Day-ahead power generation plan compilation method and system considering probability constraint, computer equipment and storage medium

Abstract

The invention discloses a probability constraint-considered day-ahead power generation plan compiling method and system, computer equipment and a storage medium. The method comprises the steps of constructing a unit model required by day-ahead power generation plan compiling; generating a plurality of output prediction scenes with different confidence levels based on a new energy output prediction algorithm; taking the lowest total operation cost of a unit model required by a day-ahead power generation plan compilation scheme as an objective function, solving the objective function in an output prediction scene with the highest confidence level, and obtaining a corresponding unit commitment optimization result; solving the objective function in an output prediction scene with a second high confidence level to obtain a corresponding unit commitment optimization result; and so on, unit commitment optimization results under all output prediction scenes are obtained. And integrating unit commitment optimization results under all output prediction scenes by adopting a weighted average method to obtain a final day-ahead power generation plan scheme.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system dispatching automation, and specifically relates to a method, system, computer equipment and storage medium for compiling a day-ahead power generation plan taking probability constraints into consideration. Background Art

[0002] Renewable energy generation is characterized by randomness, intermittency and volatility. Its large-scale access poses severe challenges to the safe and stable operation of the power system. Therefore, the construction of a new power system requires, on the one hand, efforts to improve the flexible adjustment capabilities of the power system, and on the other hand, to strengthen the ability to ensure safe and reliable power supply. At present, thermal power will continue to serve as the "ballast stone" of power supply security for a long time. How to fully release the thermal power regulation capacity, achieve large-scale coordinated optimization, and help absorb a high proportion of new energy is a new challenge and an urgent problem that the new power system needs to solve.

[0003] At present, the existing day-ahead power generation plan preparation method is based on load forecasting, new energy power forecasting and the power generation capacity of various units to carry out deterministic planning, which fails to fully consider the uncertainty of new energy. The planning results fail to meet the large fluctuations of new energy, resulting in greater pressure on daily scheduling operations. At the same time, the power generation capacity of thermal power units is generated based on the static parameters of the units, which fails to fully consider the future operation obstructions of the units. Summary of the invention

[0004] Purpose of the invention: To solve the problem that the existing day-ahead power generation plan preparation method fails to fully consider the uncertainty of new energy, to solve the problem that the results produced by the existing day-ahead power generation plan preparation method fail to meet the large fluctuations of new energy, and to solve the problem that the power generation capacity of the thermal power unit in the existing day-ahead power generation plan preparation method is generated based on the static parameters of the unit and fails to fully consider the future operation obstruction of the unit, the present invention proposes a day-ahead power generation plan preparation method, system, computer equipment and storage medium considering probability constraints.

[0005] Technical solution: A method for preparing a day-ahead power generation plan considering probability constraints, comprising the following steps:

[0006] Constructing a unit model required for the preparation of a day-ahead power generation plan, wherein the unit model includes a new energy unit model and other unit models;

[0007] Based on the new energy output prediction algorithm, multiple output prediction scenarios with different confidence levels are generated;

[0008] Taking the lowest total operating cost of the unit model required for the day-ahead power generation plan preparation as the objective function, the objective function is solved in the output forecast scenario with the highest confidence level to obtain the corresponding unit combination optimization result;

[0009] Under the output forecast scenario with the second highest confidence level, the objective function is solved to obtain the corresponding unit commitment optimization result;

[0010] By analogy, the unit combination optimization results under all output forecast scenarios are obtained;

[0011] The weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan.

[0012] Furthermore, the other unit models include a thermal power unit model and an energy storage unit model;

[0013] The objective function is to minimize the total operating cost of the unit model required for the preparation of the day-ahead power generation plan, which is expressed as:

[0014]

[0015] Where N G is the number of thermal power units, N T is the number of calculation periods, u it and u it-1 are the start and stop states of thermal power unit i in time periods t and t-1, SU i , SD i is the startup cost and shutdown cost of thermal power unit i, N S is the number of scenes, N c is the number of energy storage units, is the output of thermal power unit i in time period t in scenario s, F cc is the operating cost of energy storage unit c, is the output of energy storage unit c in time period t in scenario s, is the operating cost function of thermal power unit i in time period t in scenario s.

[0016] Furthermore, the objective function is solved by using constraint conditions; the constraint conditions include: thermal power unit operation constraints, energy storage unit operation constraints, new energy unit constraints and system operation constraints.

[0017] Furthermore, the thermal power unit operation constraints include thermal power unit output range constraints, thermal power unit ramp rate constraints and thermal power unit start and stop time constraints.

[0018] Furthermore, the energy storage unit operation constraints include: energy storage charging and discharging power constraints and energy storage quantity constraints.

[0019] Furthermore, the system operation constraints include: system balance constraints and system standby constraints.

[0020] Furthermore, in the output forecast scenario with the second highest confidence level, solving the objective function to obtain the corresponding unit combination optimization result; and so on, obtaining the unit combination optimization results in all output forecast scenarios can be replaced by the following steps:

[0021] The unit combination optimization result includes the combination state of each unit model and the output of each unit model;

[0022] The combined state of each unit model in the unit combination optimization result obtained under the output prediction scenario with the highest confidence level is set as the original basic solution;

[0023] In the output forecast scenario with the second highest confidence level, the original basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the original basic solution continues to participate in the optimization calculation in the output forecast scenario with the third highest confidence level; if not, the unit combination optimization result of the original basic solution is used as a unit power generation plan; then, in the output forecast scenario with the second highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the combined state of each unit model in the unit combination optimization result is used as the new basic solution;

[0024] In the output forecast scenario with the third highest confidence level, the original basic solution or the new basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the original basic solution or the new basic solution is used to continue to participate in the optimization calculation in the output forecast scenario with the fourth highest confidence level; if not, the unit combination optimization result of the original basic solution or the new basic solution is used as a unit power generation plan; then, in the output forecast scenario with the third highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the combined state of each unit model in the unit combination optimization result is used as the new basic solution;

[0025] By analogy, the unit combination optimization results under all output forecast scenarios are obtained.

[0026] Furthermore, the weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan. The specific operations include:

[0027] According to different confidence levels of the output forecast scenarios, weight factors corresponding to the unit commitment optimization results under each output forecast scenario are assigned;

[0028] According to the weight factors of the unit combination optimization results under each output forecast scenario, the weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan.

[0029] The present invention discloses a system for preparing a day-ahead power generation plan taking into account probability constraints, comprising:

[0030] A unit model building module is used to build a unit model required for the preparation of a day-ahead power generation plan, wherein the unit model includes a new energy unit model and other unit models;

[0031] An output prediction scenario generation module is used to generate multiple output prediction scenarios with different confidence levels based on a new energy output prediction algorithm;

[0032] The unit combination optimization module is used to take the lowest total operating cost of the unit model required for the day-ahead power generation plan preparation scheme as the objective function, solve the objective function in the output forecast scenario with the highest confidence level, and obtain the corresponding unit combination optimization result, which includes the combination state of each unit model and the output of each unit model; solve the objective function in the output forecast scenario with the second highest confidence level, and obtain the corresponding unit combination optimization result; and so on, to obtain the unit combination optimization results in all output forecast scenarios;

[0033] The day-ahead power generation plan preparation output module is used to integrate the unit combination optimization results under all output forecast scenarios using the weighted average method to obtain the final day-ahead power generation plan.

[0034] Furthermore, the other unit models include a thermal power unit model and an energy storage unit model;

[0035] The objective function is to minimize the total operating cost of the unit model required for the preparation of the day-ahead power generation plan, which is expressed as:

[0036]

[0037] Where N G is the number of thermal power units, N T is the number of calculation periods, u it and u it-1 are the start and stop states of thermal power unit i in time periods t and t-1, SU i , SD i is the startup cost and shutdown cost of thermal power unit i, N S is the number of scenes, N c is the number of energy storage units, is the output of thermal power unit i in time period t in scenario s, F cc is the operating cost of energy storage unit c, is the output of energy storage unit c in time period t in scenario s, is the operating cost function of thermal power unit i in time period t in scenario s.

[0038] Furthermore, the objective function is solved by using constraint conditions; the constraint conditions include: thermal power unit operation constraints, energy storage unit operation constraints, new energy unit constraints and system operation constraints.

[0039] Furthermore, the thermal power unit operation constraints include thermal power unit output range constraints, thermal power unit ramp rate constraints and thermal power unit start and stop time constraints.

[0040] Furthermore, the energy storage unit operation constraints include: energy storage charging and discharging power constraints and energy storage quantity constraints.

[0041] Furthermore, the system operation constraints include: system balance constraints and system standby constraints.

[0042] Furthermore, in the output forecast scenario with the second highest confidence level, solving the objective function to obtain the corresponding unit combination optimization result; and so on, obtaining the unit combination optimization results in all output forecast scenarios can be replaced by the following steps:

[0043] The unit combination optimization result includes the combination state of each unit model and the output of each unit model;

[0044] The combined state of each unit model in the unit combination optimization result obtained under the output prediction scenario with the highest confidence level is set as the original basic solution;

[0045] In the output forecast scenario with the second highest confidence level, the original basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the original basic solution continues to participate in the optimization calculation in the output forecast scenario with the third highest confidence level; if not, the unit combination optimization result of the original basic solution is used as a unit power generation plan; then, in the output forecast scenario with the second highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the combined state of each unit model in the unit combination optimization result is used as the new basic solution;

[0046] In the output forecast scenario with the third highest confidence level, the original basic solution or the new basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the original basic solution or the new basic solution is used to continue to participate in the optimization calculation in the output forecast scenario with the fourth highest confidence level; if not, the unit combination optimization result of the original basic solution or the new basic solution is used as a unit power generation plan; then, in the output forecast scenario with the third highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the combined state of each unit model in the unit combination optimization result is used as the new basic solution;

[0047] By analogy, the unit combination optimization results under all output forecast scenarios are obtained.

[0048] Furthermore, the weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan. The specific operations include:

[0049] According to different confidence levels of the output forecast scenarios, weight factors corresponding to the unit commitment optimization results under each output forecast scenario are assigned;

[0050] According to the weight factors of the unit combination optimization results under each output forecast scenario, the weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan.

[0051] The present invention discloses a computer device, including a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for compiling a day-ahead power generation plan considering probability constraints disclosed above are implemented.

[0052] The present invention discloses a storage medium storing a day-ahead power generation plan compilation program. When the day-ahead power generation plan compilation program is executed by at least one processor, the steps of the day-ahead power generation plan compilation method considering probability constraints disclosed above are implemented.

[0053] Beneficial effects: Compared with the prior art, the present invention has the following advantages:

[0054] (1) The method / system of the present invention generates probabilistic multi-scenario data based on the results of renewable energy probability prediction and other models and boundary data required for day-ahead power generation planning. On this basis, a day-ahead unit commitment optimization objective function considering probability constraints is constructed, and the unit commitment decision results of all scenarios are calculated. Based on the different unit commitment decision results, a weighted average method is used to obtain a day-ahead power generation plan that takes into account both robustness and conservatism.

[0055] (2) The method / system of the present invention can proactively deal with the problem of strong uncertainty of new energy sources in the context of new power systems, and provide a powerful support means for daily dispatching and operation decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A flow chart of the method for preparing day-ahead power generation plans considering probabilistic scenarios;

[0058] Figure 2 Schematic diagram of the functional modules of the day-ahead power generation plan preparation system considering probabilistic scenarios. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present invention clearer, the following will further illustrate a method for compiling a day-ahead power generation plan considering probability constraints proposed by the present invention in conjunction with the accompanying drawings in the present invention.

[0060] Embodiment 1:

[0061] like Figure 1 This embodiment provides a method for preparing a day-ahead power generation plan considering probability constraints, which mainly includes the following steps:

[0062] Step 1: Generate output forecast scenarios with different confidence levels based on new energy probabilistic forecasting technology; based on the historical average accuracy level of deterministic new energy forecasts, taking into account the robustness and conservatism of the optimization scheme, output forecast scenarios with a confidence level of more than 60% can be selected for optimization calculation.

[0063] Step 2: Obtain various scenario models required for the preparation of the day-ahead power generation plan. The various scenario models mainly include the object definitions and attribute parameter information of various thermal power units, energy storage units and new energy units.

[0064] Obtain the data required for the preparation of the previous power generation plan, which mainly includes system load forecast, busbar load forecast, new energy output forecast, various types of obstruction information of thermal power units in the 96 periods of the day before, tie line planning data and standby demand planning data. Various types of obstruction information of thermal power units in the 96 periods of the day before, including but not limited to heating obstruction, obstruction due to poor coal quality and obstruction due to defects of thermal power units. Superimposing various types of obstruction information on the maximum and minimum technical outputs of thermal power units can obtain more reliable output range information of thermal power units.

[0065] Step 3: Establish a multi-scenario unit combination optimization model. Specifically include:

[0066] The unit combination optimization calculation is carried out for multiple output forecast scenarios with different confidence levels, with the lowest operating cost of each type of unit as the objective function. The operating cost includes the unit's conventional output cost, start-up and shutdown cost, and probabilistic scenario rescheduling cost, which is expressed as:

[0067]

[0068] Where N G is the number of thermal power units, N T is the number of calculation periods, u it and u it-1 are the start and stop states of thermal power unit i in time periods t and t-1, SU i , SD i is the startup and shutdown cost of thermal power unit i, N S is the number of scenes, N c is the number of energy storage units, is the output of thermal power unit i in time period t in scenario s, F cc is the operating cost of energy storage unit c, is the output of energy storage unit c in time period t in scenario s, is the operating cost function of thermal power unit i in time period t in scenario s, and the general expression is:

[0069]

[0070] Among them, a i , b i 、c i is the cost operation parameter of thermal power unit i.

[0071] The constraints take into account the operation constraints of thermal power units, energy storage units, new energy units and system operation constraints.

[0072] Specifically, the operation constraints of thermal power units include: thermal power unit output range constraints, thermal power unit ramp rate constraints and thermal power unit start and stop time constraints.

[0073] Among them, the output range constraint of thermal power units is expressed as:

[0074] P imin ≤P it ≤P imax

[0075] Where P imax and P imax are the maximum power generation and minimum power generation of thermal power unit i, respectively. Since the characteristics of thermal power units are the same in each scenario, the scenario information will not be specifically described (the same below). it is the power generation capacity of thermal power unit i in time period t.

[0076] Among them, the thermal power unit ramp rate constraint is expressed as:

[0077] -ΔP idown ≤P it -P it-1 ≤ΔP iup

[0078] P it-1 is the power generation of thermal power unit i in period t-1, ΔP iup is the maximum ramp rate of thermal power unit i, ΔP idown The maximum landslide velocity.

[0079] Among them, the start and stop time constraint of thermal power units is expressed as:

[0080]

[0081] Where, T i on and T i off are the minimum start-up time and minimum shutdown time of thermal power unit i respectively.

[0082] Specifically, the operation constraints of the energy storage unit include: energy storage charging and discharging power constraints and energy storage power constraints.

[0083] Among them, the energy storage charging and discharging power constraint is expressed as:

[0084]

[0085] Where P ct is the output power of energy storage unit c in period t, P ct d and P c c t are the discharge power and charging power of energy storage unit c in period t, P c dmax and P c dmin are the upper and lower limits of the discharge power of energy storage unit c, P c cmax and P c cmin They are the upper and lower limits of the charging power of energy storage unit c respectively.

[0086] Among them, the energy storage capacity constraint is expressed as:

[0087]

[0088] E cmin ≤E ct ≤E cmax

[0089] In the formula, α c is the charging efficiency coefficient of energy storage unit c, β c is the discharge efficiency coefficient of energy storage unit c, E ct is the accumulated power of energy storage unit c in period t, E ct-1 is the accumulated power of energy storage unit c in period t-1, E cmax and E cmin They are respectively the upper and lower limits of the accumulated power of energy storage unit c.

[0090] Specifically, the system operation constraints include: system balance constraints and system standby constraints.

[0091] Among them, the system balance constraint is expressed as:

[0092]

[0093] Where, L t is the load demand of the system in period t, P mt is the exchange power of tie line m in period t, N M is the number of tie lines in the power grid, N N is the number of new energy units, P nt is the predicted power of new energy unit n in time period t.

[0094] Among them, the system backup constraint is expressed as:

[0095]

[0096] In the formula, R t is the system's backup demand in period t.

[0097] Step 4: Solve the objective function, calculate the unit combination optimization results of all output forecast scenarios, and use the weighted average method to obtain the final day-ahead power generation plan. In this embodiment, weight factors corresponding to different unit combination optimization results can be assigned according to the probability size to ensure that the optimization results have good robustness and low conservatism.

[0098] In this embodiment, the following steps may be used to calculate the unit commitment optimization results for all output prediction scenarios, including:

[0099] In the output prediction scenario with the highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, each of which includes the combination state of each unit model and the output of each unit model;

[0100] Under the output forecast scenario with the second highest confidence level, the objective function is solved to obtain the corresponding unit commitment optimization result;

[0101] By analogy, the unit combination optimization results under all output forecast scenarios are obtained.

[0102] In this embodiment, the following steps may also be used to calculate the unit commitment optimization results of all output prediction scenarios, including:

[0103] The combined state of each unit model in the unit combination optimization result obtained under the output prediction scenario with the highest confidence level is set as the original basic solution;

[0104] In the output forecast scenario with the second highest confidence level, the original basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the optimization calculation of the output forecast scenario with the third highest confidence level is continued; if not, the unit power generation plan result of the original basic solution is used as a unit power generation plan scheme; then, in the output forecast scenario with the second highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the optimal solution is used as the new basic solution;

[0105] In the output forecast scenario with the third highest confidence level, the original basic solution or the new basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the optimization calculation of the output forecast scenario with the fourth highest confidence level is continued; if not, the unit power generation results of the original basic solution or the new basic solution are used as a unit power generation plan; then, in the output forecast scenario with the third highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the optimal solution is used as the new basic solution;

[0106] By analogy, the unit combination optimization results under all output forecast scenarios are obtained.

[0107] Embodiment 2:

[0108] like Figure 2 As shown, this embodiment proposes a system for preparing a day-ahead power generation plan considering probability constraints, which mainly includes the following modules:

[0109] A unit model building module is used to build the unit model required for the preparation of the day-ahead power generation plan, wherein the unit model includes a thermal power unit model, an energy storage unit model and a new energy unit model;

[0110] An output prediction scenario generation module is used to generate multiple output prediction scenarios with different confidence levels based on a new energy output prediction algorithm;

[0111] The unit combination optimization module is used to take the lowest total operating cost of the unit model required for the day-ahead power generation plan preparation scheme as the objective function, solve the objective function in the output forecast scenario with the highest confidence level, and obtain the corresponding unit combination optimization result, which includes the combination state of each unit model and the output of each unit model; solve the objective function in the output forecast scenario with the second highest confidence level, and obtain the corresponding unit combination optimization result; and so on, to obtain the unit combination optimization results in all output forecast scenarios;

[0112] The day-ahead power generation plan preparation output module is used to integrate the unit combination optimization results under all output forecast scenarios using the weighted average method to obtain the final day-ahead power generation plan.

[0113] In this embodiment, the following steps may also be used to calculate the unit commitment optimization results of all output prediction scenarios, including:

[0114] The combined state of each unit model in the unit combination optimization result obtained under the output prediction scenario with the highest confidence level is set as the original basic solution;

[0115] In the output forecast scenario with the second highest confidence level, the original basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the optimization calculation of the output forecast scenario with the third highest confidence level is continued; if not, the unit power generation plan result of the original basic solution is used as a unit power generation plan scheme; then, in the output forecast scenario with the second highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the optimal solution is used as the new basic solution;

[0116] In the output forecast scenario with the third highest confidence level, the original basic solution or the new basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the optimization calculation of the output forecast scenario with the fourth highest confidence level is continued; if not, the unit power generation results of the original basic solution or the new basic solution are used as a unit power generation plan; then, in the output forecast scenario with the third highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the optimal solution is used as the new basic solution;

[0117] By analogy, the unit combination optimization results under all output forecast scenarios are obtained.

[0118] Embodiment 3:

[0119] This embodiment discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps disclosed in any of the above embodiments are implemented.

[0120] Embodiment 4:

[0121] This embodiment discloses a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps disclosed in any of the above embodiments are implemented.

[0122] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0123] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0124] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for preparing a day-ahead power generation plan considering probability constraints, characterized in that: The following steps are involved: Constructing a unit model required for the preparation of a day-ahead power generation plan, wherein the unit model includes a new energy unit model and other unit models; Based on the new energy output prediction algorithm, multiple output prediction scenarios with different confidence levels are generated; Taking the lowest total operating cost of the unit model required for the day-ahead power generation plan preparation as the objective function, the objective function is solved in the output forecast scenario with the highest confidence level to obtain the corresponding unit combination optimization result; Under the output forecast scenario with the second highest confidence level, the objective function is solved to obtain the corresponding unit commitment optimization result; By analogy, the unit combination optimization results under all output forecast scenarios are obtained; The weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan.

2. A method for compiling a day-ahead power generation plan considering probability constraints according to claim 1, characterized in that: The other unit models include thermal power unit models and energy storage unit models; The objective function is to minimize the total operating cost of the unit model required for the preparation of the day-ahead power generation plan, which is expressed as: Where N G is the number of thermal power units, N T is the number of calculation periods, u it and u it-1 are the start and stop states of thermal power unit i in time periods t and t-1, SU i , SD i is the startup cost and shutdown cost of thermal power unit i, N S is the number of scenes, N c is the number of energy storage units, is the output of thermal power unit i in time period t in scenario s, F cc is the operating cost of energy storage unit c, is the output of energy storage unit c in time period t in scenario s, is the operating cost function of thermal power unit i in time period t in scenario s.

3. A method for compiling a day-ahead power generation plan considering probability constraints according to claim 2, characterized in that: The objective function is solved by using constraint conditions, wherein the constraint conditions include: thermal power unit operation constraints, energy storage unit operation constraints, new energy unit constraints and system operation constraints.

4. The method for compiling a day-ahead power generation plan considering probability constraints according to claim 3, characterized in that: The thermal power unit operation constraints include thermal power unit output range constraints, thermal power unit ramp rate constraints and thermal power unit start and stop time constraints.

5. The method for compiling a day-ahead power generation plan considering probability constraints according to claim 3, characterized in that: The energy storage unit operation constraints include: energy storage charging and discharging power constraints and energy storage quantity constraints.

6. The method for compiling a day-ahead power generation plan considering probability constraints according to claim 3, characterized in that: The system operation constraints include: system balance constraints and system standby constraints.

7. The method for compiling a day-ahead power generation plan considering probability constraints according to claim 1, characterized in that: In the output forecast scenario with the second highest confidence level, solving the objective function to obtain the corresponding unit combination optimization result; and so on, obtaining the unit combination optimization results in all output forecast scenarios can be replaced by the following steps: The unit combination optimization result includes the combination state of each unit model and the output of each unit model; The combined state of each unit model in the unit combination optimization result obtained under the output prediction scenario with the highest confidence level is set as the original basic solution; In the output forecast scenario with the second highest confidence level, the original basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the original basic solution continues to participate in the optimization calculation in the output forecast scenario with the third highest confidence level; if not, the unit combination optimization result of the original basic solution is used as a unit power generation plan; then, in the output forecast scenario with the second highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the combined state of each unit model in the unit combination optimization result is used as the new basic solution; In the output forecast scenario with the third highest confidence level, the original basic solution or the new basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the original basic solution or the new basic solution is used to continue to participate in the optimization calculation in the output forecast scenario with the fourth highest confidence level; if not, the unit combination optimization result of the original basic solution or the new basic solution is used as a unit power generation plan; then, in the output forecast scenario with the third highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the combined state of each unit model in the unit combination optimization result is used as the new basic solution; By analogy, the unit combination optimization results under all output forecast scenarios are obtained.

8. The method for compiling a day-ahead power generation plan considering probability constraints according to claim 1, characterized in that: The weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan. The specific operations include: According to different confidence levels of the output forecast scenarios, weight factors corresponding to the unit commitment optimization results under each output forecast scenario are assigned; According to the weight factors of the unit combination optimization results under each output forecast scenario, the weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan.

9. A system for preparing a day-ahead power generation plan considering probability constraints, characterized in that: include: A unit model building module is used to build a unit model required for the preparation of a day-ahead power generation plan, wherein the unit model includes a new energy unit model and other unit models; An output prediction scenario generation module is used to generate multiple output prediction scenarios with different confidence levels based on a new energy output prediction algorithm; The unit combination optimization module is used to take the lowest total operating cost of the unit model required for the day-ahead power generation plan preparation scheme as the objective function, solve the objective function in the output forecast scenario with the highest confidence level, and obtain the corresponding unit combination optimization result, which includes the combination state of each unit model and the output of each unit model; solve the objective function in the output forecast scenario with the second highest confidence level, and obtain the corresponding unit combination optimization result; and so on, to obtain the unit combination optimization results in all output forecast scenarios; The day-ahead power generation plan preparation output module is used to integrate the unit combination optimization results under all output forecast scenarios using the weighted average method to obtain the final day-ahead power generation plan.

10. A day-ahead power generation plan preparation system considering probability constraints according to claim 9, characterized in that: The other unit models include thermal power unit models and energy storage unit models; The objective function is to minimize the total operating cost of the unit model required for the preparation of the day-ahead power generation plan, which is expressed as: Where N G is the number of thermal power units, N T is the number of calculation periods, u it and u it-1 are the start and stop states of thermal power unit i in time periods t and t-1, SU i , SD i is the startup cost and shutdown cost of thermal power unit i, N S is the number of scenes, N c is the number of energy storage units, is the output of thermal power unit i in time period t in scenario s, F cc is the operating cost of energy storage unit c, is the output of energy storage unit c in time period t in scenario s, is the operating cost function of thermal power unit i in time period t in scenario s.

11. A day-ahead power generation plan preparation system considering probability constraints according to claim 9, characterized in that: The objective function is solved by using constraint conditions, wherein the constraint conditions include: thermal power unit operation constraints, energy storage unit operation constraints, new energy unit constraints and system operation constraints.

12. A system for preparing a day-ahead power generation plan considering probability constraints according to claim 11, characterized in that: The thermal power unit operation constraints include thermal power unit output range constraints, thermal power unit ramp rate constraints and thermal power unit start and stop time constraints.

13. A system for preparing a day-ahead power generation plan considering probability constraints according to claim 11, characterized in that: The energy storage unit operation constraints include: energy storage charging and discharging power constraints and energy storage quantity constraints.

14. A system for preparing a day-ahead power generation plan considering probability constraints according to claim 11, characterized in that: The system operation constraints include: system balance constraints and system standby constraints.

15. The system for preparing a day-ahead power generation plan considering probability constraints according to claim 9, characterized in that: In the output forecast scenario with the second highest confidence level, solving the objective function to obtain the corresponding unit combination optimization result; and so on, obtaining the unit combination optimization results in all output forecast scenarios can be replaced by the following steps: The unit combination optimization result includes the combination state of each unit model and the output of each unit model; The combined state of each unit model in the unit combination optimization result obtained under the output prediction scenario with the highest confidence level is set as the original basic solution; In the output forecast scenario with the second highest confidence level, the original basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the original basic solution continues to participate in the optimization calculation in the output forecast scenario with the third highest confidence level; if not, the unit combination optimization result of the original basic solution is used as a unit power generation plan; then, in the output forecast scenario with the second highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the combined state of each unit model in the unit combination optimization result is used as the new basic solution; In the output forecast scenario with the third highest confidence level, the original basic solution or the new basic solution is used to determine whether the optimal solution of the objective function can be obtained by adjusting the output of each unit model alone. If so, the original basic solution or the new basic solution is used to continue to participate in the optimization calculation in the output forecast scenario with the fourth highest confidence level; if not, the unit combination optimization result of the original basic solution or the new basic solution is used as a unit power generation plan; then, in the output forecast scenario with the third highest confidence level, the objective function is solved to obtain the corresponding unit combination optimization result, and the combined state of each unit model in the unit combination optimization result is used as the new basic solution; By analogy, the unit combination optimization results under all output forecast scenarios are obtained.

16. A system for preparing a day-ahead power generation plan taking into account probability constraints according to claim 9, characterized in that: The weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan. The specific operations include: According to different confidence levels of the output forecast scenarios, weight factors corresponding to the unit commitment optimization results under each output forecast scenario are assigned; According to the weight factors of the unit combination optimization results under each output forecast scenario, the weighted average method is used to integrate the unit combination optimization results under all output forecast scenarios to obtain the final day-ahead power generation plan.

17. A computer device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a method for preparing a day-ahead power generation plan taking into account probability constraints as described in any one of claims 1 to 8 are implemented.

18. A storage medium, characterized in that: The storage medium stores a day-ahead power generation plan compilation program, and when the day-ahead power generation plan compilation program is executed by at least one processor, the steps of a day-ahead power generation plan compilation method considering probability constraints as described in any one of claims 1 to 8 are implemented.

Images