A multi-time scale intelligent scheduling method for offshore wind power energy storage system

Abstract

The application discloses a multi-time scale intelligent scheduling method for an offshore wind power energy storage system. The method provided by the application determines the optimal number of open thermal power generating units based on a larger time scale, and adjusts other power generation output powers based on a smaller time scale. The method does not need to open enough thermal power generating units in advance to cope with the volatility of wind power as in traditional scheduling schemes, reduces power generation cost, and is more environmentally friendly.

Description

Technical Field

[0001] This invention relates to the field of new energy technology, and in particular to a multi-timescale intelligent scheduling method for offshore wind power energy storage systems. Background Technology

[0002] Because wind power is greatly affected by natural factors and exhibits high uncertainty, current technologies rely on increasing the reserve capacity of thermal power plants to address potential fluctuations in wind power output in order to ensure the safe and stable operation of the power system. This approach is detrimental to both power generation costs and environmental protection.

[0003] Therefore, existing technologies still need to be improved and enhanced. Summary of the Invention

[0004] To address the aforementioned shortcomings of existing technologies, this invention provides a multi-timescale intelligent scheduling method for offshore wind power energy storage systems, aiming to solve the environmentally unfriendly problem of adjusting wind power output fluctuations by increasing the reserve capacity of thermal power plants in existing technologies.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0006] A first aspect of the present invention provides a multi-timescale intelligent scheduling method for offshore wind power energy storage systems, the method comprising:

[0007] Obtain first forecast information before the target date. The first forecast information includes first wind power forecast information and first electricity load demand forecast information within the target date. The first wind power forecast information is obtained based on wind forecast data.

[0008] Based on the first prediction information, multiple solutions to the scheduling scheme are randomly generated and added to the target set. The scheduling scheme includes the output power of the wind turbines, the charging and discharging status of the energy storage system, the charging and discharging power of the energy storage system, the number of thermal power units in operation, and the output power of the thermal power units for each time period within the target date. The solutions in the target set are iteratively mutated and optimized to obtain the target scheduling scheme within the target date.

[0009] Within the target date, within the target time period, obtain the second forecast information for the next time period, the second forecast information including the second wind power forecast information and the second electricity load forecast demand information;

[0010] Based on the difference information, the output power of the wind turbines, the output power of the activated thermal power generators, the charging and discharging status of the energy storage system, and the charging / discharging power of the energy storage system in the next time period of the target scheduling scheme are updated. The difference information includes the difference between the second wind power prediction information and the first wind power prediction information, and the difference between the second user load demand prediction information and the first electricity load demand prediction information.

[0011] The multi-timescale intelligent scheduling method for offshore wind power energy storage systems, wherein the iterative mutation optimization of solutions in the target set includes:

[0012] In each iteration, perform the following operations:

[0013] The solutions in the target set are subjected to crossover mutation to obtain a first solution, and the first solution is added to the target set;

[0014] The solutions in the target set are constrained based on power grid constraints to update the target set;

[0015] The solutions in the target set are sorted according to the objective function value corresponding to each solution in the updated target set, and a preset number of solutions are retained in the target set according to the sorting result;

[0016] End the current iteration, and re-execute the step of performing crossover mutation on the solutions in the target set to start a new round of iterations until the preset number of iterations is reached;

[0017] The objective function value includes multiple sub-objective function values, which include a first sub-objective function value, a second sub-objective function value, a third sub-objective function value, and a fourth sub-objective function value.

[0018] The value of the first sub-objective function is obtained based on the operating cost of the wind turbine.

[0019] The value of the second sub-objective function is obtained based on the operating cost of thermal power units;

[0020] The value of the third sub-objective function is obtained based on the energy storage consumption cost;

[0021] The value of the fourth sub-objective function is obtained based on a preset formula for calculating wind curtailment penalty.

[0022] The multi-timescale intelligent scheduling method for offshore wind power energy storage systems includes the following grid constraints: wind turbine operation constraints, thermal power unit operation constraints, grid security constraints, grid fluctuation constraints, spinning reserve constraints, and branch power flow constraints.

[0023] The multi-timescale intelligent scheduling method for offshore wind power energy storage systems, wherein the step of sorting the solutions in the target set according to the sub-objective function value corresponding to each solution in the updated target set includes:

[0024] Sort the results according to the weighted summation of the sub-objective function values ​​corresponding to each solution in the updated objective set;

[0025] The sorted solutions are divided into several layers. The solutions in the first n layers are kept in the target set, and the remaining solutions are removed from the target set. n satisfies the first objective condition, which is: the number of all solutions in the first n-1 layers is less than the preset number, and the number of all solutions in the first n layers is greater than the preset number.

[0026] For each layer retained in the target set, the solutions in that layer are sorted according to the corresponding m-th sub-objective function value. After sorting, the difference coefficients corresponding to all solutions in each layer are calculated. The difference coefficients reflect the differences between two adjacent solutions.

[0027] At least one solution is removed from the target set based on the difference coefficient corresponding to the solution in the target set, so that the number of solutions in the target set is the preset number.

[0028] The multi-timescale intelligent scheduling method for offshore wind power energy storage systems, wherein calculating the difference coefficients corresponding to all solutions in each layer includes:

[0029] Obtain the values ​​of each of the sub-objective functions corresponding to two adjacent solutions of the objective solution;

[0030] The sum of each sub-difference result is obtained as the difference coefficient corresponding to the objective solution, wherein the x-th sub-difference result is the distance between the x-th sub-objective function values ​​corresponding to the two adjacent solutions.

[0031] The multi-timescale intelligent scheduling method for offshore wind power energy storage systems, wherein removing at least one solution from the target set based on the difference coefficient corresponding to the solutions in the target set, such that the number of solutions in the target set is the preset number, includes:

[0032] Select M pairs of target solutions from the target set. The target solution pairs satisfy the second target condition, which is that the two solutions in the target solution pair belong to the same layer, and the difference between the difference coefficients of the two solutions in the target solution pair is within a preset range, where M is the difference between the number of solutions in the current target set and the preset number.

[0033] For the target solution pair belonging to the k-th layer, the solutions of the (k-1)-th layer, the (k+1)-th layer, and the k-th layer are added to the new layer. The difference coefficients corresponding to the target solution pair in the new layer are calculated. The solutions with larger difference coefficients in the new layer are retained in the target set, while the solutions with smaller difference coefficients in the new layer are removed from the target set.

[0034] The multi-timescale intelligent scheduling method for offshore wind power energy storage systems, wherein updating the output power of wind turbines, the output power of activated thermal power generators, the charging / discharging status of the energy storage system, and the charging / discharging power of the energy storage system in the next time period of the target scheduling scheme based on difference information includes:

[0035] Based on the optimization objective of minimizing power fluctuations on the power grid interconnection line, the power generation of wind turbines, the power generation of activated thermal power generators, the charging and discharging status of energy storage systems, and the charging / discharging power of energy storage systems in the scheduling data for the next time period are updated according to the difference information.

[0036] A second aspect of the present invention provides a multi-timescale intelligent scheduling device for an offshore wind power energy storage system, comprising:

[0037] The day-ahead forecasting module is used to obtain first forecast information before the target date. The first forecast information includes first wind power forecast information and first electricity load demand forecast information within the target date. The first wind power forecast information is obtained based on wind forecast data.

[0038] The day-ahead scheduling module is used to randomly generate multiple scheduling scheme solutions based on the first prediction information and add them to the target set. The scheduling scheme includes the output power of wind turbines, the charging and discharging status of energy storage systems, the charging and discharging power of energy storage systems, the number of thermal power units in operation, and the output power of thermal power units for each time period within the target date. The solution in the target set is iteratively mutated and optimized to obtain the target scheduling scheme within the target date.

[0039] The daytime forecasting module is used to obtain second forecast information for the next time period within the target time period on the target date. The second forecast information includes second wind power forecast information and second electricity load forecast demand information.

[0040] The daytime scheduling module is used to update the output power of wind turbines, the output power of activated thermal power generators, the charging and discharging status of energy storage systems, and the charging / discharging power of energy storage systems in the next time period of the target scheduling scheme based on the difference information. The difference information includes the difference between the second wind power prediction information and the first wind power prediction information, and the difference between the second user load demand prediction information and the first electricity load demand prediction information.

[0041] A third aspect of the present invention provides a terminal, the terminal including a processor and a computer-readable storage medium communicatively connected to the processor, the computer-readable storage medium being adapted to store a plurality of instructions, and the processor being adapted to invoke the instructions in the computer-readable storage medium to execute the steps of implementing the multi-timescale intelligent scheduling method for the offshore wind power energy storage system described in any of the preceding claims.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the multi-timescale intelligent scheduling method for offshore wind power energy storage systems described in any of the preceding claims.

[0043] Compared with existing technologies, this invention provides a multi-timescale intelligent scheduling method and related equipment for offshore wind power energy storage systems. The method obtains first wind power prediction information and first electricity load demand prediction information based on wind forecast data before the target date, generates an initial solution for the scheduling scheme, and iteratively optimizes the solution under constraints. The scheduling scheme includes the output power of wind turbines, the charging and discharging status of the energy storage system, the charging and discharging power of the energy storage system, the number of activated thermal power units, and the output power of the thermal power units for each time period within the target date. After determining the optimal solution as the target scheduling scheme, the second wind power forecast and the second electricity load demand forecast for the next time period are obtained within the previous time period before the target date. The target scheduling scheme generated before the target date is updated at the time period level based on the new forecast information. During the update, the status of whether the thermal power units in the scheduling scheme are turned on is not updated. In this way, the optimal number of thermal power units to be turned on is determined first based on a larger time scale, and then other power generation output is adjusted based on a smaller time scale. Unlike traditional scheduling schemes, it is not necessary to turn on enough thermal power units in advance to cope with the fluctuation of wind power, which reduces the power generation cost and is more environmentally friendly. Attached Figure Description

[0044] Figure 1A flowchart illustrating an embodiment of the multi-timescale intelligent scheduling method for offshore wind power energy storage systems provided by the present invention;

[0045] Figure 2 A structural schematic diagram of an embodiment of the multi-timescale intelligent scheduling device for an offshore wind power energy storage system provided by the present invention;

[0046] Figure 3 A schematic diagram illustrating the principle of an embodiment of the terminal provided by the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0048] The multi-timescale intelligent scheduling method for offshore wind power energy storage systems provided by this invention can be applied to terminals with computing capabilities. The terminals can execute the multi-timescale intelligent scheduling method for offshore wind power energy storage systems provided by this invention to perform grid scheduling. The terminals can be, but are not limited to, various computers, mobile terminals, smart home appliances, wearable devices, etc.

[0049] Example 1

[0050] like Figure 1 As shown, one embodiment of the multi-timescale intelligent scheduling method for the offshore wind power energy storage system includes the following steps:

[0051] S100. Obtain first forecast information before the target date. The first forecast information includes first wind power forecast information and first electricity load demand forecast information within the target date. The first wind power forecast information is obtained based on wind forecast data.

[0052] In the scheduling method provided in this embodiment, to avoid operating an excessive number of thermal power units unnecessarily to cope with wind power fluctuations, before the target date, first wind power forecast information for the target date is obtained based on wind forecast data, and first electricity load demand forecast information for the target date is also obtained. The first electricity load demand forecast information can be predicted based on actual user electricity consumption data over a certain period before the target date, and can also be calculated in conjunction with production schedules reported by each user. Specifically, the first wind power forecast information includes wind power forecast results for each time period within the target date, and the first electricity load demand forecast information includes electricity load demand forecast results for each time period within the target date.

[0053] S200. Based on the first prediction information, randomly generate solutions for multiple scheduling schemes and add them to the target set. The scheduling scheme includes the output power of wind turbines, the charging and discharging status of energy storage systems, the charging and discharging power of energy storage systems, the number of thermal power units in operation, and the output power of thermal power units for each time period within the target date. Iteratively mutate and optimize the solutions in the target set to obtain the target scheduling scheme within the target date.

[0054] Based on the first prediction information, multiple scheduling schemes that satisfy the first prediction information can be generated. Specifically, the scheduling scheme includes the output power of wind turbines, the charging and discharging status of energy storage systems, the charging and discharging power of energy storage systems, the number of thermal power units in operation, and the output power of thermal power units for each time period within the target date. Subsequently, a mutation approach is used to search for a better scheduling scheme solution. The finally determined optimal solution serves as the framework for scheduling the output power of wind turbines, the charging and discharging status of energy storage systems, the charging and discharging power of energy storage systems, the number of thermal power units in operation, and the output power of thermal power units within the target date. The scheduling scheme is then adjusted within the target date by incorporating prediction information over a smaller time scale.

[0055] Specifically, the iterative mutation optimization of the solutions in the target set includes:

[0056] In each iteration, perform the following operations:

[0057] The solutions in the target set are subjected to crossover mutation to obtain a first solution, and the first solution is added to the target set;

[0058] The solutions in the target set are constrained based on power grid constraints to update the target set;

[0059] The solutions in the target set are sorted according to the objective function value corresponding to each solution in the updated target set, and a preset number of solutions are retained in the target set according to the sorting result;

[0060] End the current iteration, and re-execute the step of performing crossover mutation on the solutions in the target set to start a new round of iterations until the preset number of iterations is reached.

[0061] Specifically, in this embodiment, the evaluation of the quality of the scheduling scheme corresponding to different solutions is determined based on the objective function value corresponding to the solution. That is, based on the scheduling scheme corresponding to the solution, the corresponding objective function value is calculated. The better the objective function value, the better the corresponding scheduling scheme.

[0062] In this embodiment, the objective function value includes multiple sub-objective function values, which include a first sub-objective function value, a second sub-objective function value, a third sub-objective function value, and a fourth sub-objective function value.

[0063] The value of the first sub-objective function is obtained based on the operating cost of the wind turbine.

[0064] The value of the second sub-objective function is obtained based on the operating cost of thermal power units;

[0065] The value of the third sub-objective function is obtained based on the energy storage consumption cost;

[0066] The value of the fourth sub-objective function is obtained based on a preset formula for calculating wind curtailment penalty.

[0067] Specifically, on the one hand, to improve the economic efficiency of the power grid system, it is desirable to minimize the operating costs of generator units and the consumption costs of energy storage systems. Therefore, a first sub-objective function value, a second sub-objective function value, and a third sub-objective function value are set. On the other hand, considering the maximization of green energy utilization, it is also desirable to utilize wind power as much as possible. Therefore, a fourth sub-objective function value is set. The wind curtailment penalty calculation formula is used to calculate the wind curtailment penalty value, which is positively correlated with the abandoned wind power resources. However, it is not difficult to see that some of these sub-objective function values ​​are contradictory, and it is impossible to achieve the optimal value for all sub-objective function values. For example, minimizing the operating cost of wind turbine units will obviously increase the operating cost of thermal power units. In this embodiment, different weights can be set for each sub-objective function value according to different actual needs. The objective function value is obtained by weighted summation of all sub-objective function values, and the optimal scheduling scheme for the objective function value is found through iteration.

[0068] Specifically, in order to make the obtained scheduling scheme feasible in reality, grid constraints are set in this embodiment. The scheduling scheme should meet the grid constraints, which include wind turbine operation constraints, thermal power unit operation constraints, grid security constraints, grid fluctuation constraints, spinning reserve constraints, and branch power flow constraints.

[0069] The step of sorting the solutions in the target set according to the sub-objective function value corresponding to each solution in the updated target set includes:

[0070] Sort the results according to the weighted summation of the sub-objective function values ​​corresponding to each solution in the updated objective set;

[0071] The sorted solutions are divided into several layers. The solutions in the first n layers are kept in the target set, and the remaining solutions are removed from the target set. n satisfies the first objective condition, which is: the number of all solutions in the first n-1 layers is less than the preset number, and the number of all solutions in the first n layers is greater than the preset number.

[0072] For each layer retained in the target set, the solutions in that layer are sorted according to the corresponding m-th sub-objective function value. After sorting, the difference coefficients corresponding to all solutions in each layer are calculated. The difference coefficients reflect the differences between two adjacent solutions.

[0073] At least one solution is removed from the target set based on the difference coefficient corresponding to the solution in the target set, so that the number of solutions in the target set is the preset number.

[0074] For the solutions in the target set, they are sorted according to the merit order of the corresponding objective function values ​​and divided into several layers. The solutions in the first n layers are retained in the target set, and the remaining solutions are discarded. The number of solutions in the first n-1 layers is less than the preset number, and the number of solutions in the first n layers is greater than the preset number. At this time, the number of solutions in the target set is greater than the preset number, and some solutions need to be removed. In the method provided in this embodiment, for each layer retained in the target set, the m-th sub-objective function value is sorted according to its merit order. Specifically, the m-th sub-objective function value can be the first sub-objective function value, the second sub-objective function value, the third sub-objective function value, or the fourth sub-objective function value. The sub-objective function value with the largest weight is used for sorting within the layer, which prioritizes the sub-objective function value with the largest weight and approaches the optimal solution faster.

[0075] The difference coefficient corresponding to the solution reflects the difference between two adjacent solutions (the previous solution and the next solution) after sorting. The greater the difference, the more likely the mutation of that solution will produce a solution with even greater difference, thus broadening the search range for the optimal solution. Specifically, calculating the difference coefficient corresponding to all solutions in each layer includes:

[0076] Obtain the values ​​of each of the sub-objective functions corresponding to two adjacent solutions of the objective solution;

[0077] The sum of each sub-difference result is obtained as the difference coefficient corresponding to the objective solution, wherein the x-th sub-difference result is the distance between the x-th sub-objective function values ​​corresponding to the two adjacent solutions.

[0078] The step of removing at least one solution from the target set based on the difference coefficient corresponding to the solutions in the target set, so that the number of solutions in the target set is the preset number, includes:

[0079] Select M pairs of target solutions from the target set. The target solution pairs satisfy the second target condition, which is that the two solutions in the target solution pair belong to the same layer, and the difference between the difference coefficients of the two solutions in the target solution pair is within a preset range, where M is the difference between the number of solutions in the current target set and the preset number.

[0080] For the target solution pair belonging to the k-th layer, the solutions of the (k-1)-th layer, the (k+1)-th layer, and the k-th layer are added to the new layer. The difference coefficients corresponding to the target solution pair in the new layer are calculated. The solutions with larger difference coefficients in the new layer are retained in the target set, while the solutions with smaller difference coefficients in the new layer are removed from the target set.

[0081] For two solutions with similar difference coefficients in a layer, one can be removed to avoid the mutation generating too many similar solutions, which would affect the optimization efficiency of the algorithm. Specifically, after expanding the two solutions into a larger range, their corresponding difference coefficients are determined, and the solution with the smaller difference coefficient is removed from the target set.

[0082] Once the number of solutions in the target set reaches the preset number, one iteration ends and a new iteration begins, that is, the step of cross-mutating the solutions in the target set is repeated until the preset number of iterations is reached.

[0083] After reaching a preset number of iterations, the scheduling scheme of the optimal solution in the target set (the solution with the optimal objective function value) is taken as the target scheduling scheme.

[0084] Please refer to it again. Figure 1 The method provided in this embodiment further includes the following steps:

[0085] S300. Within the target date, within the target time period, obtain the second forecast information for the next time period, the second forecast information including the second wind power forecast information and the second electricity load forecast demand information.

[0086] S400. Update the output power of the wind turbines, the output power of the activated thermal power generators, the charging and discharging status of the energy storage system, and the charging / discharging power of the energy storage system in the next time period of the target scheduling scheme according to the difference information. The difference information includes the difference between the second wind power prediction information and the first wind power prediction information, and the difference between the second user load demand prediction information and the first electricity load demand prediction information.

[0087] After obtaining the target scheduling scheme corresponding to the target date, the target scheduling scheme is executed in the first time period of the target date. The second wind power forecast information and the second electricity load forecast demand information for the next time period are obtained in real time. They are compared with the first wind power forecast information and the first user load forecast demand information used to generate the target scheduling scheme to obtain difference information. Based on the difference information, the output power of the wind turbines, the output power of the activated thermal power generators, the charging and discharging status of the energy storage system, and the charging / discharging power of the energy storage system for the next time period in the target scheduling scheme are updated.

[0088] Specifically, since starting and operating thermal power units requires a long time and incurs significant costs, in this embodiment, after generating the target scheduling scheme based on the predicted information before the target date and determining the operating status (on or off) of each thermal power unit, the corresponding thermal power units are started within the target date according to their operating status in the target scheduling scheme, and no new thermal power units are started thereafter. Although the predicted information within the target date differs from the predicted information before the target date, the difference is not significant. Therefore, real-time fluctuations can be addressed using only wind turbines, already-operated thermal power units, and energy storage systems. Updating the output power of wind turbines, the output power of the operated thermal power units, the charging / discharging status of the energy storage system, and the charging / discharging power of the energy storage system for the next time period in the target scheduling scheme based on the difference information includes:

[0089] Based on the optimization objective of minimizing power fluctuations on the power grid interconnection line, the power generation of wind turbines, the power generation of activated thermal power generators, the charging and discharging status of energy storage systems, and the charging / discharging power of energy storage systems in the scheduling data for the next time period are updated according to the difference information.

[0090] When updating the target scheduling scheme, the optimization objective is to minimize power fluctuations on the power grid interconnection line to ensure the stability of external power supply.

[0091] In summary, this embodiment provides a multi-timescale intelligent scheduling method for offshore wind power energy storage systems. Based on wind forecast data prior to the target date, it obtains first wind power prediction information and first electricity load demand prediction information, generating an initial solution for the scheduling scheme. Under constraints, iteratively optimizes the solution through mutation. The scheduling scheme includes the output power of wind turbines, the charging and discharging status of the energy storage system, the charging and discharging power of the energy storage system, the number of activated thermal power units, and the output power of the thermal power units for each time period within the target date. After obtaining the optimal solution as the target scheduling scheme, it obtains second wind power prediction information and second electricity load demand prediction information for the next time period within the previous time period within the target date. Based on the new prediction information, it updates the target scheduling scheme generated before the target date at the time-scale level. During the update, it does not update the activation status of thermal power units in the scheduling scheme. Thus, by first determining the optimal number of activated thermal power units based on a larger time scale, and then adjusting the output power of other power generation units based on a smaller time scale, it eliminates the need to activate enough thermal power units in advance to cope with wind power fluctuations, as is required in traditional scheduling schemes, reducing power generation costs and making it more environmentally friendly.

[0092] It should be understood that although the steps in the flowcharts shown in the accompanying drawings are displayed sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0093] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0094] Example 2

[0095] Based on the above embodiments, the present invention also provides a multi-time-scale intelligent scheduling device for offshore wind power energy storage systems, such as... Figure 2 As shown, the multi-timescale intelligent scheduling device for the offshore wind power energy storage system includes:

[0096] The day-ahead forecasting module is used to obtain first forecast information before the target date. The first forecast information includes first wind power forecast information and first electricity load demand forecast information within the target date. The first wind power forecast information is obtained based on wind forecast data, as specifically described in Embodiment 1.

[0097] The day-ahead scheduling module is used to randomly generate multiple scheduling scheme solutions based on the first prediction information and add them to the target set. The scheduling scheme includes the output power of wind turbines, the charging and discharging status of energy storage systems, the charging and discharging power of energy storage systems, the number of thermal power units in operation, and the output power of thermal power units for each time period within the target date. The solution in the target set is iteratively mutated and optimized to obtain the target scheduling scheme within the target date, as specifically described in Embodiment 1.

[0098] The daytime forecasting module is used to obtain second forecast information for the next time period within the target time period on the target date. The second forecast information includes second wind power forecast information and second electricity load forecast demand information, as specifically described in Embodiment 1.

[0099] The daytime scheduling module is used to update the output power of wind turbines, the output power of activated thermal power generators, the charging and discharging status of energy storage systems, and the charging / discharging power of energy storage systems in the next time period of the target scheduling scheme based on the difference information. The difference information includes the difference between the second wind power prediction information and the first wind power prediction information, and the difference between the second user load demand prediction information and the first electricity load demand prediction information, as specifically described in Embodiment 1.

[0100] Example 3

[0101] Based on the above embodiments, the present invention also provides a terminal, such as... Figure 3 As shown, the terminal includes a processor 10 and a memory 20. Figure 3 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0102] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a multi-timescale intelligent scheduling program 30 for an offshore wind power energy storage system. This multi-timescale intelligent scheduling program 30 can be executed by the processor 10, thereby implementing the multi-timescale intelligent scheduling method for the offshore wind power energy storage system in this application.

[0103] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other chip, used to run program code stored in the memory 20 or process data, such as executing the multi-timescale intelligent scheduling method of the offshore wind power energy storage system.

[0104] In one embodiment, when the processor 10 executes the multi-timescale intelligent scheduling program 30 for the offshore wind power energy storage system in the memory 20, the following steps are performed:

[0105] Obtain first forecast information before the target date. The first forecast information includes first wind power forecast information and first electricity load demand forecast information within the target date. The first wind power forecast information is obtained based on wind forecast data.

[0106] Based on the first prediction information, multiple scheduling schemes are randomly generated and added to the target set. The scheduling scheme includes the output power of wind turbines, the charging and discharging status of energy storage systems, the charging and discharging power of energy storage systems, the number of thermal power units in operation, and the output power of thermal power units for each time period within the target date. The solutions in the target set are iteratively mutated and optimized to obtain the target scheduling scheme within the target date.

[0107] Within the target date, within the target time period, obtain the second forecast information for the next time period, the second forecast information including the second wind power forecast information and the second electricity load forecast demand information;

[0108] Based on the difference information, the output power of the wind turbines, the output power of the activated thermal power generators, the charging and discharging status of the energy storage system, and the charging / discharging power of the energy storage system in the next time period of the target scheduling scheme are updated. The difference information includes the difference between the second wind power prediction information and the first wind power prediction information, and the difference between the second user load demand prediction information and the first electricity load demand prediction information.

[0109] The iterative mutation optimization of the solutions in the target set includes:

[0110] In each iteration, perform the following operations:

[0111] The solutions in the target set are subjected to crossover mutation to obtain a first solution, and the first solution is added to the target set;

[0112] The solutions in the target set are constrained based on power grid constraints to update the target set;

[0113] The solutions in the target set are sorted according to the objective function value corresponding to each solution in the updated target set, and a preset number of solutions are retained in the target set according to the sorting result;

[0114] End the current iteration, and re-execute the step of performing crossover mutation on the solutions in the target set to start a new round of iterations until the preset number of iterations is reached;

[0115] The objective function value includes multiple sub-objective function values, which include a first sub-objective function value, a second sub-objective function value, a third sub-objective function value, and a fourth sub-objective function value.

[0116] The value of the first sub-objective function is obtained based on the operating cost of the wind turbine.

[0117] The value of the second sub-objective function is obtained based on the operating cost of thermal power units;

[0118] The value of the third sub-objective function is obtained based on the energy storage consumption cost;

[0119] The value of the fourth sub-objective function is obtained based on a preset formula for calculating wind curtailment penalty.

[0120] The grid constraints include: wind turbine operation constraints, thermal power unit operation constraints, grid security constraints, grid fluctuation constraints, spinning reserve constraints, and branch power flow constraints.

[0121] The step of sorting the solutions in the target set according to the sub-objective function value corresponding to each solution in the updated target set includes:

[0122] Sort the results according to the weighted summation of the sub-objective function values ​​corresponding to each solution in the updated objective set;

[0123] The sorted solutions are divided into several layers. The solutions in the first n layers are kept in the target set, and the remaining solutions are removed from the target set. n satisfies the first objective condition, which is: the number of all solutions in the first n-1 layers is less than the preset number, and the number of all solutions in the first n layers is greater than the preset number.

[0124] For each layer retained in the target set, the solutions in that layer are sorted according to the corresponding m-th sub-objective function value. After sorting, the difference coefficients corresponding to all solutions in each layer are calculated. The difference coefficients reflect the differences between two adjacent solutions.

[0125] At least one solution is removed from the target set based on the difference coefficient corresponding to the solution in the target set, so that the number of solutions in the target set is the preset number.

[0126] The calculation of the difference coefficients corresponding to all solutions in each layer includes:

[0127] Obtain the values ​​of each of the sub-objective functions corresponding to two adjacent solutions of the objective solution;

[0128] The sum of each sub-difference result is obtained as the difference coefficient corresponding to the objective solution, wherein the x-th sub-difference result is the distance between the x-th sub-objective function values ​​corresponding to the two adjacent solutions.

[0129] The step of removing at least one solution from the target set based on the difference coefficient corresponding to the solutions in the target set, so that the number of solutions in the target set is the preset number, includes:

[0130] Select M pairs of target solutions from the target set. The target solution pairs satisfy the second target condition, which is that the two solutions in the target solution pair belong to the same layer, and the difference between the difference coefficients of the two solutions in the target solution pair is within a preset range, where M is the difference between the number of solutions in the current target set and the preset number.

[0131] For the target solution pair belonging to the k-th layer, the solutions of the (k-1)-th layer, the (k+1)-th layer, and the k-th layer are added to the new layer. The difference coefficients corresponding to the target solution pair in the new layer are calculated. The solutions with larger difference coefficients in the new layer are retained in the target set, while the solutions with smaller difference coefficients in the new layer are removed from the target set.

[0132] The step of updating the output power of wind turbines, the output power of activated thermal power generators, the charging / discharging status of energy storage systems, and the charging / discharging power of energy storage systems in the next time period according to the difference information includes:

[0133] Based on the optimization objective of minimizing power fluctuations on the power grid interconnection line, the power generation of wind turbines, the power generation of activated thermal power generators, the charging and discharging status of energy storage systems, and the charging / discharging power of energy storage systems in the scheduling data for the next time period are updated according to the difference information.

[0134] Example 4

[0135] The present invention also provides a computer-readable storage medium storing one or more programs, which can be executed by one or more processors to implement the steps of the multi-timescale intelligent scheduling method for offshore wind power energy storage systems as described above.

[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; 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; and these 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 multi-timescale intelligent scheduling method for offshore wind power energy storage systems, characterized in that, The method includes: Obtain first forecast information before the target date. The first forecast information includes first wind power forecast information and first electricity load demand forecast information within the target date. The first wind power forecast information is obtained based on wind forecast data. Based on the first prediction information, multiple scheduling schemes are randomly generated and added to the target set. The scheduling scheme includes the output power of wind turbines, the charging and discharging status of energy storage systems, the charging and discharging power of energy storage systems, the number of thermal power units in operation, and the output power of thermal power units for each time period within the target date. The solutions in the target set are iteratively mutated and optimized to obtain the target scheduling scheme within the target date. Within the target date, within the target time period, obtain the second forecast information for the next time period, the second forecast information including the second wind power forecast information and the second electricity load forecast demand information; The output power of the wind turbines, the output power of the activated thermal power generators, the charging and discharging status of the energy storage system, and the charging / discharging power of the energy storage system in the next time period of the target scheduling scheme are updated based on the difference information. The difference information includes the difference between the second wind power prediction information and the first wind power prediction information, and the difference between the second user load demand prediction information and the first electricity load demand prediction information. The iterative mutation optimization of the solutions in the target set includes: In each iteration, perform the following operations: The solutions in the target set are subjected to crossover mutation to obtain a first solution, and the first solution is added to the target set; The solutions in the target set are constrained based on power grid constraints to update the target set; The solutions in the target set are sorted according to the objective function value corresponding to each solution in the updated target set, and a preset number of solutions are retained in the target set according to the sorting result; End the current iteration, and re-execute the step of performing crossover mutation on the solutions in the target set to start a new round of iterations until the preset number of iterations is reached; The objective function value includes multiple sub-objective function values, which include a first sub-objective function value, a second sub-objective function value, a third sub-objective function value, and a fourth sub-objective function value. The value of the first sub-objective function is obtained based on the operating cost of the wind turbine. The value of the second sub-objective function is obtained based on the operating cost of thermal power units; The value of the third sub-objective function is obtained based on the energy storage consumption cost; The value of the fourth sub-objective function is obtained based on a preset formula for calculating wind curtailment penalty; The step of sorting the solutions in the target set according to the sub-objective function value corresponding to each solution in the updated target set includes: Sort the results according to the weighted summation of the sub-objective function values ​​corresponding to each solution in the updated objective set; The sorted solutions are divided into several layers. The solutions in the first n layers are kept in the target set, and the remaining solutions are removed from the target set. n satisfies the first objective condition, which is: the number of all solutions in the first n-1 layers is less than the preset number, and the number of all solutions in the first n layers is greater than the preset number. For each layer retained in the target set, the solutions in that layer are sorted according to the corresponding m-th sub-objective function value. After sorting, the difference coefficients corresponding to all solutions in each layer are calculated. The difference coefficients reflect the differences between two adjacent solutions. At least one solution is removed from the target set based on the difference coefficient corresponding to the solution in the target set, such that the number of solutions in the target set is the preset number; The step of removing at least one solution from the target set based on the difference coefficient corresponding to the solutions in the target set, so that the number of solutions in the target set is the preset number, includes: Select M pairs of target solutions from the target set. The target solution pairs satisfy the second target condition, which is that the two solutions in the target solution pair belong to the same layer, and the difference between the difference coefficients of the two solutions in the target solution pair is within a preset range, where M is the difference between the number of solutions in the current target set and the preset number. For the target solution pair belonging to the k-th layer, the solutions of the (k-1)-th layer, the (k+1)-th layer, and the k-th layer are added to the new layer. The difference coefficients corresponding to the target solution pair in the new layer are calculated. The solutions with larger difference coefficients in the new layer are retained in the target set, while the solutions with smaller difference coefficients in the new layer are removed from the target set.

2. The multi-timescale intelligent scheduling method for offshore wind power energy storage systems according to claim 1, characterized in that, The grid constraints include: wind turbine operation constraints, thermal power unit operation constraints, grid security constraints, grid fluctuation constraints, spinning reserve constraints, and branch power flow constraints.

3. The multi-timescale intelligent scheduling method for offshore wind power energy storage systems according to claim 1, characterized in that, The calculation of the difference coefficients corresponding to all solutions in each layer includes: Obtain the values ​​of each of the sub-objective functions corresponding to two adjacent solutions of the objective solution; The sum of each sub-difference result is obtained as the difference coefficient corresponding to the objective solution, wherein the x-th sub-difference result is the distance between the x-th sub-objective function values ​​corresponding to the two adjacent solutions.

4. The multi-timescale intelligent scheduling method for offshore wind power energy storage systems according to claim 1, characterized in that, The step of updating the output power of wind turbines, the output power of activated thermal power generators, the charging and discharging status of energy storage systems, and the charging / discharging power of energy storage systems in the next time period of the target scheduling scheme based on the difference information includes: Based on the optimization objective of minimizing power fluctuations on the power grid interconnection line, the power generation of wind turbines, the power generation of activated thermal power generators, the charging and discharging status of energy storage systems, and the charging / discharging power of energy storage systems in the scheduling data for the next time period are updated according to the difference information.

5. A multi-timescale intelligent scheduling device for an offshore wind power energy storage system, wherein the multi-timescale intelligent scheduling device for the offshore wind power energy storage system is used to implement the multi-timescale intelligent scheduling method for the offshore wind power energy storage system according to any one of claims 1-4, characterized in that, include: The day-ahead forecasting module is used to obtain first forecast information before the target date. The first forecast information includes first wind power forecast information and first electricity load demand forecast information within the target date. The first wind power forecast information is obtained based on wind forecast data. The day-ahead scheduling module is used to randomly generate multiple scheduling scheme solutions based on the first prediction information and add them to the target set. The scheduling scheme includes the output power of wind turbines, the charging and discharging status of energy storage systems, the charging and discharging power of energy storage systems, the number of thermal power units in operation, and the output power of thermal power units for each time period within the target date. The solution in the target set is iteratively mutated and optimized to obtain the target scheduling scheme within the target date. The daytime forecasting module is used to obtain second forecast information for the next time period within the target time period on the target date. The second forecast information includes second wind power forecast information and second electricity load forecast demand information. The daytime scheduling module is used to update the output power of wind turbines, the output power of activated thermal power generators, the charging and discharging status of energy storage systems, and the charging / discharging power of energy storage systems in the next time period of the target scheduling scheme based on the difference information. The difference information includes the difference between the second wind power prediction information and the first wind power prediction information, and the difference between the second user load demand prediction information and the first electricity load demand prediction information.

6. A terminal, characterized in that, The terminal includes: a processor and a computer-readable storage medium communicatively connected to the processor. The computer-readable storage medium is adapted to store multiple instructions, and the processor is adapted to call the instructions in the computer-readable storage medium to execute the steps of implementing the multi-timescale intelligent scheduling method for the offshore wind power energy storage system according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the multi-timescale intelligent scheduling method for offshore wind power energy storage systems as described in any one of claims 1-4.

Images