Power system simulation operation oriented maintenance plan optimization method and device

Abstract

The invention discloses a maintenance plan optimization method and device for power system simulation operation, and the method comprises the steps: building a maintenance plan generation model based on a maintenance historical boundary under the condition of a given unit and historical maintenance data of the unit; according to the model, the maintenance state constraint, the maintenance starting and ending balance constraint, the maintenance type constraint, the maintenance frequency constraint, the maintenance duration constraint, the maintenance availability constraint and the deviation constraint are taken as constraint conditions, and the maintenance plan is obtained by solving the model, so that the reasonable maintenance plan can be quickly and effectively generated; the technical problem that an existing maintenance plan making method is difficult to provide scientific and reasonable maintenance plan input for power system simulation operation is solved.

Description

Technical Field

[0001] This invention relates to the field of power system maintenance technology, and in particular to a method and apparatus for optimizing maintenance plans for power system simulation operation. Background Technology

[0002] Power system simulation is an important technical means for the power industry to conduct planning and design, operation mode formulation, and safety assessment. In various power system simulations, the reasonable setting of unit maintenance plans directly affects the reliability and practicality of simulation results and is one of the key factors determining simulation quality.

[0003] Traditional maintenance planning methods face significant challenges when applied to system simulation: First, maintenance arrangements based on human experience lack a rigorous mathematical foundation, making it difficult to guarantee global optimality within the simulation cycle and unsuitable for the computational demands of large-scale systems. Second, existing maintenance optimization models often focus on practical operation and maintenance applications, neglecting consistency with system operation simulation, leading to a disconnect between maintenance plans and simulated operating conditions. Third, with the large-scale integration of new energy sources, the net load characteristics of the system change significantly, making traditional fixed-cycle maintenance models ill-suited to the flexibility requirements of new power systems. Therefore, there is an urgent need to establish maintenance planning optimization methods closely coupled with system operating status to provide more scientific and reasonable maintenance plan inputs for power system simulation. Summary of the Invention

[0004] This invention provides a method and apparatus for optimizing maintenance plans for power system simulation operation, which solves the technical problem that existing maintenance plan formulation methods are unable to provide scientific and reasonable maintenance plan inputs for power system simulation operation.

[0005] In view of this, the first aspect of the present invention provides a method for optimizing maintenance plans for power system simulation operation, comprising:

[0006] Acquire unit data and historical unit maintenance data;

[0007] Based on unit data and historical unit maintenance data, a maintenance plan generation model is constructed.

[0008] Solve the maintenance plan generation model to obtain the maintenance plan;

[0009] The maintenance plan generation model includes an objective function and constraints. The objective function aims to minimize the annual maintenance capacity deviation. The constraints include maintenance status constraints, maintenance start-up and end balance constraints, maintenance type constraints, maintenance frequency constraints, maintenance duration constraints, maintenance availability constraints, and deviation constraints.

[0010] Optionally, the objective function is:

[0011]

[0012] Where M represents the total number of months. This is the penalty coefficient for the positive deviation of the maximum maintenance capacity in the m-th month. Let be the penalty coefficient for the positive deviation of the total maintenance capacity in month m. This is the penalty coefficient for the negative deviation of the maximum maintenance capacity in the m-th month. This is the penalty coefficient for the negative deviation of the total maintenance capacity in the m-th month. , , , This is the deviation coefficient.

[0013] Optionally, the maintenance status constraint is:

[0014]

[0015]

[0016]

[0017]

[0018] in, Let be a binary decision variable used to indicate whether unit i is under maintenance in week t. Let i be a binary decision variable used to indicate whether unit i is under maintenance in week t-1. Let be the binary decision variable used to represent the start of maintenance for unit i in week t. Let T be the decision variable used to represent the end of maintenance for unit i in week t, where T is the total number of weeks and N is the total number of units.

[0019] Optionally, the maintenance start-up and end balance constraints are:

[0020]

[0021] in, Let be the binary decision variable used to represent the start of maintenance for unit i in week t. Let T be the decision variable used to represent the end of maintenance for unit i in week t, where T is the total number of weeks and N is the total number of units.

[0022] Optionally, the maintenance type constraint is:

[0023]

[0024] Where k represents the maintenance type. Let i be the set of maintenance types, t be the unit number, t be the time variable in weeks, T be the total number of weeks, and N be the total number of units. Let be the binary decision variable used to represent the unit i that chooses to start maintenance in week t when selecting maintenance type k.

[0025] Optionally, the number of maintenance operations is constrained as follows:

[0026]

[0027] Where k represents the maintenance type. Let i be the set of maintenance types, t be the unit number, t be the time variable in weeks, T be the total number of weeks, and N be the total number of units. This represents the maximum number of maintenance cycles for the k-th maintenance type of the unit. Let be the binary decision variable used to represent the unit i that chooses to start maintenance in week t when selecting maintenance type k.

[0028] Optionally, the maintenance time constraint is:

[0029]

[0030] in, Let be the binary decision variable used to represent the unit i that chooses k types of maintenance to start maintenance in week t. The number of weeks required to perform the k-th type of maintenance on unit i. Let be a binary decision variable used to indicate whether unit i is under maintenance in week t.

[0031] Optionally, the maintenance availability constraint is:

[0032]

[0033] in, Let be a binary decision variable used to indicate whether unit i is under maintenance in week t. For the available start week of unit i, This is the available end week for unit i.

[0034] Optionally, the deviation constraint is:

[0035]

[0036]

[0037]

[0038] in, For the capacity of unit i, This represents the maximum maintenance capacity in the m-th month. This represents the maximum total maintenance capacity for the m-th month. Let N be the week corresponding to the m-th month, and N be the total number of units. Let m be the set of all weeks contained in month m. Let y be the y-th deviation variable.

[0039] A second aspect of the present invention provides a maintenance plan optimization device for power system simulation operation, comprising:

[0040] The data acquisition module is used to acquire unit data and historical maintenance data of the unit;

[0041] The model building module is used to build a maintenance plan generation model based on unit data and historical maintenance data.

[0042] The solver module is used to solve the maintenance plan generation model to obtain the maintenance plan;

[0043] The maintenance plan generation model includes an objective function and constraints. The objective function aims to minimize the annual maintenance capacity deviation. The constraints include maintenance status constraints, maintenance start-up and end balance constraints, maintenance type constraints, maintenance frequency constraints, maintenance duration constraints, maintenance availability constraints, and deviation constraints.

[0044] As can be seen from the above technical solutions, the maintenance plan optimization method for power system simulation operation provided by this invention has the following advantages:

[0045] The present invention provides a maintenance plan optimization method for power system simulation operation. Under the condition of given unit and historical maintenance data of the unit, a maintenance plan generation model based on the maintenance history boundary is established. The model considers maintenance status constraints, maintenance start and end balance constraints, maintenance type constraints, maintenance frequency constraints, maintenance duration constraints, maintenance availability constraints, and deviation constraints as constraints. The maintenance plan is obtained by solving the model, which can quickly and effectively generate reasonable maintenance plans. It solves the technical problem that existing maintenance plan formulation methods are difficult to provide scientific and reasonable maintenance plan inputs for power system simulation operation.

[0046] This invention introduces binary decision variables to accurately describe the unit's maintenance status, start time, and end time. Under complex constraints, it automatically finds the globally optimal or near-optimal maintenance plan, significantly improving the scientific and economic efficiency of the plan. Secondly, the model constructed in this invention determines the number of days for each unit's maintenance type based on the unit's specific circumstances and converts it into corresponding weeks, effectively avoiding a single maintenance duration scheme and increasing the flexibility and rationality of the generated maintenance plan. Simultaneously, the model constructed in this invention considers the full life-cycle maintenance constraints of the dynamic time windows for unit commissioning and decommissioning, ensuring the rationality of the generated maintenance plan and making it more realistic. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart illustrating a maintenance plan optimization method for power system simulation operation provided in an embodiment of the present invention.

[0049] Figure 2 This is a schematic diagram of a maintenance plan optimization device for power system simulation operation provided in an embodiment of the present invention. Detailed Implementation

[0050] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and 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.

[0051] For easier understanding, please refer to Figure 1 This invention provides an embodiment of a voltage ride-through adaptive control method for direct-drive wind turbine generators, comprising:

[0052] Step 101: Obtain unit data and historical maintenance data.

[0053] It should be noted that in this invention, the first step is to acquire unit data and historical unit maintenance data. Unit data includes the unit's location, capacity, name, available start week, and available end week. Historical unit maintenance data includes historical daily unit maintenance plans and the number of weeks required for maintenance of different capacity units of various maintenance types.

[0054] Step 102: Based on the unit data and historical maintenance data, construct a maintenance plan generation model.

[0055] It should be noted that, based on historical daily unit maintenance plans, the maximum daily maintenance capacity and total monthly maintenance volume of the units are calculated on a monthly basis:

[0056]

[0057]

[0058] Where p represents the region (province) where the generator set is located, g represents the generator set type, m represents the month, and i represents the generator set number. Let m be the set of days in the m-th month. Let p be the set of units of the g-th unit type in region p. For the capacity of unit i, This represents the maintenance status of unit i on day d. This represents the maximum daily maintenance capacity of the g-th unit type in region p during the m-th month. This represents the total monthly maintenance volume for the g-th unit type in region p in the m-th month.

[0059] From the perspective of program scale and solution speed, generating maintenance plans on a daily basis would lead to an excessively large solution scale, affecting efficiency. Therefore, in this invention, the maintenance plan generation model uses a week as the time unit, meaning that the unit's maintenance status is the same every day within a week. The maintenance plan generation model includes an objective function and constraints. The objective function aims to minimize the annual maintenance capacity deviation, and is as follows:

[0060]

[0061] Where M represents the total number of months. This is the penalty coefficient for the positive deviation of the maximum maintenance capacity in the m-th month. Let be the penalty coefficient for the positive deviation of the total maintenance capacity in month m. This is the penalty coefficient for the negative deviation of the maximum maintenance capacity in the m-th month. This is the penalty coefficient for the negative deviation of the total maintenance capacity in the m-th month. , , , This is the deviation coefficient.

[0062] Maintenance status constraints are used to define the maintenance status of a unit and the start and stop times for maintenance. The maintenance status constraints are as follows:

[0063]

[0064]

[0065]

[0066]

[0067] in, Let be a binary decision variable used to indicate whether unit i is under maintenance in week t. Let i be a binary decision variable used to indicate whether unit i is under maintenance in week t-1. Let be the binary decision variable used to represent the start of maintenance for unit i in week t. Let T be the decision variable used to represent the end of maintenance for unit i in week t, where T is the total number of weeks and N is the total number of units.

[0068] The maintenance start-up and end-of-life balance constraint is used to constrain the time span of the procedure to one year. Unit maintenance must be carried out within this time span; cases where maintenance spans across years are not considered. The maintenance start-up and end-of-life balance constraint is as follows:

[0069]

[0070] in, Let be the binary decision variable used to represent the start of maintenance for unit i in week t. Let T be the decision variable used to represent the end of maintenance for unit i in week t, where T is the total number of weeks and N is the total number of units.

[0071] During unit maintenance, there are four maintenance types: A, B, C, and D. Each type of maintenance requires a different duration, and each unit can only undergo one type of maintenance within a given time period. Maintenance type constraints indicate that each unit is allowed to perform at most one type of maintenance within each time period, and different types of maintenance are not allowed to coexist on the same unit. This is represented as:

[0072]

[0073] Where k represents the maintenance type. Let i be the set of maintenance types, t be the unit number, t be the time variable in weeks, T be the total number of weeks, and N be the total number of units. Let be the binary decision variable used to represent the unit i that chooses to start maintenance in week t when selecting maintenance type k.

[0074] Within a given time span, different types of generating units have different maximum maintenance limits, and each unit cannot exceed this maximum number of maintenance operations. The maintenance frequency constraints are as follows:

[0075]

[0076] Where k represents the maintenance type. Let i be the set of maintenance types, t be the unit number, t be the time variable in weeks, T be the total number of weeks, and N be the total number of units. This represents the maximum number of maintenance cycles for the k-th maintenance type of the unit. Let be the binary decision variable used to represent the unit i that chooses to start maintenance in week t when selecting maintenance type k.

[0077] During unit maintenance, different types of maintenance correspond to different maintenance durations. In the model of this invention, maintenance duration is measured in weeks. When a unit undergoes a certain type of maintenance, the maintenance duration must meet the relevant duration requirements. The maintenance duration constraints are as follows:

[0078]

[0079] in, Let be the binary decision variable used to represent the unit i that chooses k types of maintenance to start maintenance in week t. The number of weeks required to perform the k-th type of maintenance on unit i. Let be a binary decision variable used to indicate whether unit i is under maintenance in week t.

[0080] In actual programming, the Big M method can be used to handle this constraint:

[0081]

[0082]

[0083] Where M is a sufficiently large positive number.

[0084] When generating a maintenance plan, the commissioning and decommissioning of the unit must be considered. Maintenance cannot be performed before the unit is commissioned or after it is decommissioned. Maintenance availability constraints are as follows:

[0085]

[0086] in, Let be a binary decision variable used to indicate whether unit i is under maintenance in week t. For the available start week of unit i, This is the available end week for unit i.

[0087] When scheduling maintenance operations, historical maintenance data of the unit is typically used as boundary conditions. In the model of this invention, a certain deviation between the program-generated maintenance plan and the historical boundary conditions is allowed. The deviation constraint is as follows:

[0088]

[0089]

[0090]

[0091] in, For the capacity of unit i, This represents the maximum maintenance capacity in the m-th month. This represents the maximum total maintenance capacity for the m-th month. Let N be the week corresponding to the m-th month, and N be the total number of units. Let m be the set of all weeks contained in month m. Let y be the y-th deviation variable.

[0092] Step 103: Solve the maintenance plan generation model to obtain the maintenance plan.

[0093] It should be noted that existing solution tools are used to solve the maintenance plan generation model to obtain the maintenance plan corresponding to the optimal solution, and the optimal maintenance plan is output.

[0094] The present invention provides a maintenance plan optimization method for power system simulation operation. Under the condition of given unit and historical maintenance data of the unit, a maintenance plan generation model based on the maintenance history boundary is established. The model considers maintenance status constraints, maintenance start and end balance constraints, maintenance type constraints, maintenance frequency constraints, maintenance duration constraints, maintenance availability constraints, and deviation constraints as constraints. The maintenance plan is obtained by solving the model, which can quickly and effectively generate reasonable maintenance plans. It solves the technical problem that existing maintenance plan formulation methods are difficult to provide scientific and reasonable maintenance plan inputs for power system simulation operation.

[0095] This invention introduces binary decision variables to accurately describe the unit's maintenance status, start time, and end time. Under complex constraints, it automatically finds the globally optimal or near-optimal maintenance plan, significantly improving the scientific and economic efficiency of the plan. Secondly, the model constructed in this invention determines the number of days for each unit's maintenance type based on the unit's specific circumstances and converts it into corresponding weeks, effectively avoiding a single maintenance duration scheme and increasing the flexibility and rationality of the generated maintenance plan. Simultaneously, the model constructed in this invention considers the full life-cycle maintenance constraints of the dynamic time windows for unit commissioning and decommissioning, ensuring the rationality of the generated maintenance plan and making it more realistic.

[0096] To verify the effectiveness of the maintenance plan optimization method for power system simulation operation provided by this invention, this invention selects unit data and historical maintenance data of a certain power source type in a certain province for testing. There are a total of 170 units of this type. The maintenance plan optimization method for power system simulation operation provided by this invention is used to solve the problem. The solution takes only 304.24 seconds on a 4-core 8-thread processor. The solution results are compared with the historical boundary results as shown in Table 1.

[0097] Table 1

[0098]

[0099] As can be seen from Table 1, the maintenance plan optimization method for power system simulation operation provided by this invention has a fast solution speed, and the deviation between the solution results and historical data is small. Therefore, the maintenance plan optimization method for power system simulation operation provided by this invention can quickly and effectively generate reasonable maintenance plans for technical personnel.

[0100] For easier understanding, please refer to Figure 2 This invention provides an embodiment of a maintenance plan optimization device for power system simulation operation, comprising:

[0101] The data acquisition module is used to acquire unit data and historical maintenance data of the unit;

[0102] The model building module is used to build a maintenance plan generation model based on unit data and historical maintenance data.

[0103] The solver module is used to solve the maintenance plan generation model to obtain the maintenance plan;

[0104] The maintenance plan generation model includes an objective function and constraints. The objective function aims to minimize the annual maintenance capacity deviation. The constraints include maintenance status constraints, maintenance start-up and end balance constraints, maintenance type constraints, maintenance frequency constraints, maintenance duration constraints, maintenance availability constraints, and deviation constraints.

[0105] In one embodiment, the objective function is:

[0106]

[0107] Where M represents the total number of months. This is the penalty coefficient for the positive deviation of the maximum maintenance capacity in the m-th month. Let be the penalty coefficient for the positive deviation of the total maintenance capacity in month m. This is the penalty coefficient for the negative deviation of the maximum maintenance capacity in the m-th month. This is the penalty coefficient for the negative deviation of the total maintenance capacity in the m-th month. , , , This is the deviation coefficient.

[0108] In one embodiment, the maintenance status constraint is:

[0109]

[0110]

[0111]

[0112]

[0113] in, Let be a binary decision variable used to indicate whether unit i is under maintenance in week t. Let i be a binary decision variable used to indicate whether unit i is under maintenance in week t-1. Let be the binary decision variable used to represent the start of maintenance for unit i in week t. Let T be the decision variable used to represent the end of maintenance for unit i in week t, where T is the total number of weeks and N is the total number of units.

[0114] In one embodiment, the maintenance start-up and end balance constraint is:

[0115]

[0116] in, Let be the binary decision variable used to represent the start of maintenance for unit i in week t. Let T be the decision variable used to represent the end of maintenance for unit i in week t, where T is the total number of weeks and N is the total number of units.

[0117] In one embodiment, the maintenance type constraint is:

[0118]

[0119] Where k represents the maintenance type. Let i be the set of maintenance types, t be the unit number, t be the time variable in weeks, T be the total number of weeks, and N be the total number of units. Let be the binary decision variable used to represent the unit i that chooses to start maintenance in week t when selecting maintenance type k.

[0120] In one embodiment, the maintenance frequency constraint is:

[0121]

[0122] Where k represents the maintenance type. Let i be the set of maintenance types, t be the unit number, t be the time variable in weeks, T be the total number of weeks, and N be the total number of units. This represents the maximum number of maintenance cycles for the k-th maintenance type of the unit. Let be the binary decision variable used to represent the unit i that chooses to start maintenance in week t when selecting maintenance type k.

[0123] In one embodiment, the maintenance time constraint is:

[0124]

[0125] in, Let be the binary decision variable used to represent the unit i that chooses k types of maintenance to start maintenance in week t. The number of weeks required to perform the k-th type of maintenance on unit i. Let be a binary decision variable used to indicate whether unit i is under maintenance in week t.

[0126] In one embodiment, the maintenance availability constraint is:

[0127]

[0128] in, Let be a binary decision variable used to indicate whether unit i is under maintenance in week t. For the available start week of unit i, This is the available end week for unit i.

[0129] In one embodiment, the deviation constraint is:

[0130]

[0131]

[0132]

[0133] in, For the capacity of unit i, This represents the maximum maintenance capacity in the m-th month. This represents the maximum total maintenance capacity for the m-th month. Let N be the week corresponding to the m-th month, and N be the total number of units. Let m be the set of all weeks contained in month m. Let y be the y-th deviation variable.

[0134] In one embodiment, acquiring unit data and historical unit maintenance data includes:

[0135] Obtain the unit's location, capacity, name, available start week, available end week, historical daily maintenance schedule, and the number of weeks required for maintenance of units of different capacities and maintenance types.

[0136] The maintenance plan optimization device for power system simulation operation provided in this invention is used to execute the maintenance plan optimization method for power system simulation operation provided in this invention. Its principle and the technical effects achieved are the same as those of the maintenance plan optimization method for power system simulation operation provided in this invention, and will not be repeated here.

[0137] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0138] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing maintenance plans for power system simulation operation, characterized in that, include: Acquire unit data and historical unit maintenance data; Based on unit data and historical unit maintenance data, a maintenance plan generation model is constructed. Solve the maintenance plan generation model to obtain the maintenance plan; The maintenance plan generation model includes an objective function and constraints. The objective function aims to minimize the annual maintenance capacity deviation. The constraints include maintenance status constraints, maintenance start-up and end balance constraints, maintenance type constraints, maintenance frequency constraints, maintenance duration constraints, maintenance availability constraints, and deviation constraints.

2. The maintenance plan optimization method for power system simulation operation according to claim 1, characterized in that, The objective function is: Where M represents the total number of months. This is the penalty coefficient for the positive deviation of the maximum maintenance capacity in the m-th month. Let be the penalty coefficient for the positive deviation of the total maintenance capacity in month m. This is the penalty coefficient for the negative deviation of the maximum maintenance capacity in the m-th month. This is the penalty coefficient for the negative deviation of the total maintenance capacity in the m-th month. , , , This is the deviation coefficient.

3. The maintenance plan optimization method for power system simulation operation according to claim 2, characterized in that, The maintenance status constraints are: in, Let be a binary decision variable used to indicate whether unit i is under maintenance in week t. Let i be a binary decision variable used to indicate whether unit i is under maintenance in week t-1. Let be the binary decision variable used to represent the start of maintenance for unit i in week t. Let T be the decision variable used to represent the end of maintenance for unit i in week t, where T is the total number of weeks and N is the total number of units.

4. The maintenance plan optimization method for power system simulation operation according to claim 3, characterized in that, The balance constraints for maintenance start-up and shutdown are: in, Let be the binary decision variable used to represent the start of maintenance for unit i in week t. Let T be the decision variable used to represent the end of maintenance for unit i in week t, where T is the total number of weeks and N is the total number of units.

5. The maintenance plan optimization method for power system simulation operation according to claim 4, characterized in that, The maintenance type constraint is: Where k represents the maintenance type. Let i be the set of maintenance types, t be the unit number, t be the time variable in weeks, T be the total number of weeks, and N be the total number of units. Let be the binary decision variable used to represent the unit i that chooses to start maintenance in week t when selecting maintenance type k.

6. The maintenance plan optimization method for power system simulation operation according to claim 5, characterized in that, The maintenance frequency is constrained as follows: Where k represents the maintenance type. Let i be the set of maintenance types, t be the unit number, t be the time variable in weeks, T be the total number of weeks, and N be the total number of units. This represents the maximum number of maintenance cycles for the k-th maintenance type of the unit. Let be the binary decision variable used to represent the unit i that chooses to start maintenance in week t when selecting maintenance type k.

7. The maintenance plan optimization method for power system simulation operation according to claim 6, characterized in that, The maintenance time constraint is as follows: in, Let be the binary decision variable used to represent the unit i that chooses k types of maintenance to start maintenance in week t. The number of weeks required to perform the k-th type of maintenance on unit i. Let be a binary decision variable used to indicate whether unit i is under maintenance in week t.

8. The maintenance plan optimization method for power system simulation operation according to claim 7, characterized in that, Maintenance availability constraints are: in, Let be a binary decision variable used to indicate whether unit i is under maintenance in week t. For the available start week of unit i, This is the available end week for unit i.

9. The maintenance plan optimization method for power system simulation operation according to claim 8, characterized in that, Deviation constraints are: in, For the capacity of unit i, This represents the maximum maintenance capacity in the m-th month. This represents the maximum total maintenance capacity for the m-th month. Let N be the week corresponding to the m-th month, and N be the total number of units. Let m be the set of all weeks contained in month m. Let y be the y-th deviation variable.

10. A maintenance plan optimization device for power system simulation operation, characterized in that, include: The data acquisition module is used to acquire unit data and historical maintenance data of the unit; The model building module is used to build a maintenance plan generation model based on unit data and historical maintenance data. The solver module is used to solve the maintenance plan generation model to obtain the maintenance plan; The maintenance plan generation model includes an objective function and constraints. The objective function aims to minimize the annual maintenance capacity deviation. The constraints include maintenance status constraints, maintenance start-up and end balance constraints, maintenance type constraints, maintenance frequency constraints, maintenance duration constraints, maintenance availability constraints, and deviation constraints.

Images