Heavy overload power transfer method based on genetic algorithm dynamic programming technology

Abstract

The present application relates to a heavy overload power transfer method, device, computer equipment and storage medium based on genetic algorithm dynamic programming technology. The method includes: obtaining the power consumption pattern of the target power station in the current area within a first preset time period; generating target prediction data based on the power consumption pattern and reference power consumption pattern within the first preset time period based on the genetic algorithm; generating predicted operating data and at least one power distribution plan of the target power station based on the target prediction data, and distributing power to the target power station based on the predicted operating data and the at least one power distribution plan. This method can be used to predict the operating data of the target power station and distribute power to the electrical equipment of the target power station based on the predicted data, thereby achieving the effect of improving the rationality of power load distribution.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a heavy overload power transfer method, device, computer equipment and storage medium based on genetic algorithm dynamic programming technology. Background Art

[0002] At present, the power supply bureau allocates peak and valley loads based on the power station data in the region. The power supply bureau monitors the power consumption patterns of the power stations through the central control platform, determines the load and duration of the power station's peak and valley periods, and generates operating parameter tables for power equipment, thereby providing data support for the power supply bureau to reasonably carry out peak and valley adjustments.

[0003] The scale and coverage area of ​​the completed power station are basically determined. However, with the increasingly rapid completion of new buildings in China and the rise of new industries, the electricity consumption patterns have changed rapidly, affecting the electricity consumption data collected by power stations in the current area. The traditional power supply distribution method of power stations has reduced the utilization rate of power resources. Summary of the Invention

[0004] Based on this, it is necessary to provide a heavy overload power transfer method, device, computer equipment and storage medium based on genetic algorithm dynamic programming technology to address the above technical problems.

[0005] A heavy overload power transfer method based on genetic algorithm dynamic programming technology, the method comprising: obtaining the power consumption pattern of a target power station in a current area within a first preset time period; generating target prediction data based on the power consumption pattern within the first preset time period and a reference power consumption pattern based on a genetic algorithm, the reference power consumption pattern being the power consumption pattern of a non-target power station in the current area within a second preset time period or the power consumption pattern of any power station in a non-current area within a third preset time period; generating predicted operating data and at least one power distribution plan of the target power station based on the target prediction data, and distributing power to the target power station based on the predicted operating data and the at least one power distribution plan.

[0006] In one embodiment, the target power station is provided with a plurality of power-consuming equipment, and obtaining the power consumption pattern of the target power station in the current area within a first preset time period includes: obtaining the data type of each power-consuming equipment of the target power station; collecting the numerical pattern of each data type within the first preset time period; and obtaining the power consumption pattern of the target power station within the first preset time period based on the data type of the power-consuming equipment and the numerical pattern.

[0007] In one embodiment, the genetic algorithm-based method generates target prediction data based on the power consumption pattern within the first preset time period and the reference power consumption pattern, including: searching for a matching reference power consumption pattern based on the power consumption pattern within the first preset time period; using the power consumption pattern within the first preset time period as a fitness parameter set and the reference power consumption pattern as an initial population to perform a cross-genetic operation to obtain a candidate parameter set; predicting the operating pattern of the target power station in a fourth preset time period based on the candidate parameter set, and using the operating pattern of the fourth preset time period as the target prediction data of the target power station in the fourth preset time period.

[0008] In one embodiment, the searching for a matching reference power usage pattern based on the power usage pattern within the first preset time period includes: generating a first characteristic curve of the power usage pattern within the first preset time period; searching for a reference characteristic curve of the reference power usage pattern based on the first characteristic curve; and when the degree of overlap between the first characteristic curve and the reference characteristic curve exceeds a preset overlap threshold, using the reference power usage pattern as the matching reference power usage pattern.

[0009] In one embodiment, the searching for a matching reference power usage pattern based on the power usage pattern within the first preset time period includes: generating a first characteristic curve of the power usage pattern within the first preset time period; searching for a reference characteristic curve of the reference power usage pattern based on the first characteristic curve; and when the degree of overlap between the first characteristic curve and the reference characteristic curve exceeds a preset overlap threshold, using the reference power usage pattern as the matching reference power usage pattern.

[0010] In one embodiment, the generating of predicted operating data and at least one power distribution plan of the target power station based on the target prediction data includes: arranging the data types in the target prediction data based on power-consuming equipment; obtaining the early warning thresholds of each data type of the power-consuming equipment, and generating the predicted operating data based on the early warning thresholds; distributing the load for the power-consuming equipment that exceeds the early warning thresholds in the prediction, and generating at least one power distribution plan.

[0011] In one embodiment, the method further includes: visualizing the predicted operation data and the power distribution plan to generate and display a predicted operation chart and a power distribution diagram.

[0012] In one embodiment, the visualization of the predicted operating data and the power distribution plan includes: filling the predicted operating data into the corresponding data area in the graphical template based on the electrical equipment; connecting the distribution objects involved in the power distribution plan and marking the distribution direction according to the load distribution direction in the power distribution plan, and setting corresponding color markings for the electrical equipment that exceeds the warning threshold.

[0013] A heavy overload power transfer device based on genetic algorithm dynamic programming technology, the device comprising: an acquisition module for acquiring the power consumption pattern of a target power station in a current area within a first preset time period; a prediction data generation module for generating target prediction data based on the power consumption pattern within the first preset time period and a reference power consumption pattern based on a genetic algorithm, wherein the reference power consumption pattern is the power consumption pattern of a non-target power station in the current area within a second preset time period or the power consumption pattern of any power station in a non-current area within a third preset time period; a data processing module for generating predicted operation data and at least one power distribution plan of the target power station based on the target prediction data, and distributing power to the target power station based on the predicted operation data and the at least one power distribution plan.

[0014] A computer device includes a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program: obtaining the power consumption pattern of a target power station in a current area within a first preset time period; generating target prediction data based on the power consumption pattern within the first preset time period and a reference power consumption pattern based on a genetic algorithm, wherein the reference power consumption pattern is the power consumption pattern of a non-target power station in the current area within a second preset time period or the power consumption pattern of any power station in a non-current area within a third preset time period; generating predicted operation data and at least one power distribution plan of the target power station based on the target prediction data, and distributing power to the target power station based on the predicted operation data and the at least one power distribution plan.

[0015] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps: obtaining a power consumption pattern of a target power station in a current region within a first preset time period; generating target prediction data based on the power consumption pattern within the first preset time period and a reference power consumption pattern based on a genetic algorithm, wherein the reference power consumption pattern is the power consumption pattern of a non-target power station in the current region within a second preset time period or the power consumption pattern of any power station in a non-current region within a third preset time period; generating predicted operating data and at least one power distribution scheme of the target power station based on the target prediction data, and distributing power to the target power station based on the predicted operating data and the at least one power distribution scheme.

[0016] The above-mentioned heavy overload power transfer method, device, computer equipment and storage medium based on genetic algorithm dynamic programming technology obtains the power consumption pattern of the target power station in the current area within a first preset time period, generates target prediction data based on the power consumption pattern within the first preset time period and the reference power consumption pattern of non-target power stations in the current area within a second preset time period or the reference power consumption pattern of any power station in the non-current area within a third preset time period based on the genetic algorithm, organizes the target prediction data to generate predicted operating data and at least one power distribution plan for the target power station, and distributes power to the target power station based on the predicted operating data and at least one power distribution plan. Compared with the traditional method of distributing power through parameter tables, this solution uses the power consumption pattern of the target power station and the reference power consumption patterns of other power stations to predict the operating data of the target power station, and distributes power to the power-consuming equipment in the target power station based on the predicted data, making power distribution more reasonable and improving the utilization rate of power resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is an application environment diagram of a heavy overload power transfer method based on a genetic algorithm dynamic programming technology in one embodiment;

[0018] Figure 2 1. A schematic flow chart of a method for transferring power under heavy overload conditions based on a genetic algorithm dynamic programming technique in one embodiment;

[0019] Figure 3 A flowchart of the steps of obtaining a power usage pattern within a first preset time period in one embodiment;

[0020] Figure 4 Schematic diagram of a flow chart of a method for generating target prediction data in one embodiment;

[0021] Figure 5 A schematic diagram of a process for generating predicted operating data and a power distribution plan in one embodiment;

[0022] Figure 6 A flowchart of a visualization process in one embodiment;

[0023] Figure 7 A structural block diagram of a heavy overload power transfer device based on a genetic algorithm dynamic programming technology in one embodiment;

[0024] Figure 8 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0026] The heavy overload transfer method based on genetic algorithm dynamic programming technology provided in this application can be applied to Figure 1 In the application environment shown. The terminal 102 communicates with the server 104 via a network. The terminal 102 can obtain the power consumption pattern of the target power station in the current area within a first preset time period, and generate target prediction data based on the power consumption pattern within the first preset time period and the reference power consumption pattern based on the genetic algorithm, and then organize the target prediction data to generate predicted operating data and at least one power allocation plan for the target power station. The power consumption pattern and the reference power consumption pattern can be obtained from the server 104, which can be a device for obtaining and storing power consumption data of each power station in the above-mentioned area. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers, and the server 104 can be implemented as an independent server or a server cluster consisting of multiple servers.

[0027] In one embodiment, Figure 2 As shown in the figure, a heavy overload transfer method based on genetic algorithm dynamic programming technology is provided. Figure 1 The following steps are used as an example to illustrate the terminal in the figure:

[0028] S202: Obtain the power consumption pattern of the target power station in the current area within a first preset time period.

[0029] First, an administrative region or location area can be divided into multiple regions based on power distribution. One region is selected from these multiple regions as the region to be processed, i.e., the current region. The current region may be home to multiple power stations, and one of these power stations is selected as the power station to which power distribution is to be performed, i.e., the target power station. Specifically, terminal 102 obtains power usage data for the target power station in the current region over a first preset time period, analyzes the power usage data, and determines a power usage pattern over the first preset time period. The first preset time period can be set as needed. For example, the first preset time period can be a continuous time period or a combination of multiple discontinuous time periods.

[0030] It is understood that power usage can include the power usage of multiple electrical devices. These devices may include transformers, high-voltage circuit breakers, busbars, lightning arresters, capacitors, reactors, and the like. The power usage of each electrical device may refer to the variation patterns of multiple parameters of that device. For example, the power usage of a transformer may include the variation patterns of its operating voltage, operating current, and operating temperature; the power usage of a transformer may include the variation patterns of its temperature; the switching conditions of a circuit breaker may also be included. The types of parameters for the power usage of an electrical device can be selected based on actual needs and are provided here for reference only and are not intended to be limiting.

[0031] S204, generating target prediction data based on the genetic algorithm according to the power consumption pattern within the first preset time period and the reference power consumption pattern, where the reference power consumption pattern is the power consumption pattern of the non-target power station in the current area within the second preset time period or the power consumption pattern of any power station in the non-current area within the third preset time period.

[0032] To predict the target power station's power consumption pattern within the first preset time, it is necessary to use the historical power consumption patterns of other power stations as a reference. Specifically, the power consumption patterns of non-target power stations in the current area can be used as a reference, or the power consumption patterns of power stations in other areas can be used as a reference.

[0033] Among them, the power consumption pattern is the numerical pattern of the parameter type in the power consumption of each power-consuming device in the power station. Among them, the power consumption pattern of the target power station refers to the power consumption pattern within the first preset time period of the power station that needs to distribute power, and the reference power consumption pattern can be the power consumption pattern of the non-target power station in the current area, or the power consumption pattern of any power station in the non-current area. It is worth noting that the second preset time period and the third preset time period can be set as needed, and the length relationship between the first preset time period, the second preset time period and the third preset time period is not limited. However, in order to increase the ease of matching between the power consumption pattern of the target power station and the reference power consumption pattern, the second preset time period and the third preset time period are often made longer to include more data.

[0034] Genetic algorithms are computational models of biological evolution that simulate the natural selection and genetic mechanisms of Darwinian evolution. They are a method for searching for optimal solutions by simulating natural evolutionary processes. Their key features are direct operations on structural objects, without the constraints of derivatives or function continuity; inherent implicit parallelism and enhanced global optimization capabilities; and a probabilistic optimization approach that automatically acquires and guides the optimal search space without the need for specific rules, adaptively adjusting the search direction. Selection, crossover, and mutation constitute the genetic operations of genetic algorithms; while parameter encoding, initial population setting, fitness function design, genetic operation design, and control parameter setting constitute the core elements of genetic algorithms. Because the overall search strategy and optimization search method of genetic algorithms do not rely on gradient information or other auxiliary knowledge during computation, but only on the objective function and corresponding fitness function that influence the search direction, genetic algorithms provide a general framework for solving complex system problems. They are independent of the specific problem domain and are highly robust to the type of problem, leading to their widespread application in many scientific fields.

[0035] Specifically, the terminal 102 may generate target prediction data based on the power consumption pattern within the first preset time period and the reference power consumption pattern using a genetic algorithm, wherein the target prediction data may be prediction data for the operation data of the target power station.

[0036] In this embodiment, the power consumption pattern within the first preset time period can be used as the fitness parameter set, and the reference power consumption pattern can be used as the initial population. Based on the genetic algorithm, the target prediction data is formed according to the power consumption pattern within the first preset time period and the power consumption pattern of non-target power stations in the current area within the second preset time period, or the power consumption pattern of any power station in the non-current area within the third preset time period.

[0037] Step S206 : generating predicted operation data and at least one power allocation plan of the target power station according to the target predicted data, and allocating power to the target power station according to the predicted operation data and the at least one power allocation plan.

[0038] The predicted operating data may be predicted data for operating information of a target power station. The terminal 102 may use the target predicted data to generate predicted operating data and at least one power allocation plan for the target power station. The terminal 102 may also use the predicted operating data and at least one power allocation plan to allocate power to the target power station. For example, if the terminal 102 detects that the predicted operating data of the target power station exceeds a preset warning threshold for a period of time or at a certain point in time, the terminal 102 may generate a power allocation plan based on the exceeded operating data, allocating more power to the target power station for the period of time or at a certain point in time.

[0039] Specifically, the target prediction data is the original collected data. To facilitate subsequent visualization and analysis of electrical equipment by maintenance personnel, the target prediction data needs to be reorganized to generate predicted operating data. Simultaneously, based on pre-set thresholds, the predicted operating data is identified as exceeding the threshold. Based on this exceeding threshold, power is automatically allocated, thereby forming at least one power allocation plan. It is understood that the automatic power allocation rules can be manually set based on the actual power network or automatically derived from power network data using algorithms such as artificial intelligence.

[0040] In the above-mentioned heavy overload power transfer method based on genetic algorithm dynamic programming technology, by obtaining the power consumption pattern of the target power station in the current area within the first preset time period, based on the genetic algorithm, according to the power consumption pattern within the first preset time period and the reference power consumption pattern of non-target power stations in the current area within the second preset time period or the reference power consumption pattern of any power station in the non-current area within the third preset time period, target prediction data is generated, the target prediction data is organized to generate predicted operating data and at least one power distribution plan of the target power station, and power is distributed to the target power station based on the predicted operating data and at least one power distribution plan. Compared with the traditional method of distributing power through parameter tables, this solution uses the power consumption pattern of the target power station and the reference power consumption pattern of other power stations to predict the operating data of the target power station, and distributes power to the power-consuming equipment in the target power station based on the predicted data, making power distribution more reasonable.

[0041] In one embodiment, obtaining the power consumption pattern of the target power station in the current area within the first preset time period includes: S302, obtaining the data type of each power-consuming device of the target power station; S304, collecting the numerical pattern of the data type within the first preset time period; S306, obtaining the power consumption pattern of the target power station within the first preset time period according to the data type and numerical pattern of the power-consuming device.

[0042] In this embodiment, Figure 3 As shown, Figure 3The present invention is a flowchart for obtaining the power consumption pattern within a first preset time period in one embodiment. The target power station is provided with a plurality of power-consuming devices. The terminal 102 can obtain the data type of each power-consuming device of the target power station and collect the data pattern of the data type within the first preset time period. The terminal 102 can also generate an operation data table of the power-consuming device according to the data type and numerical pattern of the power-consuming device, and can also generate an operation data graph according to the data type and numerical pattern of the power-consuming device. Specifically, since the data is divided according to the power-consuming device when the predicted operation data is subsequently generated, the data type of each data, such as voltage, current, and power, must be collected and distinguished for each power-consuming device in the target power station, and the change pattern of these data types within the first preset time period is recorded, thereby forming the original operation data table or operation data graph of the power-consuming device. It is worth noting that step S202 directly uses the data sent back by the collection end, such as the voltage sensor, temperature sensor, etc., as a table of power consumption patterns. The terminal 102 can organize the data into a raw data table. The raw data table is divided according to the data type (such as the power table), so it is not suitable for operation and maintenance personnel to directly obtain the operating status of the electrical equipment. Therefore, it is necessary to reorganize the raw data table in a subsequent manner, so that the terminal 102 can obtain the power consumption pattern of the target power station within the first preset time period based on the operation data table.

[0043] In this embodiment, the terminal can use the numerical variation rules of each power-consuming device in the target power station to obtain the operation data table of the power-consuming device, and thus can obtain the power consumption rule of the target power station based on the operation data table, thereby improving the rationality of power transfer.

[0044] In one embodiment, Figure 4 The figure is a flow chart of generating target prediction data in one embodiment. The target prediction data is generated based on the power consumption pattern within the first preset time period and the reference power consumption pattern based on the genetic algorithm, including:

[0045] S402: Search for a matching reference power usage pattern based on the power usage pattern within a first preset time period.

[0046] Since the power consumption patterns of different power plants in two different periods are often not exactly the same, directly comparing the power consumption patterns of different power plants in two periods is not practically meaningful. Therefore, the consistency of the power consumption patterns of the two periods is determined by the degree of overlap of the characteristic curves. For each reference power consumption pattern obtained, a reference characteristic curve is generated. Then, in the same manner, a first characteristic curve of the power consumption pattern within a first preset time period is extracted. The first characteristic curve is compared with the reference characteristic curve, and the reference power consumption patterns corresponding to those exceeding the preset overlap threshold are added to the candidate list. The candidate list can contain multiple reference power consumption patterns, and the corresponding overlap data of these reference power consumption patterns should be recorded for subsequent judgment.

[0047] S404 , using the electricity usage pattern within the first preset time period as a fitness parameter set and the reference electricity usage pattern as an initial population, performing a crossover genetic algorithm to obtain a candidate parameter set.

[0048] In genetic algorithms, crossover refers to exchanging some of the genes of two paired chromosomes in a certain way to form two new individuals. Crossover is an important feature that distinguishes genetic algorithms from other evolutionary algorithms and is the main method for generating new individuals. In this embodiment, the electricity consumption pattern within the first preset time period is used as the fitness parameter set, the reference electricity consumption pattern is used as the initial population, and the reference electricity consumption value is encoded. The electricity consumption values ​​of different power stations in different regions will form different populations. The electricity consumption pattern within the first preset time period is then used as the fitness function set. Individuals with higher fitness are selected from each population to perform crossover operations, thereby selecting an electricity consumption pattern that is adapted to the electricity consumption pattern within the first preset time period from the reference electricity consumption pattern. When the convergence conditions of the genetic algorithm are met, the candidate parameter set is output.

[0049] S406 : Predicting an operating rule of the target power station in a fourth preset time period according to the candidate parameter set, and using the operating rule of the fourth preset time period as target prediction data of the target power station in the fourth preset time period.

[0050] It can be understood that the fourth preset time length is the actual usage time length, and the fourth preset time length can also be set according to needs. The longer the fourth preset time length is, the greater the error will be, and the shorter the fourth preset time length is, the smaller the corresponding error will be.

[0051] Specifically, the power consumption pattern of the time period to be predicted is generated according to the candidate parameter set obtained in the above S404, that is, the target prediction data of the fourth preset time period.

[0052] In this embodiment, the terminal 102 can use the power consumption pattern of the target power station to obtain a reference power consumption pattern, and use the reference power consumption pattern to predict the prediction data of the target power station, so that the prediction data can be used to allocate electricity, thereby improving the rationality of power distribution.

[0053] In one embodiment, predicted operating data of a target power station and at least one power distribution plan are generated based on target prediction data, including: S502, arranging the data types in the target prediction data based on power-consuming equipment; S504, obtaining early warning thresholds for each data type of the power-consuming equipment, and generating predicted operating data based on the early warning thresholds; S506, distributing loads to power-consuming equipment that exceeds the early warning thresholds in the prediction, and generating at least one power distribution plan.

[0054] In this embodiment, Figure 5 As shown, Figure 5 The following is a flow chart illustrating a process for generating predicted operating data and a power allocation plan in one embodiment. Terminal 102 can organize the data types in target predicted data by electrical device, obtain warning thresholds for each data type of the electrical device, and combine the warning thresholds with the organized target predicted data to generate predicted operating data. Terminal 102 can then distribute load to electrical devices that exceed the warning thresholds in the prediction, thereby generating at least one power allocation plan. Specifically, since the target predicted data is organized by data type, in order to intuitively display the load variation patterns of each power consumption in the target power station, the target predicted data needs to be reorganized. By grouping the values ​​of different data types for the same electrical device into tables for that electrical device, the data tables are organized based on the electrical device. Since the organized target predicted data is predicted data, a power allocation plan can be constructed based on the predicted data in this step. Warning thresholds for each data type are pre-set in the system. When a value in the predicted data exceeds the corresponding warning threshold, load distribution to the electrical device corresponding to the predicted data is initiated. It is understandable that, since the lines of the power network are often complex, there are often multiple ways to distribute the load. Therefore, there can be multiple power distribution plans generated in the end, and at least one of them is the optimal distribution plan.

[0055] Through this embodiment, the terminal 102 can use the warning threshold to analyze the predicted operation data, and allocate power to the power equipment when the operation data exceeds the warning threshold, thereby obtaining a corresponding power allocation plan and improving the rationality of power allocation.

[0056] In one embodiment, after organizing the target prediction data to generate the prediction operation data of the target power station and at least one power distribution plan, the method further includes: visualizing the prediction operation data and the power distribution plan to generate and display a prediction operation chart and a power distribution diagram.

[0057] In this embodiment, the predicted operation data and power distribution plan obtained by the terminal 102 are actually stored in the form of data. In order to improve the decision-making speed of the operation and maintenance personnel, the terminal 102 can visualize the predicted operation data and the power distribution plan, and display the predicted operation data and the corresponding power distribution plan in an intuitive form. For example, different icons are set for different electrical equipment, and the predicted numerical value change law is displayed near the icon in the form of a histogram, a coordinate curve, etc. The power distribution plan can also be displayed through a load flow route map, and the optimal power distribution plan is placed in the front. It is understandable that since the data included in the power consumption law varies greatly, the corresponding power distribution plans are also different. Therefore, the predicted operation chart and power distribution chart finally displayed also have multiple visualization forms, which are not limited by this application.

[0058] Through this embodiment, the terminal 102 can visualize information such as operating data, thereby improving the efficiency of power distribution.

[0059] In one embodiment, the predicted operating data and the power distribution plan are visualized, including: step S610, filling the predicted operating data into the corresponding data area in the graphical template based on the power-consuming equipment; step S620, connecting the distribution objects involved in the power distribution plan and marking the distribution direction according to the load distribution direction in the power distribution plan, and setting corresponding color markings for the power-consuming equipment that exceeds the warning threshold.

[0060] In this embodiment, Figure 6 As shown, Figure 6 The figure is a flow chart of visualization processing in one embodiment. The terminal 102 can fill the predicted operation data into the corresponding data area in the graphical template based on the electrical equipment as a unit, and connect the distribution objects involved in the power distribution plan and mark the distribution direction according to the load distribution direction in the power distribution plan. The terminal 102 can also set a corresponding color mark for the electrical equipment that exceeds the warning threshold. For example, the terminal 102 can preset an icon corresponding to the electrical equipment in the graphical template. Therefore, during the visualization process, the icon is associated with the electrical equipment, and the predicted operation data of the electrical equipment is placed near the icon so that the operation and maintenance personnel can directly understand the future status of the electrical equipment. On the other hand, corresponding to the power distribution plan, since power distribution is directional, this embodiment uses a graphic with distribution direction to represent the distribution plan. For example, if a certain electrical equipment that exceeds the threshold distributes the power load to two other electrical equipment, then two arrows are used to represent the distribution direction, and the thickness of the arrow is set to represent the amount of distribution. At the same time, in order to indicate the extent to which the electrical equipment exceeds the warning threshold, the electrical equipment is marked with a corresponding color so that operation and maintenance personnel can find electrical equipment running at high load at a glance.

[0061] Specifically, in one embodiment, setting corresponding color markings for electrical devices that exceed a warning threshold includes: setting a first color for the icons of electrical devices that exceed a first percentage of the warning threshold; setting a second color for the icons of electrical devices that exceed a second percentage of the warning threshold; wherein the first percentage is greater than the second percentage. In this embodiment, the terminal 102 can mark the electrical devices with different colors based on the extent to which the warning threshold is exceeded, for example: setting a first color, such as yellow, for the icons of electrical devices that exceed a first percentage of the warning threshold; setting a second color, such as red, for the icons of electrical devices that exceed a second percentage of the warning threshold; wherein the first percentage is greater than the second percentage.

[0062] Through the above embodiments, the terminal 102 can visualize information such as operating data, thereby improving the efficiency of power distribution.

[0063] It should be understood that although Figure 2-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2-Figure 6 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0064] In one embodiment, Figure 7 As shown, a heavy overload transfer distribution device based on genetic algorithm dynamic programming technology is provided, including: an acquisition module 700, a prediction data generation module 702 and a data processing module 704, wherein:

[0065] The acquisition module 700 is configured to acquire the power consumption pattern of the target power station in the current region within a first preset time period.

[0066] The prediction data generation module 702 is used to generate target prediction data based on the power consumption pattern within the first preset time period and the reference power consumption pattern based on the genetic algorithm. The reference power consumption pattern is the power consumption pattern of the non-target power station in the current area within the second preset time period or the power consumption pattern of any power station in the non-current area within the third preset time period.

[0067] The data processing module 704 is configured to generate predicted operating data and at least one power allocation scheme of the target power station according to the target prediction data, and allocate power to the target power station according to the predicted operating data and the at least one power allocation scheme.

[0068] In one embodiment, the acquisition module further includes: a data type acquisition submodule, used to acquire the data type of each electrical equipment of the target power station; a numerical pattern collection submodule, used to collect the numerical pattern of the data type within a first preset time length; and a power consumption pattern generation submodule, used to obtain the power consumption pattern of the target power station within the first preset time length based on the data type of the electrical equipment and the numerical pattern.

[0069] In one embodiment, the prediction data generation module also includes: a reference rule search submodule, which is used to search for a matching reference power consumption rule based on the power consumption rule within a first preset time period; a candidate parameter acquisition submodule, which is used to use the power consumption rule within the first preset time period as a fitness parameter set and the reference power consumption rule as an initial population to perform a cross-genetic operation to obtain a candidate parameter set; a prediction data acquisition submodule, which is used to predict the operating rule of the target power station in a fourth preset time period based on the candidate parameter set, and the operating rule of the fourth preset time period is used as the target prediction data of the target power station in the fourth preset time period.

[0070] In one embodiment, the reference pattern search submodule also includes: a characteristic curve generation unit, used to generate a first characteristic curve of the power consumption pattern within a first preset time length; a reference characteristic curve generation unit, used to search for a reference characteristic curve of the reference power consumption pattern based on the first characteristic curve; a reference power consumption pattern determination unit, used to add the reference power consumption pattern to an alternative list when the degree of overlap between the first characteristic curve and the reference characteristic curve exceeds a preset overlap threshold, and obtain a matching reference power consumption pattern based on the alternative list.

[0071] In one embodiment, the data processing module also includes: a data type arrangement submodule, which is specifically used to arrange the data types in the target prediction data based on electrical equipment; a predicted operation data generation submodule, which is used to obtain the warning threshold of each data type of the electrical equipment and generate predicted operation data based on the warning threshold; an allocation plan generation submodule, which is used to distribute the load to the electrical equipment that exceeds the warning threshold in the prediction and generate at least one power allocation plan.

[0072] In one embodiment, the apparatus further comprises a visualization module for visualizing the predicted operation data and the power distribution plan, and generating and displaying a predicted operation chart and a power distribution diagram.

[0073] In one embodiment, the visualization module also includes: a data area generation submodule, which is used to fill the predicted operation data into the corresponding data area in the graphical template based on the electrical equipment; a color marking submodule, which is used to connect the distribution objects involved in the power distribution plan and mark the distribution direction according to the load distribution direction in the power distribution plan, and set corresponding color markings for electrical equipment that exceeds the warning threshold.

[0074] Regarding the specific definition of the heavy overload transfer device based on genetic algorithm dynamic programming technology, please refer to the definition of the heavy overload transfer method based on genetic algorithm dynamic programming technology above, which will not be repeated here. The various modules in the above-mentioned heavy overload transfer device based on genetic algorithm dynamic programming technology can be fully or partially implemented by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0075] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for distributing power loads is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0076] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0077] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining the power consumption pattern of a target power station in a current area within a first preset time period; generating target prediction data based on the power consumption pattern within the first preset time period and a reference power consumption pattern based on a genetic algorithm, wherein the reference power consumption pattern is the power consumption pattern of a non-target power station in the current area within a second preset time period or the power consumption pattern of any power station in a non-current area within a third preset time period; generating predicted operation data and at least one power distribution plan of the target power station based on the target prediction data, and distributing power to the target power station based on the predicted operation data and the at least one power distribution plan.

[0078] In one embodiment, when the processor executes the computer program, it also implements the following steps: obtaining the data type of each electrical device of the target power station; collecting the numerical pattern of each data type within a first preset time period; and obtaining the power consumption pattern of the target power station within the first preset time period based on the data type of the electrical device and the numerical pattern.

[0079] In one embodiment, when the processor executes the computer program, it also implements the following steps: searching for a matching reference power consumption pattern based on the power consumption pattern within the first preset time period; using the power consumption pattern within the first preset time period as a fitness parameter set and the reference power consumption pattern as an initial population, performing a cross-genetic operation to obtain a candidate parameter set; predicting the operating pattern of the target power station in a fourth preset time period based on the candidate parameter set, and using the operating pattern of the fourth preset time period as the target prediction data of the target power station in the fourth preset time period.

[0080] In one embodiment, when the processor executes the computer program, it also implements the following steps: generating a first characteristic curve of the power consumption pattern within the first preset time period; searching for a reference characteristic curve of the reference power consumption pattern based on the first characteristic curve; when the degree of overlap between the first characteristic curve and the reference characteristic curve exceeds a preset overlap threshold, using the reference power consumption pattern as the matching reference power consumption pattern.

[0081] In one embodiment, when the processor executes the computer program, it also implements the following steps: arranging the data types in the target prediction data based on electrical equipment; obtaining the warning thresholds of each data type of the electrical equipment, and generating predicted operation data based on the warning thresholds; distributing the load for the electrical equipment that exceeds the warning thresholds in the prediction, and generating at least one power distribution plan.

[0082] In one embodiment, when the processor executes the computer program, the processor further implements the following steps: visualizing the predicted operation data and the power distribution plan, generating and displaying a predicted operation chart and a power distribution diagram.

[0083] In one embodiment, when the processor executes the computer program, it also implements the following steps: filling the predicted operation data into the corresponding data area in the graphical template based on the electrical equipment; connecting the distribution objects involved in the power distribution plan and marking the distribution direction according to the load distribution direction in the power distribution plan, and setting corresponding color markings for electrical equipment that exceeds the warning threshold.

[0084] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: obtaining the power consumption pattern of a target power station in a current area within a first preset time period; generating target prediction data based on the power consumption pattern within the first preset time period and a reference power consumption pattern based on a genetic algorithm, wherein the reference power consumption pattern is the power consumption pattern of a non-target power station in the current area within a second preset time period or the power consumption pattern of any power station in a non-current area within a third preset time period; generating predicted operation data and at least one power distribution scheme of the target power station based on the target prediction data, and distributing power to the target power station based on the predicted operation data and the at least one power distribution scheme.

[0085] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the data type of each electrical device of the target power station; collecting the numerical pattern of each data type within a first preset time period; and obtaining the power consumption pattern of the target power station within the first preset time period based on the data type of the electrical device and the numerical pattern.

[0086] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: searching for a matching reference power consumption pattern based on the power consumption pattern within the first preset time period; using the power consumption pattern within the first preset time period as a fitness parameter set and the reference power consumption pattern as an initial population, performing a cross-genetic operation to obtain a candidate parameter set; predicting the operating pattern of the target power station in a fourth preset time period based on the candidate parameter set, and using the operating pattern of the fourth preset time period as the target prediction data of the target power station in the fourth preset time period.

[0087] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: generating a first characteristic curve of the power consumption pattern within the first preset time period; searching for a reference characteristic curve of the reference power consumption pattern based on the first characteristic curve; when the degree of overlap between the first characteristic curve and the reference characteristic curve exceeds a preset overlap threshold, using the reference power consumption pattern as the matching reference power consumption pattern.

[0088] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: arranging the data types in the target prediction data based on electrical equipment; obtaining the warning thresholds of each data type of the electrical equipment, and generating prediction operation data based on the warning thresholds; distributing the load for the electrical equipment that exceeds the warning thresholds in the prediction, and generating at least one power distribution plan.

[0089] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: visualizing the predicted operation data and the power distribution plan, generating and displaying a predicted operation chart and a power distribution diagram.

[0090] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: filling the predicted operation data into the corresponding data area in the graphical template based on the electrical equipment; connecting the distribution objects involved in the power distribution plan and marking the distribution direction according to the load distribution direction in the power distribution plan, and setting corresponding color markings for electrical equipment that exceeds the warning threshold.

[0091] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0092] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0093] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A heavy overload power transfer method based on genetic algorithm dynamic programming technology, characterized in that: The method comprises: Obtaining a power consumption pattern of a target power station in the current region within a first preset time period; the power consumption pattern is obtained by analyzing the power consumption of transformers, high-voltage circuit breakers, busbars, lightning arresters, capacitors, and reactors in the target power station; the power consumption pattern refers to the variation pattern of multiple parameters of the power-consuming equipment; generating target prediction data based on the power consumption pattern within the first preset time period and a reference power consumption pattern using a genetic algorithm, wherein the reference power consumption pattern is the power consumption pattern of a non-target power station in the current region within the second preset time period or the power consumption pattern of any power station in the non-current region within the third preset time period; generating predicted operating data and at least one power allocation plan of the target power station according to the target predicted data, and allocating power to the target power station according to the predicted operating data and the at least one power allocation plan; The generating target prediction data based on the power usage pattern within the first preset time period and the reference power usage pattern based on the genetic algorithm includes: Searching for a matching reference power usage pattern based on the power usage pattern within the first preset duration; using the power usage pattern within the first preset duration as a fitness parameter set and the reference power usage pattern as an initial population to perform a crossover genetic algorithm to obtain a candidate parameter set; predicting an operating pattern of the target power station for a fourth preset duration based on the candidate parameter set, using the operating pattern of the fourth preset duration as target prediction data for the target power station for the fourth preset duration; The searching for a matching reference power usage pattern according to the power usage pattern within the first preset time period includes: Generate a first characteristic curve of the power consumption pattern within the first preset time period; search for a reference characteristic curve of the reference power consumption pattern based on the first characteristic curve; when the degree of overlap between the first characteristic curve and the reference characteristic curve exceeds a preset overlap threshold, use the reference power consumption pattern as the matching reference power consumption pattern.

2. The method according to claim 1, characterized in that The target power station is provided with a plurality of power-consuming devices, and obtaining the power consumption pattern of the target power station in the current area within the first preset time period includes: Obtaining data types of various electrical devices of the target power station; Collect the numerical pattern of each data type within a first preset time period; The power consumption pattern of the target power station within a first preset time period is obtained according to the data type of the power-consuming equipment and the numerical pattern.

3. The method according to claim 2, characterized in that Generating the predicted operating data of the target power station and at least one power allocation plan according to the target prediction data includes: Arranging the data types in the target prediction data based on electrical equipment; Obtaining warning thresholds for various data types of the electrical equipment, and generating predicted operation data based on the warning thresholds; Load distribution is performed on the electrical equipment that exceeds the warning threshold in the forecast, and at least one power distribution plan is generated.

4. The method according to claim 1, wherein The method further includes: visually processing the predicted operation data and the power distribution plan to generate and display a predicted operation chart and a power distribution diagram.

5. The method according to claim 4, characterized in that The visualizing of the predicted operation data and the power distribution plan includes: Fill the predicted operation data into the corresponding data area in the graphical template based on the electrical equipment; According to the load distribution direction in the power distribution plan, the distribution objects involved in the power distribution plan are connected and the distribution direction is marked, and corresponding color markings are set for electrical equipment that exceeds the warning threshold.

6. A heavy overload power transfer device based on genetic algorithm dynamic programming technology, characterized in that: The device comprises: an acquisition module for acquiring a power consumption pattern of a target power station in a current region within a first preset time period; the power consumption pattern is obtained by analyzing the power consumption of transformers, high-voltage circuit breakers, busbars, lightning arresters, capacitors, and reactors in the target power station; the power consumption pattern refers to a change pattern of multiple parameters of the power-consuming equipment; a prediction data generation module, configured to generate target prediction data based on a genetic algorithm according to a power consumption pattern within the first preset time period and a reference power consumption pattern, wherein the reference power consumption pattern is a power consumption pattern of a non-target power station in the current region within a second preset time period or a power consumption pattern of any power station in a non-current region within a third preset time period; a data processing module, configured to generate predicted operating data and at least one power allocation scheme for the target power station based on the target predicted data, and allocate power to the target power station based on the predicted operating data and the at least one power allocation scheme; The generating target prediction data based on the power usage pattern within the first preset time period and the reference power usage pattern based on the genetic algorithm includes: Searching for a matching reference power usage pattern based on the power usage pattern within the first preset duration; using the power usage pattern within the first preset duration as a fitness parameter set and the reference power usage pattern as an initial population to perform a crossover genetic algorithm to obtain a candidate parameter set; predicting an operating pattern of the target power station for a fourth preset duration based on the candidate parameter set, using the operating pattern of the fourth preset duration as target prediction data for the target power station for the fourth preset duration; The searching for a matching reference power usage pattern according to the power usage pattern within the first preset time period includes: Generate a first characteristic curve of the power consumption pattern within the first preset time period; search for a reference characteristic curve of the reference power consumption pattern based on the first characteristic curve; when the degree of overlap between the first characteristic curve and the reference characteristic curve exceeds a preset overlap threshold, use the reference power consumption pattern as the matching reference power consumption pattern.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images