A data-driven multi-stage operation scheduling method and system for urban power grid

Abstract

The application discloses a data-driven urban power grid multi-stage operation scheduling method and system, and establishes a mathematical model of a power distribution system coordination scheduling problem containing multiple energies; based on the obtained mathematical model of the power distribution system coordination scheduling problem, a linear budget constraint generation method based on historical data is used to construct a budget uncertainty set; based on the obtained budget uncertainty set, a multi-stage robust optimization method based on an implicit decision strategy is used to determine a coordination scheduling scheme; and the coordination scheduling of multiple resources and devices is adaptively optimized in a rolling time domain mode.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power system planning, and particularly relates to a data-driven multi-stage operation scheduling method and system for urban power grids. BACKGROUND

[0002] With the transformation of global energy structure, the improvement of environmental awareness, and the requirement of urban safety, economy and low-carbon energy use, renewable energy, especially wind energy and solar energy, has become an important part of urban power grid low-carbon, economic construction and operation. However, the intermittency and uncertainty of renewable energy output, such as wind energy and solar energy, have brought new challenges to the safe and stable operation and economic and efficient dispatching of power systems. In order to cope with this challenge and improve the reliability and stability of power systems, active distribution networks and energy storage devices have gradually become the focus of solving the problem of uncertainty of renewable energy.

[0003] In the distribution system, the scheduling problem of multiple energy resources and energy storage and supply devices is usually regarded as a typical multi-stage stochastic optimization problem. In this optimization problem, two difficulties are mainly faced: one is how to accurately describe the multi-dimensional uncertainty of multiple energy resources, and the other is how to design an optimal decision rule to cope with multi-dimensional uncertainty. There are many existing uncertainty set generation methods for describing multi-dimensional uncertainty, including scenario-based modeling, box uncertainty set, and budget uncertainty set.

[0004] In the existing methods, the calculation complexity of the scenario / scenario tree method increases sharply with the increase of the number of scenario sets, which cannot effectively cope with the problem of high-dimensional uncertainty, and the quality of the selected scenario also has a great influence on the result, making it difficult to accurately reflect the uncertainty in the system; the box uncertainty set is simple in calculation, but it ignores the correlation between different uncertainty dimensions, and cannot fully and accurately describe the uncertainty in the actual system, especially in the joint scheduling of multiple resources, it cannot fully consider the complementarity between resources; the linear budget uncertainty set (a convex polyhedron form of uncertainty set) considers the correlation between uncertainty variables, can effectively balance the prediction accuracy and model convexity, and is more suitable for the uncertainty set of power system optimization scheduling, but the existing budget constraint generation method often relies on experience, and it is difficult to obtain accurate constraint conditions with strong universality through objective data or algorithm, which may inevitably bring errors, thereby affecting the accuracy and effect of scheduling.

[0005] In summary, the existing technology has great limitations in describing the multi-dimensional uncertainty of multiple energy resources and making decisions in the multi-resource scheduling problem. In order to solve these problems, a budget uncertainty set generation method that can avoid human factor interference and handle the spatio-temporal coupling relationship, and a more adaptive decision rule are proposed, which are crucial for improving the safe, stable and economic operation of urban power grids. SUMMARY

[0006] The technical problem solved by the present application is to provide a data-driven urban power grid multi-stage operation scheduling method and system to solve the technical problem that the existing budget constraint generation method cannot reflect the spatio-temporal coupling relationship of multiple energy resources and the effectiveness is greatly affected by human parameter selection and setting.

[0007] The present application adopts the following technical solutions:

[0008] A data-driven urban power grid multi-stage operation scheduling method, comprising the following steps:

[0009] Establish a power distribution system coordinated scheduling problem mathematical model containing multiple energy sources;

[0010] Based on the obtained power distribution system coordinated scheduling problem mathematical model, a linear budget constraint generation method based on historical data is used to construct a budget uncertainty set;

[0011] Based on the obtained budget uncertainty set, a multi-stage robust optimization method based on implicit decision strategy is used to determine the coordinated scheduling scheme.

[0012] Preferably, the objective function of the power distribution system coordinated scheduling problem mathematical model is the total generation cost, the system operation constraints include power flow constraints, various boundary constraints, thermal power unit operation constraints, budget constraints and specific boundary conditions, and the uncertainty set of wind power output power uncertainty variables is composed of the above.

[0013] Preferably, the total generation cost includes the cost of purchasing / selling electricity from the main grid and the fuel cost of thermal power units, and the objective function is as follows:

[0014]

[0015] Where, is the time period is the active power transmission is the cost of purchasing / selling electricity from the main grid at time is the time period is the bus is the output power of the thermal power unit is the fuel cost at time, and the specific cost function can refer to existing research.

[0016] Preferably, the load balance constraint in the power flow constraint is:

[0017]

[0018]

[0019]

[0020]

[0021]

[0022]

[0023] where, denotes the branch from bus to bus , denote the inbound and outbound branch sets of bus , are the active and reactive power on branch in period , are the active and reactive net injection power on bus in period , are the active and reactive transmission power on bus in period , are the active and reactive load demand on bus in period , are the thermal, wind, PV output power and renewable curtailment on bus in period , is the energy storage level on bus in period , is the voltage squared value on bus in period ;

[0024] Voltage security constraints in power flow constraints:

[0025]

[0026] where, are the lower and upper bounds of voltage on bus in period ;

[0027] Transmission capacity constraints in power flow constraints:

[0028]

[0029] where, is the maximum apparent power capacity of branch ;

[0030] Bounds constraints on active and reactive transmission power:

[0031]

[0032] wherein, are lower and upper bounds of active transmission power, are lower and upper bounds of reactive transmission power;

[0033] Energy storage level limits and charge-discharge level limits of the energy storage system:

[0034]

[0035]

[0036] wherein, wherein are lower and upper bounds of energy storage level, are maximum charge and discharge capabilities of the bus ;

[0037] Renewable energy curtailment constraints:

[0038]

[0039] Boundary constraints of reactive generation power:

[0040]

[0041] wherein, are upper and lower bounds of reactive generation power;

[0042] Generation capacity constraints, ramping constraints and minimum start / stop time constraints:

[0043]

[0044]

[0045]

[0046] wherein, are time periods are start-stop decision variables of the thermal generator units on the bus , are upper and lower bounds of active generation power, are ramping rate upper and lower bounds of the thermal generator units on the bus , are sets of nodes, are sets of time periods, are sets of feasible states of switching on and off.

[0047] Preferably, the budget uncertainty set is constructed by a linear budget constraint generation method based on historical data, specifically:

[0048] Initialize a box set based on historical data , which wraps all historical data points, representing the initial uncertainty range;

[0049] In the uncertainty set Select a vertex as far away from all historical data points as possible ; The vertex with the maximum distance from the historical data points is obtained by solving the following optimization problem;

[0050] By introducing auxiliary variables , the minimum distance between the vertex and each historical data is maximized, and it is reconstructed into a single-layer structure;

[0051] Find the cut plane between the vertex and all historical data with the maximum distance from the selected vertex, find the budget constraint closest to the historical data set;

[0052] Repeat until the generated budget uncertainty set reaches the expected number of cut planes, and the final generated budget set is used as the uncertainty constraint in subsequent system scheduling.

[0053] Preferably, the objective function of the optimization problem represents finding a vertex that maximizes the distance from the historical data, as follows:

[0054]

[0055] where is a variable describing the convex combination, is the selected vertex variable, is the th historical data, ;

[0056] The constraints of the optimization problem represent the convex combination of all historical data, the selected vertex should not be cut by the existing cut plane, and the limit must be a vertex, as follows:

[0057]

[0058]

[0059]

[0060] where and are the coefficients of the existing budget constraints, and are the box uncertainty set and the vertex set, respectively, is a set of convex combination coefficients.

[0061] Preferably, finding the closest budget constraint to the historical data set is described as an optimization problem as follows:

[0062]

[0063] s.t.

[0064]

[0065] where, and are the undetermined coefficients of the budget constraint currently being found, is the selected farthest vertex, is the th historical data, is the total number of historical data.

[0066] Preferably, the multi-stage robust optimization method based on implicit decision strategy is used to determine the coordinated scheduling scheme, which is specifically:

[0067] The mathematical model of the coordinated scheduling problem of the power distribution system is expressed in a compressed form;

[0068] According to the convex optimization and robust optimization theory, the feasibility of the decision is ensured by optimizing the robust decision space;

[0069] Before the uncertainty is observed, the pre-optimization feasible decision space is used to solve the following scheduling problem using the constraint generation method;

[0070] After the uncertainty is observed, the decision is optimized by the rolling horizon method to obtain an optimization model.

[0071] Preferably, the optimization model is as follows:

[0072]

[0073] s.t.

[0074]

[0075]

[0076] where, is the current stage, is the uncertainty observation value of the current stage, is the expected prediction value in the future, is the cost of the time period, is the cost of the t time period, and is t a period coefficient matrix, is t a column vector of a period, is a state of a current period, and is t a lower bound and an upper bound of a feasible region of a period.

[0077] In a second aspect, an embodiment of the present application provides a data-driven multi-stage operation scheduling system for urban power grid, comprising:

[0078] a construction module, which establishes a mathematical model of coordinated scheduling problem of power distribution system containing multiple energy sources;

[0079] a set module, which, based on the obtained mathematical model of coordinated scheduling problem of power distribution system, constructs a budget uncertainty set by using a linear budget constraint generation method based on historical data;

[0080] a scheduling module, which, based on the obtained budget uncertainty set, determines a coordinated scheduling scheme by using a multi-stage robust optimization method based on implicit decision strategy.

[0081] In a third aspect, a computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above data-driven multi-stage operation scheduling method for urban power grid when executing the computer program.

[0082] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium comprising a computer program, and the computer program implements the steps of the above data-driven multi-stage operation scheduling method for urban power grid when executed by a processor.

[0083] In a fifth aspect, a chip comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above data-driven multi-stage operation scheduling method for urban power grid when executing the computer program.

[0084] In a sixth aspect, an embodiment of the present application provides an electronic device comprising a computer program, and the computer program implements the steps of the above data-driven multi-stage operation scheduling method for urban power grid when executed by the electronic device.

[0085] Compared with the prior art, the present application has at least the following beneficial effects:

[0086] The application discloses a data-driven multi-stage operation scheduling method for an urban power grid, and relates to the technical field of power grid operation scheduling.

[0087] Further, the power distribution system coordination scheduling problem mathematical model selects total power generation cost as a target function, which is for the consideration of economic and low-carbon operation of the power grid; power flow constraints including load balance constraints, voltage safety constraints and transmission capacity constraints are for the safety of line transmission; various boundary constraints including transmission power, energy storage systems and renewable energy curtailment are for the safety of operation of various devices and full use of renewable energy; thermal power unit operation constraints including power generation capacity constraints, climbing constraints and minimum start / stop time constraints are for the safety of operation of thermal power units; and the uncertainty set composed of budget constraints and specific boundary conditions limits the possible range of uncertain variables such as wind power and photovoltaic power. The mathematical model composed of the above target function and constraints accurately describes the power distribution system coordination scheduling problem and is a prerequisite for obtaining a reliable scheduling scheme.

[0088] Further, the linear budget constraint generation method based on historical data is used to construct the budget uncertainty set, which can avoid the problem that the traditional budget uncertainty set is usually obtained based on experience and is difficult to accurately describe the uncertainty of renewable energy output and the inherent space-time coupling relationship. In addition, the budget constraint iteration generation method based on historical data is computationally feasible, and by setting an initial box set, selecting the farthest vertex and optimizing the cutting plane, a cutting plane that can cut off as large a volume as possible from the original box set is constructed every time, and after multiple iterations of solving relatively simple optimization problems, the budget constraint that can effectively improve the accuracy of the uncertainty set is obtained, and the difficulty of solving high-dimensional irregular convex hulls is effectively avoided.

[0089] Further, the budget-constrained iterative generation method based on historical data greatly simplifies the solution of the budget convex polyhedron uncertain set, but due to the large number of vertices of the high-dimensional box set, it is impossible to completely traverse, and it is necessary to find an optimal vertex that can cut off as much invalid volume as possible. Based on the thought that the minimum distance of the vertex to all data in the historical data set can represent the expectation of the volume that can be cut off by the vertex, the present application sets the objective function of the vertex optimization problem to maximize the minimum distance of the vertex to the historical data set.

[0090] Further, the size of the distance from the vertex to the cutting plane can represent the size of the volume cut from the original box set. Therefore, after selecting the vertex, finding the budget constraint closest to the historical data set is equivalent to finding the cutting plane that cuts off the largest volume of the original box set, which can be converted into the following optimization problem: the objective function represents the maximum distance between the cutting plane and the selected vertex; the constraint condition represents that the cutting plane should cut off the selected vertex, but not all the historical data points.

[0091] Further, the explicit decision strategy in the traditional method needs to define the decision function in advance, which is easy to cause errors due to the inconsistency between the preset decision strategy and the optimal decision function; the present application adopts a multi-stage robust optimization method based on an implicit decision strategy, which does not preset the decision strategy, but adjusts the decision adaptively through a rolling optimization method: before observing the uncertainty, the feasible decision space is pre-optimized according to the generated uncertainty set; after observing the uncertainty, the decision is further optimized through a rolling horizon method. The above method effectively improves the optimization performance of power system scheduling under uncertainty, and realizes the flexibility and robustness of multi-stage decision-making.

[0092] It can be understood that the beneficial effects of the above-mentioned second aspect to sixth aspect can be referred to the related description in the first aspect, which will not be repeated here.

[0093] In summary, the present application can more accurately express the spatio-temporal coupling relationship between different renewable energies, and as much as possible to reduce or avoid the setting of artificial parameters; and on this basis, a multi-stage robust optimization method based on an implicit decision strategy is designed to realize the adaptive optimization of the coordinated scheduling of multiple resources and devices based on a rolling horizon method.

[0094] The technical solutions of the present application will be further described in detail below with the help of the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0095] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly introduced as follows. Obviously, the drawings described below only represent some of the embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0096] Figure 1 Data-driven city grid multi-stage low-carbon economic operation technical flowchart;

[0097] Figure 2 Data-driven budget constraint generation algorithm flowchart;

[0098] Figure 3 IEEE 33 bus system structure diagram for testing;

[0099] Figure 4 Historical daily output curve diagram of photovoltaic and wind power;

[0100] Figure 5 Budget constraint coefficient schematic diagram;

[0101] Figure 6 Schematic diagram of a computer device provided by an embodiment of the present application;

[0102] Figure 7 Block diagram of a chip provided by an embodiment of the present application. DETAILED DESCRIPTION

[0103] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort fall within the protection scope of the present application.

[0104] In the description of the present application, it should be understood that the terms "include" and "contain" indicate the existence of described features, whole, steps, operations, elements and / or components, but do not exclude the existence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0105] It should also be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0106] It should be further understood that the term "and / or" as used herein refers to a combination of one or more of the associated listed items, and all possible combinations, and includes these combinations, for example, A and / or B can mean: A alone, A and B together, and B alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects.

[0107] It should be understood that, although the terms first, second, third, etc. can be used in embodiments of the present application to describe a certain range, etc., these ranges should not be limited to these terms. These terms are only used to distinguish the ranges from each other. For example, the first preset range can also be referred to as the second preset range, and similarly, the second preset range can also be referred to as the first preset range without departing from the scope of the embodiments of the present application.

[0108] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if it is determined" or "if (a stated condition or event) is detected" can be interpreted to mean "when it is determined" or "in response to determining" or "when (a stated condition or event) is detected" or "in response to detecting (a stated condition or event)".

[0109] Various structural diagrams according to the disclosed embodiments of the present application are shown in the accompanying drawings. These drawings are not drawn to scale, in which certain details are exaggerated for the purpose of clarity and certain details can be omitted. The shapes of various regions, layers and their relative sizes and positional relationships shown in the drawings are only exemplary, and in actuality, they can deviate due to manufacturing tolerances or technical limitations, and a person skilled in the art can additionally design regions / layers with different shapes, sizes and relative positions according to actual needs.

[0110] The present application provides a data-driven urban power grid multi-stage operation scheduling method, establishes a basic mathematical model of power distribution system coordinated scheduling problem, including objective function, constraint condition and formula expression of budget uncertainty set; then adopts the budget constraint generation method based on data driving proposed in the present application, and constructs the budget uncertainty set based on the historical data of renewable energy; finally, according to the multi-stage robust optimization method based on implicit decision strategy proposed in the present application, the optimal power grid coordinated scheduling scheme is obtained; the present application can improve the prediction accuracy of renewable energy with uncertainty such as wind power, expand the full-scenario feasible interval of power grid scheduling, and thus efficiently obtain a low-carbon operation scheduling scheme of power system with high renewable energy utilization rate.

[0111] Please refer to Figure 1The application is a data-driven urban power grid multi-stage operation scheduling method, comprising the following steps:

[0112] S1, establishing a mathematical model of the system;

[0113] The mathematical model of the system mainly includes an objective function, system operation constraints and budget constraints, wherein the objective function is total power generation cost, the system operation constraints include power flow constraints, various boundary constraints, thermal power unit operation constraints and the like, and the budget constraints usually and specific boundary conditions jointly constitute an uncertainty set of uncertain variables such as wind power output.

[0114] S101, the objective function;

[0115] For such power system scheduling problems, the objective function used in the application is to minimize the total power generation cost. Specifically, the total power generation cost includes the cost of power purchase / sale from the main grid and the fuel cost of the thermal power unit. The objective function expression is as follows:

[0116]

[0117] wherein, is the power purchase / sale cost from the main grid at time is the active power transmission at time is the fuel cost of the thermal power unit at time is the total bus voltage at time is the output power of the thermal power unit at time is the fuel cost at time The specific cost function can refer to the existing research.

[0118] S102, system operation constraints;

[0119] The system operation constraints include power flow constraints for ensuring the safety of line transmission, various boundary constraints for ensuring the safety and economy of equipment operation, and thermal power unit operation constraints.

[0120] The load balance constraint in the power flow constraint:

[0121]

[0122]

[0123]

[0124]

[0125]

[0126]

[0127] wherein, denote the branches from bus , denote the inbound and outbound branch sets of bus denote the active and reactive power on branch denote the active and reactive net injection power on bus denote the active and reactive transmission power on bus denote the active and reactive load demand on bus denote the active and reactive output power of thermal, wind, and PV generation on bus denote the active and reactive renewable curtailment on bus denote the energy storage level on bus denote the voltage squared value on bus It should be noted that since each bus has only one upstream node in radial distribution networks, there is only one element. The present invention represents the balancing bus as bus 0 and connects it to the main grid.

[0128] Voltage security constraints in power flow constraints:

[0129]

[0130] where are the lower and upper bounds of voltage on bus Transmission capacity constraints in power flow constraints:

[0131]

[0132]

[0133] where is the maximum apparent power capacity of branch Bounds constraints on active and reactive transmission power:

[0134]

[0135]

[0136] where,​​​​​​​​​​​​​​​​​​ lower and upper bounds of active transmission power, lower and upper bounds of reactive transmission power.

[0137] energy storage level limits and charge / discharge level limits of energy storage system:

[0138]

[0139]

[0140] wherein, wherein lower and upper bounds of energy storage level, maximum charge / discharge capability of bus .

[0141] renewable energy curtailment constraint, i.e., the sum of output power of wind power and photovoltaic power at least reaches renewable energy reduction requirement, specifically as follows:

[0142]

[0143] reactive power generation power bound constraint:

[0144]

[0145] wherein, upper and lower bounds of reactive power generation power.

[0146] operation constraints of thermal power units, including power generation capacity constraints, climbing constraints and minimum start / stop time constraints, specifically as follows:

[0147]

[0148]

[0149]

[0150] wherein, time period bus start / stop decision variable of thermal power unit, upper and lower bounds of active power generation power, climbing rate upper and lower bounds of thermal power unit .

[0151] S103, budget constraint;

[0152] The budget uncertainty set is used to describe Solving the convex polyhedron-form budget uncertainty set is essentially equivalent to solving the linear budget constraint. For the sake of computational feasibility, the budget constraint is usually pre-defined empirically.

[0153] For example, a widely used representation of budget uncertainty set is as follows:

[0154]

[0155] where, is the budget value, is the budget deviation.

[0156] Obviously, the above budget uncertainty set is generated empirically and only describes part of the spatial correlation, and cannot reflect the spatio-temporal coupling relationship.

[0157] Therefore, the present application proposes a new data-driven budget constraint generation method to construct a more accurate budget uncertainty set to reflect the spatio-temporal coupling relationship between uncertain variables, thereby improving the safety and economy of power system operation.

[0158] S2, a data-driven budget constraint generation method;

[0159] The present application proposes a data-driven budget constraint generation method to solve the problem that the traditional budget uncertainty set is usually obtained based on experience and is difficult to accurately describe the uncertainty of renewable energy output. The method analyzes the historical data of renewable energy and constructs a polyhedron set (i.e. budget uncertainty set) to wrap all historical data and cover potential uncertainty scenarios.

[0160] To cope with the computational difficulty brought by the increase of dimensions, the present application proposes an iterative generation method based on historical data, that is, in each iteration process, a cutting plane is generated to gradually reduce the range of the uncertainty set until the accuracy requirement is met. Combined with Figure 2 The two-dimensional example shown in the figure is used to describe the specific process:

[0161] First, initialize a box set based on historical data to wrap all historical data points, representing the initial uncertainty range.

[0162] Then, select a vertex as far as possible from all historical data points in the uncertainty set . The vertex farthest from the historical data points can be obtained by solving the following optimization problem.

[0163] The objective function of the optimization problem represents finding a vertex ​To maximize its distance from historical data, as follows:

[0164]

[0165] in, These are variables that describe convex combinations. It is the selected vertex variable. It is the first historical data, .

[0166] The constraints of the optimization problem are, in order, convex combinations of all historical data, the selected vertex should not be cut by an existing cut plane, and restrictions. It must be a vertex, as follows:

[0167]

[0168]

[0169]

[0170] in, and It is a coefficient of the existing budget constraint. and Let them represent the box-shaped uncertainty set and the vertex set, respectively.

[0171] However, the above optimization problem has a max-min structure and is difficult to solve directly; this invention introduces auxiliary variables. This maximizes the minimum distance between each vertex and every historical data point, reconstructing it into a single-layer structure for easier solution; the single-layer structure is as follows:

[0172]

[0173] st

[0174]

[0175]

[0176] Selected Vertex Then, the cutting plane (i.e., the budget constraint) is further optimized to remove invalid regions that do not contain historical data as much as possible.

[0177] The main idea of ​​cutting plane optimization is to optimize the cutting plane at the vertices. and all historical data find a cut plane with the largest distance to the selected vertex, in other words, find the budget constraint that is closest to the historical data set. The above idea can be described as the following optimization problem:

[0178]

[0179] s.t.

[0180]

[0181] The above process is repeated until the generated budget uncertainty set is accurate enough, or the expected number of cut planes is reached. At this time, the final generated budget set can more accurately describe the historical data distribution, and can be used as an uncertainty constraint in subsequent system scheduling.

[0182] Compared with the traditional box set, the budget uncertainty set generated by the present application has significant advantages in accuracy and computational efficiency. On the one hand, the data-driven method can more comprehensively capture the uncertainty distribution characteristics; on the other hand, solving the optimization problem of vertex and cut plane also avoids the computational difficulty of high-dimensional convex hull solving, thereby improving the computational feasibility.

[0183] S3, a multi-stage robust optimization method based on implicit decision strategy;

[0184] After constructing the budget uncertainty set, the present application proposes a multi-stage robust optimization method based on implicit decision strategy to realize coordinated scheduling. Unlike the explicit decision strategy in traditional methods, the implicit decision strategy does not need to define an explicit decision function in advance, but adjusts the decision adaptively through rolling optimization to cope with uncertainty scenarios. This method can avoid errors caused by the inconsistency between the preset decision strategy and the optimal decision function, thereby improving the optimization performance.

[0185] To simplify the expression, the system model in step S1 is uniformly represented in the following compressed form:

[0186]

[0187]

[0188] wherein, is a decision variable, is an uncertainty variable. In order to ensure the computational efficiency of the model, all nonlinear functions can be linearized.

[0189] According to the theory of convex optimization and robust optimization, if all vertices in the uncertainty set have feasible solutions, then any scenario in the uncertainty set has a feasible solution. Therefore, the feasibility of the decision can be guaranteed by optimizing the robust decision space. There is a proposition that if the feasible decision space satisfies the constraints

[0190]

[0191]

[0192] then there exists a set of which can be constructed according to the following formula to achieve a feasible solution for any possible uncertainty realization.

[0193]

[0194] Based on the above proposition, the following implicit decision strategy can be proposed:

[0195] First, before observing the uncertainty, the feasible decision space is pre-optimized. It should be noted that the size of the vertex is usually large. In order to simplify the calculation, the constraint generation method is usually used to solve the following scheduling problem.

[0196]

[0197] s.t.

[0198]

[0199] Then, after observing the uncertainty, the decision can be optimized by the receding horizon method, and the specific optimization model is as follows:

[0200]

[0201] s.t.

[0202]

[0203]

[0204] where represents the current stage, represents the uncertainty observation value of the current stage, represents the expected prediction value in the future.

[0205] The multi-stage robust optimization method based on the implicit decision strategy effectively improves the optimization performance of power system scheduling under uncertainty scenarios, and realizes the flexibility and robustness of multi-stage decision-making.

[0206] Those skilled in the art can understand that each aspect of the present application can be implemented as a system, a method or a program product. Therefore, each aspect of the present application can be specifically implemented as follows: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combined with hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "platform" here.

[0207] In another embodiment of the present application, a data-driven multi-stage operation scheduling system for urban power grid is provided, which can be used to implement the data-driven multi-stage operation scheduling method for urban power grid. Specifically, the data-driven multi-stage operation scheduling system for urban power grid comprises a construction module, a set module and a scheduling module.

[0208] The construction module establishes a mathematical model of the coordinated scheduling problem of the power distribution system containing multiple energies.

[0209] The set module uses a linear budget constraint generation method based on historical data to construct a budget uncertainty set based on the obtained mathematical model of the coordinated scheduling problem of the power distribution system.

[0210] The scheduling module determines a coordinated scheduling scheme by using a multi-stage robust optimization method based on an implicit decision strategy based on the obtained budget uncertainty set.

[0211] In another embodiment of the present application, a terminal device is provided, which comprises a processor and a memory. The memory is used to store a computer program, the computer program comprises program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, graphics processing units (GPUs), tensor processing units (TPUs), digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement a corresponding method flow or a corresponding function. The processor in the embodiment of the present application can be used for the operation of the data-driven multi-stage operation scheduling method for urban power grid, which comprises:

[0212] A mathematical model of a coordinated scheduling problem of a power distribution system containing multiple energy sources is established; based on the obtained mathematical model of the coordinated scheduling problem of the power distribution system, a linear budget constraint generation method based on historical data is used to construct a budget uncertainty set; based on the obtained budget uncertainty set, a multi-stage robust optimization method based on an implicit decision strategy is used to determine a coordinated scheduling scheme.

[0213] Please refer to Figure 6 , the terminal device is a computer device, the computer device 60 of the embodiment includes a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61, and the computer program 63 implements the data-driven urban power grid multi-stage operation scheduling method in the embodiment when executed by the processor 61. To avoid repetition, details are not repeated here. Alternatively, the computer program 63 implements the functions of each model / unit in the data-driven urban power grid multi-stage operation scheduling system of the embodiment when executed by the processor 61. To avoid repetition, details are not repeated here.

[0214] The computer device 60 can be a desktop computer, a notebook computer, a palm computer, and a cloud server, etc. The computer device 60 can include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art can understand that Figure 6 The computer device 60 is only an example and does not constitute a limitation on the computer device 60, and can include more or fewer components than shown, or combine certain components, or different components, for example, the computer device can also include an input / output device, a network access device, a bus, etc.

[0215] The processor 61 can be a central processing unit (CPU), and can also be other general-purpose processors, graphics processing units (GPUs), tensor processing units (TPUs), digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0216] The memory 62 can be an internal storage unit of the computer device 60, such as a hard disk or a memory of the computer device 60. The memory 62 can also be an external storage device of the computer device 60, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, and the like.

[0217] Further, the memory 62 can include both an internal storage unit and an external storage device of the computer device 60. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 can also be used to temporarily store data that has been output or will be output.

[0218] Referring to Figure 7 , the terminal device is an electronic device 600 in the form of a general computing device. Components of the electronic device can include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, and the like.

[0219] The storage unit stores program codes that can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present application described in the method part of the present specification. For example, the processing unit 610 can perform the steps as shown in Figure 1 .

[0220] The storage unit 620 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 6201 and / or a cache memory 6202, and can further include a read-only memory (ROM) 6203.

[0221] The storage unit 620 can further include a program / utility 6204 having a set of (at least one) program modules 6205, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or a combination can include implementation of a network environment.

[0222] The bus 630 can be one or more of several types of bus structures, including a storage unit bus or storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit bus, or a local bus using any of a variety of bus architectures.

[0223] The electronic device 600 can also communicate with one or more external devices 700 such as a keyboard or pointing device, a Bluetooth device, or a database, and / or one or more devices that enable a user to interact with the electronic device 600 and / or one or more devices (e.g., a router, a modem, a server, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication can occur via an input / output (I / O) interface 650. Still yet, the electronic device 600 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, through a network adapter 660. The network adapter 660 can communicate with the other components of the electronic device 600 via the bus 630. It should be understood that, although not shown explicitly, other hardware and / or software components could be used in conjunction with the electronic device 600. These include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0224] In still another embodiment of the present application, the present application also provides a storage medium, specifically a computer readable storage medium, which is a memory device in a terminal device, used for storing programs and data. It should be understood that the computer readable storage medium herein can include a built-in storage medium in the terminal device, and of course can also include an extended storage medium supported by the terminal device. The computer readable storage medium provides a storage space, which stores an operating system of the terminal. In addition, one or more instructions adapted to be loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more computer programs. It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory.

[0225] The one or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the data-driven multi-stage operation scheduling method of the urban power grid in the above embodiments. The one or more instructions stored in the computer readable storage medium are loaded and executed by the processor to perform the following steps:

[0226] A mathematical model of a coordinated scheduling problem of a power distribution system containing multiple energy sources is established; based on the obtained mathematical model of the coordinated scheduling problem of the power distribution system, a linear budget constraint generation method based on historical data is used to construct a budget uncertainty set; based on the obtained budget uncertainty set, a multi-stage robust optimization method based on an implicit decision strategy is used to determine a coordinated scheduling scheme.

[0227] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0228] A numerical test was performed on a modified IEEE 33-bus system, which includes thermal power, wind power, solar power and energy storage devices, and the specific structure is as shown in Figure 3

[0229] The system contains a balanced bus with transmission power limit [-3, 3] MW, and the average expected load demand is 2.96 MW (peak 3.75 MW, minimum 1.98 MW). The total installed capacity of wind power (WT) and photovoltaic (PV) is 2 MW, the maximum power generation capacity of the thermal power unit is 1 MW, and the energy capacity of the energy storage is 8 MWh, and the rated charge and discharge power is 4 MW. The voltage of the balanced bus is 1.0 p.u., and the voltage limit of the remaining buses is [0.9, 1.1] p.u.. The historical daily output curves of Figure 4 The historical daily output curves of photovoltaic and wind power (for one month).

[0230] Using the above parameters, the implicit decision rule based on the budget uncertainty set proposed in the present application is tested and compared with existing methods, including the LDR method and the scenario-based stochastic optimization method. In addition, assuming that all uncertainty observations are completely known, the upper bound optimality gap approximation based on complete knowledge is also tested. The solution based on complete knowledge can provide an upper bound approximation of the theoretical optimal solution, that is, the solution obtained by any method will not be better than (at most equal to) the solution based on complete knowledge.

[0231] First, the budget uncertainty set generated by the method proposed in the present application is as shown in Figure 5 Figure 5 It is a 48-dimensional embodiment (one photovoltaic power station and one wind turbine, each with 24 time periods). The lighter the color, the larger the absolute value of the coefficient in the budget constraint, that is, the stronger the correlation. From this, two main conclusions can be drawn: (1) there is strong correlation between consecutive time periods; (2) the spatio-temporal coupling relationship is not symmetric. This means that the existing empirical-based budget constraint is not very suitable.​​

[0232] Table 1 Simulation results of different methods

[0233]

[0234] To further test the performance of the method proposed in the application, 500 Monte Carlo simulations are performed to estimate the expected operating cost of different methods, and the results are shown in Table 1. It can be seen from the table that the average cost of the method proposed in the application is lower than that of the LDR method and the scenario-based stochastic optimization method. In addition, the optimality gap of the method proposed in the application with the solution based on complete knowledge is very small, which indicates that the optimality gap of the proposed method is less than 0.46%, verifying the effectiveness of the method proposed in the application.

[0235] In summary, the data-driven multi-stage operation scheduling method and system for urban power grids of the application effectively solve the problem that the budget constraint generation in the prior art cannot accurately reflect the spatio-temporal coupling relationship of multiple energy sources and the problem that the influence of artificial parameter selection is too large. Through the linear budget constraint generation method based on historical data and the multi-stage robust optimization method based on implicit decision strategy, the application improves the prediction accuracy of uncertain information such as wind power and photovoltaic output power, improves the optimization performance of the power grid scheduling scheme, and enhances the adaptability and robustness of the decision. The application first establishes a coordinated scheduling mathematical model containing multiple constraints to accurately describe the power grid scheduling problem; then, the budget uncertainty set is generated based on historical data to avoid the limitations of traditional methods; finally, the implicit decision strategy is used to adaptively adjust the decision through the rolling horizon to ensure the optimization performance under different uncertainty scenarios. The results of application to the embodiments show that the method of the application is superior to existing methods in terms of average operating cost, and the optimality gap is very small, verifying its effectiveness. The application improves the flexibility and reliability of power grid scheduling by accurately modeling the problem, especially greatly improving the generation of uncertainty sets, and adaptively optimizing the design of scheduling scheme decisions, and has important application value.

[0236] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0237] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0238] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0239] In the embodiments provided by the present application, it should be understood that the disclosed devices / terminals and methods can be implemented by other ways. For example, the device / terminal embodiments described above are only schematic, and the division of the modules or units is only a logical function division, and there can be another division way in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection between each displayed or discussed unit can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0240] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0241] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0242] The integrated module / unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer-readable storage medium. The computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms. The computer-readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the computer-readable medium can include or exclude contents according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0243] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices, and computer program products of embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks

[0244] These computer program instructions can also be stored in a computer-readable storage medium that can guide the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable storage medium produce a manufactured product including instruction devices that implement the functions specified in the flowcharts and / or block diagrams. Figure 1one or more processes and / or blocks Figure 1 the function specified in the one or more blocks.

[0245] These computer program instructions can also be loaded into computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable data processing devices to generate a computer-implemented process, so that the instructions executed on the computer or other programmable data processing devices provide a process for implementing the flow Figure 1 one or more processes and / or blocks Figure 1 the function specified in the one or more blocks.

[0246] The above is only to illustrate the technical idea of the present application, and cannot limit the protection scope of the present application. Any modification made according to the technical idea of the present application on the basis of the technical scheme falls within the protection scope of the claims of the present application.

Claims

1. A data-driven multi-stage operation and scheduling method for urban power grids, characterized in that, Includes the following steps: Establish a mathematical model for the coordinated scheduling problem of power distribution systems that include multiple energy sources; Based on the obtained mathematical model of the power distribution system coordination and scheduling problem, a budget uncertainty set is constructed using a linear budget constraint generation method based on historical data. Specifically, the construction of the budget uncertainty set using this method involves: Initialize a box set based on historical data. This is used to enclose all historical data points, representing the initial range of uncertainty; In the uncertain set Select a vertex that is as far away as possible from all historical data points. The vertex with the largest distance from historical data points is obtained by solving the following optimization problem. By introducing auxiliary variables This maximizes the minimum distance between the vertex and each historical data point, reconstructing a single-layer structure. At the farthest vertex and all historical data Find the cutting plane that has the largest distance to the selected vertex, and find the budget constraint that is closest to the historical dataset; Repeat this process until the generated budget uncertainty set reaches the expected number of cutting planes, and use the final generated budget set as an uncertainty constraint in subsequent system scheduling; The objective function of the optimization problem is to find a vertex. To maximize its distance from historical data, as follows: in, These are variables that describe convex combinations. It is the selected vertex variable. It is the first historical data, ; The constraints of the optimization problem are, in order, convex combinations of all historical data, the selected vertex should not be cut by an existing cutting plane, and restrictions. It must be a vertex, as follows: in, and These are the coefficients for the existing budget constraints. and These are the box-type uncertainty set and the vertex set, respectively. It is a set of convex combination coefficients; Finding the budget constraint that best matches the historical dataset can be described as the following optimization problem: s.t. in, and These are the undetermined coefficients for the budget constraint currently being sought. For the selected farthest vertex, For the first historical data, This represents the total number of historical data. Based on the obtained budget uncertainty set, a multi-stage robust optimization method based on implicit decision-making strategy is adopted to determine the coordination and scheduling scheme.

2. The data-driven multi-stage operation and scheduling method for urban power grids according to claim 1, characterized in that, The objective function of the mathematical model for the coordinated scheduling problem of the power distribution system is the total power generation cost. The system operation constraints include power flow constraints, various boundary constraints, thermal power unit operation constraints, budget constraints, and specific boundary conditions, which together constitute the uncertainty set of uncertain variables in the wind power output power.

3. The data-driven multi-stage operation and scheduling method for urban power grids according to claim 2, characterized in that, The total power generation cost includes the cost of purchasing / selling electricity from the main grid and the fuel cost of thermal power units. The objective function is as follows: in, For time period Active transmission is The cost of purchasing / selling electricity from the main grid at that time For time period bus The output power of the thermal power unit is fuel costs at that time For bus sets, For a set of time periods.

4. The data-driven multi-stage operation and scheduling method for urban power grids according to claim 2, characterized in that, Load balance constraints in power flow constraints: in, Indicates from the bus to bus branch , These represent the forward and reverse connections to the bus, respectively. The set of branches, Time periods Branches Active and reactive power on the surface Time periods bus Net active and reactive power injection on the surface Time periods bus Active and reactive power transmission on the surface Time periods bus The active and reactive load demands on the device, Time periods bus The output power of thermal power, wind power, photovoltaic power and renewable energy in the area has been reduced. For time period End bus On the energy storage level, For time period bus The square of the voltage across; Voltage safety constraints in power flow constraints: in, It is a time period bus The lower and upper bounds of the voltage; Transmission capacity constraints in power flow constraints: in, For branches Maximum apparent power capacity; Boundary constraints on active and reactive power transmission: in, These are the lower and upper bounds of the active power transmission capacity. These are the lower and upper bounds of reactive power transmission. Energy storage level limitations and charge / discharge level limitations of energy storage systems: in, These are the lower and upper bounds of energy storage levels. , For bus Maximum charging and discharging capacity; Renewable energy curtailment constraints: Boundary constraints on reactive power generation: in, This represents the upper and lower bounds of reactive power generation. Generation capacity constraints, ramp-up constraints, and minimum start / stop time constraints: in, For time period bus Variables for starting and stopping thermal power units , These represent the upper and lower bounds of active power generation. For bus Upper and lower limits of the climbing rate of the thermal power unit. For bus sets, For time period sets, This is the set of feasible states for powering on and off.

5. The data-driven multi-stage operation and scheduling method for urban power grids according to claim 1, characterized in that, A multi-stage robust optimization method based on implicit decision-making strategy is adopted to determine the specific coordination and scheduling scheme as follows: The mathematical model of the power distribution system coordination and scheduling problem is expressed in a compressed form; Based on convex optimization and robust optimization theories, the feasibility of decisions is ensured by optimizing the robust decision space; Before observing uncertainties, pre-optimize the feasible decision space and use constraint generation methods to solve the scheduling problem; After observing the uncertainty, the decision is optimized by using the rolling time-domain method to obtain the optimized model.

6. The data-driven multi-stage operation and scheduling method for urban power grids according to claim 5, characterized in that, The optimized model is as follows: s.t. in, For the current time period, These are uncertain observations for the current time period. This is a projected value for the future. for Cost of time period for t Time-of-use cost and for t Time period coefficient matrix for t The column vector of time periods, This represents the current state. and for t The lower and upper bounds of the feasible region for a given time period.

7. A data-driven multi-stage operation and dispatching system for urban power grids, characterized in that, include: Build modules to establish a mathematical model for the coordinated scheduling problem of power distribution systems that include multiple energy sources; The set module, based on the obtained mathematical model of the power distribution system coordination and scheduling problem, constructs a budget uncertainty set using a linear budget constraint generation method based on historical data. Specifically, the construction of the budget uncertainty set using this method involves: Initialize a box set based on historical data. This is used to enclose all historical data points, representing the initial range of uncertainty; In the uncertain set Select a vertex that is as far away as possible from all historical data points. The vertex with the largest distance from historical data points is obtained by solving the following optimization problem. By introducing auxiliary variables This maximizes the minimum distance between the vertex and each historical data point, reconstructing a single-layer structure. At the apex and all historical data Find the cutting plane that has the largest distance to the selected vertex, and find the budget constraint that is closest to the historical dataset; Repeat this process until the generated budget uncertainty set reaches the expected number of cutting planes, and use the final generated budget set as an uncertainty constraint in subsequent system scheduling; The objective function of the optimization problem is to find a vertex. To maximize its distance from historical data, as follows: in, These are variables that describe convex combinations. It is the selected vertex variable. It is the first historical data, ; The constraints of the optimization problem are, in order, convex combinations of all historical data, the selected vertex should not be cut by an existing cutting plane, and restrictions. It must be a vertex, as follows: in, and These are the coefficients for the existing budget constraints. and These are the box-type uncertainty set and the vertex set, respectively. It is a set of convex combination coefficients; Finding the budget constraint that best matches the historical dataset can be described as the following optimization problem: s.t. in, and These are the undetermined coefficients for the budget constraint currently being sought. For the selected farthest vertex, For the first historical data, This represents the total number of historical data. The scheduling module, based on the obtained budget uncertainty set, uses a multi-stage robust optimization method based on implicit decision-making strategy to determine the coordination and scheduling scheme.

Images