Method for optimizing power of power equipment and electronic equipment

Abstract

The invention discloses a power optimization method of power equipment and electronic equipment, and relates to the field of information processing, and the method comprises the steps: obtaining preset parameter data of the power equipment, the preset parameter data comprising equipment parameter data and operation parameter data of the power equipment; according to the preset parameter data and preset optimization conditions, a target power distribution scheme is determined, and the preset optimization conditions comprise reduction of network loss, improvement of power transmission efficiency and reduction of power loss of power equipment; and controlling the output power of the power equipment according to the target power distribution scheme.

Description

Technical Field

[0001] The present application relates to the field of information processing, and in particular to a method for optimizing the power of an electric device and an electronic device. Background Art

[0002] Power equipment power optimization refers to the adjustment and optimization of the operating power of power equipment through various technical means and management measures, so that it can operate as efficiently as possible under different working conditions, thereby achieving the goals of reducing energy consumption, improving equipment utilization and ensuring stable operation of the power system.

[0003] In the traditional field of power equipment power optimization, power allocation and optimization mainly rely on manual experience and simple mathematical models. Power allocation is generally based on rule-based control strategies and mathematical models based on single-objective optimization.

[0004] However, existing methods cannot cope with complex and changeable power system conditions, and the overall optimization effect is poor. Summary of the Invention

[0005] A first aspect of the present application provides a method for optimizing the power of an electric power device, comprising:

[0006] Obtaining preset parameter data of the electric power equipment, wherein the preset parameter data includes equipment parameter data and operation parameter data of the electric power equipment;

[0007] Determining a target power allocation scheme based on the preset parameter data and preset optimization conditions, wherein the preset optimization conditions include reducing network losses, improving transmission efficiency, and reducing power losses of power equipment;

[0008] According to the target power allocation scheme, the output power of the power equipment is controlled.

[0009] In a possible implementation, determining the target power allocation scheme based on the preset parameter data and the preset optimization condition includes:

[0010] generating an initial power allocation scheme according to the preset parameter data;

[0011] Iteratively optimizing the initial power allocation scheme according to a preset iterative optimization method to obtain at least two optimized power allocation schemes;

[0012] According to a preset optimization condition, a target power allocation scheme is determined among the initial power allocation scheme and at least two optimized power allocation schemes, and the target power allocation scheme satisfies the preset optimization condition.

[0013] In a possible implementation, the iterative optimization of the initial power allocation scheme according to a preset iterative optimization method to obtain at least two optimized power allocation schemes includes:

[0014] generating an initial population according to the initial power allocation scheme, wherein the initial population includes a plurality of individuals, and each individual in the initial population represents an initial power allocation scheme;

[0015] According to a preset iterative optimization method, the initial population is iteratively optimized to obtain at least one optimized population, the optimized population including a plurality of individuals, and each individual in the optimized population represents an optimized power allocation scheme.

[0016] In a possible implementation, performing iterative optimization on the initial population according to a preset iterative optimization method to obtain at least one optimized population includes:

[0017] Optimizing the first population according to a preset amount of variation to obtain a second population, wherein the amount of variation between offspring individuals in the second population and parent individuals in the first population satisfies the preset amount of variation, the first population comprising an initial population and an optimized population obtained by iteratively optimizing the initial population;

[0018] A third population is obtained based on a crossover operation between the parent individuals in the first population and the offspring individuals in the second population, wherein the third population includes offspring crossover individuals;

[0019] The first population, the second population, and the third population are combined to obtain the optimized population.

[0020] In a possible implementation, determining the target power allocation scheme from the initial power allocation scheme and the at least two optimized power allocation schemes according to the preset optimization condition includes:

[0021] According to the preset optimization condition, at least one candidate individual is selected from the at least one optimized population; the degree to which the candidate individual is influenced by the non-candidate individual in the optimized population to which it belongs is less than the degree to which the non-candidate individual is influenced by any individual in the optimized population to which it belongs;

[0022] Among the individuals to be selected, a target individual is determined, and the target individual corresponds to a target power allocation scheme.

[0023] In a possible implementation, selecting at least one candidate individual from the at least one optimized population according to the preset optimization condition includes:

[0024] Determining a target value corresponding to each individual in a target population based on the preset optimization condition, where the target population is any one of the at least one optimized population, and the target value represents a degree of match between the individual and the preset optimization condition;

[0025] Determining, based on the target value corresponding to each individual in the target population, the non-dominated hierarchy of each individual in the target population to which it belongs, wherein the non-dominated hierarchy represents the degree to which the corresponding individual is influenced by other individuals in the target population to which it belongs, and the level of the non-dominated hierarchy is negatively correlated with the degree of influence;

[0026] In each non-dominated level, the individuals in the current non-dominated level are determined as the candidates for the target population.

[0027] In a possible implementation, determining a target individual from among the individuals to be selected includes:

[0028] According to the target value of the candidate individuals, the candidate individuals in at least one optimized population are respectively placed into a preset list, the preset list can carry a preset number of candidates, and the candidates in the preset list are sorted according to the target value;

[0029] A target individual is determined according to the ranking of the candidates in the preset list, and the target value of the target individual is higher than the target value of any non-target individual in the preset list.

[0030] In a possible implementation, the method further includes:

[0031] After placing the candidate individuals determined in the first non-dominated hierarchy into a preset list, determining whether the preset list is full;

[0032] Based on the fact that the preset list is not full, placing the candidate individuals determined in a second non-dominated hierarchy into the preset list, the second non-dominated hierarchy being lower than the first non-dominated hierarchy;

[0033] Based on the fact that the preset list is full, a target individual is determined according to each candidate individual in the preset list.

[0034] In one possible implementation, controlling the output power of the power equipment according to the target power allocation scheme includes:

[0035] According to the target power allocation scheme, the output power of at least one electrical device is controlled within a preset time period.

[0036] A second aspect of the present application provides an electronic device, including:

[0037] An interface for obtaining preset parameter data of the power equipment, wherein the preset parameter data includes equipment parameter data and operation parameter data of the power equipment;

[0038] The processor is used to determine a target power allocation scheme based on the preset parameter data and preset optimization conditions, where the preset optimization conditions include reducing network losses, improving transmission efficiency, and reducing power losses of power equipment; and control the output power of the power equipment based on the target power allocation scheme.

[0039] The third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the method for optimizing the power of an electric power device according to the first aspect or any implementation of the first aspect.

[0040] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0041] The memory is used to store computer programs;

[0042] The processor is used to execute the computer program so that the electronic device can implement the method for optimizing the power of an electric power device according to the first aspect or any implementation manner of the first aspect.

[0043] The fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the method for optimizing the power of an electric device according to the above-mentioned first aspect or any implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0045] Figure 1 This is a flow chart of a method for optimizing power of electric equipment provided in an embodiment of the present application;

[0046] Figure 2 This is a flow chart of determining a target power allocation solution based on the preset parameter data and preset optimization conditions provided in an embodiment of the present application;

[0047] Figure 3 This is a flow chart of iteratively optimizing the initial power allocation scheme according to a preset iterative optimization method to obtain at least two optimized power allocation schemes according to an embodiment of the present application;

[0048] Figure 4This is a flow chart of iteratively optimizing the initial population according to a preset iterative optimization method to obtain at least one optimized population according to an embodiment of the present application;

[0049] Figure 5 This is a flow chart of determining a target power allocation scheme from the initial power allocation scheme and at least two optimized power allocation schemes based on preset optimization conditions provided by an embodiment of the present application;

[0050] Figure 6 is a schematic diagram of a process for selecting at least one candidate individual from the at least one optimized population according to the preset optimization condition provided in an embodiment of the present application;

[0051] Figure 7 1 is a flow chart of determining a target individual from the individuals to be selected, as provided in an embodiment of the present application;

[0052] Figure 8 This is another flow chart of a method for optimizing the power of an electric power device provided in an embodiment of the present application;

[0053] Figure 9 This is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

[0054] Figure 10 This is a schematic diagram of the structure of an apparatus for optimizing the power of electric equipment provided in an embodiment of the present application;

[0055] Figure 11 This is another structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The terms used in the implementation methods of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0057] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0058] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0059] Reference Figure 1 , Figure 1 This is a flow chart of a method for optimizing the power of an electric device provided in an embodiment of the present application, such as Figure 1 As shown, an embodiment of the present application provides a method for optimizing the power of an electric device, which may include steps 101 to 103, and these steps are described in detail below.

[0060] 101. Obtain preset parameter data of an electric power device, where the preset parameter data includes device parameter data and operation parameter data of the electric power device;

[0061] The method can be applied to an electronic device, which can serve as a central control device of an electric power system and can control electric power equipment in the electric power system.

[0062] Among them, the equipment parameter data is the parameters of the power equipment itself, which may include impedance, rated power, rated voltage, etc.

[0063] Among them, the operating parameter data changes in value during the operation of the power equipment. It can be collected during the operation, such as real-time current, real-time voltage, etc., or it can be calculated using the collected data during the operation, such as real-time angular power factor angle, etc.

[0064] The preset parameter data of the power equipment should include parameter data of the power equipment (in the equipment network where the power equipment is located) as much as possible, so that detailed data can be used to determine the target power allocation solution later.

[0065] This application does not limit the specific content of the preset parameter data, and the parameters it contains can be set according to needs.

[0066] In a possible implementation, the equipment parameter data of the power equipment is generally set when the equipment leaves the factory. Therefore, the equipment parameter data can be saved in a preset storage space. When the preset parameter data is obtained, the equipment parameter data of the power equipment is obtained from the preset storage space.

[0067] In one possible implementation, the operating parameter data of the power equipment may be a value detected by a sensor installed at the power equipment, such as a voltmeter or an ammeter; or it may be obtained by converting an analog voltage / current signal into a digital signal using an analog-to-digital converter (ADC) and calculating the result.

[0068] In one possible implementation, the obtained preset parameter data can be preprocessed, including filling missing values using the Lagrange interpolation method, detecting and processing outliers using the 3σ principle, and linearly scaling the data to the range of [0, 1] through minimum-maximum normalization to improve the completeness and accuracy of the data.

[0069] The Lagrangian interpolation method is a polynomial interpolation method used to fill missing values in a dataset. In this application, the Lagrangian interpolation method is used to estimate and fill these missing values based on the relationship between each data point in the known preset parameter data, effectively solving the problem of incomplete data and improving the accuracy and completeness of the data.

[0070] The 3σ principle, also known as the Laida criterion, is a method for detecting and handling outliers based on the normal distribution characteristics of data. In a normal distribution, the probability of data falling within the range of the mean plus or minus three standard deviations is approximately 99.7%. The 3σ principle identifies data points outside this range as outliers. In this application, the 3σ principle is used to detect outliers in the interpolated basic data, and then delete, replace, or correct them to obtain the basic data after the outliers are removed. This ensures data validity and avoids incorrect decisions caused by abnormal data.

[0071] Min-Max Normalization is a data normalization method that applies a linear transformation to the original data, scaling it to a specified range. In this application, the basic data, after removing outliers, is linearly scaled to the range [0, 1]. This not only improves the efficiency and accuracy of the algorithm but also allows for fairer comparison and evaluation of different data points.

[0072] 102. Determine a target power allocation plan based on the preset parameter data and preset optimization conditions, where the preset optimization conditions include reducing network losses, improving power transmission efficiency, and reducing power loss of power equipment;

[0073] The preset parameter data may be processed to obtain a plurality of power allocation schemes, and according to each of the preset optimization conditions, one that best meets the preset optimization conditions is selected from the plurality of power allocation schemes as the target power allocation scheme.

[0074] Among them, the preset optimization conditions evaluate the pros and cons of power distribution of power equipment from three perspectives: network loss, transmission efficiency, and power loss of power equipment, while considering multiple performance indicators to ensure the comprehensiveness and optimality of the obtained optimization results.

[0075] In a possible implementation, a processing model may be pre-set, and the processing model may be pre-trained according to preset optimization conditions. The processing model is used to process preset parameter data to obtain a target power allocation solution.

[0076] This processing model can utilize an artificial intelligence (AI) model, which offers the advantages of greater efficiency and continuous training and optimization during application, continuously improving accuracy and performance. Given the vast amount of parameter data involved in power systems, the use of AI models can more quickly and accurately determine target power allocation solutions.

[0077] 103. Control the output power of the power equipment according to the target power allocation plan.

[0078] After the target power allocation scheme is determined, the output power of the power equipment can be adjusted using the target power allocation scheme, so as to achieve an operating state of the power equipment that matches the optimization condition.

[0079] Among them, the power equipment involved in the embodiments of the present application can be several power equipment. Optimization is performed on the multiple power equipment to obtain the power allocated to each power equipment so that the multiple power equipment as a whole can reach the preset optimization conditions.

[0080] Among them, the power equipment involved in the embodiment of the present application can be a power equipment, and the power distribution of the power equipment is optimized in the time dimension. The obtained distribution scheme is to control the output power of the power equipment in different time periods to achieve preset optimization conditions.

[0081] In a possible implementation, the output power of at least one electrical device is controlled within a preset time period according to the target power allocation scheme.

[0082] The preset time period is a future time period after the current moment, and the method for optimizing the power of the electric equipment is a basis for controlling the power of the electric equipment in the future electric power system.

[0083] The target power allocation scheme may be for output power control of a power device over a period of time in the future, or may be for output power control of each power device in the power system over a period of time in the future.

[0084] Accordingly, a preset time period of the power allocation scheme can be set according to actual needs. The time period is a future time period of the current moment. The future time period can be continuous or discontinuous with the current moment, and there is no restriction in this application.

[0085] In this embodiment, preset parameter data for the power equipment is obtained, including equipment parameter data and operating parameter data for the power equipment. A target power allocation scheme is determined based on the preset parameter data and preset optimization conditions, wherein the preset optimization conditions include reducing network losses, improving transmission efficiency, and reducing power loss in the power equipment. The output power of the power equipment is controlled based on the target power allocation scheme. Using the preset parameter data for the power equipment, a target power allocation scheme that meets the optimization conditions can be automatically determined and the output power of the power equipment can be controlled. The preset optimization conditions evaluate the quality of the power allocation of the power equipment from three perspectives: network loss, transmission efficiency, and power loss in the power equipment. Multiple performance indicators are simultaneously considered to ensure the comprehensiveness and optimality of the resulting optimization results.

[0086] Figure 2 This is a flow chart of determining a target power allocation scheme based on the preset parameter data and preset optimization conditions provided in an embodiment of the present application, which may include steps 201 to 203. These steps are described in detail below.

[0087] 201. Generate an initial power allocation plan based on the preset parameter data;

[0088] In a possible implementation, an initial power allocation scheme is generated based on the preset parameter data. The allocation scheme may be a power allocation method for power equipment, or a power allocation method for each power equipment in the power system.

[0089] The initial power allocation scheme is randomly generated according to preset parameter data.

[0090] Accordingly, the obtained initial power allocation scheme may be an average power allocation for each power device or an arbitrary random power allocation.

[0091] As an example, the power system includes 10 power devices, and an initial power allocation solution may be to evenly allocate power to the 10 power devices.

[0092] In a possible implementation, multiple initial power allocation schemes are generated based on preset parameter data, and then each initial power allocation scheme is iteratively optimized to obtain multiple optimized power allocation schemes.

[0093] 202. Perform iterative optimization on the initial power allocation scheme according to a preset iterative optimization method to obtain at least two optimized power allocation schemes;

[0094] Among them, the electronic device that executes the power optimization method of the electric power equipment in this application has a preset iterative optimization method.

[0095] The initial power allocation scheme is iteratively optimized using a preset iterative optimization method to obtain multiple optimized power allocation schemes.

[0096] The optimized power allocation scheme differs from the initial power allocation scheme, and the difference may be partial or complete. The partial difference may be that the power allocation of some power devices is different, while the power allocation of some power devices is the same. The complete difference may be that the power allocated to the same power device in any optimized power allocation scheme is different from that in the initial power allocation scheme.

[0097] Among them, the preset iterative optimization method can be to set the corresponding optimization variables, and use the variables to adjust the power allocated to one or more power equipment in the initial power allocation scheme to obtain multiple optimized power allocation schemes. The multiple optimized power allocation schemes can be partially the same or completely different.

[0098] 203. According to a preset optimization condition, determine a target power allocation scheme from the initial power allocation scheme and at least two optimized power allocation schemes, where the target power allocation scheme satisfies the preset optimization condition.

[0099] The initial power allocation scheme and the optimized power allocation scheme are both used as alternative schemes, from which the target power allocation scheme is determined.

[0100] The power distribution of the electric equipment in the target power distribution scheme satisfies the preset optimization condition.

[0101] Among them, the preset optimization conditions include reducing network losses, improving transmission efficiency and reducing power losses of power equipment. Therefore, the power distribution of power equipment in the target power distribution scheme meets the overall effect of low network losses, high transmission efficiency and low power losses of power equipment.

[0102] In one possible implementation, weights can be set for each of the three conditions in the preset optimization condition to reflect their relative importance in the overall optimization process. These weight coefficients can be adjusted according to actual needs to balance conflicts between different objectives.

[0103] As an example, in a scenario where more emphasis is placed on reducing network losses, a higher weight can be set for network losses and a lower weight can be set for transmission efficiency and power loss of power equipment, so as to determine the one with lower network loss as the target power allocation scheme from the initial power allocation scheme and at least two optimized power allocation schemes, while satisfying the overall effect of low network loss, high transmission efficiency and low power loss of power equipment.

[0104] As an example, in a scenario where more emphasis is placed on reducing the power loss of power equipment, a higher weight can be set for the power loss of power equipment and a lower weight can be set for the transmission efficiency and the power loss of power equipment, so as to determine the one with lower power loss of power equipment as the target power allocation scheme from the initial power allocation scheme and at least two optimized power allocation schemes, while satisfying the overall effects of low network loss, high transmission efficiency and low power loss of power equipment.

[0105] In this embodiment, an initial power allocation scheme is first generated based on preset parameter data; then, the initial power allocation scheme is iteratively optimized based on a preset iterative optimization method to obtain at least two optimized power allocation schemes; finally, based on the preset optimization conditions, a target power allocation scheme is determined among the initial power allocation scheme and the at least two optimized power allocation schemes, and the target power allocation scheme meets the preset optimization conditions, thereby realizing the use of preset parameter data to generate multiple power allocation schemes, and using the preset optimization conditions to comprehensively analyze each power allocation scheme, and screen out the target power allocation scheme that meets the preset optimization conditions, thereby improving the accuracy of selecting the target power allocation scheme.

[0106] Figure 3 The embodiment of the present application provides a flow chart for iteratively optimizing the initial power allocation scheme according to a preset iterative optimization method to obtain at least two optimized power allocation schemes, which may include steps 301 to 302. These steps are described in detail below.

[0107] 301. Generate an initial population according to the initial power allocation scheme, where the initial population includes a number of individuals, and each individual in the initial population represents an initial power allocation scheme;

[0108] In this application, a genetic algorithm is used to optimize and iterate the power allocation scheme.

[0109] Among them, multiple initial power allocation schemes are generated according to preset parameter data, and the power allocated to the power equipment in any two initial power allocation schemes is different; then an initial power allocation scheme is regarded as an individual, and the individuals corresponding to the multiple initial power allocation schemes constitute an initial population.

[0110] As an example, 10 initial power allocation schemes are generated according to preset parameter data, each of the 10 initial power allocation schemes is regarded as an individual, and the 10 individuals constitute an initial population.

[0111] In the subsequent optimization process, the initial power allocation scheme corresponding to each individual is optimized to obtain multiple corresponding optimized power allocation schemes. Therefore, the data processing amount of the entire optimization process is positively correlated with the number of initial power allocation schemes.

[0112] In one possible implementation, the computing power of the electronic device can be combined with the number of individuals included in the initial population. Accordingly, in the process of generating the initial power allocation scheme based on the preset parameter data of the power equipment, the number of generated initial power allocation schemes can be limited based on the data of the individual.

[0113] 302. Perform iterative optimization on the initial population according to a preset iterative optimization method to obtain at least one optimized population, where the optimized population includes a plurality of individuals, and each individual in the optimized population represents an optimized power allocation solution.

[0114] Among them, the initial population is iteratively optimized according to a preset iterative optimization method, which can be to optimize each individual in the initial population to obtain a corresponding plurality of optimized individuals, and the optimized population can be obtained by combining the plurality of optimized individuals with the individuals in the initial population.

[0115] During the iterative optimization process, the initial population can be optimized to obtain an optimized population, and the optimized population can be further iteratively optimized to obtain a new optimized population. By analogy, multiple optimized populations can be obtained.

[0116] In a possible implementation, several individuals may be randomly selected from the initial population for optimization to obtain an optimized population.

[0117] In the subsequent process, an individual can be determined in the optimization population, and the power allocation solution corresponding to the individual meets the preset optimization conditions.

[0118] In this embodiment, an initial population is generated based on the initial power allocation scheme, the initial population comprising a plurality of individuals, each of which represents an initial power allocation scheme. The initial population is iteratively optimized based on a preset iterative optimization method to obtain at least one optimized population, comprising a plurality of individuals, each of which represents an optimized power allocation scheme. The initial power allocation scheme is treated as an individual to generate the initial population, and the initial population is iteratively optimized using genetic algorithms to obtain an optimized population. This achieves the process of optimizing the initial power allocation scheme to obtain multiple optimized power allocation schemes. Due to the strong global search capability of the genetic algorithm, the optimized population obtained using the genetic algorithm is more likely to contain the optimal power allocation scheme, making it easier to find the optimal power allocation scheme that meets the preset optimization conditions.

[0119] Figure 4 This is a flow chart of iteratively optimizing the initial population according to a preset iterative optimization method to obtain at least one optimized population provided in an embodiment of the present application, which may include steps 401 to 403. These steps are described in detail below.

[0120] 401. Optimize the first population based on a preset mutation amount to obtain a second population, wherein the mutation amount between the offspring individuals in the second population and the parent individuals in the first population satisfies the preset mutation amount, and the first population includes an initial population and an optimized population obtained by iteratively optimizing the initial population;

[0121] Among them, the individuals in the first population serve as parent individuals, and according to the mutation strategy of the differential evolution algorithm, the parent individuals are used to generate offspring mutant individuals, and the offspring mutant individuals constitute the second population.

[0122] The preset mutation amount is the mutation amount used in the mutation strategy of the differential evolution algorithm. It can be used in the form of a vector to optimize the parent individuals. The introduction of the preset mutation amount can explore new solution spaces to increase the diversity of the population and increase the options for power allocation schemes.

[0123] If the first population is the initial population, then the mutation strategy of the differential evolution algorithm is used to optimize the initial individuals of the initial population to obtain offspring mutant individuals, which constitute the second population.

[0124] If the first population is the optimized population after iterative optimization of the initial population, then each individual in the optimized population is used as a parent individual, and the mutation strategy of the differential evolution algorithm is used for optimization to obtain offspring mutant individuals, which constitute the second population.

[0125] Among them, the offspring individuals in the second population have a certain amount of variation and a certain degree of heredity compared to the parent individuals in the first population. The characteristics of the offspring individuals have some similarities and some differences with those of the parent individuals.

[0126] Since one individual corresponds to one power allocation scheme, the power allocation scheme corresponding to the offspring individual is partially identical to and partially different from the power allocation scheme corresponding to the parent individual, and the different parts satisfy the variation.

[0127] 402. Perform a crossover operation between the parent individuals in the first population and the offspring individuals in the second population to obtain a third population, wherein the third population includes offspring crossover individuals.

[0128] Among them, the individuals in the first population are parent individuals, and the offspring individuals in the second population are offspring variant individuals. The parent individuals and offspring variant individuals are cross-operated to generate offspring crossover individuals, and the offspring crossover individuals constitute the third population.

[0129] The offspring crossover individuals in this third population inherit the characteristics of the parent individuals and the offspring variant individuals.

[0130] Since the offspring crossover individuals inherit the characteristics of the parent individuals and the offspring variant individuals, and one individual corresponds to a power allocation scheme, the power allocation scheme corresponding to the offspring crossover individuals is partially the same as the power allocation scheme corresponding to the parent individuals, and partially the same as the power allocation scheme corresponding to the offspring variant individuals.

[0131] 403. Combine the first population, the second population, and the third population to obtain an optimized population.

[0132] Among them, the individuals in the first population serve as the parent individuals of this optimization iteration, the individuals in the second population serve as the offspring mutation individuals of this optimization iteration, and the individuals in the third population serve as the offspring crossover individuals of this optimization iteration. The parent individuals, offspring mutation individuals and offspring crossover individuals are combined to obtain an optimized population.

[0133] The optimized population includes all individuals generated by this iterative optimization, corresponding to several power allocation schemes of iterative optimization.

[0134] In this embodiment, the first population is optimized according to a preset variation to obtain a second population, and the variation between the offspring individuals in the second population and the parent individuals in the first population meets the preset variation. The first population includes an initial population and an optimized population after iterative optimization of the initial population. A third population is obtained according to a crossover operation between the parent individuals in the first population and the offspring individuals in the second population, and the third population includes offspring crossover individuals. The first population, the second population, and the third population are combined to obtain an optimized population. An optimization iteration process is introduced, and all individuals involved in an iterative optimization are combined to obtain an optimized population. By introducing a preset variation, it is possible to explore a new solution space to increase the diversity of the population and increase the optional options for the power allocation scheme.

[0135] Figure 5 The embodiment of the present application provides a flow chart for determining a target power allocation scheme in the initial power allocation scheme and at least two optimized power allocation schemes based on preset optimization conditions, which may include steps 501 to 502. These steps are described in detail below.

[0136] 501. According to the preset optimization condition, at least one candidate individual is selected from the at least one optimized population; the degree to which the candidate individual is influenced by the non-candidate individual in the optimized population is less than the degree to which the non-candidate individual is influenced by any individual in the optimized population;

[0137] In this application, the Pareto dominance relationship is used to screen and sort the individuals in the optimization population to obtain elite individuals (i.e., individuals to be selected). The elite individuals are one or several individuals in the optimization population that are closest to the optimization conditions.

[0138] In the Pareto dominance relationship in multi-objective optimization, if a solution is not inferior to another solution in all optimization objectives and is better than another solution in at least one objective, then the solution is said to dominate the other solution. In this application, the solution refers to an individual, and one individual corresponds to a power allocation scheme.

[0139] Correspondingly, in a population, the degree to which an individual is influenced by other individuals corresponds to its domination status. If individual A is influenced by many other individuals, it means that individual A is more heavily dominated, or if individual B is heavily influenced by individual C, it also means that individual B is more heavily dominated.

[0140] Among them, according to the preset optimization conditions, in the optimization population, the candidate individuals are selected, and the candidate individuals are one or more individuals in the corresponding optimization population that meet the preset optimization conditions, and are better than the degree to which the non-candidate individuals in the optimization population meet the preset optimization conditions.

[0141] In one possible implementation, a preset number of individuals to be selected can be pre-set, and individuals to be selected are selected from the generated optimized population according to the order in which the optimized population is generated. If the number of individuals to be selected in an optimized population reaches the preset number, further selection can be stopped. If the number of individuals to be selected in an optimized population does not reach the preset number, the population can be optimized again, and selection can be continued from the optimized population until the preset number of individuals to be selected is reached.

[0142] 502. Determine a target individual among the individuals to be selected, where the target individual corresponds to a target power allocation scheme.

[0143] Among the selected individuals, one is determined as the target individual.

[0144] The number of the individuals to be selected may be one or more, and one individual to be selected corresponds to one power allocation scheme.

[0145] Compared with the power allocation schemes corresponding to other individuals in the population, the power allocation scheme corresponding to the selected individual is more in line with the preset optimization conditions.

[0146] In one possible implementation, among the individuals to be selected, an individual that better meets the preset optimization conditions is selected as the target individual, and the power allocation scheme corresponding to the target individual can be used as the target power allocation scheme, which is then directly applied to the power control of the power equipment.

[0147] In this embodiment, based on preset optimization conditions, at least one candidate individual is selected from at least one optimized population; the degree to which the candidate individual is influenced by non-candidate individuals in the optimized population to which it belongs is less than the degree to which the non-candidate individual is influenced by any individual in the optimized population to which it belongs; among the candidate individuals, a target individual is determined, and the target individual corresponds to a target power allocation scheme, thereby first selecting the candidate individual in the optimized population, and then determining the target individual among the candidate individuals, and obtaining a power allocation scheme that meets the preset optimization conditions through layer-by-layer screening.

[0148] Figure 6 The embodiment of the present application provides a flow chart for selecting at least one individual to be selected from the at least one optimized population based on the preset optimization condition, which may include steps 601 to 603. These steps are described in detail below.

[0149] 601. Determine a target value corresponding to each individual in a target population based on the preset optimization condition, where the target population is any one of the at least one optimized population, and the target value represents a degree of matching between the individual and the preset optimization condition.

[0150] The target value represents the optimization effect of the corresponding individual on the overall preset optimization conditions. The larger the target value, the better the optimization effect, and vice versa.

[0151] The preset optimization condition can be expressed by a multi-objective function, and the preset optimization condition includes an objective function corresponding to each optimization objective.

[0152] The multi-objective function of the preset optimization condition can be expressed by the following formula (1):

[0153] (1)

[0154] Among them, F(x) represents the target value of individual x; x∈{parent individual, offspring mutation individual, offspring crossover individual}; f1(x) represents the network loss function; f2(x) represents the transmission efficiency loss function; f3(x) represents the power equipment power loss function.

[0155] The network loss function can be expressed as follows:

[0156] (2)

[0157] Among them, I real Re(Z) represents the real part of the impedance Z of the power equipment.

[0158] The transmission efficiency loss function can be expressed as follows:

[0159] (3)

[0160] Among them, P active Indicates the active power of the power equipment; P rated Indicates the rated power of the electrical equipment; V real Indicates the real-time voltage of the power equipment; V rated represents the rated voltage of the power equipment; θ represents the real-time power factor angle, which is the phase difference between the real-time voltage and real-time current of the power equipment; cos(θ) represents the power factor, which is the ratio of active power to real-time power.

[0161] The power loss function of the power equipment can be expressed by the following formula (4):

[0162] (4)

[0163] Among them, P active Indicates the active power of the power equipment; P rated Indicates the rated power of electrical equipment.

[0164] In one possible implementation, a weight coefficient is assigned to each loss function in formula (1), and the weight coefficient is used to reflect the relative importance of the corresponding loss function in the overall optimization process.

[0165] The above formulas (1)-(4) can be used to determine the target value for the power allocation scheme corresponding to each individual. The target value represents the degree of matching between the corresponding individual and the preset optimization conditions.

[0166] The larger the value of F(x), the higher the matching degree with the preset optimization condition; conversely, the smaller the value of F(x), the lower the matching degree with the preset optimization condition.

[0167] 602. Determine the non-dominant level of each individual in the target population based on the target value corresponding to each individual in the target population. The non-dominant level represents the degree to which the corresponding individual is influenced by other individuals in the target population. The level of the non-dominant level is negatively correlated with the degree of influence.

[0168] Among them, each individual in the target population is sorted according to the target value, and the target value is used to determine whether each individual in the target population is dominated by other individuals. According to the dominance influence, the target population can be divided into multiple non-dominated levels.

[0169] The level of dominance is related to the degree to which an individual is influenced by other individuals. The greater the degree to which an individual is influenced by other individuals, the lower the non-dominance level he or she belongs to.

[0170] The higher the dominance level of an individual, the better its target value for the overall preset optimization conditions is than other solutions, and at least one of the preset optimization conditions is also better than other solutions.

[0171] 603. In each non-dominated level, determine the individuals in the current non-dominated level as the candidates for selection of the target population.

[0172] According to the order of non-dominated levels from high to low, the individuals to be selected are determined in each non-dominated level in turn until the number of individuals to be selected in the target population reaches the preset number.

[0173] Among them, the candidate individual is an elite individual in the non-dominated hierarchy to which it belongs, and it can be an individual that converges to the parte frontier (the set of all parte optimal solutions), and the parte frontier corresponds to the non-dominated hierarchy.

[0174] In one possible implementation, parte convergence can be used for the target population to obtain a multi-layer parte frontier, with each layer of parte serving as a non-dominated level.

[0175] In each non-dominated level, the individuals to be selected in the non-dominated level are determined according to the relationship between the number of individuals and a preset number threshold.

[0176] In this application, the Pareto dominance relationship and crowding degree are used to screen and sort the individuals in the optimized population to obtain the individuals to be selected.

[0177] Among them, crowding can measure the relative density of an individual in the population, which is obtained by calculating the density of other individuals around the individual. Crowding screening individuals can maintain the diversity of the population and prevent the algorithm from converging to the local optimal solution too early.

[0178] In one possible implementation, a first number of individuals in a first non-dominated hierarchy is determined; if the first number is not greater than a preset threshold, each individual in the first non-dominated hierarchy is selected as a candidate for selection in the optimized population; if the first number is greater than the preset threshold, the individual is determined to be a candidate for selection in the optimized population based on whether the crowding degree of each individual in the first non-dominated hierarchy satisfies a selection condition. Satisfying the selection condition includes the crowding degree of the individual being greater than the crowding degrees of other individuals in the first non-dominated hierarchy, where the crowding degree is related to the degree of influence of the individual on other individuals in the optimized population.

[0179] Among them, using Pareto dominance relationship and crowding degree to screen individuals not only ensures the retention and inheritance of the optimal solution, but also improves the diversity and robustness of the algorithm through crowding degree sorting.

[0180] As an example, the preset number threshold is 2, and the non-dominated level a contains 2 individuals, and these 2 individuals are used as candidates for selection in the non-dominated level a.

[0181] As an example, the preset number threshold is 3, and the non-dominated level b contains 1 individual. The crowding degree of each individual in the non-dominated level is determined, and the three individuals with the highest crowding degree are selected as the candidates for the non-dominated level b. The crowding degree is sorted from high to low.

[0182] As an example, the initial population is iteratively optimized to obtain an optimized population, and a non-dominated layer is determined for each individual in the optimized population. The candidates are determined from high to low according to the order of the non-dominated layer until the number of candidates reaches a preset number.

[0183] In this embodiment, based on preset optimization conditions, a target value corresponding to each individual in a target population is determined, where the target population is any one of at least one optimized population, and the target value represents the degree of match between the individual and the preset optimization conditions. Based on the target value corresponding to each individual in the target population, a non-dominated level of each individual in the target population is determined, where the non-dominated level represents the degree to which the corresponding individual is influenced by other individuals in the target population, and the level of the non-dominated level is negatively correlated with the degree of influence. In each non-dominated level, individuals in the non-dominated level are determined as candidates for the target population, thereby utilizing the Pareto dominance relationship and the crowding degree to screen individuals in the optimized population to obtain candidates. This method can distinguish the pros and cons of power allocation schemes corresponding to different individuals, and the power allocation scheme corresponding to the ultimately screened candidate individuals is superior to the power allocation schemes corresponding to the unselected individuals, thereby accelerating the convergence speed of the algorithm and avoiding the problems of premature convergence and falling into a local optimum, thereby effectively improving the universality and optimality of the optimization results.

[0184] Figure 7 This is a flow chart of determining a target individual from the individuals to be selected provided by an embodiment of the present application, which may include steps 701 to 702. These steps are described in detail below.

[0185] 701. According to the target value of the candidate individual, the candidate individuals in at least one optimized population are respectively placed into a preset list, the preset list can carry a preset number of candidates, and the candidates in the preset list are sorted according to the target value;

[0186] Based on the above Figure 6 After determining the candidate individuals of the target population, the candidate individuals are placed in a preset list.

[0187] The preset list is used to carry the individuals to be selected from each optimized population. The preset list is sorted according to the target values of the individuals to be selected, and the target values of the individuals to be selected are related to the degree of matching between the corresponding power allocation scheme and the preset optimization conditions.

[0188] The preset list is sorted according to the target value of the candidate individual. The higher the target value of the candidate individual, the closer the power allocation scheme corresponding to the candidate individual is to the preset optimization condition, and accordingly, the higher the ranking in the preset list.

[0189] In one possible implementation, if the number of individuals to be selected in the first optimized population determined using the initial population has reached a preset number, then the subsequent process of re-determining the optimized population will no longer be performed, and the subsequent process of determining the target individual will be directly performed based on the individuals to be selected in the preset list.

[0190] As an example, the preset queue carries 3 individuals to be selected, and there are 4 individuals to be selected in the first optimized population determined by the initial population. After one individual to be selected is determined, it is placed in the preset queue. After the 4th individual to be selected is determined, the target value of the 4th individual to be selected is compared with the target values of the 3 individuals to be selected that already exist in the preset queue. If the target value of the 4th individual to be selected is smaller than the target value of the 3rd individual to be selected in the preset queue, the 4th individual to be selected is ignored. Otherwise, the 4th individual to be selected is inserted into the preset pair, and the one with the smallest target value among the 3 individuals to be selected in the current preset queue is eliminated to obtain the final preset list.

[0191] In one possible implementation, if the number of individuals to be selected in the first optimized population determined using the initial population fails to reach the preset number, then the process of determining the optimized population again is continued, and the individuals to be selected in the subsequently determined optimized population are continued to be added to the preset list until the number of individuals to be selected in the preset list reaches the preset number, and the subsequent process of determining the target individual is performed based on each individual to be selected in the preset list.

[0192] As an example, the preset queue carries three candidates. The first optimized population determined using the initial population contains one candidate, which is placed in the preset queue. Iterative optimization is then performed using the first optimized population to obtain a second optimized population. Three candidates are determined in the second optimized population. The first and second candidates are determined in the second optimized population and then placed in the preset queue. The target value of the third candidate is compared with the target values of the three candidates already in the preset queue. If the target value of the fourth candidate is less than the target value of the third candidate in the preset queue, the fourth candidate is ignored. Otherwise, the fourth candidate is inserted into the preset pair, and the candidate with the smallest target value among the three candidates in the current preset queue is removed to obtain the final preset list.

[0193] 702. Determine a target individual based on the ranking of the candidates in the preset list, wherein the target value of the target individual is higher than the target value of any non-target individual in the preset list.

[0194] The candidates in the preset list are sorted according to the target value, which represents the degree of fit between the power allocation scheme corresponding to the individual and the preset optimization conditions. The higher the ranking of the candidate, the better the optimization effect and the more it meets the preset optimization conditions.

[0195] In a possible implementation, the one ranked first in the preset list is selected as the target individual.

[0196] In this embodiment, based on the target value of the individual to be selected, the individuals to be selected in at least one optimized population are respectively placed in a preset list, which can carry a preset number of individuals to be selected, and each individual to be selected in the preset list is sorted according to the target value; based on the sorting of each individual to be selected in the preset list, the target individual is determined, and the target value of the target individual is higher than the target value of any non-target individual in the preset list. By selecting the individual to be selected from the optimized population as one or several individuals that best meet the optimization conditions, the preset list is used to sort the individuals to be selected, so that the algorithm can dynamically track and update the optimal solution, thereby providing strong support for ultimately finding the optimal power allocation solution that meets actual needs.

[0197] Figure 8 This is another flow chart of a method for optimizing the power of an electric power device provided in an embodiment of the present application. Figure 8 The flow chart shown is the power optimization method of power equipment except Figure 7 The steps shown in also include steps 801 to 803, which are described in detail below.

[0198] 801. After placing the candidate individuals determined in the first non-dominated hierarchy into a preset list, determine whether the preset list is full.

[0199] In this embodiment, whether to stop the screening process is determined based on whether the preset list is full.

[0200] Among them, individuals are screened in a preferred population according to the Pareto dominance relationship and crowding degree. During the screening process, individuals are screened in descending order according to the non-dominated hierarchy.

[0201] Determine individuals to be selected in a first non-dominated hierarchy, put the individuals to be selected into a preset list, and determine whether the preset list is full.

[0202] In one possible implementation, within a non-dominated hierarchy, individuals can be determined in batches in two steps. First, a determination is made as to whether the number of individuals in the non-dominated hierarchy exceeds the preset number of individuals that can be accommodated in the preset list. If the number of individuals in the non-dominated hierarchy is not greater than the preset number, the individuals in the non-dominated hierarchy are directly placed in the preset list as candidates for selection. If the number of individuals in the non-dominated hierarchy is greater than the preset number, the individuals in the non-dominated hierarchy are sorted according to their crowding degree, and individuals with higher crowding degrees are selected as candidates for selection in the non-dominated hierarchy, and the individuals in the non-dominated hierarchy are placed in the preset list as candidates for selection.

[0203] In one possible implementation, the process of placing the candidate individuals in the first non-dominated hierarchy into the preset list is to sort the candidate individuals in the first non-dominated hierarchy and the candidates in the preset list according to their target values, and then place the candidate individuals in the first non-dominated hierarchy into the preset list according to the sorting.

[0204] The first non-dominated layer is a non-dominated layer higher than the second non-dominated layer. The first non-dominated layer can be the highest non-dominated layer in the preferred population or another non-dominated layer. The second non-dominated layer can be the lowest non-dominated layer in the preferred population or another non-dominated layer.

[0205] 802. Based on the fact that the preset list is not full, add the candidate individuals determined in the second non-dominated level into the preset list, where the second non-dominated level is lower than the first non-dominated level;

[0206] If, after the candidates in the first non-dominated level are placed in the preset list, the preset list is not full, candidates are determined in the next non-dominated level (i.e., the second non-dominated level) and placed in the preset list in the same manner as the candidates in the first non-dominated level are placed in the preset list.

[0207] If the preset list of candidates in the second non-dominated level is not full, the next non-dominated level after the second non-dominated level (i.e., the second non-dominated level) is used to determine the candidates and put them into the preset list, and so on, until the preset list is full, and the process ends.

[0208] In a possible implementation, for each optimized population, the process of placing the individuals to be selected into the preset list in this embodiment may be performed separately according to the order in which the optimized population is generated.

[0209] 803. Based on the fact that the preset list is full, determine the target individual according to the individuals to be selected in the preset list.

[0210] If the preset list is full, the screening of the candidates is stopped and the target individual is determined from among the candidates in the preset list.

[0211] In a possible implementation, the individuals to be selected in each non-dominated level can also be placed in a preset list, and only a preset number of individuals to be selected are retained in the preset list. When the preset list is full, the preset list can be updated using the target value of the most recently determined individual to be selected.

[0212] In this embodiment, after the candidates determined in the first non-dominated hierarchy are placed in a preset list, it is determined whether the preset list is full. Based on the fact that the preset list is not full, the candidates determined in the second non-dominated hierarchy are placed in the preset list, where the second non-dominated hierarchy is lower than the first non-dominated hierarchy. Based on the fact that the preset list is full, a target individual is determined based on the candidates in the preset list, and the candidates determined in each non-dominated hierarchy are placed in the preset list to sort the candidates, so that the algorithm can dynamically track and update the optimal solution.

[0213] The above describes a method for optimizing the power of an electric device provided in an embodiment of the present application. The following describes an electronic device that executes the above method for optimizing the power of an electric device.

[0214] See also Figure 9 , Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 9 As shown, the electronic device 900 includes:

[0215] Interface 901, used to obtain preset parameter data of the power equipment, the preset parameter data including device parameter data and operation parameter data of the power equipment;

[0216] Processor 902 is used to determine a target power allocation scheme based on the preset parameter data and preset optimization conditions, where the preset optimization conditions include reducing network losses, improving transmission efficiency, and reducing power losses of power equipment; and control the output power of the power equipment based on the target power allocation scheme.

[0217] In one possible implementation, the processor determines a target power allocation scheme based on the preset parameter data and preset optimization conditions, including:

[0218] generating an initial power allocation plan based on the preset parameter data;

[0219] Iteratively optimizing the initial power allocation scheme according to a preset iterative optimization method to obtain at least two optimized power allocation schemes;

[0220] According to a preset optimization condition, a target power allocation scheme is determined among the initial power allocation scheme and the at least two optimized power allocation schemes, and the target power allocation scheme satisfies the preset optimization condition.

[0221] In one possible implementation, the processor iteratively optimizes the initial power allocation scheme according to a preset iterative optimization method to obtain at least two optimized power allocation schemes, including:

[0222] An initial population is generated according to the initial power allocation scheme, where the initial population includes a number of individuals, and each individual in the initial population represents an initial power allocation scheme;

[0223] According to a preset iterative optimization method, the initial population is iteratively optimized to obtain at least one optimized population, the optimized population including a plurality of individuals, and each individual in the optimized population represents an optimized power allocation scheme.

[0224] In one possible implementation, the processor performs iterative optimization on the initial population according to a preset iterative optimization method to obtain at least one optimized population, including:

[0225] Optimizing the first population according to a preset amount of variation to obtain a second population, wherein the variation between offspring individuals in the second population and parent individuals in the first population satisfies the preset amount of variation, the first population comprising an initial population and an optimized population obtained by iteratively optimizing the initial population;

[0226] According to the crossover operation between the parent individuals in the first population and the offspring individuals in the second population, a third population is obtained, wherein the third population includes offspring crossover individuals;

[0227] The first population, the second population, and the third population are combined to obtain the optimized population.

[0228] In a possible implementation, the processor determines, based on a preset optimization condition, a target power allocation scheme from the initial power allocation scheme and at least two optimized power allocation schemes, including:

[0229] According to the preset optimization condition, at least one candidate individual is selected from the at least one optimized population; the degree to which the candidate individual is influenced by the non-candidate individual in the optimized population to which it belongs is less than the degree to which the non-candidate individual is influenced by any individual in the optimized population to which it belongs;

[0230] Among the individuals to be selected, a target individual is determined, and the target individual corresponds to a target power allocation scheme.

[0231] In a possible implementation, the processor selects at least one candidate individual from the at least one optimized population according to the preset optimization condition, including:

[0232] Determining a target value corresponding to each individual in a target population based on the preset optimization condition, where the target population is any one of the at least one optimized population, the target value representing a degree of match between the individual and the preset optimization condition;

[0233] Based on the target value corresponding to each individual in the target population, the non-dominated hierarchy of each individual in the target population is determined. The non-dominated hierarchy represents the degree to which the corresponding individual is influenced by other individuals in the target population. The level of the non-dominated hierarchy is negatively correlated with the degree of influence.

[0234] In each non-dominated level, the individuals in the current non-dominated level are determined as the candidates for the target population.

[0235] In a possible implementation, the processor determines the target individual from the individuals to be selected, including:

[0236] According to the target value of the candidate individual, the candidate individuals in at least one optimized population are respectively placed into a preset list, the preset list can carry a preset number of candidates, and the candidates in the preset list are sorted according to the target value;

[0237] A target individual is determined according to the ranking of the candidates in the preset list, and the target value of the target individual is higher than the target value of any non-target individual in the preset list.

[0238] In one possible implementation, the processor is configured to:

[0239] After placing the candidates determined in the first non-dominated level into a preset list, determining whether the preset list is full;

[0240] Based on the fact that the preset list is not full, placing the candidate individuals determined in a second non-dominated hierarchy into the preset list, the second non-dominated hierarchy being lower than the first non-dominated hierarchy;

[0241] Because the preset list is full, a target individual is determined based on each candidate individual in the preset list.

[0242] In a possible implementation, the processor controls the output power of the power device according to the target power allocation scheme, including:

[0243] According to the target power allocation scheme, the output power of at least one electrical device is controlled within a preset time period.

[0244] It should be noted that for the functional explanation of each component structure in an electronic device provided in the embodiments of the present application, please refer to the explanation in the aforementioned method embodiment, and no further details will be given here.

[0245] In this embodiment, the interface is used to obtain preset parameter data for the power equipment, which includes device parameter data and operating parameter data for the power equipment. The processor is used to determine a target power allocation scheme based on the preset parameter data and preset optimization conditions, which include reducing network losses, improving transmission efficiency, and reducing power loss in the power equipment. The output power of the power equipment is then controlled based on the target power allocation scheme. Using the preset parameter data for the power equipment, a target power allocation scheme that meets the optimization conditions can be automatically determined and the output power of the power equipment can be controlled. The preset optimization conditions evaluate the power allocation of the power equipment from three perspectives: network losses, transmission efficiency, and power loss in the power equipment. Multiple performance indicators are simultaneously considered to ensure the comprehensiveness and optimality of the resulting optimization results.

[0246] The above describes a method for optimizing the power of an electric device provided in an embodiment of the present application. The following describes an apparatus for executing the above method for optimizing the power of an electric device.

[0247] See also Figure 10 , Figure 10 This is a schematic diagram of the structure of an electric power equipment power optimization device provided in an embodiment of the present application. Figure 10 As shown, the power optimization device 1000 for electric power equipment includes:

[0248] An acquisition module 1001 is configured to obtain preset parameter data of an electric power device, wherein the preset parameter data includes device parameter data and operation parameter data of the electric power device;

[0249] A determination module 1002 is configured to determine a target power allocation scheme based on the preset parameter data and preset optimization conditions, wherein the preset optimization conditions include reducing network losses, improving power transmission efficiency, and reducing power loss of power equipment;

[0250] The control module 1003 is configured to control the output power of the power equipment according to the target power allocation scheme.

[0251] In a possible implementation, the determining module includes:

[0252] A generating unit, configured to generate an initial power allocation scheme according to the preset parameter data;

[0253] an optimization unit, configured to iteratively optimize the initial power allocation scheme according to a preset iterative optimization method to obtain at least two optimized power allocation schemes;

[0254] The determining unit is configured to determine a target power allocation scheme from the initial power allocation scheme and at least two optimized power allocation schemes according to a preset optimization condition, wherein the target power allocation scheme satisfies the preset optimization condition.

[0255] In a possible implementation, the optimization unit includes:

[0256] A generating subunit, configured to generate an initial population according to the initial power allocation scheme, wherein the initial population includes a plurality of individuals, and each individual in the initial population represents an initial power allocation scheme;

[0257] The optimization subunit is used to iteratively optimize the initial population according to a preset iterative optimization method to obtain at least one optimized population, the optimized population including a plurality of individuals, and each individual in the optimized population represents an optimized power allocation scheme.

[0258] In a possible implementation, the optimization subunit is specifically configured to:

[0259] Optimizing the first population according to a preset amount of variation to obtain a second population, wherein the variation between offspring individuals in the second population and parent individuals in the first population satisfies the preset amount of variation, the first population comprising an initial population and an optimized population obtained by iteratively optimizing the initial population;

[0260] According to the crossover operation between the parent individuals in the first population and the offspring individuals in the second population, a third population is obtained, wherein the third population includes offspring crossover individuals;

[0261] The first population, the second population, and the third population are combined to obtain the optimized population.

[0262] In a possible implementation, the determining unit includes:

[0263] A selection subunit is configured to select at least one candidate individual from the at least one optimized population according to the preset optimization condition; the degree to which the candidate individual is influenced by the non-candidate individuals in the optimized population to which it belongs is less than the degree to which the non-candidate individual is influenced by any individual in the optimized population to which it belongs;

[0264] The determination subunit is used to determine a target individual among the individuals to be selected, where the target individual corresponds to a target power allocation scheme.

[0265] In a possible implementation, the subunit is selected to:

[0266] Determining a target value corresponding to each individual in a target population based on the preset optimization condition, where the target population is any one of the at least one optimized population, the target value representing a degree of match between the individual and the preset optimization condition;

[0267] Based on the target value corresponding to each individual in the target population, the non-dominated hierarchy of each individual in the target population is determined. The non-dominated hierarchy represents the degree to which the corresponding individual is influenced by other individuals in the target population. The level of the non-dominated hierarchy is negatively correlated with the degree of influence.

[0268] In each non-dominated level, the individuals in the current non-dominated level are determined as the candidates for the target population.

[0269] In a possible implementation, the subunit is determined to be specifically configured to:

[0270] According to the target value of the candidate individual, the candidate individuals in at least one optimized population are respectively placed into a preset list, the preset list can carry a preset number of candidates, and the candidates in the preset list are sorted according to the target value;

[0271] A target individual is determined according to the ranking of the candidates in the preset list, and the target value of the target individual is higher than the target value of any non-target individual in the preset list.

[0272] In a possible implementation, determining the subunit is further used for:

[0273] After placing the candidates determined in the first non-dominated level into a preset list, determining whether the preset list is full;

[0274] Based on the fact that the preset list is not full, placing the candidate individuals determined in a second non-dominated hierarchy into the preset list, the second non-dominated hierarchy being lower than the first non-dominated hierarchy;

[0275] Because the preset list is full, a target individual is determined based on each candidate individual in the preset list.

[0276] In a possible implementation, the control module is specifically configured to:

[0277] According to the target power allocation scheme, the output power of at least one electrical device is controlled within a preset time period.

[0278] It should be noted that for the functional explanation of the various components of the power optimization device for electric equipment provided in the embodiment of the present application, please refer to the explanation in the aforementioned method embodiment, which will not be repeated here.

[0279] In this embodiment, an acquisition module is used to obtain preset parameter data for an electric power device, the preset parameter data including device parameter data and operating parameter data for the electric power device; a determination module is used to determine a target power allocation scheme based on the preset parameter data and preset optimization conditions, the preset optimization conditions including reducing network losses, improving transmission efficiency, and reducing power losses of the electric power device; and a control module is used to control the output power of the electric power device based on the target power allocation scheme. Using the preset parameter data for the electric power device, a target power allocation scheme that meets the optimization conditions can be automatically determined and the output power of the electric power device can be controlled. The preset optimization conditions evaluate the quality of the power allocation of the electric power device from three perspectives: network losses, transmission efficiency, and power losses of the electric power device, while simultaneously considering multiple performance indicators to ensure the comprehensiveness and optimality of the resulting optimization results.

[0280] An electronic device is also provided in an embodiment of the present application. Figure 11 , which shows another structural schematic diagram of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 11 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0281] like Figure 11 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1102 or programs loaded from a storage device 1108 into a random access memory (RAM) 1103. When the electronic device is powered on, the RAM 1103 also stores various programs and data required for the operation of the electronic device. The processing device 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0282] Typically, the following devices may be connected to the I / O interface 1105: an input device 1106 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1107 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1108 including, for example, a memory card, a hard disk, etc.; and a communication device 1109. The communication device 1109 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Figure 11The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0283] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the power optimization methods for electric power equipment provided in the embodiment of the present application.

[0284] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any one of the power optimization methods for electric power equipment provided in the embodiment of the present application.

[0285] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.

[0286] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0287] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0288] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, training device or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center that includes one or more available media integrations. The available medium can be a magnetic medium, (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state drive (SSD)).

Claims

1. A method for optimizing the power of an electric power device, comprising: Obtaining preset parameter data of the electric power equipment, wherein the preset parameter data includes equipment parameter data and operation parameter data of the electric power equipment; Determining a target power allocation scheme based on the preset parameter data and preset optimization conditions, wherein the preset optimization conditions include reducing network losses, improving transmission efficiency, and reducing power losses of power equipment; According to the target power allocation scheme, the output power of the power equipment is controlled.

2. The method for optimizing power of electric power equipment according to claim 1, wherein determining the target power allocation scheme based on the preset parameter data and the preset optimization conditions comprises: generating an initial power allocation scheme according to the preset parameter data; Iteratively optimizing the initial power allocation scheme according to a preset iterative optimization method to obtain at least two optimized power allocation schemes; According to a preset optimization condition, a target power allocation scheme is determined among the initial power allocation scheme and at least two optimized power allocation schemes, and the target power allocation scheme satisfies the preset optimization condition.

3. The method for optimizing power of electric power equipment according to claim 2, wherein the initial power allocation scheme is iteratively optimized according to a preset iterative optimization method to obtain at least two optimized power allocation schemes, comprising: generating an initial population according to the initial power allocation scheme, wherein the initial population includes a plurality of individuals, and each individual in the initial population represents an initial power allocation scheme; According to a preset iterative optimization method, the initial population is iteratively optimized to obtain at least one optimized population, the optimized population including a plurality of individuals, and each individual in the optimized population represents an optimized power allocation scheme.

4. The method for optimizing the power of electric equipment according to claim 3, wherein the iterative optimization of the initial population is performed according to a preset iterative optimization method to obtain at least one optimized population, comprising: Optimizing the first population according to a preset amount of variation to obtain a second population, wherein the amount of variation between offspring individuals in the second population and parent individuals in the first population satisfies the preset amount of variation, the first population comprising an initial population and an optimized population obtained by iteratively optimizing the initial population; A third population is obtained based on a crossover operation between the parent individuals in the first population and the offspring individuals in the second population, wherein the third population includes offspring crossover individuals; The first population, the second population, and the third population are combined to obtain the optimized population.

5. The method for optimizing power of electric equipment according to claim 3, wherein determining a target power allocation scheme from the initial power allocation scheme and at least two optimized power allocation schemes based on a preset optimization condition comprises: According to the preset optimization condition, selecting at least one candidate individual from the at least one optimized population; The degree to which the candidate individual is influenced by the non-candidate individual in the optimized population to which it belongs is less than the degree to which the non-candidate individual is influenced by any individual in the optimized population to which it belongs; Among the individuals to be selected, a target individual is determined, and the target individual corresponds to a target power allocation scheme.

6. The method for optimizing the power of electric power equipment according to claim 5, wherein the step of selecting at least one candidate individual from the at least one optimization population according to the preset optimization condition comprises: Determining a target value corresponding to each individual in a target population based on the preset optimization condition, where the target population is any one of the at least one optimized population, and the target value represents a degree of match between the individual and the preset optimization condition; Determining, based on the target value corresponding to each individual in the target population, the non-dominated hierarchy of each individual in the target population to which it belongs, wherein the non-dominated hierarchy represents the degree to which the corresponding individual is influenced by other individuals in the target population to which it belongs, and the level of the non-dominated hierarchy is negatively correlated with the degree of influence; In each non-dominated level, the individuals in the current non-dominated level are determined as the candidates for the target population.

7. The method for optimizing power of electric equipment according to claim 6, wherein determining a target individual from among the individuals to be selected comprises: According to the target value of the candidate individuals, the candidate individuals in at least one optimized population are respectively placed into a preset list, the preset list can carry a preset number of candidates, and the candidates in the preset list are sorted according to the target value; A target individual is determined according to the ranking of the candidates in the preset list, and the target value of the target individual is higher than the target value of any non-target individual in the preset list.

8. The method for optimizing power of electric equipment according to claim 7, further comprising: After placing the candidate individuals determined in the first non-dominated hierarchy into a preset list, determining whether the preset list is full; Based on the fact that the preset list is not full, placing the candidate individuals determined in a second non-dominated hierarchy into the preset list, the second non-dominated hierarchy being lower than the first non-dominated hierarchy; Based on the fact that the preset list is full, a target individual is determined according to each candidate individual in the preset list.

9. The method for optimizing power of an electric power device according to claim 1, wherein controlling the output power of the electric power device according to the target power allocation scheme comprises: According to the target power allocation scheme, the output power of at least one electrical device is controlled within a preset time period.

10. An electronic device comprising: An interface for obtaining preset parameter data of the power equipment, wherein the preset parameter data includes equipment parameter data and operation parameter data of the power equipment; The processor is used to determine a target power allocation scheme based on the preset parameter data and preset optimization conditions, where the preset optimization conditions include reducing network losses, improving transmission efficiency, and reducing power losses of power equipment; and control the output power of the power equipment based on the target power allocation scheme.

Images