A method, apparatus, computer equipment, and storage medium for determining maintenance plans.

Abstract

This invention relates to the field of power system technology, specifically to a method, apparatus, computer equipment, and storage medium for determining maintenance plans. In this invention, by analyzing power flow without considering maintenance plans, the number of integer variables in the maintenance plan is effectively reduced, thus reducing the column size of the maintenance plan model. Simultaneously, when the maintenance plan model has no solution, a linear relaxation model is constructed. Lagrange multipliers are used to identify maintenance branch variables that affect power flow exceedance limits. Furthermore, because the linear model solves quickly, its impact on overall computation time is negligible. For cases where branch exceedances cannot be eliminated, short-term and certain degrees of exceedances are allowed, constructing flexible limit constraints to improve the model's convergence.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and more specifically to a method, apparatus, computer equipment, and storage medium for determining maintenance plans. Background Technology

[0002] In power system operation, equipment maintenance is a necessary step to ensure the long-term stable and reliable operation of the power grid. In existing technologies, maintenance plans are typically solved using mixed-integer programming models. These models involve a large number of integer variables related to maintenance scheduling (such as whether a branch is to be maintained during a certain period, the start and end times of the maintenance, etc.) and rely on specific software for solving them.

[0003] However, existing technologies have significant problems in practical applications. On the one hand, the large number of integer variables involved in maintenance plans leads to excessively large model sizes and extremely long solution times, making it difficult to meet the needs of rapid maintenance plan development in actual dispatching work. On the other hand, during maintenance, the power grid's transmission capacity decreases due to the shutdown of some equipment, significantly increasing the risk of power flow exceeding limits. However, existing models often require comprehensive and rigorous consideration of power flow constraints for all branches. This "indiscriminate" treatment of all branches not only further increases the complexity of the model but may also lead to convergence difficulties due to excessive constraints, making it impossible to obtain a feasible maintenance plan. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, computer equipment and storage medium for determining maintenance plans, in order to solve the problem that feasible maintenance plans cannot be obtained in the prior art.

[0005] In a first aspect, the present invention provides a method for determining a maintenance plan, the method comprising: determining the power flow of the power grid based on a power generation plan model without maintenance, and determining a set of branches with fixed maintenance times based on the power flow; using the set of branches with fixed maintenance times as constraints, establishing and solving an initial maintenance plan model with the objective function of minimizing total operating cost and maintenance deviation penalty; when the initial maintenance plan model has no solution, adding power flow over-limit penalty and power flow over-limit constraint to the initial maintenance plan model to obtain a feasibility relaxation model and solving it to obtain a relaxation solution; replacing integer variables in the feasibility relaxation model with continuous variables, and adding constraints on integer solutions in the relaxation solution to obtain a linear model, determining a set of critical branches based on the Lagrange multipliers of the constraints after solving the linear model; adding power flow over-limit penalty and elastic limit constraint considering elastic limits to the maintenance plan model, and using the set of branches with fixed maintenance times excluding the set of critical branches as constraints to obtain an optimized maintenance plan model, and solving it to obtain the maintenance plan.

[0006] In this invention, by analyzing power flow without considering maintenance plans, the number of integer variables in the maintenance plan is effectively reduced, thus decreasing the column size of the maintenance plan model. Simultaneously, when the maintenance plan model has no solution, a linear relaxation model is constructed. Lagrange multipliers are used to identify maintenance branch variables that affect power flow exceedance limits. Furthermore, because the linear model solves quickly, its impact on overall computation time is negligible. For cases where branch exceedances cannot be eliminated, short-term and certain degrees of exceedances are allowed, constructing flexible limit constraints to improve model convergence.

[0007] In one optional implementation, the power flow is determined based on the power generation planning model without maintenance, including: using the minimum sum of unit operating costs and start-up and shutdown costs as the objective function; constructing constraint conditions based on unit minimum start-up and shutdown time constraints, unit output constraints, node power balance constraints, and branch power flow constraints; constructing a power generation planning model based on the objective function and constraint conditions; and solving the power generation planning model to obtain the power flow results.

[0008] In this invention, by constructing a power generation planning model with the goal of minimizing costs and covering multiple constraints to solve the power grid flow, the operation schedule of generating units can be accurately optimized. Under the constraints of generating units and the network, the economical and efficient operation of the power grid is guaranteed, and accurate power flow data is provided for the formulation of subsequent maintenance plans.

[0009] In one optional implementation, determining the set of branches with fixed maintenance times based on the power grid flow includes: acquiring the power flow of each branch in the power grid flow; and determining the set of branches with fixed maintenance times based on whether the power flow of each branch is within the power flow limit.

[0010] In this invention, the set of branches with fixed maintenance times is determined based on the power flow of the power grid. By obtaining the power flow of each branch and verifying whether it is within the limit, branches with sufficient power flow and maintenance that will not affect the safety of the power grid can be accurately screened, thereby determining the fixed maintenance period in advance and reducing the column size of the maintenance plan model.

[0011] In one optional implementation, the set of branches with fixed maintenance times is used as a constraint condition, and an initial maintenance plan model is established and solved with the objective function of minimizing the total operating cost and maintenance deviation penalty. This includes: using the minimum sum of the total operating cost and maintenance deviation penalty as the objective function, where the total operating cost is the sum of the unit operating cost and start-up / shutdown cost, and the maintenance deviation penalty is the deviation between the initial maintenance plan and the actual maintenance status; using constraints such as minimum unit start-up / shutdown time, unit output, branch power flow, node power balance considering branch maintenance status, project duration, continuous maintenance, mutually exclusive maintenance, maintenance quantity, and the set of branches with fixed maintenance times as constraints; and constructing and solving the initial maintenance plan model based on the objective function and constraints.

[0012] In this invention, when constructing the initial maintenance plan model, the goal is to minimize the total operating cost and maintenance deviation penalty. This approach can take into account the unit's operating costs and ensure that the deviation penalty is consistent with the actual maintenance. At the same time, multi-dimensional constraints (unit, branch, maintenance rules, etc.) are set to ensure the feasibility of the plan.

[0013] In an optional implementation, when the initial maintenance plan model has no solution, power flow violation penalties and constraints are added to the initial maintenance plan model to obtain a feasibility relaxation model and solve for the relaxed solution. This includes: when the initial maintenance plan model has no solution, using the minimum sum of total operating cost, maintenance deviation penalty, and power flow violation penalty as the objective function; using constraints such as minimum unit start-up and shutdown time constraints, unit output constraints, branch power flow constraints considering power flow violation, project duration constraints, continuous maintenance constraints, mutually exclusive maintenance constraints, maintenance quantity constraints, and the set of branches with fixed maintenance time as constraints; constructing a feasibility relaxation model based on the objective function and constraints, and solving for the relaxed solution.

[0014] In this invention, when the initial maintenance plan model has no solution, a feasible relaxation model is constructed by introducing power flow violation penalty and constraint. This model can break through strict constraints, explore feasible solutions through reasonable "relaxation", and provide a data basis for determining power flow violation branches.

[0015] In one optional implementation, the constraints of the integer solution include unit start-up and shutdown state constraints, branch maintenance state constraints, and maintenance state change constraints. The key branch set is determined based on the Lagrange multipliers of the constraints after solving the linear model, including: solving the linear model to determine the Lagrange multipliers of the branch maintenance state constraints; and constructing the key branch set based on the branches whose Lagrange multipliers are greater than zero.

[0016] In this invention, the use of Lagrange multipliers for branch selection can focus on branches that have a significant impact on power flow over-limit.

[0017] In one optional implementation, the maintenance plan model is supplemented with power flow violation penalties and flexible limit constraints that consider flexible limits. The set of branches in the set of branches with fixed maintenance times, excluding the set of critical branches, is used as a constraint condition to obtain an optimized maintenance plan model. Solving this model yields the maintenance plan, which includes: using the minimum sum of total operating cost, maintenance deviation penalty, and power flow violation penalty considering flexible limits as the objective function; using constraints such as minimum unit start-up and shutdown time constraints, unit output constraints, branch power flow constraints considering flexible limits, project duration constraints, continuous maintenance constraints, mutually exclusive maintenance constraints, maintenance quantity constraints, and the set of branches in the set of branches with fixed maintenance times, excluding the set of critical branches, as constraints; constructing an optimized maintenance plan model based on the objective function and constraints, and solving this model to obtain the maintenance plan.

[0018] This invention, by introducing flexible limits and related penalties and constraints, optimizes the objective function and constraints, thereby enhancing the flexibility of maintenance plans while ensuring power grid safety. By eliminating critical branches and focusing on remaining branches, it utilizes the results of previous critical branch identification and balances costs and over-limit risks through a flexible mechanism. This helps to formulate more realistic, economical, and safe maintenance plans, improving the scientific rigor and feasibility of power grid operation and maintenance decisions.

[0019] Secondly, the present invention provides a maintenance plan determination device, the device comprising: a maintenance time fixing module, used to determine the power flow based on a power generation plan model without maintenance, and to determine a set of branches with fixed maintenance times based on the power flow; an initial maintenance plan determination module, used to establish and solve an initial maintenance plan model with the set of branches with fixed maintenance times as constraints, and with the objective function of minimizing total operating cost and maintenance deviation penalty; and a feasibility relaxation model determination module, used to add power flow over-limit penalty and power flow over-limit constraint to the initial maintenance plan model when the initial maintenance plan model has no solution. The system employs a first-order constraint mechanism to obtain a feasibility relaxation model and solve for the relaxation solution. A second-order constraint mechanism is used to replace integer variables in the feasibility relaxation model with continuous variables and add constraints on integer solutions in the relaxation solution to obtain a linear model. Based on the Lagrange multipliers of the variables obtained from the linear model, the system determines the set of critical branches. A third-order constraint mechanism is used to add power flow violation penalties and elastic limit constraints to the maintenance plan model, and remove the set of critical branches from the set of branches with fixed maintenance times as constraints to obtain an optimized maintenance plan model. Finally, the system solves for the maintenance plan.

[0020] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the maintenance plan determination method of the first aspect or any corresponding embodiment described above.

[0021] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the maintenance plan determination method of the first aspect or any corresponding embodiment thereof.

[0022] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the maintenance plan determination method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating the maintenance plan determination method according to an embodiment of the present invention;

[0025] Figure 2 This is a flowchart illustrating another maintenance plan determination method according to an embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram showing the power variation of a branch at different time periods when different methods are used according to embodiments of the present invention;

[0027] Figure 4 This is a structural block diagram of a maintenance plan determination device according to an embodiment of the present invention;

[0028] Figure 5 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] According to an embodiment of the present invention, a method for determining a maintenance plan is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This embodiment provides a method for determining a maintenance plan, which can be used for electronic devices such as computers, mobile phones, and tablets. Figure 1 This is a flowchart of a maintenance plan determination method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0032] Step S101: Determine the power flow based on the power generation plan model without maintenance, and determine the set of branches with fixed maintenance times based on the power flow. Specifically, by analyzing the power flow, the set of branches with fixed maintenance times is first determined, thereby reducing the relevant variables in the maintenance plan. The power flow refers to the flow state of electricity in each branch of the power grid, including the magnitude and direction of active and reactive power transmitted in the branches. The power transmitted in the branches is related to unit output, load distribution, and branch network topology. Therefore, a power generation plan model can be constructed using unit output, load forecasting, and branch network topology, and the power flow can be determined using this model.

[0033] The power flow determined by the generation planning model includes the power flow results of each branch (branch transmission power). By analyzing these results, a preliminary set of branches with fixed maintenance times is determined. This set of branches with fixed maintenance times can be understood as those whose maintenance times are predetermined when a maintenance plan is subsequently developed.

[0034] Step S102: Using the set of branches with fixed maintenance times as constraints, and taking the minimization of total operating cost and maintenance deviation penalty as the objective function, establish and solve the initial maintenance plan model.

[0035] Specifically, using a set of branches with fixed maintenance times as constraints can be understood as meaning that in this initial maintenance plan model, the maintenance times of the branches in this set are fixed. That is, the model is used to determine the maintenance plans for other branches based on the determined maintenance times of some branches. The maintenance deviation penalty represents the deviation between the initial maintenance plan and the actual maintenance status. It should be noted that branch maintenance is usually carried out by different maintenance departments, and a pre-formulated maintenance plan must be submitted and approved by superiors before implementation. The initial maintenance plan here refers to the submitted maintenance plan. The actual maintenance status is the variable in this initial maintenance plan model, that is, the maintenance plan determined by this model.

[0036] Step S103: When the initial maintenance plan model has no solution, add power flow violation penalty and power flow violation constraint to the initial maintenance plan model to obtain a feasibility relaxation model and solve it to obtain a relaxation solution.

[0037] Specifically, because the initial maintenance plan model above fixes the maintenance time for some branches, the model may have no solution. That is, when solving the initial maintenance plan model, the model does not converge, and in this case, the maintenance plan cannot be obtained. It is necessary to consider relaxing the safety constraints. It should be noted that if the initial maintenance plan model converges, the maintenance plan can be obtained directly, and no further steps are needed.

[0038] When the initial maintenance plan model has no solution, this embodiment adds power flow violation penalty and power flow violation constraint to the initial maintenance plan model. That is, the power flow of the branch is allowed to exceed the limit in the model. At this time, the feasibility relaxation model has a solution (i.e., relaxation solution).

[0039] Step S104: Replace the integer variables in the feasibility relaxation model with continuous variables, and add constraints on the integer solutions in the relaxation solution to obtain a linear model. Based on the linear model, determine the set of critical branches by solving the Lagrange multipliers of the constraints.

[0040] Specifically, although the feasibility relaxation model has a solution, this solution is obtained based on power flow exceeding limits, therefore the maintenance plan cannot be directly determined based on the solution. However, the model can be transformed into a linear model and solved, and the branches affecting power flow exceeding limits can be identified using Lagrange multipliers. It should be noted that Lagrange multipliers are a natural byproduct of the linear programming solution process. Specifically, Lagrange multipliers are a "sensitivity parameter" generated along with the constraints when solving this linear model. They represent the magnitude of change in the objective function (such as total system cost or exceeding limit penalty) when the limit of the constraint changes slightly.

[0041] Since the linear model is derived from the feasibility relaxation model, which includes power flow violation penalties, the Lagrange multipliers determined by solving the linear model essentially reflect the relationship between whether the branch power flow violates the limit and the penalty cost. Therefore, the critical branches that are most sensitive to and have the greatest impact on power flow violation can be identified through the Lagrange multipliers, thereby determining the set of critical branches.

[0042] Step S105: Add power flow over-limit penalty and flexible limit constraint considering flexible limit to the maintenance plan model, and take the set of branches in the set of branches with fixed maintenance time after removing the set of critical branches as the constraint condition to obtain the optimized maintenance plan model, and solve it to obtain the maintenance plan.

[0043] Specifically, after determining the set of critical branches, branches included in the set of branches with fixed maintenance times can be removed; that is, branches with significant power flow exceedances are no longer subject to fixed maintenance times. Furthermore, considering the possibility of some unavoidable exceedances, a power flow exceedance penalty and elastic limit constraint considering flexible limits (i.e., allowing branches to exceed limits for a certain time and degree) are added back to the initial maintenance plan model. After removing the set of critical branches from the set of branches with fixed maintenance times, the constraints are redefined, resulting in an optimized maintenance plan model. Solving this optimized maintenance plan model yields the final maintenance plan.

[0044] The maintenance plan determination method provided in this invention effectively reduces the integer variables in the maintenance plan and the column size of the maintenance plan model by analyzing power flow without considering the maintenance plan. Simultaneously, when the maintenance plan model has no solution, a linear relaxation model is constructed. Lagrange multipliers are used to identify maintenance branch variables that affect power flow exceedance limits. Furthermore, since the linear model solves quickly, its impact on overall computation time is negligible. For cases where branch exceedance limits cannot be eliminated, a flexible limit constraint is constructed, allowing for short periods and a certain degree of exceedance, thus improving the model's convergence.

[0045] This embodiment provides a method for determining a maintenance plan, the process of which includes the following steps:

[0046] Step S201: Determine the power flow of the power grid based on the power generation plan model without maintenance, and determine the set of branches with fixed maintenance times based on the power flow.

[0047] Specifically, step S201 includes:

[0048] Step S2011 uses the minimum sum of unit operating cost and start-up / shutdown cost as the objective function; specifically, when constructing the power generation planning model, the minimum total system operating cost is used as the optimization objective, and this objective function is expressed by the following formula:

[0049]

[0050] In the formula, Indicates the unit i Operating costs Indicates the unit i At any moment t of effort, Indicates the unit i At any moment t Start-up and shutdown costs. T This represents the total number of time periods. N g This represents the number of generating units.

[0051] Step S2012: Construct constraint conditions using unit minimum start-up and shutdown time constraints, unit output constraints, node power balance constraints, and branch power flow constraints.

[0052] Specifically, the unit combination must meet the minimum start-up and shutdown time, as expressed by the following formula:

[0053]

[0054] In the formula, , For the unit i Minimum continuous power-on time and minimum continuous power-off time. , For the unit i exist t The time elapsed is the duration of continuous operation and the duration of continuous shutdown. Indicates the unit i During the period t The start / stop status is indicated by 0, where 0 indicates the unit is stopped and 1 indicates the unit is started.

[0055] The unit output satisfies the following formula:

[0056]

[0057] In the formula, P i,min , P i,max The units i The minimum and maximum output.

[0058] The node power balance constraint is expressed by the following formula:

[0059]

[0060] In the formula, Φ Gn Φ Ln Φ Dn They are nodes n On the conventional units, branches, and load collection, branch road The trend direction, the beginning is n The value is 1 if it is 1, otherwise it is -1. branch road At any moment t The trend For load d At any moment t The load forecast value.

[0061] Branch flow constraints satisfy the following formula:

[0062]

[0063]

[0064] In the formula, θ ls,t θ le,t branch road At any moment t The first and last phase angles, For the reactance of the branch circuit, P l,max , P l,min branch road The upper and lower limits of trends.

[0065] Step S2013: Construct a power generation plan model based on the objective function and constraints.

[0066] Step S2014: Solve the power generation plan model to obtain the power grid flow results.

[0067] Specifically, the power generation planning model constructed using the objective function and constraints expressed by the above formula is a mixed-integer programming model, which can be solved using optimization software such as CPLEX to obtain the power flow results. .

[0068] Step S2015: Obtain the power flow of each branch in the power grid; determine the set of branches with fixed maintenance times based on whether the power flow of each branch is within the power flow limit. Specifically, for the branches to be maintained... k If, during the initial maintenance schedule, a branch is far from its power limit (which, for a branch, represents the branch's power flow limit), it can be considered to have a relatively low power load and maintenance can be scheduled. This forms the maintainable set. The maintainable set is represented by the following formula:

[0069]

[0070] In the formula, Given a repairable threshold, such as 0.7, Indicates that branch k is in The trend of the time branch road k The initial maintenance status, when the branch road k exist The initial maintenance state at that time is the maintenance rule. The value is 1 if the condition is not met, and 0 otherwise. Since the initial state of the branches in this repairable set is under maintenance, this repairable set can also be represented as a set of branches with fixed maintenance times.

[0071] Step S202: Using the set of branches with fixed maintenance times as constraints, and taking the minimization of total operating cost and maintenance deviation penalty as the objective function, establish and solve the initial maintenance plan model.

[0072] Specifically, step S202 includes:

[0073] Step S2021 sets the objective function to minimize the sum of total operating cost and maintenance deviation penalty. The total operating cost is the sum of unit operating cost and start-up / shutdown cost. The maintenance deviation penalty is the deviation between the initial maintenance plan and the actual maintenance status. Specifically, a deviation penalty cost exists when the maintenance date (the actual maintenance date) deviates from the initial maintenance plan; the larger the deviation, the larger the penalty cost. Therefore, considering the maintenance time of some branches, the objective function determined by minimizing the sum of total operating cost and maintenance deviation penalty is expressed by the following formula:

[0074]

[0075] In the formula, Indicates the unit i Operating costs Indicates the unit i At any moment t of effort, It is a generator set i time t Start-up and shutdown costs. It is a side road At any moment t Deviation penalty cost coefficient, Indicates the number of branches. It is a side road At any moment t The scheduled maintenance status is indicated by a value of 1 if in maintenance mode and 0 otherwise. branch road The initial maintenance status (i.e., the maintenance status determined by the initial maintenance plan).

[0076] Step S2022 uses the following constraints as conditions: minimum start-up and shutdown time constraints, unit output constraints, branch power flow constraints, node power balance constraints considering branch maintenance status, project duration constraints, continuous maintenance constraints, mutually exclusive maintenance constraints, maintenance quantity constraints, and the set of branches with fixed maintenance times. The minimum start-up and shutdown time constraints, unit output constraints, and branch power flow constraints are described in step S2012 above and will not be repeated here.

[0077] The nodal power balance constraint considering branch maintenance conditions is expressed by the following formula:

[0078]

[0079] The duration constraint is expressed by the following formula:

[0080]

[0081] branch road The construction period, i.e. the total maintenance time.

[0082] The maintenance time for branch lines is continuous, therefore the amount of change in maintenance status is increased. , When the side road When transitioning from operation to maintenance The value is 1 for the branch road and 0 for the rest of the time. From maintenance to operation If the value is 1 for all time periods and 0 for the rest of the time periods, then the continuous maintenance constraint satisfies the following formula:

[0083]

[0084] because It can only take the values ​​0 or 1, so the formula shows that... , Because it is constrained and cannot take a number that is neither 0 nor 1, it can be set... , The variables are continuous variables in the interval [0,1], thus not increasing the number of integer variables in the model.

[0085] To ensure power grid transmission capacity and prevent situations such as electrical islanding, certain branches should avoid simultaneous maintenance shutdowns. Therefore, the mutual exclusion maintenance constraint is expressed by the following formula:

[0086]

[0087] In the formula, branch i and branch roads j These are mutually exclusive branches.

[0088] By controlling the total number of maintenance checks during the same period, the risk of system operation can be reduced. Therefore, the constraint on the number of maintenance checks is expressed by the following formula:

[0089]

[0090] In the formula, K t,max For a moment t The upper limit on the number of branch lines subject to power outage maintenance.

[0091] The fixed maintenance time of some branches is determined by the set of branches with fixed maintenance times, and is expressed by the following formula:

[0092]

[0093] Step S2023: Construct and solve the initial maintenance plan model based on the objective function and constraints. Specifically, the initial maintenance plan model constructed using the objective function and constraints expressed by the above formula is a mixed integer programming model, which can be solved using optimization software such as CPLEX. If convergence is achieved, the maintenance plan result is obtained; otherwise, proceed to step S203.

[0094] Step S203: When the initial maintenance plan model has no solution, add power flow violation penalty and power flow violation constraint to the initial maintenance plan model to obtain a feasibility relaxation model and solve it to obtain a relaxation solution.

[0095] Specifically, step S203 includes:

[0096] Step S2031: When the initial maintenance plan model has no solution, the objective function is to minimize the sum of the total operating cost, maintenance deviation penalty, and power flow violation penalty. Specifically, when the initial maintenance plan model has no solution, a penalty for exceeding safety constraints is added to the objective function of the initial maintenance plan model. The resulting objective function is expressed by the following formula:

[0097]

[0098] In the formula, , Branch roads At any moment t The values ​​above and below the upper and lower limits are variables. M is a coefficient with a relatively large value, for example, 10000.

[0099] Step S2032 uses the following constraints as constraints: minimum start-up and shutdown time of the unit, unit output constraint, branch power flow constraint considering power flow overruns, construction period constraint, continuous maintenance constraint, mutually exclusive maintenance constraint, maintenance quantity constraint, and the set of branches with fixed maintenance time. Specifically, the constraints of minimum start-up and shutdown time of the unit, unit output constraint, construction period constraint, continuous maintenance constraint, mutually exclusive maintenance constraint, maintenance quantity constraint, and the set of branches with fixed maintenance time are described in step S2022 above and will not be repeated here.

[0100] The branch power flow constraint considering power flow exceeding the limit is expressed by the following formula:

[0101]

[0102]

[0103] Step S2033: Construct a feasibility relaxation model based on the objective function and constraints, and solve for the relaxed solution. Specifically, the feasibility relaxation model constructed using the objective function and constraints expressed by the above formula is a mixed integer programming model, which can be solved using optimization software such as CPLEX to obtain the relaxed solution. This relaxed solution includes integer solutions. , , , In this model, the start-up and shutdown status of the unit, the maintenance status of the branch, and the change in maintenance status can only take integer values ​​of 0 or 1.

[0104] Step S204 involves replacing integer variables in the feasibility relaxation model with continuous variables and adding constraints on integer solutions in the relaxation solution to obtain a linear model. Based on the Lagrange multipliers obtained from solving the constraints of the linear model, the set of critical branches is determined. Specifically, since only models with continuous variables can calculate Lagrange multipliers, the integer variables in the feasibility relaxation model are replaced with continuous variables. , , , Replace with continuous variables , , , And by adding the following equality constraints, a linear model is formed.

[0105]

[0106]

[0107]

[0108]

[0109] Specifically, the above linear model is optimized and solved to obtain the branch road maintenance state constraints. Lagrange multipliers The conditions will be met. branch road Establish a set of critical branches .

[0110] Step S205: Add power flow over-limit penalty and flexible limit constraint considering flexible limit to the maintenance plan model, and take the set of branches in the set of branches with fixed maintenance time after removing the set of critical branches as the constraint condition to obtain the optimized maintenance plan model, and solve it to obtain the maintenance plan.

[0111] Specifically, step S205 includes:

[0112] Step S2051 sets the objective function to minimize the sum of total operating cost, maintenance deviation penalty, and power flow over-limit penalty considering flexible limits. Specifically, since some over-limit situations may occur that cannot be eliminated, flexible limits are adopted, that is, allowing over-limit for a certain time and degree for these branches. Therefore, the objective function is expressed by the following formula:

[0113]

[0114] In the formula, , Branches considering flexible limits At any moment t The higher the upper limit, the lower the lower limit.

[0115] Step S2052 uses the following constraints as conditions: minimum start-up and shutdown time constraints, unit output constraints, branch power flow constraints considering flexible limits, construction period constraints, continuous maintenance constraints, mutually exclusive maintenance constraints, maintenance quantity constraints, and the branch set excluding the critical branch set from the branch set with fixed maintenance time. Specifically, the minimum start-up and shutdown time constraints, unit output constraints, construction period constraints, continuous maintenance constraints, mutually exclusive maintenance constraints, and maintenance quantity constraints are described in step S2022 above and will not be repeated here.

[0116] The branch set that removes the critical branch set from the branch set with fixed maintenance time (i.e., in the set) The middle set excludes the branch lines that influence the trend. The corresponding constraints are expressed by the following formula:

[0117]

[0118] Branch power flow constraints considering flexible limits are expressed by the following formula:

[0119]

[0120]

[0121]

[0122]

[0123]

[0124]

[0125] In the formula, , Branch roads At any moment tThe state that exceeds the upper or lower limit is 1 if it exceeds the limit and 0 if it does not exceed the limit. , Branch roads The maximum allowed time to exceed the upper and lower limits. It is a side road The maximum permissible over-limit ratio.

[0126] Step S2053: Construct an optimized maintenance plan model based on the objective function and constraints, and solve for the maintenance plan. Specifically, the optimized maintenance plan model constructed using the objective function and constraints expressed by the above formula is a mixed integer programming model, which can be solved using optimization software such as CPLEX to obtain the maintenance plan result.

[0127] As a specific application embodiment of the present invention, such as Figure 2 As shown, the maintenance plan is determined using the following process:

[0128] Step S1: Calculate the power flow under maintenance-free conditions and preliminarily determine the set of branches with fixed maintenance times. Specifically, establish a generation plan model M1 under maintenance-free conditions, and optimize the power flow to obtain the power flow, including the objective function and constraints. Model M1 is a mixed-integer programming model, which can be solved using CPLEX to obtain the power flow results. For the branch roads awaiting maintenance k If a component is far from its power limit during the initial maintenance schedule, it can be considered to have a low power load and maintenance can be scheduled. This forms the maintainable set. .

[0129] Step S2: Establish a maintenance plan model with some fixed variables and perform optimization calculations. Specifically, establish a maintenance plan model M2 with some fixed variables, including the objective function and constraints. Model M2 is a mixed integer programming model, which can be solved using CPLEX. If it converges, the maintenance plan result is obtained; otherwise, proceed to step S3.

[0130] Step S3: Establish a feasibility relaxation model, obtain the Lagrange multipliers of relevant variables, and acquire the set of critical branches. Specifically, relax the safety constraints to establish a feasibility relaxation model M3. Model M3 is a mixed integer programming model, which can be solved using mature commercial optimization software such as CPLEX to obtain a relaxed solution. Replace the integer variables in the feasibility relaxation model M3 with continuous variables and add equality constraints to form a linear model M4. M4 is a linear model; optimize and solve M4 to obtain the Lagrange multipliers of the branch maintenance state constraints. For those that meet the conditions branch road Establish a set of critical branches .

[0131] Step S4 involves constructing flexible quota constraints for branches exceeding the limits, forming a feasible accelerated optimization model for the maintenance plan, and performing optimization calculations. Specifically, a feasible accelerated optimization model M5 is established, including the objective function and constraints. Model M5 is a mixed-integer programming model, which can be solved using CPLEX to obtain the maintenance plan results.

[0132] This invention constructs several easily solvable maintenance plan sub-models, including a maintenance plan sub-model that does not consider network constraints, a model with most integer variables fixed, and a linearized and relaxable model, etc. It explores whether branch maintenance has an effect on power flow exceeding limits, significantly reducing the model size of the maintenance plan. In addition, it introduces flexible limit constraints to improve the model convergence within the allowable range of safe power grid operation, thereby improving the computational performance of the maintenance plan.

[0133] This invention addresses the dimensionality reduction problem of large-scale integer variables in maintenance plans by establishing a method for fixing some variables based on power flow, and obtaining the set of key branches through Lagrange multipliers of a feasible relaxation model, effectively reducing the size of inactive integer variables in the maintenance plan. Furthermore, considering the situation where power flow exceeding limits cannot be eliminated in a few scenarios, an elastic limit constraint is constructed for the branches exceeding the limit, forming a feasible accelerated optimization model for the maintenance plan, thereby improving the convergence of the maintenance plan.

[0134] To verify the effectiveness of the above-mentioned maintenance plan determination method, a simulated maintenance plan development model was constructed based on the IEEE 118-node system. Here, N1 represents the conventional maintenance plan model; N2 represents the method proposed in this invention. The computational scale and performance of methods N1 and N2 are shown in Table 1 below.

[0135] Table 1 Computational scale and performance of N1 and N2

[0136]

[0137] Compared to N1, the process constructed by N2 significantly reduces the scale of integer variables to be solved by fixing the integer variables (97.58% of the integer variables are fixed), thus greatly improving the model solving efficiency (the solving efficiency is improved by 39.9 times).

[0138] Reducing the capacity limit of a certain branch road to 160MW resulted in its exceeding the limit being impossible to eliminate. The following method was adopted:

[0139] A1: Conventional maintenance plan model, no solution for the maintenance plan;

[0140] A2: Maintenance planning model with relaxed safety constraints;

[0141] A3: The flexible limit constraint proposed in this invention.

[0142] The power of the branch corresponding to methods A2 and A3 above at different time periods is as follows: Figure 3 As shown, the time for branch road to exceed the limit has been reduced to less than 30 minutes, and the extent of the exceedance has also been reduced. Within the allowable range of safe operation, the convergence of the maintenance plan has been improved.

[0143] This embodiment also provides a maintenance plan determination device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0144] This embodiment provides a maintenance plan determination device, such as... Figure 4 As shown, it includes:

[0145] The maintenance time fixing module 41 is used to determine the power flow of the power grid based on the power generation plan model when there is no maintenance, and to determine the set of branches whose maintenance time can be fixed based on the power flow.

[0146] The initial maintenance plan determination module 42 is used to take the set of branches with fixed maintenance time as constraints, and to establish and solve the initial maintenance plan model with the objective function of minimizing total operating cost and maintenance deviation penalty.

[0147] The feasibility relaxation model determination module 43 is used to add power flow violation penalty and power flow violation constraint to the initial maintenance plan model when the initial maintenance plan model has no solution, so as to obtain a feasibility relaxation model and solve it to obtain a relaxation solution.

[0148] The critical branch set determination module 44 is used to replace the integer variables in the feasibility relaxation model with continuous variables and add constraints on the integer solutions in the relaxation solution to obtain a linear model. Based on the Lagrange multipliers of the variables after solving the linear model, the critical branch set is determined.

[0149] The maintenance plan determination module 45 is used to add power flow over-limit penalty and elastic limit constraint considering elastic limit to the maintenance plan model, and take the set of branches in the set of branches with fixed maintenance time, excluding the set of critical branches, as the constraint condition to obtain an optimized maintenance plan model, and solve for the maintenance plan.

[0150] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0151] This invention also provides a computer device having the above-described features. Figure 4 The maintenance plan determination device shown.

[0152] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 5 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 Take a processor 10 as an example.

[0153] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GPA), or any combination thereof.

[0154] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0155] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device as shown by a landing page for an app. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0156] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0157] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0158] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0159] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0160] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for determining a maintenance plan, characterized in that, The method includes: The power flow is determined based on the power generation plan model without maintenance, and the set of branches with fixed maintenance times is determined based on the power flow. Using the set of branches with fixed maintenance times as constraints, and with the objective function of minimizing total operating cost and maintenance deviation penalty, an initial maintenance plan model is established and solved. When the initial maintenance plan model has no solution, power flow violation penalty and power flow violation constraint are added to the initial maintenance plan model to obtain a feasibility relaxation model and solve it to obtain a relaxation solution. The integer variables in the feasibility relaxation model are replaced with continuous variables, and constraints on the integer solutions in the relaxation solution are added to obtain a linear model. The set of critical branches is determined based on the Lagrange multipliers of the constraints after solving the linear model. In the maintenance plan model, a power flow over-limit penalty and a flexible limit constraint considering the flexible limit are added, and the set of branches in the set of branches with fixed maintenance time, after removing the set of critical branches, is used as a constraint condition to obtain an optimized maintenance plan model, and the maintenance plan is obtained by solving it. The constraints for integer solutions include unit start-up and shutdown state constraints, branch maintenance state constraints, and constraints on changes in maintenance state. Based on the Lagrange multipliers of the constraints obtained after solving the linear model, the set of critical branches is determined, including: Solve the linear model to determine the Lagrange multipliers for branch maintenance state constraints; Construct a set of key branches based on branches whose Lagrange multipliers are greater than zero.

2. The method according to claim 1, characterized in that, The power flow is determined based on the generation planning model under maintenance-free conditions, including: The objective function is to minimize the sum of unit operating costs and start-up and shutdown costs. The constraints are constructed using the minimum start-up and shutdown time constraints of the unit, the unit output constraints, the node power balance constraints, and the branch power flow constraints. Construct a power generation planning model based on the objective function and constraints; The power flow results are obtained by solving the power generation planning model.

3. The method according to claim 1, characterized in that, Based on the power flow, a set of branches with fixed maintenance times is determined, including: Obtain the power flow of each branch in the power grid; The set of branches with fixed maintenance times is determined based on whether the power flow of each branch is within the power flow limit.

4. The method according to claim 1, characterized in that, Using the set of branches with fixed maintenance times as constraints, and with the objective function of minimizing total operating cost and maintenance deviation penalty, an initial maintenance plan model is established and solved, including: The objective function is to minimize the sum of total operating cost and maintenance deviation penalty, where total operating cost is the sum of unit operating cost and start-up and shutdown cost, and maintenance deviation penalty is the deviation between the initial maintenance plan and the actual maintenance status. The constraints are: minimum start-up and shutdown time of the unit, unit output, branch power flow, node power balance considering branch maintenance status, construction period, continuous maintenance, mutually exclusive maintenance, maintenance quantity, and the set of branches with fixed maintenance time. An initial maintenance plan model is constructed and solved based on the objective function and constraints.

5. The method according to claim 1, characterized in that, When the initial maintenance plan model has no solution, power flow violation penalties and constraints are added to the initial maintenance plan model to obtain a feasibility relaxation model, and the relaxed solution is obtained by solving it, including: When the initial maintenance plan model has no solution, the objective function is to minimize the sum of total operating cost, maintenance deviation penalty, and power flow over-limit penalty. The constraints are: minimum start-up and shutdown time of the unit, unit output constraint, branch power flow constraint considering power flow over-limit, construction period constraint, continuous maintenance constraint, mutually exclusive maintenance constraint, maintenance quantity constraint, and the set of branches with fixed maintenance time. A feasible relaxation model is constructed based on the objective function and constraints, and the relaxed solution is obtained by solving it.

6. The method according to claim 1, characterized in that, In the maintenance plan model, power flow over-limit penalties and flexible limit constraints considering flexible limits are added. The set of branches in the set of branches with fixed maintenance times, excluding the set of critical branches, is used as a constraint condition to obtain an optimized maintenance plan model. Solving this model yields the maintenance plan, including: The objective function is to minimize the sum of total operating cost, maintenance deviation penalty, and power flow over-limit penalty considering flexibility limits; The constraints are the minimum start-up and shutdown time of the unit, the unit output, the branch power flow constraints considering the flexible limit, the construction period, the continuous maintenance, the mutually exclusive maintenance, the maintenance quantity, and the branch set that removes the critical branch set from the branch set with fixed maintenance time. An optimized maintenance plan model is constructed based on the objective function and constraints, and the maintenance plan is obtained by solving the model.

7. A maintenance plan determination device, characterized in that, The device includes: The maintenance time fixing module is used to determine the power flow of the grid based on the power generation plan model when there is no maintenance, and to determine the set of branches with fixed maintenance time based on the power flow. The initial maintenance plan determination module is used to take the set of branches with fixed maintenance time as constraints, and to establish and solve the initial maintenance plan model with the objective function of minimizing total operating cost and maintenance deviation penalty. The feasibility relaxation model determination module is used to add power flow violation penalty and power flow violation constraint to the initial maintenance plan model when the initial maintenance plan model has no solution, so as to obtain a feasibility relaxation model and solve it to obtain a relaxation solution. The critical branch set determination module is used to replace the integer variables in the feasibility relaxation model with continuous variables and add constraints on the integer solutions in the relaxation solution to obtain a linear model. Based on the Lagrange multipliers of the variables after solving the linear model, the critical branch set is determined. The maintenance plan determination module is used to add power flow over-limit penalty and elastic limit constraint considering elastic limit to the maintenance plan model, and take the set of branches in the set of branches with fixed maintenance time after removing the set of critical branches as the constraint condition to obtain an optimized maintenance plan model, and solve for the maintenance plan. The constraints for integer solutions include unit start-up and shutdown state constraints, branch maintenance state constraints, and constraints on changes in maintenance state. Based on the Lagrange multipliers of the constraints obtained after solving the linear model, the set of critical branches is determined, including: Solve the linear model to determine the Lagrange multipliers for branch maintenance state constraints; Construct a set of key branches based on branches whose Lagrange multipliers are greater than zero.

8. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the maintenance plan determination method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the maintenance plan determination method according to any one of claims 1 to 6.

Images