Method and device for acquiring operation scheme of power distribution network, and electronic equipment

Abstract

The invention discloses a power distribution network operation scheme obtaining method and device and electronic equipment. The method comprises the following steps: acquiring multiple groups of historical operation data in a preset period of the power distribution network, and calculating a first per-unit value and a second per-unit value based on the historical operation data; converting the target model into a model constraint condition, obtaining an operation constraint condition, and combining the model constraint condition and the operation constraint condition into a constraint condition set; solving the constraint condition set by taking the minimum operation cost of the power distribution network as an optimization target to obtain a power distribution network operation scheme; and generating a plurality of to-be-determined power distribution network operation schemes through the power distribution network operation scheme, determining a constraint satisfaction probability of the power distribution network operation scheme, and determining a target power distribution network operation scheme from the plurality of to-be-determined power distribution network operation schemes and the power distribution network operation schemes based on the constraint satisfaction probability. Through the method and the device, the problem of low efficiency of obtaining the real-time operation scheme of the power distribution network in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of power dispatching of distribution networks, and in particular to a method, device and electronic equipment for acquiring an operation plan of a distribution network. Background Art

[0002] In related technologies, as the topological complexity of urban distribution networks gradually increases and the requirements for safe operation become more stringent, power flow calculations become more complex. Power flow calculations in urban distribution networks are mainly based on Kirchhoff's circuit law to construct network voltage and current balance constraints. Then, iterative solutions are performed through iterative solution algorithms, such as the Newton-Raphson algorithm. This algorithm has extremely high calculation accuracy, but requires complete and accurate line impedance parameters.

[0003] With the large-scale access of high-power loads such as electric vehicles to the distribution network, the lines and equipment in the urban distribution network need to be continuously transformed and upgraded, which in turn makes the topology and equipment complexity of the urban distribution network continue to increase, and the impedance parameters of the distribution network are increasingly difficult to obtain accurately. On the one hand, too many distribution network nodes and frequency and voltage regulation equipment make it more difficult to solve the power flow solution algorithm based on the physical model; on the other hand, since the impedance parameters of the distribution network are difficult to obtain accurately, the distribution network power flow obtained may deviate greatly from the actual situation, making it difficult to ensure safe operation requirements. This makes it more difficult to achieve real-time operation optimization of the distribution network. However, the increasingly complex distribution network structure also urgently needs more accurate optimization operation plans to guide it in order to achieve efficient and safe operation. Therefore, the distribution network operation plan in the related technology requires detailed distribution network topology and impedance data calculation, which is not easy to obtain in actual application scenarios; in addition, the obtained distribution network topology data may have a large deviation from the actual operating conditions, and cannot fully meet the constraints of safe operation; the algorithm for solving the distribution network operation plan in the related technology takes too long to solve, which is difficult to meet the requirements of real-time optimization operation of the distribution network.

[0004] With regard to the problem of low efficiency in obtaining real-time operation plans of distribution networks in related technologies, no effective solution has been proposed so far. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device and electronic device for obtaining a distribution network operation plan, so as to solve the problem of low efficiency in obtaining a real-time operation plan of a distribution network in the related art.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for obtaining a distribution network operation plan is provided. The method includes: obtaining multiple groups of historical operation data within a preset period of the distribution network, calculating the first per-unit value and the second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is the minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is the minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint; converting the target model into model constraints, and obtaining the operation constraints of the distribution network, combining the model constraints and the operation constraints into a constraint set, wherein the target model is trained by multiple groups of training samples, each of which is a set of training samples. A set of training samples includes a set of historical operation data, a set of first per-unit values ​​and a set of second per-unit values ​​of the historical operation data; taking the minimization of the operation cost of the distribution network as the optimization goal, solving the constraint condition set based on the optimization goal, and obtaining the distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, the power generation power and the purchased power of the distribution network; generating multiple pending distribution network operation plans through the distribution network operation plan, determining the constraint satisfaction probability of the distribution network operation plan based on the multiple pending distribution network operation plans, and determining the target distribution network operation plan from the multiple pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability.

[0007] Optionally, calculating the first per unit value and the second per unit value of the historical operation data based on each group of historical operation data includes: determining the node voltage of each node of the distribution network and the line current of each line, determining the maximum node voltage and the minimum node voltage in the voltage boundary constraint of the distribution network, and determining the maximum line current in the current boundary constraint of the distribution network; for each node, calculating a first difference between the maximum node voltage and the node voltage of the node, and calculating the ratio of the first difference to the rated voltage of the distribution network to obtain the first voltage per unit value of the node; calculating the node voltage of the node and the minimum node voltage; and calculating the ratio of the node voltage to the rated voltage of the distribution network. The second voltage difference is calculated, and the ratio of the second difference to the rated voltage of the distribution network is calculated to obtain the second voltage per unit value of the node; the minimum voltage per unit value is determined from the first voltage per unit value and the second voltage per unit value of all nodes, and the minimum voltage per unit value is determined as the first per unit value; for each line, the third difference between the maximum line current and the line current of the line is calculated, and the ratio of the third difference to the maximum line current is calculated to obtain the current per unit value of the line; the minimum current per unit value is determined from the current per unit values ​​of all lines, and the minimum current per unit value is determined as the second per unit value.

[0008] Optionally, converting the target model into model constraints includes: determining the input layer, hidden layer and output layer of the target model, and determining the model parameters of the target model; determining the expression of the input layer as the first constraint, determining the linear mapping expression of the hidden layer as the second constraint, determining the output expression of the activation function of the hidden layer as the third constraint, and determining the expression of the output layer as the fourth constraint; determining the first constraint, the second constraint, the third constraint and the fourth constraint as model constraints.

[0009] Optionally, the operation cost of the distribution network is obtained by: determining the electricity purchase price and the total electricity purchase amount of the distribution network, calculating the product of the electricity purchase price and the total electricity purchase amount, and obtaining the operation cost of the distribution network.

[0010] Optionally, generating multiple pending distribution network operation plans through the distribution network operation plan includes: randomly generating multiple candidate distribution network operation plans to obtain a set of candidate distribution network operation plans; for each candidate distribution network operation plan, calculating the sum of the energy storage power, power generation power and power purchase power of the distribution network of the candidate distribution network operation plan to obtain a first load power of the candidate distribution network operation plan; determining the second load power of the distribution network operation plan, removing the candidate distribution network operation plans with different first load powers and second load powers from the set of candidate distribution network operation plans, and removing the candidate distribution network operation plans that do not meet the power constraint conditions from the set of candidate distribution network operation plans to obtain an updated set of candidate distribution network operation plans; for each candidate distribution network operation plan in the updated set of candidate distribution network operation plans, calculating the power difference between the candidate distribution network operation plan and the distribution network operation plan, and determining the candidate distribution network operation plan with a power difference less than a power difference threshold as the pending distribution network operation plan, wherein the power difference includes at least one of the following: the energy storage power difference, the power generation power difference and the power purchase power difference of the distribution network.

[0011] Optionally, determining the constraint satisfaction probability of a distribution network operation scheme based on multiple pending distribution network operation schemes includes: calculating a first per-unit value and a second per-unit value of each pending distribution network operation scheme based on a target model; determining a pending distribution network operation scheme whose first per-unit value or second per-unit value is less than a preset value as a constraint violation scheme, determining the number of constraint violation schemes to obtain a first number; determining the number of pending distribution network operation schemes to obtain a second number, calculating the ratio of the first number to the second number, and obtaining the constraint satisfaction probability of the distribution network operation scheme.

[0012] Optionally, determining a target distribution network operation plan from multiple pending distribution network operation plans and distribution network operation plans based on the constraint satisfaction probability includes: when the constraint satisfaction probability of the distribution network operation plan is less than the constraint satisfaction probability threshold, determining the distribution network operation plan as the target distribution network operation plan; when the constraint satisfaction probability of the distribution network operation plan is greater than or equal to the constraint satisfaction probability threshold, taking each pending distribution network operation plan as an updated distribution network operation plan, generating multiple sub-pending distribution network operation plans through the updated distribution network operation plan, and calculating the constraint satisfaction probability of the pending distribution network operation plan based on the multiple sub-pending distribution network operation plans and the pending distribution network operation plan to obtain a set of constraint satisfaction probabilities; determining at least one pending distribution network operation plan whose constraint satisfaction probability is less than the constraint satisfaction probability threshold from the multiple pending distribution network operation plans, and determining the plan with the minimum operating cost among the at least one pending distribution network operation plan as the target distribution network operation plan.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for acquiring a distribution network operation plan is provided. The device includes: an acquisition unit, which is used to acquire multiple groups of historical operation data within a preset period of the distribution network, and calculate the first per-unit value and the second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is the minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is the minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint; a conversion unit, which is used to convert the target model into a model constraint condition, and acquire the operation constraint condition of the distribution network, and combine the model constraint condition and the operation constraint condition into a constraint condition set, wherein the target model is trained by multiple groups of training samples, and each group of training samples is a set of training samples. A group of training samples includes a group of historical operation data, a group of first per-unit values ​​and a group of second per-unit values ​​of the historical operation data; a solving unit is used to solve a set of constraints based on the optimization goal with the minimization of the operation cost of the distribution network as the optimization goal, and obtain a distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, the power generation power and the purchased power of the distribution network; a generating unit is used to generate a plurality of pending distribution network operation plans through the distribution network operation plan, determine the constraint satisfaction probability of the distribution network operation plan based on the plurality of pending distribution network operation plans, and determine a target distribution network operation plan from the plurality of pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability.

[0014] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the method for obtaining the distribution network operation plan described in each embodiment of the present application.

[0015] Through the present application, the following steps are adopted: obtaining multiple groups of historical operation data within a preset period of the distribution network, calculating the first per-unit value and the second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is the minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is the minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint; converting the target model into a model constraint condition, and obtaining the operation constraint condition of the distribution network, combining the model constraint condition and the operation constraint condition into a constraint condition set, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes a group of historical The invention discloses a method for obtaining a distribution network operation plan, a method for obtaining a distribution network operation plan, a method for obtaining a distribution network operation plan, a method for obtaining a distribution network operation plan, a method for obtaining a distribution network operation plan, and a method for obtaining a distribution network operation plan. The method comprises the following steps: taking the minimization of the operation cost of the distribution network as the optimization goal, solving the constraint condition set based on the optimization goal, and obtaining the distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, the power generation power, and the power purchase power of the distribution network; generating multiple pending distribution network operation plans through the distribution network operation plan, determining the constraint satisfaction probability of the distribution network operation plan based on the multiple pending distribution network operation plans, and determining the target distribution network operation plan from the multiple pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability, thereby solving the problem of low efficiency in obtaining the real-time operation plan of the distribution network in the related technology. The distribution of the historical operation data of the distribution network is learned by the target model based on machine learning, and the learned data distribution is further embedded into the constraint condition set of the real-time operation optimization of the distribution network, replacing the distribution network flow calculation part. Furthermore, considering that there are errors in the neural network fitting in the target model, in order to ensure that the safety constraints are met as much as possible and improve the economy, the Monte Carlo method is used to evaluate the constraint satisfaction probability after the optimization model is solved, and the distribution network operation plan is corrected, thereby achieving the effect of improving the efficiency of obtaining the real-time operation plan of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 is a flow chart of a method for obtaining a distribution network operation plan provided in an embodiment of the present application;

[0018] Figure 2 is a schematic diagram of an optional method for obtaining a distribution network operation plan provided in an embodiment of the present application;

[0019] Figure 3 is a schematic diagram of a device for acquiring a distribution network operation plan according to an embodiment of the present application;

[0020] Figure 4is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0025] It should be noted that the information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0026] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flow chart of a method for obtaining a distribution network operation plan according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0027] Step S101, obtaining multiple groups of historical operation data within a preset period of the distribution network, and calculating a first per-unit value and a second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is the minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is the minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint.

[0028] Specifically, the historical operation data may include the node voltage, line current, network loss (power loss during the operation of the distribution network) and other operation data of each node in the distribution network. The historical operation data also includes the safe operation range of the node voltage of the distribution network (i.e., voltage boundary constraints), the safe operation range of the line current (i.e., current boundary constraints) and other parameters. The preset period may be one year or one month. By acquiring multiple groups of historical operation data of the distribution network in the past year, and calculating the first per-unit value of the interval between the node voltage of each node in the distribution network and its corresponding voltage boundary constraint, and the second per-unit value of the interval between the line current of each line and its corresponding current boundary constraint based on the historical operation data, the operation data of each node in the distribution network is characterized by the first per-unit value and the second per-unit value, and the distribution of the operation data of the distribution network is characterized based on the first per-unit value and the second per-unit value of all nodes.

[0029] Step S102, converting the target model into model constraints, obtaining the operating constraints of the distribution network, and combining the model constraints and the operating constraints into a constraint set, wherein the target model is obtained by training multiple groups of training samples, and each group of training samples includes a group of historical operating data, a group of first per-unit values ​​and a second per-unit value of the historical operating data.

[0030] Specifically, as the topological complexity of the distribution network gradually increases, it is increasingly difficult to obtain quasi-detailed distribution network topology and impedance data. Therefore, a target model is trained through deep learning, and deep learning technology is used to learn the distribution of historical operation data of the distribution network. The learned data distribution is further embedded in the real-time operation optimization of the distribution network, that is, the target model is converted into model constraints, and the model constraints replace the flow calculation part of the distribution network operation data in the relevant technology.

[0031] For example, the target model can be three deep neural networks composed of multi-layer sensors, which respectively learn the following under different load distributions (distribution of node voltage and line current) and different historical distribution network operation schemes: a. The minimum per-unit value of the interval between the node voltage and its corresponding voltage boundary constraint among all nodes; b. The minimum per-unit value of the interval between the line current of the line and its corresponding current boundary constraint among all lines; c. The overall network loss rate of the distribution network.

[0032] After determining the target model, the target model is converted into model constraints by disassembling the neural network, and then combined with the obtained operation constraints of the distribution network to obtain the set of constraints that need to be met in the real-time optimization operation plan of the distribution network.

[0033] Step S103, taking the minimization of the operation cost of the distribution network as the optimization goal, solving the constraint condition set based on the optimization goal, and obtaining the distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, power generation power and power purchase power of the distribution network.

[0034] Specifically, after determining the set of constraints, the optimal distribution network operation plan can be obtained by solving the set of constraints. The distribution network operation plan can include the estimated total energy storage power of all energy storage system nodes in the distribution network, the total power purchase power of all user nodes in the distribution network, and the total power generation power of all power generation nodes in the distribution network. When solving the set of constraints, multiple distribution network operation plans can be obtained, and the minimum operation cost of the distribution network is selected as the optimization goal of the distribution network operation plan, so as to solve the distribution network operation plan that minimizes the operation cost and satisfies the set of constraints.

[0035] Step S104, generating multiple pending distribution network operation plans through the distribution network operation plan, determining the constraint satisfaction probability of the distribution network operation plan based on the multiple pending distribution network operation plans, and determining the target distribution network operation plan from the multiple pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability.

[0036] Specifically, considering that there are errors in the distribution network operation data fitted by the neural network, in order to ensure that the distribution network operation plan meets the safety constraints (that is, meets the set of constraint conditions) while improving the economy, the Monte Carlo method is used to generate multiple pending distribution network operation plans after the optimization model is solved, and the constraint satisfaction probability of each distribution network operation plan is evaluated. The distribution network operation plan is further optimized based on the constraint satisfaction probability, so as to obtain the final optimized target distribution network operation plan.

[0037] For example, after each distribution network operation plan is solved, the Monte Carlo method is used to generate suboptimal scheduling plans (i.e., pending distribution network operation plans) near the array optimal scheduling plan (i.e., distribution network operation plan), and then the trained neural network is used to calculate the situations where these pending distribution network operation plans do not meet the constraint condition set, and the constraint satisfaction probability of the distribution network operation plan is calculated based on the pending distribution network operation plan. If the constraint satisfaction probability exceeds the specified threshold, the pending distribution network operation plan that meets the constraint condition set is selected, and the Monte Carlo method is repeated for these pending distribution network operation plans respectively to generate sub-pending distribution network operation plans for each pending distribution network operation plan, and the constraint satisfaction probability of each pending distribution network operation plan that meets the constraint condition set is calculated based on the sub-pending distribution network operation plan. Find the pending distribution network operation plan whose constraint satisfaction probability does not exceed the threshold, and select the plan that relatively minimizes the operating cost as the target distribution network operation plan.

[0038] The method for obtaining the distribution network operation plan provided in the embodiment of the present application obtains multiple groups of historical operation data within a preset period of the distribution network, and calculates the first per-unit value and the second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is the minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is the minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint; converts the target model into a model constraint condition, and obtains the operation constraint condition of the distribution network, and combines the model constraint condition and the operation constraint condition into a constraint condition set, wherein the target model is trained by multiple groups of training samples, and each group of training samples The invention comprises a set of historical operation data, a set of first per unit value and a second per unit value of the historical operation data; taking the minimization operation cost of the distribution network as the optimization target, solving the constraint condition set based on the optimization target, and obtaining the distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, power generation power and power purchase power of the distribution network; generating multiple pending distribution network operation plans through the distribution network operation plan, determining the constraint satisfaction probability of the distribution network operation plan based on the multiple pending distribution network operation plans, and determining the target distribution network operation plan from the multiple pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability, thereby solving the problem of low efficiency in obtaining the real-time operation plan of the distribution network in the related technology. The distribution of the historical operation data of the distribution network is learned by the target model based on machine learning, and the learned data distribution is further embedded into the constraint condition set of the real-time operation optimization of the distribution network, replacing the distribution network flow calculation part therein. Furthermore, considering the errors in the neural network fitting in the target model, in order to ensure that the safety constraints are met as much as possible while improving the economy, the Monte Carlo method is used to evaluate the constraint satisfaction probability after the optimization model is solved, and the distribution network operation plan is corrected, thereby achieving the effect of improving the efficiency of obtaining the distribution network operation plan.

[0039] The operating conditions of the historical operating data of the distribution network are characterized by calculating the per-unit value. Optionally, in the method for acquiring the distribution network operation plan provided in the embodiment of the present application, the first per-unit value and the second per-unit value of the historical operating data are calculated based on each group of historical operating data, including: determining the node voltage of each node of the distribution network and the line current of each line, determining the maximum node voltage and the minimum node voltage in the voltage boundary constraint of the distribution network, and determining the maximum line current in the current boundary constraint of the distribution network; for each node, calculating the first difference between the maximum node voltage and the node voltage of the node, and calculating the ratio of the first difference to the rated voltage of the distribution network, to obtain a first voltage per unit value of a node; calculating a second difference between the node voltage and the minimum node voltage, and calculating the ratio of the second difference to the rated voltage of the distribution network to obtain the second voltage per unit value of the node; determining the minimum voltage per unit value from the first voltage per unit values ​​and the second voltage per unit values ​​of all nodes, and determining the minimum voltage per unit value as the first per unit value; for each line, calculating a third difference between the maximum line current and the line current of the line, and calculating the ratio of the third difference to the maximum line current to obtain the current per unit value of the line; determining the minimum current per unit value from the current per unit values ​​of all lines, and determining the minimum current per unit value as the second per unit value.

[0040] Specifically, first, obtain the node voltage of each node in the distribution network, the line current of each line and other operating data, and obtain the parameters such as the node voltage safe operating range and line current safe operating range of the distribution network, that is, the maximum node voltage, the minimum node voltage and the maximum line current. The calculation formula of the first per unit value is as follows:

[0041]

[0042] Where, ΔV t It is the minimum per-unit value of the node voltage of all nodes in the distribution network at time t and the interval between their voltage boundary constraints, that is, the first per-unit value, V i,t is the node voltage of node i in the distribution network at time t, is the rated voltage of node i (e.g. 220V), is the maximum node voltage constrained by the voltage boundary for safe operation of the distribution network, is the minimum node voltage constrained by the voltage boundary. The second per unit value is calculated as follows:

[0043]

[0044] Among them, ΔI t It is the minimum per-unit value of the line current of all lines in the distribution network at time t and the interval between their current boundary constraints, that is, the second per-unit value, I j,tis the line current of line j in the distribution network at time t, is the line current rating of line j, i.e., the maximum line current in the current boundary constraint.

[0045] This embodiment characterizes the operation status of the distribution network by calculating the first per-unit value and the second per-unit value. It does not rely on the detailed grid structure of the distribution network. Only the historical operation data of the distribution network is needed to predict the safe operation status of the distribution network, thereby improving the efficiency of obtaining the distribution network operation plan.

[0046] In order to solve an operation plan in which the distribution network can operate safely, it is necessary to convert the target model obtained based on historical operation data learning into model constraints. Optionally, in the method for obtaining the distribution network operation plan provided in an embodiment of the present application, converting the target model into model constraints includes: determining the input layer, hidden layer and output layer of the target model, and determining the model parameters of the target model; determining the expression of the input layer as the first constraint, determining the linear mapping expression of the hidden layer as the second constraint, determining the output expression of the activation function of the hidden layer as the third constraint, and determining the expression of the output layer as the fourth constraint; determining the first constraint, the second constraint, the third constraint and the fourth constraint as model constraints.

[0047] In some examples, the target models learned by this embodiment through historical operation data may include three, namely, neural network models describing voltage constraint mapping relationship, current constraint mapping relationship and distribution network loss mapping relationship. The expressions of the above three neural network models are as follows:

[0048]

[0049] Among them, π V , Θ V They represent the neural network and its network parameters describing the voltage constraint mapping relationship, D t , P t are the load distribution and adjustable resource scheduling plan of the distribution network at time t. The load distribution of the distribution network includes the node voltage of each node and the line current of each line. The adjustable resource scheduling plan is the distribution network operation plan corresponding to the historical operation data of the distribution network, such as the energy storage power, power generation power and power purchase power of the distribution network. I , Θ I They represent the neural network and its network parameters describing the current constraint mapping relationship, π L , Θ L They respectively represent the neural network and network parameters for describing the distribution network loss mapping relationship.

[0050] Furthermore, the multi-layer perceptron neural network of the target model adopts a standard structure, and the model constraints for converting the target model are as follows:

[0051]

[0052] Among them, x t is the input data, i.e. D in formulas (3), (4) and (5) t , P t , is the input layer, is the output of the linear mapping of the hidden layer l, is the output of the activation function of the hidden layer l, is the output of the activation function of the hidden layer l-1; L is the set of hidden layers, and the parameter (W l , b l ) and (w |L|+1 , b |L|+1 ) is the weight and bias of the objective function, h t is the output of the output layer of the multi-layer perceptron neural network. Formula (6) is also the first constraint, formula (7) is also the second constraint, and formula (9) is also the fourth constraint.

[0053] Since formula (8) is a nonlinear constraint, the rest are linear constraints. Therefore, the operations research constraint decomposition method is used to decompose the nonlinear term in formula (8) into auxiliary standard linear constraints containing 0-1 variables:

[0054]

[0055] in, is an auxiliary variable, M is a huge constant, is a 0-1 variable. In formula (10), when When is a positive number, when When it is a negative number, Formula (10) is also the third constraint condition. By using the operations research constraint decomposition method, the nonlinear neurons in the above neural network are disassembled into auxiliary standard linear constraints containing 0-1 variables, and added to the distribution network optimization operation constraints without power flow calculation to form a complete distribution network optimization problem.

[0056] This embodiment uses a neural network to record the historical operating data of the distribution network, avoiding detailed distribution network modeling, thereby avoiding the problem of being unable to model due to opaque topological data, reducing the complexity of optimization model modeling, and improving the efficiency of optimizing the distribution network operation plan.

[0057] Furthermore, after determining the model constraints, it is also necessary to obtain the operation constraints of the distribution network. The operation constraints may include power balance constraints, energy storage output constraints, energy storage capacity constraints, gas turbine unit output constraints, voltage safety constraints, current safety constraints, etc. in the distribution network. The operation constraints, the neural network calculation equation constraints of voltage / current / network loss represented by formula (3)-formula (5), and the model constraints of formula (6), formula (7), formula (9), and formula (10) are combined into a constraint set. The expression of the constraint set is as follows:

[0058]

[0059] Where Di,t is the power load of node i at time t, Pi,t is the power generation power of node i at time t, is the photovoltaic power generation of node i at time t, is the energy storage charging and discharging power of node i at time t, is the power generation of the gas turbine unit at node i at time t, is the power purchased by node i from the upper grid at time t, is the state of charge of the energy storage device, is the upper limit of energy storage capacity, is the maximum charging power of the energy storage, is the maximum discharge power of the energy storage, It is the maximum discharge power of the gas turbine unit.

[0060] After determining the set of constraints, the set of constraints is solved according to minimizing the operating cost to obtain a distribution network operation plan. Optionally, in the method for obtaining a distribution network operation plan provided in an embodiment of the present application, the operating cost of the distribution network is obtained by determining the electricity purchase price and the total purchased electricity amount of the distribution network, calculating the product of the electricity purchase price and the total purchased electricity amount, and obtaining the operating cost of the distribution network.

[0061] Specifically, the calculation formula for the operation cost of the distribution network is as follows:

[0062]

[0063] Among them, c t is the electricity purchase price of the distribution network at each moment, is the total electricity purchased at each moment.

[0064] This embodiment solves the optimization problem consisting of a set of constraint conditions by taking minimizing the operating cost as the optimization goal, thereby obtaining the optimal operating plan of the distribution network at this time.

[0065] In order to improve the robustness of the distribution network operation plan, multiple pending distribution network operation plans are generated to optimize the distribution network operation plan. Optionally, in the method for obtaining the distribution network operation plan provided in the embodiment of the present application, generating multiple pending distribution network operation plans through the distribution network operation plan includes: randomly generating multiple candidate distribution network operation plans to obtain a set of candidate distribution network operation plans; for each candidate distribution network operation plan, calculating the sum of the energy storage power, the power generation power and the power purchase power of the distribution network of the candidate distribution network operation plan to obtain a first load power of the candidate distribution network operation plan; determining a second load power of the distribution network operation plan, and summing the first load power with the second load power; Candidate distribution network operation plans with different powers are eliminated from the candidate distribution network operation plan set, and candidate distribution network operation plans that do not meet the power constraint conditions are eliminated from the candidate distribution network operation plan set to obtain an updated candidate distribution network operation plan set; for each candidate distribution network operation plan in the updated candidate distribution network operation plan set, the power difference between the candidate distribution network operation plan and the distribution network operation plan is calculated, and the candidate distribution network operation plan with a power difference less than a power difference threshold is determined as a pending distribution network operation plan, wherein the power difference includes at least one of the following: energy storage power difference, power generation power difference and power purchase power difference of the distribution network.

[0066] Specifically, the distribution network operation plan is obtained After that, the expression of the distribution network operation plan is as follows:

[0067]

[0068] in, is the energy storage power in the distribution network operation scheme, is the power generation in the distribution network operation scheme, is the purchased power in the distribution network operation plan. By using the Monte Carlo method, n groups of candidate distribution network operation plans are generated near the distribution network operation plan. The expression of the candidate distribution network operation plan is as follows:

[0069]

[0070] Among them, P n,t is the nth candidate distribution network operation scheme, is the energy storage power in the nth candidate distribution network operation scheme, is the power generation in the nth candidate distribution network operation scheme, is the purchased power in the nth candidate distribution network operation plan. The pending distribution network operation plan selected from the candidate distribution network operation plan needs to meet some constraints. n,t The load balance constraint of the distribution network should be met. The load balance constraint expression is as follows:

[0071]

[0072] The left side of formula (15) represents the second load power, and the right side of formula (15) represents the first load power. n,t The basic unit output constraints should also be met:

[0073]

[0074] Among them, P ES,c is the maximum charging power of energy storage, P ES,d is the maximum discharge power of the energy storage, P GT,max is the maximum discharge power of the gas turbine unit, and the generated pending distribution network operation plan P n,t It should also meet the unit output changes and distribution network operation plans The maximum difference between them is the power difference threshold λ, and the power difference constraint expression is as follows:

[0075]

[0076] Since the pending distribution network operation plan has little change compared with the distribution network operation plan, it is considered that the network loss Therefore, the constraints of the distribution network are not considered.

[0077] This embodiment generates a plurality of pending distribution network operation plans for optimizing the distribution network operation plan, thereby improving the robustness of the distribution network operation plan.

[0078] In order to select a target distribution network operation scheme with higher robustness from the distribution network operation schemes and the pending distribution network operation schemes, it is necessary to calculate the constraint satisfaction probability of each scheme. Optionally, in the method for obtaining the distribution network operation scheme provided in the embodiment of the present application, determining the constraint satisfaction probability of the distribution network operation scheme based on multiple pending distribution network operation schemes includes: calculating the first per-unit value and the second per-unit value of each pending distribution network operation scheme based on the target model; determining the pending distribution network operation scheme whose first per-unit value or the second per-unit value is less than a preset value as a constraint violation scheme, determining the number of schemes of the constraint violation scheme to obtain a first number; determining the number of pending distribution network operation schemes to obtain a second number, calculating the ratio of the first number to the second number, and obtaining the constraint satisfaction probability of the distribution network operation scheme.

[0079] Specifically, the first per unit value and the second per unit value of each pending distribution network operation plan are calculated respectively, and the calculation formula is as follows:

[0080]

[0081] By inputting the pending distribution network operation plan into formula (18) and formula (19), the first per unit value and the second per unit value of the pending distribution network operation plan are obtained. After the first per unit value and the second per unit value of all the pending distribution network operation plans are obtained, the voltage / current constraint satisfaction of each pending distribution network operation plan is calculated.

[0082]

[0083] in, 1 indicates a constraint violation plan, that is, a plan with potential safety hazards. Then, based on the violation of all pending distribution network operation plans, the distribution network operation plan is calculated. The neighborhood constraint satisfies the probability η t , the constraint satisfaction probability is calculated as follows:

[0084]

[0085] in, represents the first quantity, and N represents the second quantity.

[0086] This embodiment screens out a target distribution network operation scheme with higher robustness from distribution network operation schemes and pending distribution network operation schemes by calculating the constraint satisfaction probability of each scheme.

[0087] After calculating the constraint satisfaction probability of the distribution network operation plan, a target distribution network operation plan is screened out from the distribution network operation plan and the pending distribution network operation plan. Optionally, in the method for obtaining the distribution network operation plan provided in the embodiment of the present application, determining the target distribution network operation plan from multiple pending distribution network operation plans and the distribution network operation plans based on the constraint satisfaction probability includes: when the constraint satisfaction probability of the distribution network operation plan is less than the constraint satisfaction probability threshold, determining the distribution network operation plan as the target distribution network operation plan; when the constraint satisfaction probability of the distribution network operation plan is greater than or equal to the constraint satisfaction probability threshold, taking each pending distribution network operation plan as an updated distribution network operation plan, generating multiple sub-pending distribution network operation plans through the updated distribution network operation plan, and calculating the constraint satisfaction probability of the pending distribution network operation plan based on the multiple sub-pending distribution network operation plans and the pending distribution network operation plan to obtain a set of constraint satisfaction probabilities; determining at least one pending distribution network operation plan whose constraint satisfaction probability is less than the constraint satisfaction probability threshold from the multiple pending distribution network operation plans, and determining the plan with the minimum operating cost among the at least one pending distribution network operation plan as the target distribution network operation plan.

[0088] Specifically, when the constraint satisfies the probability η t Less than the constraint satisfaction probability threshold When , the distribution network operation plan is considered to meet the operation safety requirements, and this plan is the final target distribution network operation plan. Otherwise, it is considered that the distribution network operation plan does not meet the operation safety requirements, and the target distribution network operation plan needs to be selected from the pending distribution network operation plans.

[0089] For example, among multiple pending distribution network operation plans, select The constraint is not violated, that is The pending distribution network operation plan P m,t . Wherein, the subscript m represents the number of the pending distribution network operation scheme that meets the constraints. m,t Generate multiple pending distribution network operation plans, and finally calculate these pending distribution network operation plans P m,t The constraint satisfaction probability η m,t Find out where The pending distribution network operation plan P m,t , and select the pending distribution network operation plan P that minimizes the operating cost m,t , this plan is the final target distribution network operation plan.

[0090] If there is no pending distribution network operation plan that satisfies the constraints, multiple sub-pending distribution network operation plans are repeatedly generated for these pending distribution network operation plans. Through iterative tree retrieval, the pending distribution network operation plan with a probability less than the constraint satisfaction threshold is found until a plan with a constraint satisfaction probability less than the constraint satisfaction probability threshold is found, which is the final target distribution network operation plan.

[0091] This embodiment overcomes the constraint violation caused by the uncertainty of neural network fitting to a certain extent by using the Monte Carlo-based neighborhood constraint violation posteriori, and ensures the minimized operating cost of the target distribution network operation plan.

[0092] According to another embodiment of the present application, an optional method for obtaining a distribution network operation plan is also provided. Figure 2 is a schematic diagram of an optional method for obtaining a distribution network operation plan according to an embodiment of the present application. Figure 2 As shown, the program includes:

[0093] Step 01, obtain the distribution network operation data and the designed operation range, and calculate the distance between the distribution network operation data and the safety boundary and the distribution network loss at different time points.

[0094] Specifically, the distribution network operation data may include operation data such as node voltage, line current, network loss, etc. of each node in the distribution network. The safety boundary may be a voltage boundary constraint and a current boundary constraint. The distance between the distribution network operation data and the safety boundary is also the first per-unit value and the second per-unit value.

[0095] Step 02: construct three neural networks to learn the distribution network voltage safety constraint margin, current safety constraint margin and distribution network loss under different conditions.

[0096] Specifically, the three neural networks are the networks corresponding to formula (3), formula (4) and formula (5), and different situations refer to the situations corresponding to each group of historical operation data of different training samples. The distribution network voltage safety constraint margin is also the first per-unit value, and the current safety constraint margin is also the second per-unit value.

[0097] Step 03, decompose the nonlinear neurons in the neural network into auxiliary standard linear constraints and add them to the running optimization constraints.

[0098] Specifically, the nonlinear neuron, that is, formula (8), and the auxiliary standard linear constraint, that is, formula (10), are added to the running optimization constraint to obtain the constraint condition set, that is, formula (12).

[0099] Step 04: Monte Carlo generates suboptimal scheduling solutions near the optimal scheduling solution and calculates the probability of neighborhood constraint breach in all cases.

[0100] Specifically, the optimal dispatching scheme is also the distribution network operation scheme, and the suboptimal dispatching scheme is also the pending distribution network operation scheme. All situations refer to the situations corresponding to different suboptimal dispatching schemes, and the neighborhood constraint breach probability is also the constraint satisfaction probability.

[0101] Step 05: If the probability of neighborhood constraint breach exceeds the specified value, repeat step 04 for the suboptimal scheduling plan that does not breach the contract. Continue to iterate through tree-like retrieval until a scheduling plan that meets the constraints is found.

[0102] Specifically, the specified value is also the constraint satisfaction probability threshold, and the non-default suboptimal dispatch plan refers to a dispatch plan whose first per-unit value and second per-unit value are both greater than or equal to 0. The dispatch plan that satisfies the constraints refers to the target distribution network operation plan whose constraint satisfaction probability is less than the constraint satisfaction probability threshold.

[0103] This embodiment uses a neural network to record historical data through an optional method for obtaining a distribution network operation plan, thereby avoiding detailed modeling of the distribution network, thereby avoiding the problem of being unable to model due to opaque topological data. At the same time, since the distribution network flow is not calculated, the complexity of the optimization model modeling is reduced, and the efficiency of the optimization solution is improved. The Monte Carlo-based neighborhood constraint violation posteriori is used to overcome the constraint violation caused by the uncertainty of neural network fitting to a certain extent, and ensure the economy of the optimization scheduling plan. At the same time, since the posteriori process is a simple random data generation / neural network data generation process, although the iterative process is complicated, the computer solution speed is extremely fast, and it does not affect the solution efficiency of this algorithm.

[0104] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0105] The embodiment of the present application also provides a device for obtaining a distribution network operation plan. It should be noted that the device for obtaining a distribution network operation plan in the embodiment of the present application can be used to execute the method for obtaining a distribution network operation plan provided in the embodiment of the present application. The following introduces the device for obtaining a distribution network operation plan provided in the embodiment of the present application.

[0106] Figure 3 Schematic diagram of a device for acquiring a distribution network operation plan according to an embodiment of the present application. Figure 3 As shown, the device comprises:

[0107] An acquisition unit 301 is used to acquire multiple groups of historical operation data within a preset period of the distribution network, and calculate a first per-unit value and a second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is a minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is a minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint;

[0108] A conversion unit 302 is used to convert the target model into model constraints, obtain the operation constraints of the distribution network, and combine the model constraints and the operation constraints into a constraint set, wherein the target model is obtained by training multiple groups of training samples, each group of training samples includes a group of historical operation data, a group of first per unit value and a second per unit value of the historical operation data;

[0109] A solving unit 303 is used to solve the constraint condition set based on the optimization target with the minimization of the operation cost of the distribution network as the optimization target, and obtain a distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, the power generation power and the power purchase power of the distribution network;

[0110] The generating unit 304 is used to generate a plurality of pending distribution network operation plans through the distribution network operation plan, determine the constraint satisfaction probability of the distribution network operation plan based on the plurality of pending distribution network operation plans, and determine the target distribution network operation plan from the plurality of pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability.

[0111] The device for acquiring the distribution network operation scheme provided in the embodiment of the present application acquires multiple groups of historical operation data within a preset period of the distribution network through an acquisition unit 301, and calculates the first per-unit value and the second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is the minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is the minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint; a conversion unit 302 converts the target model into model constraints, and acquires the operation constraints of the distribution network, and combines the model constraints and the operation constraints into a constraint set, wherein the target model is obtained by training multiple groups of training samples, and each group of training samples includes a group of historical operation data, a group of first per-unit value and a second per-unit value of the historical operation data; a solution unit 303 is used to The minimization of the operating cost of the distribution network is the optimization goal. Based on the optimization goal, the constraint condition set is solved to obtain the distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, power generation power and power purchase power of the distribution network; the generation unit 304 generates multiple pending distribution network operation plans through the distribution network operation plan, determines the constraint satisfaction probability of the distribution network operation plan based on the multiple pending distribution network operation plans, and determines the target distribution network operation plan from the multiple pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability, thereby solving the problem of low efficiency in obtaining the real-time operation plan of the distribution network in the related technology, and learning the distribution of the historical operation data of the distribution network through the target model based on machine learning, and further embedding the learned data distribution into the constraint condition set of the real-time operation optimization of the distribution network, replacing the distribution network flow calculation part. Furthermore, considering that there are errors in the neural network fitting in the target model, in order to ensure that the safety constraints are met as much as possible while improving the economy, the Monte Carlo method is used to evaluate the constraint satisfaction probability after the optimization model is solved, and the distribution network operation plan is corrected, thereby achieving the effect of improving the efficiency of obtaining the distribution network operation plan.

[0112] Optionally, in the device for acquiring the distribution network operation plan provided in the embodiment of the present application, the acquisition unit 301 includes: a first determination module, which is used to determine the node voltage of each node of the distribution network and the line current of each line, determine the maximum node voltage and the minimum node voltage in the voltage boundary constraint of the distribution network, and determine the maximum line current in the current boundary constraint of the distribution network; a first calculation module, which is used to calculate, for each node, a first difference between the maximum node voltage and the node voltage of the node, and calculate the ratio of the first difference to the rated voltage of the distribution network to obtain a first voltage per unit value of the node; a second calculation module, which is used to calculate the node voltage of the node and the minimum node voltage; a second difference in voltage at each point, and calculating the ratio of the second difference to the rated voltage of the distribution network to obtain a second voltage per unit value of the node; a second determining module, used to determine a minimum voltage per unit value from the first voltage per unit values ​​and the second voltage per unit values ​​of all nodes, and determine the minimum voltage per unit value as the first per unit value; a third calculating module, used to calculate, for each line, a third difference between the maximum line current and the line current of the line, and calculate the ratio of the third difference to the maximum line current to obtain the current per unit value of the line; a third determining module, used to determine a minimum current per unit value from the current per unit values ​​of all lines, and determine the minimum current per unit value as the second per unit value.

[0113] Optionally, in the device for acquiring the distribution network operation plan provided in the embodiment of the present application, the conversion unit 302 includes: a fourth determination module, used to determine the input layer, hidden layer and output layer of the target model, and determine the model parameters of the target model; a fifth determination module, used to determine the expression of the input layer as the first constraint, the linear mapping expression of the hidden layer as the second constraint, the output expression of the activation function of the hidden layer as the third constraint, and the expression of the output layer as the fourth constraint; a sixth determination module, used to determine the first constraint, the second constraint, the third constraint and the fourth constraint as model constraints.

[0114] Optionally, in the device for acquiring the distribution network operation plan provided in the embodiment of the present application, the operation cost of the distribution network is obtained by: determining the electricity purchase price and the total electricity purchase amount of the distribution network, calculating the product of the electricity purchase price and the total electricity purchase amount, and obtaining the operation cost of the distribution network.

[0115] Optionally, in the device for acquiring the distribution network operation plan provided in the embodiment of the present application, the generation unit 304 includes: a first generation module, which is used to randomly generate multiple candidate distribution network operation plans to obtain a set of candidate distribution network operation plans; a fourth calculation module, which is used to calculate the sum of the energy storage power, the power generation power and the power purchase power of the distribution network of the candidate distribution network operation plan for each candidate distribution network operation plan, and obtain the first load power of the candidate distribution network operation plan; a seventh determination module, which is used to determine the second load power of the distribution network operation plan, and select the candidate distribution network operation plans with different first load powers from the candidate distribution network operation plans. The candidate distribution network operation plans that do not meet the power constraint conditions are eliminated from the candidate distribution network operation plan set, and the updated candidate distribution network operation plan set is obtained; the fifth calculation module is used to calculate the power difference between the candidate distribution network operation plan and the distribution network operation plan for each candidate distribution network operation plan in the updated candidate distribution network operation plan set, and determine the candidate distribution network operation plan whose power difference is less than the power difference threshold as the pending distribution network operation plan, wherein the power difference includes at least one of the following: the energy storage power difference, the power generation power difference and the power purchase power difference of the distribution network.

[0116] Optionally, in the device for acquiring distribution network operation plans provided in an embodiment of the present application, the generation unit 304 includes: a sixth calculation module, used to calculate the first per-unit value and the second per-unit value of each pending distribution network operation plan based on the target model; an eighth determination module, used to determine the pending distribution network operation plan whose first per-unit value or the second per-unit value is less than a preset value as a constraint violation plan, determine the number of plans for the constraint violation plan, and obtain a first number; a ninth determination module, used to determine the number of pending distribution network operation plans, obtain a second number, calculate the ratio of the first number to the second number, and obtain the constraint satisfaction probability of the distribution network operation plan.

[0117] Optionally, in the device for acquiring the distribution network operation plan provided in the embodiment of the present application, the generation unit 304 includes: a tenth determination module, which is used to determine the distribution network operation plan as the target distribution network operation plan when the constraint satisfaction probability of the distribution network operation plan is less than the constraint satisfaction probability threshold; a second generation module, which is used to use each pending distribution network operation plan as the updated distribution network operation plan when the constraint satisfaction probability of the distribution network operation plan is greater than or equal to the constraint satisfaction probability threshold, generate multiple sub-pending distribution network operation plans through the updated distribution network operation plan, and calculate the constraint satisfaction probability of the pending distribution network operation plan based on the multiple sub-pending distribution network operation plans and the pending distribution network operation plan to obtain a set of constraint satisfaction probabilities; an eleventh determination module, which is used to determine at least one pending distribution network operation plan whose constraint satisfaction probability is less than the constraint satisfaction probability threshold from the multiple pending distribution network operation plans, and determine the plan with the minimum operating cost in the at least one pending distribution network operation plan as the target distribution network operation plan.

[0118] The device for acquiring the distribution network operation plan includes a processor and a memory. The above-mentioned acquisition unit 301, conversion unit 302, solution unit 303 and generation unit 304 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0119] The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and the efficiency of obtaining the distribution network operation plan can be improved by adjusting the kernel parameters.

[0120] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0121] An embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, a method for acquiring a distribution network operation plan is implemented.

[0122] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes a method for acquiring a distribution network operation plan when the program is running.

[0123] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. Figure 4As shown, the electronic device 401 includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining multiple groups of historical operation data within a preset period of the distribution network, calculating a first per-unit value and a second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is the minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is the minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint; converting the target model into a model constraint condition, and obtaining the operation constraint condition of the distribution network, and combining the model constraint condition and the operation constraint condition into a constraint condition. A set of components, wherein the target model is obtained by training multiple sets of training samples, each set of training samples includes a set of historical operation data, a set of first per-unit values ​​and a set of second per-unit values ​​of the historical operation data; the minimization of the operation cost of the distribution network is taken as the optimization goal, and the constraint condition set is solved based on the optimization goal to obtain the distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, power generation power and power purchase power of the distribution network; multiple pending distribution network operation plans are generated through the distribution network operation plan, and the constraint satisfaction probability of the distribution network operation plan is determined based on the multiple pending distribution network operation plans, and the target distribution network operation plan is determined from the multiple pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability. The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0124] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: obtaining multiple groups of historical operation data within a preset period of the distribution network, calculating a first per-unit value and a second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is the minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is the minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint; converting the target model into a model constraint condition, and obtaining the operation constraint condition of the distribution network, and combining the model constraint condition and the operation constraint condition into a constraint condition set , wherein the target model is obtained by training multiple groups of training samples, each group of training samples includes a group of historical operation data, a group of first per-unit values ​​and a group of second per-unit values ​​of the historical operation data; taking the minimization of the operation cost of the distribution network as the optimization goal, solving the constraint condition set based on the optimization goal, and obtaining the distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, power generation power and purchased power of the distribution network; generating multiple pending distribution network operation plans through the distribution network operation plan, determining the constraint satisfaction probability of the distribution network operation plan based on the multiple pending distribution network operation plans, and determining the target distribution network operation plan from the multiple pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability.

[0125] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0126] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0127] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0129] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0130] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0131] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0132] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0133] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0134] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for obtaining a distribution network operation plan, characterized in that: include: Acquire multiple groups of historical operation data within a preset period of the distribution network, and calculate a first per-unit value and a second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is the minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is the minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint; Converting the target model into model constraints, obtaining the operation constraints of the distribution network, and combining the model constraints and the operation constraints into a constraint set, wherein the target model is obtained by training multiple groups of training samples, each group of training samples includes a group of historical operation data, a first per-unit value and a second per-unit value of the group of historical operation data; Taking the minimization of the operation cost of the distribution network as the optimization goal, solving the constraint condition set based on the optimization goal to obtain a distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, power generation power and power purchase power of the distribution network; A plurality of pending distribution network operation plans are generated through the distribution network operation plan, constraint satisfaction probabilities of the distribution network operation plans are determined based on the plurality of pending distribution network operation plans, and a target distribution network operation plan is determined from the plurality of pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability.

2. The method according to claim 1, characterized in that Calculating the first per-unit value and the second per-unit value of the historical operation data based on each set of historical operation data includes: Determine a node voltage of each node of the distribution network and a line current of each line, determine a maximum node voltage and a minimum node voltage in a voltage boundary constraint of the distribution network, and determine a maximum line current in a current boundary constraint of the distribution network; For each node, calculating a first difference between the maximum node voltage and the node voltage of the node, and calculating a ratio of the first difference to the rated voltage of the distribution network to obtain a first voltage per unit value of the node; Calculating a second difference between the node voltage of the node and the minimum node voltage, and calculating a ratio of the second difference to the rated voltage of the distribution network to obtain a second voltage per unit value of the node; Determine a minimum voltage per unit value from the first voltage per unit values ​​and the second voltage per unit values ​​of all nodes, and determine the minimum voltage per unit value as the first voltage per unit value; For each line, calculating a third difference between the maximum line current and the line current of the line, and calculating a ratio of the third difference to the maximum line current to obtain a per-unit current value of the line; A minimum current per-unit value is determined from the current per-unit values ​​of all the lines, and the minimum current per-unit value is determined as the second per-unit value.

3. The method according to claim 1, characterized in that Converting the target model into model constraints includes: Determine the input layer, hidden layer and output layer of the target model, and determine the model parameters of the target model; Determine the expression of the input layer as the first constraint condition, determine the linear mapping expression of the hidden layer as the second constraint condition, determine the output expression of the activation function of the hidden layer as the third constraint condition, and determine the expression of the output layer as the fourth constraint condition; The first constraint condition, the second constraint condition, the third constraint condition and the fourth constraint condition are determined as the model constraint conditions.

4. The method according to claim 1, characterized in that The operating cost of the distribution network is obtained as follows: The electricity purchase price and the total electricity purchase amount of the distribution network are determined, and the product of the electricity purchase price and the total electricity purchase amount is calculated to obtain the operating cost of the distribution network.

5. The method according to claim 1, characterized in that Generating a plurality of pending distribution network operation plans through the distribution network operation plan includes: Randomly generate multiple candidate distribution network operation plans to obtain a set of candidate distribution network operation plans; For each candidate distribution network operation scheme, calculate the sum of the energy storage power, the power generation power and the power purchase power of the distribution network of the candidate distribution network operation scheme to obtain the first load power of the candidate distribution network operation scheme; Determine a second load power of the distribution network operation plan, remove candidate distribution network operation plans whose first load power is different from the second load power from the set of candidate distribution network operation plans, and remove candidate distribution network operation plans that do not meet power constraints from the set of candidate distribution network operation plans, to obtain an updated set of candidate distribution network operation plans; For each candidate distribution network operation plan in the updated set of candidate distribution network operation plans, the power difference between the candidate distribution network operation plan and the distribution network operation plan is calculated, and the candidate distribution network operation plan whose power difference is less than the power difference threshold is determined as the pending distribution network operation plan, wherein the power difference includes at least one of the following: the energy storage power difference, the power generation power difference and the power purchase power difference of the distribution network.

6. The method according to claim 1, characterized in that Determining the constraint satisfaction probability of the distribution network operation scheme based on the multiple pending distribution network operation schemes includes: Calculate a first per unit value and a second per unit value of each pending distribution network operation scheme based on the target model; Determine a pending distribution network operation scheme in which the first per unit value or the second per unit value is less than a preset value as a constraint violation scheme, determine the number of schemes of the constraint violation scheme, and obtain a first number; The number of the pending distribution network operation schemes is determined to obtain a second number, and a ratio of the first number to the second number is calculated to obtain a constraint satisfaction probability of the distribution network operation scheme.

7. The method according to claim 1, characterized in that Determining a target distribution network operation scheme from the plurality of pending distribution network operation schemes and the distribution network operation scheme based on the constraint satisfaction probability comprises: When the constraint satisfaction probability of the distribution network operation plan is less than the constraint satisfaction probability threshold, determining the distribution network operation plan as the target distribution network operation plan; In the case where the constraint satisfaction probability of the distribution network operation plan is greater than or equal to the constraint satisfaction probability threshold, each pending distribution network operation plan is used as an updated distribution network operation plan, a plurality of sub-pending distribution network operation plans are generated through the updated distribution network operation plan, and the constraint satisfaction probability of the pending distribution network operation plan is calculated based on the plurality of sub-pending distribution network operation plans and the pending distribution network operation plan to obtain a set of constraint satisfaction probabilities; Determine at least one pending distribution network operation scheme whose constraint satisfaction probability is less than the constraint satisfaction probability threshold from the multiple pending distribution network operation schemes, and determine the scheme with the minimum operating cost among the at least one pending distribution network operation scheme as the target distribution network operation scheme.

8. A device for acquiring a distribution network operation plan, characterized in that: include: An acquisition unit, used to acquire multiple groups of historical operation data within a preset period of the distribution network, and calculate a first per-unit value and a second per-unit value of the historical operation data based on each group of historical operation data, wherein the first per-unit value is a minimum per-unit value of the interval between the node voltage of each node of the distribution network and the voltage boundary constraint, and the second per-unit value is a minimum per-unit value of the interval between the line current of each line of the distribution network and the current boundary constraint; A conversion unit, used to convert the target model into model constraints, and obtain the operation constraints of the distribution network, and combine the model constraints and the operation constraints into a constraint set, wherein the target model is obtained by training multiple groups of training samples, each group of training samples includes a group of historical operation data, a first per-unit value and a second per-unit value of the group of historical operation data; A solving unit, configured to solve the set of constraints based on the optimization objective with the minimization of the operation cost of the distribution network as the optimization objective, and obtain a distribution network operation plan, wherein the distribution network operation plan at least includes the energy storage power, the power generation power and the power purchase power of the distribution network; A generating unit is used to generate a plurality of pending distribution network operation plans through the distribution network operation plan, determine the constraint satisfaction probability of the distribution network operation plan based on the plurality of pending distribution network operation plans, and determine a target distribution network operation plan from the plurality of pending distribution network operation plans and the distribution network operation plan based on the constraint satisfaction probability.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for obtaining a distribution network operation plan according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for obtaining the distribution network operation plan as described in any one of claims 1 to 7.

Images