Genetic algorithm-based day-ahead scale optimization scheduling method and device, and medium

Abstract

The invention discloses a day-ahead scale optimization scheduling method and device based on a genetic algorithm and a medium, and the method comprises the steps: obtaining a micro-grid accumulated electric energy parameter, and carrying out the non-negative processing of the micro-grid accumulated electric energy parameter, so as to obtain a one-dimensional power consumption vector; combining the one-dimensional power consumption vectors into a multi-dimensional power consumption vector in sequence, and performing payment cost minimization processing on the multi-dimensional power consumption vector to determine a micro-grid cost objective function; based on the micro-grid accumulated electric energy parameters, a first constraint condition is obtained through charging and discharging threshold value configuration; according to the accumulated electric energy parameters of the micro-grid, a second constraint condition is obtained through limitation of the charging state parameters; searching space element parameters are determined through searching space analysis; and determining day-ahead scale optimization scheduling through genetic algorithm optimization according to search space element parameters. According to the method, the technical problem that in the prior art, the economic stability of the micro-grid is poor due to the fact that the access amount is increased is solved.

Description

Technical Field

[0001] The present application relates to the field of microgrid technology, and in particular to a day-ahead scale optimization scheduling method, device and medium based on a genetic algorithm. Background Art

[0002] In recent years, new energy sources such as solar energy and wind energy and other distributed power generation technologies have flourished. These energy sources have the advantages of high energy utilization, low environmental pollution, strong power supply flexibility, and low input cost. More and more wind power and photovoltaic power generation are connected to the main power grid, which leads to an increase in the uncertainty of the total amount of wind power and photovoltaic power generation connected to the power system.

[0003] In addition, the above uncertainties also bring great challenges to the economic operation of microgrids, which are one of the important forms of wind power and photovoltaic power generation access to the power system. In the existing technical solutions to reduce the impact of uncertainty and prediction errors of wind power and photovoltaic power generation, the scheduling at the day-ahead and intraday scales is generally optimized to reduce the error between the two. The optimization of scheduling at the day-ahead scale through genetic algorithms helps to solve the problem of poor economic stability of microgrids at the day-ahead scale. Summary of the invention

[0004] The embodiments of the present application provide a method, device and medium for day-ahead scale optimization scheduling based on a genetic algorithm, which solves the technical problem in the prior art that the economic stability of a microgrid is poor due to an increase in access volume.

[0005] In a first aspect, an embodiment of the present application provides a day-ahead scale optimization scheduling method based on a genetic algorithm, characterized in that the method includes: obtaining a microgrid cumulative electric energy parameter, and performing non-negative value processing on the microgrid cumulative electric energy parameter to obtain a one-dimensional power consumption vector; merging the one-dimensional power consumption vector into a multi-dimensional power consumption vector in sequence, and performing payment cost minimization processing on the multi-dimensional power consumption vector to determine the microgrid cost objective function; based on the microgrid cumulative electric energy parameter, obtaining a first constraint condition by configuring the charge and discharge threshold; according to the microgrid cumulative electric energy parameter, obtaining a second constraint condition by limiting the charging state parameter; based on the first constraint condition and the second constraint condition, determining the search space element parameter by search space analysis; according to the search space element parameter, determining the day-ahead scale optimization scheduling by optimizing the genetic algorithm.

[0006] In one implementation of the present application, the accumulated electric energy parameters of the microgrid are processed as non-negative values ​​to obtain a one-dimensional power consumption vector, specifically including: determining the parameter step length based on the accumulated electric energy parameters of the microgrid; wherein the parameter step length includes: charging depth step length, discharging depth step length, and the accumulated electric energy parameters of the microgrid include: accumulated load demand, accumulated power generation, energy storage capacity, and charging and discharging depth; according to the parameter step length, a one-dimensional power consumption vector is obtained by determining the key parameter sign; wherein the key parameter sign determination is to determine whether the difference between the accumulated electric energy parameters of the microgrid is positive or negative, and the one-dimensional power consumption vector is represented by the following formula:

[0007] For microgrids in hourly intervals The cumulative load demand within is the cumulative power generation of wind power and photovoltaic renewable energy in the microgrid, is the capacity of the energy storage system, is the charge and discharge depth of the energy storage system, is the parameter step size.

[0008] In one implementation of the present application, the multidimensional power consumption vector is processed to minimize the payment cost to determine the microgrid cost objective function, specifically including: obtaining periodic electricity price data, and multiplying and summing the multidimensional power consumption vector within the same time period interval with the periodic electricity price data to determine the microgrid cost objective function; wherein, the calculation formula of the microgrid cost objective function is:

[0009] is the periodic electricity price data, To cover costs.

[0010] In one implementation of the present application, based on the accumulated power parameters of the microgrid, a first constraint condition is obtained by configuring the charge and discharge thresholds, specifically including: performing a discharge parameter constraint on the accumulated power parameters of the microgrid to obtain a periodic discharge constraint; based on the periodic discharge constraint, a periodic charge constraint is obtained by a charge constraint; according to the periodic discharge constraint and the periodic charge constraint, a first constraint condition is obtained; wherein the first constraint condition is expressed by the following formula:

[0011] is the periodic discharge constraint, Provide cycle charging constraints; For microgrids in hourly intervals The cumulative load demand within It is the cumulative power generation of wind power and photovoltaic renewable energy in the microgrid.

[0012] In one implementation of the present application, according to the accumulated power parameters of the microgrid, the second constraint condition is obtained by limiting the charging state parameter, specifically including: based on the accumulated power parameters of the microgrid, determining the SOC threshold through battery SOC threshold analysis; according to the SOC threshold, obtaining the second constraint condition; wherein the second constraint condition is expressed by the following formula:

[0013] is the lower limit of the SOC threshold, is the upper limit threshold of the SOC threshold.

[0014] In one implementation of the present application, based on the first constraint and the second constraint, the search space element parameters are determined through search space analysis, specifically including: based on the first constraint and the second constraint, the problem search space element is determined through the problem search space definition; and constraint condition judgment is performed on the problem search space element to determine the search space element parameters.

[0015] In one implementation of the present application, a day-ahead scale optimization scheduling is determined through genetic algorithm optimization according to search space element parameters, specifically including: randomly selecting a number of population individuals in the search space element parameters, and determining fitness parameters based on the population individuals; according to the fitness parameters, obtaining adapted individuals through population iteration, and replacing the search space element range value corresponding to the adapted individual with the value of the first constraint condition; wherein, population iteration includes: crossover and mutation.

[0016] In one implementation of the present application, after determining the day-ahead scale optimization scheduling through genetic algorithm optimization based on the search space element parameters, the method also includes: determining the intraday scale scheduling through intraday scale scheduling analysis based on the day-ahead scale optimization scheduling; performing pre-rolling optimization on the intraday scale scheduling, and determining the feedback correction strategy based on the results of the rolling optimization.

[0017] In a second aspect, an embodiment of the present application also provides a day-ahead scale optimization scheduling device based on a genetic algorithm, characterized in that the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: obtain the microgrid cumulative electric energy parameters, and perform non-negative value processing on the microgrid cumulative electric energy parameters to obtain a one-dimensional power consumption vector; merge the one-dimensional power consumption vectors into multi-dimensional power consumption vectors in sequence, and perform payment cost minimization processing on the multi-dimensional power consumption vectors to determine the microgrid cost objective function; based on the microgrid cumulative electric energy parameters, obtain a first constraint condition through charge and discharge threshold configuration; based on the microgrid cumulative electric energy parameters, obtain a second constraint condition through charging state parameter limitation; based on the first constraint condition and the second constraint condition, determine the search space element parameters through search space analysis; based on the search space element parameters, determine the day-ahead scale optimization scheduling through genetic algorithm optimization.

[0018] In a third aspect, an embodiment of the present application further provides a non-volatile computer storage medium for day-ahead scale optimization scheduling based on a genetic algorithm, storing computer executable instructions, characterized in that the computer executable instructions are set to: obtain the accumulated electric energy parameters of the microgrid, and perform non-negative value processing on the accumulated electric energy parameters of the microgrid to obtain a one-dimensional power consumption vector; merge the one-dimensional power consumption vectors into multi-dimensional power consumption vectors in sequence, and perform payment cost minimization processing on the multi-dimensional power consumption vectors to determine the microgrid cost objective function; based on the accumulated electric energy parameters of the microgrid, obtain a first constraint condition through charge and discharge threshold configuration; based on the accumulated electric energy parameters of the microgrid, obtain a second constraint condition through charging state parameter limitation; based on the first constraint condition and the second constraint condition, determine the search space element parameters through search space analysis; based on the search space element parameters, determine the day-ahead scale optimization scheduling through genetic algorithm optimization.

[0019] The embodiments of the present application provide a method, device and medium for optimizing scheduling at the day-ahead scale based on a genetic algorithm. Through the day-ahead scale scheduling analysis and intraday scale rolling prediction optimization based on the genetic algorithm, the technical problem of poor economic stability of the microgrid due to the increase in the access volume in the prior art is solved, and the day-ahead economic optimal scheduling plan analysis for the low-frequency component is realized, which significantly reduces the deviation between intraday scheduling and day-ahead scheduling, and optimizes the economic stability of the microgrid under the actual operating state. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flow chart of a day-ahead scale optimization scheduling method based on a genetic algorithm provided in an embodiment of the present application; Figure 2 A schematic diagram of the internal structure of a day-ahead scale optimization scheduling device based on a genetic algorithm is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0022] The embodiments of the present application provide a method, device and medium for optimizing scheduling at the day-ahead scale based on a genetic algorithm. Through the day-ahead scale scheduling analysis and intraday scale rolling prediction optimization based on the genetic algorithm, the technical problem of poor economic stability of the microgrid due to the increase in the access volume in the prior art is solved, and the day-ahead economic optimal scheduling plan analysis for the low-frequency component is realized, which significantly reduces the deviation between intraday scheduling and day-ahead scheduling, and optimizes the economic stability of the microgrid under the actual operating state.

[0023] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0024] Figure 1 A flow chart of a day-ahead scale optimization scheduling method based on a genetic algorithm is provided in an embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a day-ahead scale optimization scheduling method based on a genetic algorithm, which specifically includes the following steps: Step 101: Acquire the accumulated power parameters of the microgrid, and perform non-negative value processing on the accumulated power parameters of the microgrid to obtain a one-dimensional power consumption vector.

[0025] The accumulated power parameters of the power grid include but are not limited to the accumulated load demand, accumulated power generation, energy storage capacity, and charge and discharge depth. The role of non-negative value processing is to control the value of the one-dimensional power consumption vector so that it will not have negative values. The one-dimensional power consumption vector is a vectorized representation of power consumption in a certain time period or interval.

[0026] By processing the non-negative values ​​of power consumption of parameters such as cumulative load demand, cumulative power generation, energy storage capacity, and charge and discharge depth in the microgrid's cumulative power parameters, it is ensured that the values ​​of the power supply load in different situations can be calculated to obtain usable data, thereby improving the stability of the power consumption data.

[0027] Specifically, the non-negative value processing includes: determining the parameter step size based on the microgrid cumulative power parameters; wherein the parameter step size includes: charging depth step size, discharging depth step size, and the microgrid cumulative power parameters include: cumulative load demand, cumulative power generation, energy storage capacity, and charging and discharging depth; according to the parameter step size, a one-dimensional power consumption vector is obtained by determining the key parameter sign; wherein the key parameter sign determination is to determine whether the difference between the microgrid cumulative power parameters is positive or negative, and the one-dimensional power consumption vector is represented by the following formula:

[0028] For microgrids in hourly intervals The cumulative load demand within is the cumulative power generation of wind power and photovoltaic renewable energy in the microgrid, is the capacity of the energy storage system, is the charge and discharge depth of the energy storage system, is the parameter step size.

[0029] In one embodiment, an objective function is constructed to minimize the cost of the microgrid on a long day-ahead time scale, and the optimization problem is set to minimize the total cost paid by the consumer. The total cost is calculated by multiplying the power consumption in all time intervals or cycles by the power price.

[0030] The power consumption vector is a 24-dimensional real-valued vector, where each one-dimensional power consumption vector represents the amount of power imported by the microgrid from the large grid.

[0031] Since the construction of the day-ahead scale requires a 24-hour time period forecast in advance, it is necessary to analyze the situation in each hour interval separately. The one-dimensional power consumption vector This can represent the power consumption vector within an hour interval.

[0032] The one-dimensional power consumption vector is expressed by the following formula: (1) For microgrids in hourly intervals Cumulative load demand within; is the cumulative power generation of wind power and photovoltaic renewable energy in the microgrid; is the capacity of the energy storage system; is the charge and discharge depth of the energy storage system, is the parameter step size.

[0033] When the charge / discharge depth value increases or decreases in 0.01 steps, It can be expressed as ;in, represents the total inflow or outflow energy of the energy storage system within the interval 𝑖 (depending on ), Indicates the remaining energy required to fully power the load (when ), or Excess energy remaining after powering the load (possibly used to charge a battery, when ), and finally, Ensure that the one-dimensional power consumption vector Will not become negative.

[0034] Step 102: Merge the one-dimensional power consumption vectors into a multi-dimensional power consumption vector in order, and perform payment cost minimization processing on the multi-dimensional power consumption vector to determine the microgrid cost objective function.

[0035] The 24 one-dimensional power consumption vectors predicted within 24 hours are integrated into a multi-dimensional power consumption vector, which is expressed as , where each It indicates the amount of electricity that the microgrid imports from the large grid.

[0036] Since the optimization problem is to minimize the total cost paid by consumers first, it is necessary to minimize the payment cost at the day-ahead scale. By minimizing the payment cost, the payment cost of the microgrid under the daily scale scheduling is minimized, the payment cost of the microgrid is reduced, and the economic utilization rate of the microgrid is improved.

[0037] Specifically, the payment cost minimization process includes: obtaining periodic electricity price data, and multiplying and summing the multidimensional power consumption vector within the same time period interval with the periodic electricity price data to determine the microgrid cost objective function; wherein the calculation formula of the microgrid cost objective function is:

[0038] is the periodic electricity price data, To cover costs.

[0039] In one embodiment, the total cost paid by the consumer is minimized , for all time intervals With interval Internal electricity price The sum of products and the minimization of payment costs are expressed by the following formula: (2) in, is the periodic electricity price data, To cover costs.

[0040] Step 103: Based on the accumulated electric energy parameters of the microgrid, a first constraint condition is obtained by configuring the charge and discharge thresholds.

[0041] The charge and discharge threshold configuration is used to constrain the battery charge and discharge conditions in the microgrid, and the first constraint condition is the charge and discharge constraint condition within a time interval or cycle.

[0042] By constraining the charging and discharging state within a time interval or cycle and the relative relationship between power generation and load demand, the waste of charging and discharging of microgrid batteries is avoided, and the accuracy and applicability of the day-ahead scheduling of the microgrid energy storage system is improved.

[0043] Specifically, based on the accumulated power parameters of the microgrid, the first constraint condition is obtained through the charge and discharge threshold configuration, including: performing discharge parameter constraints on the accumulated power parameters of the microgrid to obtain a periodic discharge constraint; based on the periodic discharge constraint, obtaining a periodic charge constraint through the charge constraint; according to the periodic discharge constraint and the periodic charge constraint, obtaining the first constraint condition; wherein the first constraint condition is expressed by the following formula:

[0044] is the periodic discharge constraint, Constraints on cycle charging.

[0045] In one embodiment, the energy storage scheduling vector is a 24-dimensional real-valued vector , represents the day-ahead dispatch of the energy storage system in the microgrid. Indicates hour interval The depth of charge and discharge within The first constraint is satisfied and is expressed by the following formula: (3) in, is the periodic discharge constraint, Constraints on cycle charging.

[0046] It should be noted that the first constraint also ensures that the battery does not discharge during the interval when the power generation is greater than the load demand.

[0047] Step 104: According to the microgrid accumulated electric energy parameter, a second constraint condition is obtained by limiting the charging state parameter.

[0048] The charging state parameter SOC, that is, the battery state of charge, needs to be limited in order to ensure that the charging state of the microgrid energy storage system can be maintained in the optimal state.

[0049] Specifically, according to the accumulated power parameters of the microgrid, the second constraint condition is obtained by limiting the charging state parameter, including: based on the accumulated power parameters of the microgrid, the SOC threshold is determined by analyzing the battery SOC threshold; according to the SOC threshold, the second constraint condition is obtained; wherein the second constraint condition is expressed by the following formula:

[0050] is the lower limit of the SOC threshold, is the upper limit threshold of the SOC threshold.

[0051] In one embodiment, the second constraint is expressed by the following formula:

[0052] in, is the lower limit of the SOC threshold, is the upper limit threshold of the SOC threshold.

[0053] Under the condition that the battery SOC is not less than 10% or greater than 90%, the upper and lower limits of the SOC threshold are 10 and 90 respectively. The second constraint is expressed as .

[0054] Step 105: Based on the first constraint condition and the second constraint condition, determine the search space element parameters through search space analysis.

[0055] The search space is a collection of all 24-dimensional vectors. The search space element parameters include the search space magnification rate, etc. in addition to the search space elements.

[0056] Exemplarily, for any search space element, after defining its cost, each element in the search space will have several neighbor elements, and there is a path of a certain length between any two elements in the search space.

[0057] Specifically, based on the first constraint and the second constraint, the search space element parameters are determined through search space analysis, including: based on the first constraint and the second constraint, the problem search space element is determined through the problem search space definition; and constraint condition judgment is performed on the problem search space element to determine the search space element parameters.

[0058] In one embodiment, based on the energy storage scheduling vector, , where each is a real value, truncated to two decimal places, in the range within; among them, and denote the maximum discharge and charge depths in a one-hour interval, respectively. If two search space elements differ in one coordinate, they are neighbors of each other. , Cost It is expressed by the following formula: (5) The constraint conditions are the first constraint conditions and the second constraint conditions, and satisfying the constraint conditions means satisfying the first constraint conditions and the second constraint conditions at the same time.

[0059] Search Space Each element in has There is a neighbor between any two elements in the search space. The search space is enlarged by at least .

[0060] Step 106: Determine the day-ahead scale optimization scheduling through genetic algorithm optimization according to the search space element parameters.

[0061] By optimizing the day-ahead dispatch through genetic algorithm, the day-ahead dispatch of the microgrid is optimized, the accuracy and adaptability of the day-ahead prediction of the microgrid is improved, and the probability of economic uncertainty in the microgrid is reduced.

[0062] Specifically, according to the search space element parameters, the day-ahead scale optimization scheduling is determined through genetic algorithm optimization, including: randomly selecting a number of population individuals in the search space element parameters, and determining the fitness parameters based on the population individuals; according to the fitness parameters, obtaining the adapted individuals through population iteration, and replacing the search space element range values ​​corresponding to the adapted individuals with the values ​​of the first constraint conditions; wherein the population iteration includes: crossover and mutation.

[0063] In one embodiment, represents the population size. The algorithm initially randomly selects In each generation, the fittest individuals are selected from the population. The fitness of the search space elements is calculated according to the above formula (5).

[0064] The optimization problem is a minimization problem, if one individual has a lower cost function value, then it is more fit than another individual. selected individuals, forming right.

[0065] Crossover with probability Applied to each pair of individuals, this yields offspring. After crossover, the mutation probability The resulting offspring are mutated. Then, in total The most adaptable chromosome The process repeats generations. After the last generation, the fittest individuals are returned. Crossover and mutation are defined as follows: set up and Represents the parent generation. The crossover operation will produce two children. and ,in , .

[0066] set up Represents a search space element. A mutation is defined as a change in any dimension (e.g. ) is replaced by a real value in the range given by formula (3) above (truncated to two decimal places).

[0067] In one implementation of the present application, after determining the day-ahead scale optimization scheduling through genetic algorithm optimization based on the search space element parameters, the method also includes: determining the intraday scale scheduling through intraday scale scheduling analysis based on the day-ahead scale optimization scheduling; performing pre-rolling optimization on the intraday scale scheduling, and determining the feedback correction strategy based on the results of the rolling optimization.

[0068] In one embodiment, intra-day scale scheduling analysis may be implemented through MPC, which is composed of a prediction model, rolling optimization, and feedback correction.

[0069] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a day-ahead scale optimization scheduling device based on a genetic algorithm, and its structure is as follows: Figure 2 shown.

[0070] Figure 2 The internal structure diagram of a day-ahead scale optimization scheduling device based on a genetic algorithm is provided in the embodiment of the present application. Figure 2 As shown, the device includes: at least one processor 201; and, a memory 202 communicatively connected to the at least one processor; The memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 201 to enable at least one processor 201 to: The accumulated electric energy parameters of the microgrid are obtained, and the accumulated electric energy parameters of the microgrid are processed as non-negative values ​​to obtain a one-dimensional power consumption vector; the one-dimensional power consumption vector is sequentially merged into a multi-dimensional power consumption vector, and the multi-dimensional power consumption vector is processed to minimize the payment cost to determine the microgrid cost objective function; based on the accumulated electric energy parameters of the microgrid, the first constraint condition is obtained by configuring the charge and discharge thresholds; according to the accumulated electric energy parameters of the microgrid, the second constraint condition is obtained by limiting the charging state parameters; based on the first constraint condition and the second constraint condition, the search space element parameters are determined through search space analysis; according to the search space element parameters, the day-ahead scale optimization scheduling is determined through genetic algorithm optimization.

[0071] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for day-ahead scale optimization scheduling based on a genetic algorithm stores computer executable instructions, and the computer executable instructions are set as follows: The accumulated electric energy parameters of the microgrid are obtained, and the accumulated electric energy parameters of the microgrid are processed as non-negative values ​​to obtain a one-dimensional power consumption vector; the one-dimensional power consumption vector is sequentially merged into a multi-dimensional power consumption vector, and the multi-dimensional power consumption vector is processed to minimize the payment cost to determine the microgrid cost objective function; based on the accumulated electric energy parameters of the microgrid, the first constraint condition is obtained by configuring the charge and discharge thresholds; according to the accumulated electric energy parameters of the microgrid, the second constraint condition is obtained by limiting the charging state parameters; based on the first constraint condition and the second constraint condition, the search space element parameters are determined through search space analysis; according to the search space element parameters, the day-ahead scale optimization scheduling is determined through genetic algorithm optimization.

[0072] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0073] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0074] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0075] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0078] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0079] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0080] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0081] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0082] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A day-ahead scale optimization scheduling method based on genetic algorithm, characterized in that: The method comprises: Acquire a microgrid cumulative electric energy parameter, and perform non-negative value processing on the microgrid cumulative electric energy parameter to obtain a one-dimensional power consumption vector; The one-dimensional power consumption vectors are sequentially merged into a multi-dimensional power consumption vector, and the multi-dimensional power consumption vector is processed to minimize the payment cost to determine the microgrid cost objective function; Based on the accumulated electric energy parameter of the microgrid, a first constraint condition is obtained by configuring the charge and discharge threshold value; According to the microgrid accumulated electric energy parameter, a second constraint condition is obtained by limiting the charging state parameter; Based on the first constraint condition and the second constraint condition, determining search space element parameters through search space analysis; According to the search space element parameters, the day-ahead scale optimization scheduling is determined through genetic algorithm optimization.

2. The method for optimizing the day-ahead scheduling based on genetic algorithm according to claim 1, characterized in that: The microgrid accumulated electric energy parameter is processed into a non-negative value to obtain a one-dimensional power consumption vector, which specifically includes: Based on the accumulated power parameters of the microgrid, a parameter step is determined; wherein the parameter step includes: a charging depth step and a discharging depth step, and the accumulated power parameters of the microgrid include: accumulated load demand, accumulated power generation, energy storage capacity, and charge and discharge depth; According to the parameter step size, the one-dimensional power consumption vector is obtained by determining the key parameter sign; wherein the key parameter sign determination is to determine whether the difference between the accumulated power parameters of the microgrid is positive or negative, and the one-dimensional power consumption vector is represented by the following formula: For microgrids in hourly intervals The cumulative load demand within is the cumulative power generation of wind power and photovoltaic renewable energy in the microgrid, is the capacity of the energy storage system, is the charge and discharge depth of the energy storage system, is the parameter step size.

3. The method for optimizing the day-ahead scheduling based on genetic algorithm according to claim 2, characterized in that: The multi-dimensional power consumption vector is processed to minimize the payment cost to determine the microgrid cost objective function, which specifically includes: Obtain periodic electricity price data, and multiply and sum the multidimensional power consumption vector within the same time period interval with the periodic electricity price data to determine the microgrid cost objective function; wherein the calculation formula of the microgrid cost objective function is: is the periodic electricity price data, To cover costs.

4. The method for optimizing the day-ahead scheduling based on genetic algorithm according to claim 1, characterized in that: Based on the accumulated electric energy parameters of the microgrid, a first constraint condition is obtained by configuring the charge and discharge thresholds, which specifically includes: Performing discharge parameter constraints on the accumulated electric energy parameters of the microgrid to obtain periodic discharge constraints; Based on the periodic discharge constraint, a periodic charging constraint is obtained through the charging constraint; According to the periodic discharge constraint and the periodic charge constraint, the first constraint condition is obtained; wherein the first constraint condition is expressed by the following formula: is the periodic discharge constraint, For cycle charging constraints, For microgrids in hourly intervals The cumulative load demand within is the cumulative power generation of wind power and photovoltaic renewable energy in the microgrid.

5. The method for optimizing the day-ahead scheduling based on genetic algorithm according to claim 4, characterized in that: According to the microgrid accumulated electric energy parameter, the second constraint condition is obtained by limiting the charging state parameter, which specifically includes: Based on the microgrid accumulated electric energy parameter, determining the SOC threshold through battery SOC threshold analysis; According to the SOC threshold, the second constraint condition is obtained; wherein the second constraint condition is expressed by the following formula: is the lower limit threshold of the SOC threshold, is the upper limit threshold of the SOC threshold.

6. The method for day-ahead scale optimization scheduling based on genetic algorithm according to claim 1, characterized in that: Based on the first constraint condition and the second constraint condition, determining search space element parameters through search space analysis specifically includes: Based on the first constraint condition and the second constraint condition, determining a problem search space element through a problem search space definition; Constraint conditions are determined for the problem search space elements to determine the search space element parameters.

7. The method for optimizing the day-ahead scheduling based on genetic algorithm according to claim 1, characterized in that: According to the search space element parameters, the day-ahead scale optimization scheduling is determined through genetic algorithm optimization, specifically including: Randomly selecting a number of population individuals from the search space element parameters, and determining fitness parameters based on the population individuals; According to the fitness parameter, an adapted individual is obtained through population iteration, and the search space element range value corresponding to the adapted individual is replaced with the value of the first constraint condition; wherein the population iteration includes: crossover and mutation.

8. The method for optimizing the day-ahead scheduling based on genetic algorithm according to claim 1, characterized in that: After determining the day-ahead scale optimization scheduling through genetic algorithm optimization according to the search space element parameters, the method further includes: Based on the day-ahead scale optimization scheduling, determining the intraday scale scheduling through intraday scale scheduling analysis; The intraday scale scheduling is pre-rolled optimized, and a feedback correction strategy is determined based on the result of the rolling optimization.

9. A day-ahead scale optimization scheduling device based on genetic algorithm, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Acquire a microgrid cumulative electric energy parameter, and perform non-negative value processing on the microgrid cumulative electric energy parameter to obtain a one-dimensional power consumption vector; The one-dimensional power consumption vectors are sequentially merged into a multi-dimensional power consumption vector, and the multi-dimensional power consumption vector is processed to minimize the payment cost to determine the microgrid cost objective function; Based on the accumulated electric energy parameter of the microgrid, a first constraint condition is obtained by configuring the charge and discharge threshold value; According to the microgrid accumulated electric energy parameter, a second constraint condition is obtained by limiting the charging state parameter; Based on the first constraint condition and the second constraint condition, determining search space element parameters through search space analysis; According to the search space element parameters, the day-ahead scale optimization scheduling is determined through genetic algorithm optimization.

10. A non-volatile computer storage medium for day-ahead scale optimization scheduling based on a genetic algorithm, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Acquire a microgrid cumulative electric energy parameter, and perform non-negative value processing on the microgrid cumulative electric energy parameter to obtain a one-dimensional power consumption vector; The one-dimensional power consumption vectors are sequentially merged into a multi-dimensional power consumption vector, and the multi-dimensional power consumption vector is processed to minimize the payment cost to determine the microgrid cost objective function; Based on the accumulated electric energy parameter of the microgrid, a first constraint condition is obtained by configuring the charge and discharge threshold value; According to the microgrid accumulated electric energy parameter, a second constraint condition is obtained by limiting the charging state parameter; Based on the first constraint condition and the second constraint condition, determining search space element parameters through search space analysis; According to the search space element parameters, the day-ahead scale optimization scheduling is determined through genetic algorithm optimization.

Images