output prediction model and a load prediction model according to the photovoltaic power station historical data, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information;

[0009] Based on the photovoltaic output prediction model and the load prediction model, a power supply restoration strategy is formulated in combination with the time dimension;

[0010] Based on the photovoltaic output prediction model, the load prediction model and the power supply restoration strategy, traverse the fault-prone locations in the target distribution network to establish a power supply restoration solution library;

[0011] When a failure occurs in the distribution network, based on the failure information, a power supply restoration plan in the power supply restoration plan is called to quickly restore power.

[0012] Optionally, before acquiring the photovoltaic power station historical data, various meteorological data, photovoltaic output influencing factor information and load change influencing factor information, the method further includes:

[0013] Initialize network parameters of the target distribution network.

[0014] Optionally, a photovoltaic output prediction model and a load prediction model are established according to the photovoltaic power station historical data, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information, including:

[0015] According to the photovoltaic power station historical data and the various meteorological data, the photovoltaic output influencing factor information is converted into a weather type index;

[0016] Based on the weather type index, establishing the photovoltaic output prediction model;

[0017] The load prediction model is established according to the load change influencing factor information.

[0018] Optionally, based on the power supply restoration strategy, traversing the fault-prone locations in the target distribution network to establish a power supply restoration solution library includes:

[0019] Obtaining a load recovery amount of a maximized power outage zone in the target distribution network;

[0020] Using a particle swarm algorithm, combined with the photovoltaic output prediction model, the load prediction model, the power supply restoration strategy and preset network operation constraints, a power supply restoration plan for a fault-prone location in the target distribution network is obtained;

[0021] The power supply restoration schemes are summarized to obtain the power supply restoration scheme library.

[0022] In a second aspect, the present invention provides a fast power supply recovery device, comprising:

[0023] An acquisition module is used to obtain historical data of photovoltaic power stations in the target distribution network, various meteorological data, information on factors affecting photovoltaic output, and information on factors affecting load changes;

[0024] A modeling module, used to establish a photovoltaic output prediction model and a load prediction model according to the photovoltaic power station historical data, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information;

[0025] A strategy module, used to formulate a power supply restoration strategy based on the photovoltaic output prediction model and the load prediction model in combination with a time dimension;

[0026] Establishing a module for traversing the fault-prone locations in the target distribution network and establishing a power supply restoration solution library based on the photovoltaic output prediction model, the load prediction model and the power supply restoration strategy;

[0027] The recovery module is used to call the power supply recovery plan in the power supply recovery plan to quickly restore power supply based on the fault information when a fault occurs in the distribution network.

[0028] Optionally, the device further comprises:

[0029] The initialization module is used to initialize the network parameters of the target distribution network.

[0030] Optionally, the modeling module includes:

[0031] A conversion submodule, used for converting the photovoltaic output influencing factor information into a weather type index according to the photovoltaic power station historical data and the various meteorological data;

[0032] A photovoltaic submodule, used for establishing the photovoltaic output prediction model based on the weather type index;

[0033] The load submodule is used to establish the load prediction model according to the load change influencing factor information.

[0034] Optionally, the establishing module includes:

[0035] An acquisition submodule, used for acquiring the load recovery amount of the maximized power failure zone in the target distribution network;

[0036] A calculation submodule, for calculating by using a particle swarm algorithm, in combination with the photovoltaic output prediction model, the load prediction model, the power supply restoration strategy and preset network operation constraints, to obtain a power supply restoration plan for a fault-prone location in the target distribution network;

[0037] The summarizing submodule is used to summarize the power supply restoration schemes to obtain the power supply restoration scheme library.

[0038] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect are performed.

[0039] In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in the method provided in the first aspect are performed.

[0040] It can be seen from the above technical scheme that the present invention has the following advantages: the present invention provides a method for restoring power supply quickly, by acquiring historical data of photovoltaic power stations, various meteorological data, photovoltaic output influencing factor information and load change influencing factor information in the target distribution network, according to the historical data of photovoltaic power stations, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information, a photovoltaic output prediction model and a load prediction model are established, based on the photovoltaic output prediction model and the load prediction model, combined with the time dimension, a power supply restoration strategy is formulated, based on the photovoltaic output prediction model, the load prediction model and the power supply restoration strategy, the fault-prone locations in the target distribution network are traversed, and a power supply restoration plan library is established, when a fault occurs in the distribution network, based on the fault information, the power supply restoration plan in the power supply restoration plan is called to quickly restore power, by providing a power supply restoration method based on photovoltaic output and load time-varying, the technical problem that the existing traditional power supply restoration method is difficult to quickly restore power supply is solved, the power outage time is shortened, and the stable operation of the power grid is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0042] Figure 1 A flowchart of a first embodiment of a method for rapidly restoring power supply according to the present invention;

[0043] Figure 2 This is a flowchart of a second embodiment of a method for rapidly restoring power supply according to the present invention;

[0044] Figure 3 It is a flowchart of the steps of a calculation method for solving a power supply restoration scheme based on a particle swarm algorithm in a rapid power supply restoration method of the present invention;

[0045] Figure 4 It is a structural block diagram of an embodiment of a fast power supply recovery device of the present invention. DETAILED DESCRIPTION

[0046] The embodiment of the present invention provides a method and device for quickly restoring power supply of a distribution network, which are used to solve the technical problem that the existing traditional power supply restoration method is difficult to quickly restore power supply.

[0047] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] For example, see Figure 1 , Figure 1 This is a flowchart of a first embodiment of a method for rapidly restoring power supply according to the present invention, comprising:

[0049] Step S101, obtaining historical data of photovoltaic power stations in the target distribution network, various meteorological data, information on factors affecting photovoltaic output, and information on factors affecting load changes;

[0050] Step S102, establishing a photovoltaic output prediction model and a load prediction model according to the photovoltaic power station historical data, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information;

[0051] Step S103, based on the photovoltaic output prediction model and the load prediction model, a power supply restoration strategy is formulated in combination with the time dimension;

[0052] Step S104, based on the photovoltaic output prediction model, the load prediction model and the power supply restoration strategy, traverse the fault-prone locations in the target distribution network and establish a power supply restoration solution library;

[0053] Step S105, when a failure occurs in the distribution network, based on the failure information, a power supply restoration plan in the power supply restoration plan is called to quickly restore power supply.

[0054] A rapid power supply restoration method provided in an embodiment of the present invention obtains historical data of photovoltaic power stations, various meteorological data, photovoltaic output influencing factor information and load change influencing factor information in a target distribution network, establishes a photovoltaic output prediction model and a load prediction model according to the historical data of the photovoltaic power station, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information, formulates a power supply restoration strategy based on the photovoltaic output prediction model and the load prediction model in combination with the time dimension, traverses fault-prone locations in the target distribution network based on the photovoltaic output prediction model, the load prediction model and the power supply restoration strategy, establishes a power supply restoration plan library, and when a fault occurs in the distribution network, calls a power supply restoration plan in the power supply restoration plan based on the fault information to quickly restore power use, and provides a power supply restoration method based on the time-varying photovoltaic output and load, thereby solving the technical problem that the existing traditional power supply restoration method is difficult to quickly restore power supply, shortens the power outage time, and provides a guarantee for the stable operation of the power grid.

[0055] For example 2, please refer to Figure 2 , Figure 2 A flowchart of a rapid power supply recovery method of the present invention includes:

[0056] Step S201, obtaining historical data of photovoltaic power stations in the target distribution network, various meteorological data, information on factors affecting photovoltaic output, and information on factors affecting load changes;

[0057] In an optional embodiment, before acquiring the photovoltaic power station historical data, various meteorological data, photovoltaic output influencing factor information and load change influencing factor information, the following is also included:

[0058] Initialize network parameters of the target distribution network.

[0059] In an embodiment of the present invention, the network parameters of the target distribution network are first initialized, including the branch number of the line, the head node and the terminal node number, the line impedance, the transformer ratio and other data, and then the historical data of the photovoltaic power station, various meteorological data, photovoltaic output influencing factors information and load change influencing factors information are obtained.

[0060] Step S202, converting the photovoltaic output influencing factor information into a weather type index according to the photovoltaic power station historical data and the various meteorological data;

[0061] In the embodiment of the present invention, the photovoltaic output influencing factor information is converted into a weather type index based on the photovoltaic power station historical data and the various types of meteorological data.

[0062] In the specific implementation, based on the weather forecast data, the weather type is further classified using the Euclidean distance expression. Euclidean distance is a distance definition that represents the true distance between two points in a multidimensional space. The Euclidean distance is used to judge the similarity difference between different samples and classify the weather type:

[0063]

[0064] Among them, x i is the average value of photovoltaic output at different times in different weather types; i The photovoltaic output at each time of a day when the weather type needs to be judged.

[0065] By calculating the Euclidean distance between the photovoltaic output data of a certain day and the average photovoltaic output of the weather type, and by comparing the Euclidean distances of the two weather type data, it can be determined which weather type is more appropriate for two weather types with similar power generation, and the weather types can be further classified. For example, the Euclidean distances of the average power generation of a photovoltaic power station at each moment when the weather forecast is cloudy (the actual cloud cover may be less) and the average power generation of sunny weather type and cloudy weather type are d1 and d2 respectively. If d1<d2, it means that the weather type is closer to sunny weather and should be classified as sunny weather type; conversely, if d1>d2, it means that the weather type is closer to cloudy weather and should be classified as cloudy weather type.

[0066] After classification by Euclidean distance, the ratio relationship between photovoltaic output data under different weather types is mapped into a weather type index.

[0067] Step S203, establishing a photovoltaic output prediction model based on the weather type index;

[0068] In an embodiment of the present invention, a photovoltaic output prediction model is established with the weather type index as input.

[0069] In the specific implementation, the weather type index is used as input to establish a prediction model based on the BP neural network. Based on the historical data of the photovoltaic power station and various meteorological data, the processed data is used to train the BP neural network, and the trained neural network model is used to predict the short-term output of the photovoltaic power station.

[0070] Step S204, establishing a load prediction model according to the load change influencing factor information;

[0071] In the embodiment of the present invention, the load prediction model is established according to the load change influencing factor information.

[0072] In the specific implementation, the load forecast of the power system is mainly ultra-short-term load forecasting with a prediction step of fifteen minutes. The ultra-short-term load forecasting can provide a fast basic data reference for the online safety and stability analysis and online scheduling decision-making of the power supply department, and therefore can also be used for the power supply restoration plan decision in this invention.

[0073] The main factors affecting load changes include meteorological, political and economic aspects. Therefore, the selection of ultra-short-term load forecasting models should mainly consider the following points: 1) selection of historical data (similar days); 2) weather forecast; 3) selection of forecasting models; 4) the impact of social events (political, economic, etc.).

[0074] The ultra-short-term load forecast is performed on the load nodes in the distribution network to obtain the daily load curve, which is then integrated to obtain the power demand of each load node in a certain period of time, and the average load power in the period is obtained:

[0075]

[0076]

[0077] Among them, f i (x) is the load curve of load node i, L i (j) is the power consumption of load node i from time j to time j+T0; is the average load power of load node i from time j to time j+T0.

[0078] Step S205, based on the photovoltaic output prediction model and the load prediction model, a power supply restoration strategy is formulated in combination with the time dimension;

[0079] In the embodiment of the present invention, a power supply restoration strategy is obtained based on the photovoltaic output prediction model and the load prediction model and combined with the time dimension.

[0080] In the specific implementation, a rolling correction power supply restoration strategy considering the time dimension is formulated based on the photovoltaic output forecast and load forecast.

[0081] The short-term power supply restoration strategy based on PV output and load forecast divides the daily strategic planning time into several time periods. For example, at the actual time t-ΔT, the processed time periods from T1 to T n The photovoltaic output forecast value is the strategic basis, and the short-term power supply restoration plan for each period is formulated in advance; at the actual time t, the updated T2 to T n Based on the planned photovoltaic output value, the restoration plan for the corresponding period is updated and revised, and T n+1 The recovery plan for the time period is rolled out in this way.

[0082] Step S206, obtaining the load recovery amount of the maximized power failure zone in the target distribution network;

[0083] In the embodiment of the present invention, after a fault occurs in the distribution network, the primary consideration is to restore the power supply to the loads in the power failure area to the greatest extent possible before the fault is eliminated.

[0084] In the specific implementation, the objective function of power supply recovery of the distribution network is determined. When a fault occurs in the distribution network, the primary consideration is to restore the load power supply in the power-off area to the greatest extent before the fault is eliminated. Therefore, the objective function considered in the present invention is to maximize the load recovery amount in the power-off area, and its expression is shown in the following formula.

[0085]

[0086] Among them, out is the set of power-off nodes; P i is the actual active load of node i during the fault recovery period. In practice, the priority of charge loss can also be considered, and the node load in the above can be changed to ω i P i The form of i It is the weight coefficient that characterizes the priority level of power-off load.

[0087] Step S207, using a particle swarm algorithm, in combination with the photovoltaic output prediction model, the load prediction model, the power supply restoration strategy and preset network operation constraints, to calculate and obtain a power supply restoration plan for the fault-prone location in the target distribution network;

[0088] In an embodiment of the present invention, preset network operation constraints are determined, and based on the photovoltaic output prediction model, the load prediction model, the power supply restoration strategy and the preset network operation constraints, a particle swarm algorithm is used to perform calculations to obtain a power supply restoration plan for fault-prone locations in the target distribution network.

[0089] In the specific implementation, a particle swarm algorithm is used to solve the problem. For any period of time, based on the photovoltaic output forecast value and the load forecast value, with the goal of maximizing the load recovery amount in the power-off zone and the distribution network operation constraints as constraints, the fault-prone locations in the target distribution network are calculated, and the power supply restoration plan for the fault-prone locations in the target distribution network is solved.

[0090] Specifically, the network operation constraints include power flow constraints, node voltage constraints, line capacity constraints, and radiation topology constraints:

[0091] The power flow constraint conditions are specifically:

[0092]

[0093] Among them, P ij and Q ij They represent the active power and reactive power flowing through branch ij respectively; P i DG and are the active power and reactive power injected by the distributed generation on node i respectively; P i LOAD and are the active power and reactive power of the load on node i respectively.

[0094] The node voltage constraint conditions are specifically:

[0095]

[0096] Among them, out is the set of nodes without power after fault isolation; V i is the voltage amplitude of node i; U i and are the lower and upper limits of the square of the operating voltage amplitude at node i respectively.

[0097] The line capacity constraints are:

[0098]

[0099] Among them, z ij is a binary nominal variable describing the switching state of branch ij, where 0 indicates branch disconnection and 1 indicates branch closing; P ij and Q ij They represent the active power and reactive power flowing through branch ij, respectively, and the direction is from node i to node j; is the upper limit of the apparent power of branch ij.

[0100] The radiation topology constraint condition is specifically:

[0101]

[0102] Among them, n b and n s They respectively represent the total number of nodes and the total number of root nodes in the distribution system. In order to protect the setting and reduce the short-circuit current, the distribution network is generally required to operate in a radial manner, that is, there is no ring topology in the network.

[0103] Step S208, summarizing the power supply restoration schemes to obtain a power supply restoration scheme library;

[0104] Step S209: When a failure occurs in the distribution network, based on the failure information, a power supply restoration plan in the power supply restoration plan is called to quickly restore power.

[0105] A rapid power supply restoration method provided in an embodiment of the present invention obtains historical data of photovoltaic power stations, various meteorological data, photovoltaic output influencing factor information and load change influencing factor information in a target distribution network, establishes a photovoltaic output prediction model and a load prediction model according to the historical data of the photovoltaic power station, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information, formulates a power supply restoration strategy based on the photovoltaic output prediction model and the load prediction model in combination with the time dimension, traverses fault-prone locations in the target distribution network based on the photovoltaic output prediction model, the load prediction model and the power supply restoration strategy, establishes a power supply restoration plan library, and when a fault occurs in the distribution network, calls a power supply restoration plan in the power supply restoration plan based on the fault information to quickly restore power use, and provides a power supply restoration method based on the time-varying photovoltaic output and load, thereby solving the technical problem that the existing traditional power supply restoration method is difficult to quickly restore power supply, shortens the power outage time, and provides a guarantee for the stable operation of the power grid.

[0106] See also Figure 3 , Figure 3 The present invention is a flowchart of a method for calculating a power supply restoration solution based on a particle swarm algorithm in a rapid power supply restoration method of the present invention, including:

[0107] Step S301, obtaining network parameters and setting the fault type of the power supply restoration plan according to the fault location; the network parameters include network topology, line parameters, photovoltaic output prediction value and load prediction value in the corresponding time period;

[0108] Step S302, generating the initial position and initial velocity of each particle based on the network operation constraints;

[0109] Step S303, using the power supply recovery model of the distribution network, calculating the fitness function of each particle (load recovery amount in the power outage area);

[0110] Step S304, updating the position and speed of each particle according to the fitness function of each particle to obtain an updated particle;

[0111] In an optional embodiment, before step S304, the method further includes:

[0112] Compare the fitness function of each particle with the historical value to obtain the historical global optimal and local optimal particles;

[0113] In the embodiment of the present invention, the fitness function of each particle is compared with the historical value to update the historical global optimal and local optimal particles.

[0114] Step S305, determining whether the updated particles meet the network operation constraint conditions; if so, executing step S306; if not, returning to executing step S303;

[0115] Step S306, determining whether the iteration of the updated particle has reached the set number of times, and whether the global optimal position of the updated particle has reached the minimum limit; if so, determining the power supply restoration plan for the corresponding period of time of the fault position; if not, returning to execute step S303.

[0116] In a method for rapid power supply restoration of the present invention, a calculation method for solving a power supply restoration plan based on a particle swarm algorithm is used. The particle swarm algorithm is used to combine the photovoltaic output prediction model, the load prediction model, the power supply restoration strategy and the preset network operation constraints to perform calculations, and a power supply restoration plan for fault-prone locations in the target distribution network is obtained, thereby shortening the power outage time and providing a guarantee for the stable operation of the power grid.

[0117] See also Figure 4 , Figure 4 This is a structural block diagram of an embodiment of a fast power supply recovery device of the present invention, comprising:

[0118] The acquisition module 401 is used to acquire the historical data of the photovoltaic power stations in the target distribution network, various meteorological data, photovoltaic output influencing factor information and load change influencing factor information;

[0119] A modeling module 402 is used to establish a photovoltaic output prediction model and a load prediction model according to the photovoltaic power station historical data, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information;

[0120] A strategy module 403 is used to formulate a power supply restoration strategy based on the photovoltaic output prediction model and the load prediction model in combination with the time dimension;

[0121] Establishing module 404, for traversing the fault-prone locations in the target distribution network based on the photovoltaic output prediction model, the load prediction model and the power supply restoration strategy, and establishing a power supply restoration solution library;

[0122] The recovery module 405 is used to call a power supply recovery plan in the power supply recovery plan to quickly restore power supply based on the fault information when a fault occurs in the distribution network.

[0123] In an optional embodiment, the device further comprises:

[0124] The initialization module is used to initialize the network parameters of the target distribution network.

[0125] In an optional embodiment, the modeling module 402 includes:

[0126] A conversion submodule, used for converting the photovoltaic output influencing factor information into a weather type index according to the photovoltaic power station historical data and the various meteorological data;

[0127] A photovoltaic submodule, used for establishing the photovoltaic output prediction model based on the weather type index;

[0128] The load submodule is used to establish the load prediction model according to the load change influencing factor information.

[0129] In an optional embodiment, the establishing module 404 includes:

[0130] An acquisition submodule, used for acquiring the load recovery amount of the maximized power failure zone in the target distribution network;

[0131] A calculation submodule, for calculating by using a particle swarm algorithm, in combination with the photovoltaic output prediction model, the load prediction model, the power supply restoration strategy and preset network operation constraints, to obtain a power supply restoration plan for a fault-prone location in the target distribution network;

[0132] The summarizing submodule is used to summarize the power supply restoration schemes to obtain the power supply restoration scheme library.

[0133] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the fast power supply recovery method as described in any of the above embodiments.

[0134] An embodiment of the present invention further provides a computer storage medium on which a computer program is stored. When the computer program is executed by the processor, the method for quickly restoring power supply as described in any of the above embodiments is implemented.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0136] In the several embodiments provided in the present application, it should be understood that the methods, devices, electronic devices and storage media disclosed in the present invention can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0140] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for quickly restoring power supply, characterized in that: include: Obtain historical data of photovoltaic power stations in the target distribution network, various meteorological data, information on factors affecting photovoltaic output and factors affecting load changes; Establishing a photovoltaic output prediction model and a load prediction model according to the photovoltaic power station historical data, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information; Based on the photovoltaic output prediction model and the load prediction model, a power supply restoration strategy is formulated in combination with the time dimension; Based on the photovoltaic output prediction model, the load prediction model and the power supply restoration strategy, traverse the fault-prone locations in the target distribution network to establish a power supply restoration solution library; When a failure occurs in the distribution network, based on the failure information, a power supply restoration plan in the power supply restoration plan is called to quickly restore power supply; According to the photovoltaic power station historical data, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information, a photovoltaic output prediction model and a load prediction model are established, including: According to the photovoltaic power station historical data and the various meteorological data, the photovoltaic output influencing factor information is converted into a weather type index; Based on the weather type index, establishing the photovoltaic output prediction model; Establishing the load prediction model according to the load change influencing factor information; The load forecasting model is used to perform ultra-short-term load forecasting on load nodes in the distribution network, obtain a daily load curve, and obtain the power consumption demand of each load node in a certain period by integrating the daily load curve, and obtain the average load power in the period; wherein the calculation formula of the average load power is: ； in, Load node The load curve, is the load node i at time j Electricity consumption at any time; is the load node i at time j Average load power at the moment; Based on the power supply restoration strategy, traverse the fault-prone locations in the target distribution network and establish a power supply restoration solution library, including: Obtaining a load recovery amount of a maximized power outage zone in the target distribution network; Using a particle swarm algorithm, combined with the photovoltaic output prediction model, the load prediction model, the power supply restoration strategy and preset network operation constraints, a power supply restoration plan for a fault-prone location in the target distribution network is obtained; Summarizing the power supply restoration schemes to obtain the power supply restoration scheme library; The particle swarm algorithm is used to calculate the power supply restoration plan for the fault-prone location in the target distribution network by combining the photovoltaic output prediction model, the load prediction model, the power supply restoration strategy and the preset network operation constraints to obtain the power supply restoration plan specifically including: A particle swarm algorithm is used. For any period of time, based on the predicted photovoltaic output and load values, with the goal of maximizing the load recovery amount in the power-off zone and the distribution network operation constraints as constraints, the fault-prone locations in the target distribution network are calculated, and the power supply restoration plan for the fault-prone locations in the target distribution network is solved.

2. The method for rapid power supply restoration according to claim 1, characterized in that: Before obtaining the historical data of photovoltaic power stations in the target distribution network, various meteorological data, photovoltaic output influencing factor information and load change influencing factor information, it also includes: Initialize network parameters of the target distribution network.

3. A fast power supply recovery device, characterized in that: include: An acquisition module is used to obtain historical data of photovoltaic power stations in the target distribution network, various meteorological data, information on factors affecting photovoltaic output, and information on factors affecting load changes; A modeling module, used to establish a photovoltaic output prediction model and a load prediction model according to the photovoltaic power station historical data, the various meteorological data, the photovoltaic output influencing factor information and the load change influencing factor information; A strategy module, used to formulate a power supply restoration strategy based on the photovoltaic output prediction model and the load prediction model in combination with a time dimension; Establishing a module for traversing the fault-prone locations in the target distribution network and establishing a power supply restoration solution library based on the photovoltaic output prediction model, the load prediction model and the power supply restoration strategy; A recovery module, used to call a power supply recovery plan in the power supply recovery plan to quickly restore power supply based on fault information when a fault occurs in the distribution network; The modeling module includes: A conversion submodule, used for converting the photovoltaic output influencing factor information into a weather type index according to the photovoltaic power station historical data and the various meteorological data; A photovoltaic submodule, used for establishing the photovoltaic output prediction model based on the weather type index; A load submodule, used to establish the load prediction model according to the load change influencing factor information; The load forecasting model is used to perform ultra-short-term load forecasting on load nodes in the distribution network, obtain a daily load curve, and obtain the power consumption demand of each load node in a certain period by integrating the daily load curve, and obtain the average load power in the period; wherein the calculation formula of the average load power is: ； in, Load node The load curve, is the load node i at time j Electricity consumption at any time; is the load node i at time j Average load power at the moment; The establishment module includes: An acquisition submodule, used for acquiring the load recovery amount of the maximized power failure zone in the target distribution network; A calculation submodule, for calculating by using a particle swarm algorithm, in combination with the photovoltaic output prediction model, the load prediction model, the power supply restoration strategy and preset network operation constraints, to obtain a power supply restoration plan for a fault-prone location in the target distribution network; A summarizing submodule, used for summarizing the power supply restoration schemes to obtain the power supply restoration scheme library; Among them, the calculation submodule is specifically used to adopt a particle swarm algorithm. For any time period, based on the photovoltaic output forecast value and the load forecast value, with the goal of maximizing the load recovery amount in the power-off zone, and with the distribution network operation constraints as constraints, the fault-prone locations in the target distribution network are calculated to obtain the power supply restoration plan for the fault-prone locations in the target distribution network.

4. The rapid power supply recovery device according to claim 3, characterized in that: The device also includes: The initialization module is used to initialize the network parameters of the target distribution network.

5. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 2 is executed.

6. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 2 is performed.

Images