A low-voltage cabinet power consumption regulation method, device, medium and product

Abstract

This invention discloses a power consumption control method, device, medium, and product for low-voltage switchgear, comprising: collecting electrical parameters and operating temperatures of several modules in the low-voltage switchgear; calculating the real-time power consumption value and load matching degree of each module based on the electrical parameters, and calculating the theoretical optimal power consumption value of each module based on the load matching degree and operating temperature; inputting the real-time power consumption value, the theoretical optimal power consumption value, and the operating temperature into a preset decision model for feature fusion processing to obtain the operating condition feature vector of each module; determining the performance weight of each module based on the operating condition feature vector; using the performance weight of each module and the operating condition feature vector to evaluate the value of multiple preset power consumption control actions; and using the obtained evaluation values ​​to filter each power consumption control action to obtain a target power consumption control scheme to control the power consumption of the low-voltage switchgear. This invention can improve the control accuracy of low-voltage switchgear when controlling power consumption according to the needs of internal modules.

Description

Technical Field

[0001] This invention relates to the field of low-voltage power distribution technology, and in particular to a method, device, medium, and product for power consumption control of a low-voltage switchgear. Background Technology

[0002] Low-voltage switchgear, as the core equipment for power distribution, control, and protection at the end of the power distribution network, integrates multiple functional modules, including multi-core processing units, multi-source acquisition channels, multi-protocol communication interfaces, data storage modules, and dynamic power management. In actual operation, low-voltage switchgear frequently switches between various operating conditions such as idle, light load, heavy load, fault, and standby. The actual power consumption requirements of each functional module differ significantly under different operating conditions. For example, under heavy load or fault conditions, each module must operate at full load to ensure timely protection actions and complete data acquisition. Under idle or light load conditions, if each module remains at full load, a large amount of power will be wasted, increasing operating costs, accelerating component aging, shortening equipment lifespan, and exacerbating internal temperature rise, further increasing heat dissipation and power consumption. Therefore, implementing differentiated dynamic power consumption control of the low-voltage switchgear under different operating conditions is crucial for improving energy efficiency and ensuring long-term stable operation of the equipment.

[0003] Existing low-voltage switchgear power management mainly adopts the static threshold control method, but it has significant drawbacks: First, its control granularity is coarse, failing to distinguish the functional importance of different modules under specific operating conditions. Idle modules still consume a lot of standby power under light load, and protection functions may be delayed or fail due to blind frequency reduction during faults, resulting in insufficient control precision when the low-voltage switchgear adjusts power consumption according to the needs of internal modules. Second, its control strategy is out of sync with changes in operating conditions, failing to adaptively adjust power allocation based on dynamic factors such as load switching, equipment aging, or changes in ambient temperature. This easily leads to the contradiction of "energy waste in low-power scenarios and insufficient performance in high-power scenarios," resulting in low control precision when the low-voltage switchgear adjusts power consumption according to the needs of internal modules. Summary of the Invention

[0004] This invention provides a power consumption control method, device, medium, and product for low-voltage switchgear, which can improve the control accuracy of low-voltage switchgear when controlling power consumption according to the needs of internal modules.

[0005] In a first aspect, an embodiment of the present invention provides a power consumption control method for a low-voltage switchgear, comprising: Collect electrical parameters and operating temperatures of several modules in the low-voltage switchgear; Based on the electrical parameters of each module, the real-time power consumption value and load matching degree of each module are calculated, and based on the load matching degree and operating temperature of each module, the theoretical optimal power consumption value of each module is calculated. The real-time power consumption values, theoretical optimal power consumption values, and operating temperatures are input into a preset decision model for feature fusion processing to obtain the operating condition feature vectors of each module. Based on the operating condition feature vectors, the performance weights corresponding to each module are determined. The performance weights and operating condition feature vectors of each module are used to evaluate the action value of several preset power control actions to obtain several evaluation values. The evaluation values ​​are used to filter the power control actions to obtain a target power control scheme, and the power consumption of the low-voltage switchgear is controlled based on the target power control scheme.

[0006] By collecting electrical parameters and operating temperatures from several modules in the low-voltage switchgear, this method provides an independent operating condition information basis for each module, laying the foundation for improved control accuracy from the data source. Based on the electrical parameters of each module, the real-time power consumption value and load matching degree of each module are calculated, accurately quantifying the current power consumption status and load matching degree of each module. This provides precise data support for developing differentiated power consumption control strategies for different modules, ensuring control accuracy. Based on the load matching degree and operating temperature of each module, the theoretical optimal power consumption value of each module is calculated. This allows for the calculation of independent optimal power consumption targets for different modules based on their load characteristics and temperature conditions, achieving refined target setting according to module requirements. This avoids control deviations caused by uniform targets and improves the accuracy of control based on module requirements. The real-time power consumption value, theoretical optimal power consumption value, and operating temperature are input into a preset decision model for feature fusion processing, obtaining the operating condition feature vector of each module. This allows the multi-dimensional information of each module to be fused into a feature representation of its individual operating state, enabling the decision model to accurately... This invention distinguishes the operating conditions of different modules to avoid misjudgments in control due to information loss or confusion, thereby improving control accuracy. Based on the feature vectors of each operating condition, the performance weights corresponding to each module are determined. This allows the decision model to independently adjust its performance and power consumption balance strategy according to the current operating condition of each module, achieving differentiated weight allocation according to module requirements and ensuring that the control decisions of each module accurately match its actual needs. The performance weights and operating condition feature vectors of each module are used to evaluate the action value of several preset power consumption control actions, resulting in several evaluation values. These values ​​can be combined with the performance weights and operating conditions of each module to independently quantify and evaluate its candidate control actions, achieving differentiated and accurate evaluation according to module requirements. This avoids control inaccuracies caused by uniform evaluation standards and improves control accuracy. The evaluation values ​​are used to screen each power consumption control action to obtain a target power consumption control scheme. Based on this scheme, the low-voltage cabinet is controlled for power consumption control. The optimal control action can be independently selected from numerous candidate actions for each module, forming an adaptive control scheme for the individual needs of each module. Ultimately, this achieves high-precision on-demand power consumption control of each module in the low-voltage cabinet. This application can improve the control accuracy of low-voltage cabinets when controlling power consumption according to the needs of internal modules.

[0007] Furthermore, determining the performance weights of each module based on the feature vectors of each operating condition specifically includes: For each module, the cosine similarity is calculated between the working condition feature vector corresponding to the current module and the standard feature vector corresponding to each working condition in the preset working condition library to obtain several similarity values. Select the maximum value from all the similarity values, and take the working condition corresponding to the maximum value as the current operating condition of the module; Each of the aforementioned operating conditions is matched with preset performance rules to determine the performance weight corresponding to each module.

[0008] By determining the performance weights of each module based on the feature vectors of each operating condition, the decision model can independently adjust the balance strategy between performance and power consumption of each module according to its current operating condition, thereby achieving differentiated weight allocation according to module requirements and ensuring that the control decisions of each module are accurately matched with its actual needs.

[0009] Furthermore, the calculation of the theoretical optimal power consumption value for each module based on the load matching degree and operating temperature specifically includes: For each module, the operating temperature is matched with a preset state matching rule to obtain the device state correction coefficient corresponding to the current module; The module type of the current module is matched with the preset type matching rules to obtain the module function coefficient corresponding to the current module; Based on the load matching degree, the module function coefficient, the equipment state correction coefficient, and the obtained module rated power consumption, the theoretical optimal power consumption value is calculated.

[0010] In this way, the theoretical optimal power consumption value of each module can be calculated based on the load matching degree and operating temperature of each module. The independent optimal power consumption target can be calculated for the load characteristics and temperature conditions of different modules, so as to realize the fine target setting according to the needs of modules, avoid the control deviation caused by the uniform target, and improve the accuracy of control according to the needs of modules.

[0011] Furthermore, the step of inputting each of the real-time power consumption values, each of the theoretical optimal power consumption values, and each of the operating temperatures into a preset decision model for feature fusion processing to obtain the operating condition feature vector of each module specifically includes: Based on the aforementioned real-time power consumption values, the total system power consumption of the low-voltage switchgear is calculated. Based on the real-time power consumption values ​​of each module and the total power consumption of the system, the power consumption ratio of each module is calculated. The total power consumption of the system, the power consumption ratio of each module, the operating temperature, and the theoretical optimal power consumption value are normalized to obtain the normalized value of the total power consumption of the system, the normalized value of the power consumption ratio of each module, the normalized value of the operating temperature, and the normalized value of the theoretical optimal power consumption. For each module, the normalized value of the total power consumption of the system, the normalized value of the power consumption ratio corresponding to the current module, the normalized value of the operating temperature, and the normalized value of the theoretical optimal power consumption are integrated to obtain the operating condition feature vector corresponding to the current module.

[0012] By inputting real-time power consumption values, theoretical optimal power consumption values, and operating temperatures into a preset decision model for feature fusion processing, the operating condition feature vectors of each module are obtained. This allows the multi-dimensional information of each module to be fused into a feature representation that characterizes its individual operating state, enabling the decision model to accurately distinguish the differences in operating conditions between different modules, avoiding misjudgments in regulation due to information loss or confusion, thereby improving regulation accuracy.

[0013] Furthermore, the calculation of the real-time power consumption value and load matching degree corresponding to each module based on the electrical parameters of each module specifically includes: Based on the voltage and current values ​​in each of the electrical parameters, the real-time power consumption value corresponding to each module is calculated. Based on the real-time power consumption value and the preset rated power consumption value of each module, the load matching degree of each module is calculated.

[0014] In this way, the real-time power consumption value and load matching degree of each module can be calculated based on the electrical parameters of each module. This allows for precise quantification of the current power consumption status and load matching degree of each module, providing accurate data support for subsequent development of differentiated power consumption control strategies for different modules and ensuring control accuracy.

[0015] Furthermore, the step of controlling the power consumption of the low-voltage switchgear based on the target power consumption control scheme specifically includes: Based on the target power consumption control scheme, a power supply adjustment command is generated; The power supply adjustment command is sent to the power management module of the low-voltage cabinet, so that the power management module adjusts the power supply of each module in the low-voltage cabinet according to the power supply adjustment command, thereby realizing the power consumption control of the low-voltage cabinet.

[0016] By generating power supply adjustment commands based on the target power consumption control scheme, the decision results can be transformed into executable control commands, realizing a complete closed loop from decision-making to execution. The power supply adjustment commands are sent to the power management module, which adjusts the power supply of each module according to the commands. This directly controls the actual power consumption state of each module, ensuring that the decision results are accurately executed and avoiding inaccurate control due to execution deviations, thereby improving the final accuracy of power consumption control.

[0017] Furthermore, after controlling the low-voltage switchgear to regulate power consumption based on the target power consumption regulation scheme, the method further includes: After power consumption regulation is completed, the actual power consumption of each module in the low-voltage cabinet is collected. Based on the actual operating power consumption value and the control target value corresponding to each module in the target power consumption control scheme, the control deviation value of each module is calculated. Each of the aforementioned control deviation values ​​is determined to be greater than a preset threshold. If the threshold is met, a fine-tuning instruction is generated based on each of the aforementioned control deviation values. The power management module is then controlled to adjust the power supply of each module in the low-voltage cabinet according to the fine-tuning instruction, thereby achieving power consumption control of the low-voltage cabinet.

[0018] After power consumption regulation is completed, the actual power consumption of each module is collected to obtain real feedback data after regulation, providing a basis for evaluating the regulation effect. Based on the actual power consumption of each module and the regulation target value in the target power consumption regulation scheme, the regulation deviation value of each module is calculated, which can quantify the gap between the actual regulation effect of each module and the expected target, and accurately locate the regulation deviation. It is determined whether each regulation deviation value is greater than the preset threshold, and when the condition is met, a fine-tuning command is generated to control the power management module to readjust the power supply. The regulation deviation can be corrected in time, forming a closed-loop feedback optimization mechanism, and the accuracy of subsequent power consumption regulation is continuously improved through multiple iterations.

[0019] Secondly, an embodiment of the present invention provides a power consumption control device for a low-voltage switchgear, comprising a first module, a second module, and a third module; The first module is used to collect electrical parameters and operating temperature of several modules in the low-voltage switchgear; The second module is used to calculate the real-time power consumption value and load matching degree of each module based on the electrical parameters of each module, and to calculate the theoretical optimal power consumption value of each module based on the load matching degree and the operating temperature of each module. The third module is used to input the real-time power consumption values, the theoretical optimal power consumption values, and the operating temperatures into a preset decision model for feature fusion processing to obtain the operating condition feature vectors of each module. Based on the operating condition feature vectors, the module determines the performance weights corresponding to each module. The module uses the performance weights and operating condition feature vectors to evaluate the action value of a number of preset power control actions to obtain several evaluation values. The module uses the evaluation values ​​to filter the power control actions to obtain a target power control scheme, and controls the low-voltage switchgear to control power consumption based on the target power control scheme.

[0020] The first module collects electrical parameters and operating temperatures from several modules in the low-voltage switchgear, providing independent operating condition information for each module to support subsequent power consumption control based on module requirements. This data-driven approach lays the foundation for improved control accuracy. The second module calculates real-time power consumption and load matching for each module based on its electrical parameters, precisely quantifying the current power consumption status and load matching degree of each module. This provides accurate data support for developing differentiated power consumption control strategies for different modules, ensuring control accuracy. The third module calculates the theoretical optimal power consumption for each module based on its load matching degree and operating temperature. This allows for the calculation of independent optimal power consumption targets for different modules based on their load characteristics and temperature conditions, enabling refined target setting based on module requirements. This avoids control deviations caused by uniform targets and improves the accuracy of control based on module requirements. The fourth module inputs the real-time power consumption, theoretical optimal power consumption, and operating temperature into a preset decision model for feature fusion processing, obtaining the operating condition feature vector for each module. This integrates the multi-dimensional information of each module into a feature representation of its individual operating state, enabling decision-making... The model can accurately distinguish the differences in operating conditions of different modules, avoiding misjudgments in regulation due to information loss or confusion, thereby improving regulation accuracy. Based on the feature vectors of each operating condition, the model determines the performance weights corresponding to each module, allowing the decision model to independently adjust its performance and power consumption balance strategy according to the current operating condition of each module. This achieves differentiated weight allocation based on module requirements, ensuring that the regulation decisions of each module accurately match its actual needs. The model uses the performance weights and operating condition feature vectors of each module to evaluate the action value of several preset power consumption regulation actions, obtaining several evaluation values. It can then independently quantify and evaluate candidate regulation actions based on the performance weights and operating conditions of each module, achieving differentiated and accurate evaluation based on module requirements. This avoids regulation inaccuracies caused by uniform evaluation standards, improving regulation accuracy. Finally, the model uses the evaluation values ​​to screen each power consumption regulation action to obtain a target power consumption regulation scheme. Based on this scheme, it controls the low-voltage cabinet for power consumption regulation. It can independently select the optimal regulation action for each module from numerous candidate actions, forming an adaptive regulation scheme for the individual needs of each module, ultimately achieving high-precision on-demand power consumption regulation of each module in the low-voltage cabinet.

[0021] Thirdly, another embodiment of the present invention provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device or apparatus where the computer-readable storage medium is located to perform a power consumption regulation method for a low-voltage switchgear.

[0022] Fourthly, another embodiment of the present invention provides a computer program product, including a computer program or instructions, which, when executed by a communication device, implements a power consumption control method for a low-voltage switchgear. Attached Figure Description

[0023] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating one embodiment of a power consumption control method for a low-voltage switchgear provided in this application; Figure 2 This is a schematic diagram of the power consumption control device for a low-voltage switchgear provided in this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0027] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0028] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0029] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0030] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0031] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of this application according to the specific circumstances.

[0032] In the field of low-voltage power distribution technology, the power consumption requirements of various functional modules within a low-voltage switchgear vary significantly under different operating conditions. Implementing differentiated dynamic power consumption control is crucial for improving energy efficiency and ensuring long-term stable operation of equipment. Existing low-voltage switchgear power consumption management primarily employs static threshold control methods, but these methods have significant drawbacks: firstly, the control granularity is coarse, failing to distinguish the functional importance of different modules under specific operating conditions; secondly, the control strategy is disconnected from changes in operating conditions, unable to adaptively adjust power consumption allocation based on dynamic factors, resulting in insufficient control precision when adjusting power consumption according to the needs of internal modules.

[0033] See Figure 1 In order to improve the control accuracy of low-voltage switchgear when adjusting power consumption according to the internal module requirements, an embodiment of the present invention provides a power consumption control method for low-voltage switchgear, including steps S101 to S103. Step S101: Collect the electrical parameters and operating temperature of several modules in the low-voltage switchgear; In some embodiments, the electrical parameters and operating temperatures of several modules in the low-voltage switchgear are collected. Specifically, the low-voltage switchgear includes a multi-source synchronous acquisition module, a multi-core heterogeneous processing module, an edge intelligent decision-making module, a multi-modal anti-interference communication module, a distributed secure storage module, and a dynamic power management module. Through voltage and current sensors in the multi-source synchronous acquisition module, the output voltage and output current of the dynamic power management module, the operating voltage and operating current of other functional modules, and the load voltage, load current, and phase difference of the main circuit and branch circuits of the low-voltage switchgear are collected. All collected signals are analog signals. The AFE Core (Analog Front-End Core) in the multi-core heterogeneous processing module uses an analog signal conditioning circuit to perform front-end noise reduction processing on the collected analog signals. After the front-end noise reduction processing is completed, the analog signals after noise reduction are converted into digital electrical parameters by an analog-to-digital converter. At the same time, the operating temperature of each module is collected by a temperature sensor.

[0034] It should be noted that the analog signal conditioning circuit includes a filter circuit, a signal amplification circuit, and a common-mode rejection circuit, which are used to eliminate power frequency interference and noise interference in the strong electromagnetic environment of the low-voltage cabinet, and to achieve front-end noise reduction and signal amplitude matching of the analog signal; the analog-to-digital converter adopts a successive approximation type or Σ-Δ type ADC architecture, which has the characteristics of high resolution and low sampling error.

[0035] Step S102: Based on the electrical parameters of each module, calculate the real-time power consumption value and load matching degree of each module, and based on the load matching degree and operating temperature of each module, calculate the theoretical optimal power consumption value of each module. In some embodiments, calculating the real-time power consumption value and load matching degree of each module based on the electrical parameters of each module specifically includes: calculating the real-time power consumption value of each module based on the voltage and current values ​​in each of the electrical parameters; and calculating the load matching degree of each module based on the real-time power consumption value and the preset rated power consumption value of each module. Specifically, the DSP Core (Digital Signal Processing Core) within the multi-core heterogeneous processing module receives electrical parameters transmitted from the AFE Core. Based on the voltage and current values ​​in the electrical parameters of each module, as well as the DC or AC power supply characteristics of each module, it calculates the real-time power consumption of each module. If the current module is DC powered, the voltage and current values ​​are multiplied to obtain the real-time power consumption of that module. If the current module is AC powered, the voltage and current values ​​are multiplied by the cosine of the phase difference to obtain the real-time power consumption of that module. After obtaining the real-time power consumption of each module, the system's preset rated power consumption value for each module (the module's rated full-load power consumption value is a hardware calibration value, such as the MCU Core's rated power consumption of 5W) is obtained. The real-time power consumption value of each module is divided by the corresponding rated power consumption value to obtain the load matching degree of each module.

[0036] In some embodiments, the formula for calculating the real-time power consumption value and load matching degree of each module based on the electrical parameters of each module specifically includes: Formula for calculating the real-time power consumption of a DC power supply module: ; Formula for calculating the real-time power consumption of the AC power supply module: ; The formula for calculating load matching degree: ; In the formula, This indicates the module's real-time power consumption. Indicates the voltage value of the module; Indicates the current value of the module; This represents the phase difference between voltage and current. The cosine value representing the phase difference; Indicates the load matching degree of the module; This indicates the module's rated power consumption.

[0037] In this way, the real-time power consumption value and load matching degree of each module can be calculated based on the electrical parameters of each module. This allows for precise quantification of the current power consumption status and load matching degree of each module, providing accurate data support for subsequent development of differentiated power consumption control strategies for different modules and ensuring control accuracy.

[0038] In some embodiments, calculating the theoretical optimal power consumption value for each module based on the load matching degree and the operating temperature specifically includes: for each module, matching the operating temperature with a preset state matching rule to obtain the device state correction coefficient corresponding to the current module; matching the module type of the current module with a preset type matching rule to obtain the module function coefficient corresponding to the current module; and calculating the theoretical optimal power consumption value based on the load matching degree, the module function coefficient, the device state correction coefficient, and the obtained module rated power consumption. Specifically, the DSP Core (Digital Signal Processing Core) within the multi-core heterogeneous processing module matches the current module's operating temperature (collected in step S101) with a preset state matching rule to obtain the device state correction coefficient corresponding to the current module (e.g., 0 < β ≤ 1.2, where β is smaller as the operating temperature increases to avoid high-temperature, high-power operation); it then obtains the module type of the current module and matches it with a preset type matching rule to obtain the module function coefficient corresponding to the current module (e.g., 0 < α ≤ 1, where α is 0.5-1 for core modules and 0.1-0.5 for non-core modules); using the current module's load matching degree, module function coefficient, device state correction coefficient, and rated power consumption value, it calculates the theoretical optimal power consumption value of the current module, and so on, to obtain the theoretical optimal power consumption value for each module.

[0039] In some embodiments, the formula for calculating the theoretical optimal power consumption value of each module based on the load matching degree and the operating temperature of each module specifically includes: The formula for calculating the theoretical optimal power consumption is as follows: ; In the formula, This represents the module's theoretical optimal power consumption value; This indicates the module's rated power consumption. Indicates the load matching degree of the module; This represents the module's functional coefficient, with a value ranging from 0 to 1. This represents the equipment status correction factor, with a value ranging from 0 to 1.2.

[0040] In this way, the theoretical optimal power consumption value of each module can be calculated based on the load matching degree and operating temperature of each module. The independent optimal power consumption target can be calculated for the load characteristics and temperature conditions of different modules, so as to realize the fine target setting according to the needs of modules, avoid the control deviation caused by the uniform target, and improve the accuracy of control according to the needs of modules.

[0041] Step S103: Input the real-time power consumption value, the theoretical optimal power consumption value, and the operating temperature into a preset decision model for feature fusion processing to obtain the operating condition feature vector of each module. Based on the operating condition feature vector, determine the performance weight corresponding to each module. Use the performance weight and the operating condition feature vector of each module to evaluate the action value of a number of preset power control actions to obtain a number of evaluation values. Use the evaluation values ​​to filter the power control actions to obtain a target power control scheme, and control the low-voltage cabinet to control power consumption based on the target power control scheme.

[0042] In some embodiments, the step of inputting the real-time power consumption values, the theoretical optimal power consumption values, and the operating temperatures into a preset decision model for feature fusion processing to obtain the operating condition feature vector of each module specifically includes: calculating the total system power consumption of the low-voltage switchgear based on the real-time power consumption values; calculating the power consumption ratio of each module based on the real-time power consumption values ​​of each module and the total system power consumption; normalizing the total system power consumption and the power consumption ratios corresponding to each module, the operating temperatures, and the theoretical optimal power consumption values ​​to obtain normalized values ​​of the total system power consumption, normalized values ​​of the power consumption ratios corresponding to each module, normalized values ​​of the operating temperatures, and normalized values ​​of the theoretical optimal power consumption; and for each module, integrating the normalized values ​​of the total system power consumption, the normalized values ​​of the power consumption ratios corresponding to the current module, the normalized values ​​of the operating temperatures, and the normalized values ​​of the theoretical optimal power consumption to obtain the operating condition feature vector corresponding to the current module. Specifically, the DSP Cores within the multi-core heterogeneous processing module sum the real-time power consumption values ​​of all modules to obtain the total system power consumption of the low-voltage cabinet. For each module, its real-time power consumption value is divided by the total system power consumption to obtain the power consumption percentage of that module. The total system power consumption, the power consumption percentage of each module, the operating temperature of each module, and the theoretical optimal power consumption value of each module are normalized to obtain the normalized value of the total system power consumption and the normalized values ​​of the power consumption percentage, operating temperature, and theoretical optimal power consumption of each module. For each module, the normalized values ​​of the power consumption percentage, operating temperature, theoretical optimal power consumption, and total system power consumption are integrated to form the operating condition feature vector of that module.

[0043] In some embodiments, the formula for inputting the real-time power consumption values, the theoretical optimal power consumption values, and the operating temperatures into a preset decision model for feature fusion processing to obtain the operating condition feature vectors of each module specifically includes: Formula for calculating total system power consumption: ; Formula for calculating power consumption percentage: ; In the formula, Indicates the total power consumption of the system; This indicates the power consumption of the dynamic power management module itself. This represents the sum of the real-time power consumption values ​​of all other functional modules; This indicates the percentage of power consumption of the module; This indicates the module's real-time power consumption.

[0044] It should be noted that the purpose of normalization is to map all values ​​to the same numerical range in order to eliminate the influence of different units on subsequent calculations.

[0045] By inputting real-time power consumption values, theoretical optimal power consumption values, and operating temperatures into a preset decision model for feature fusion processing, the operating condition feature vectors of each module are obtained. This allows the multi-dimensional information of each module to be fused into a feature representation that characterizes its individual operating state, enabling the decision model to accurately distinguish the differences in operating conditions between different modules, avoiding misjudgments in regulation due to information loss or confusion, thereby improving regulation accuracy.

[0046] In some embodiments, determining the performance weight of each module based on the feature vectors of each operating condition specifically includes: for each module, performing cosine similarity calculation between the feature vector of the current module and the standard feature vectors corresponding to each operating condition in a preset operating condition library to obtain several similarity values; selecting the maximum value from the similarity values ​​and taking the operating condition corresponding to the maximum value as the operating condition corresponding to the current module; and matching each operating condition with preset performance rules to determine the performance weight of each module. Specifically, for each module, the edge intelligent decision-making module calculates the cosine similarity between the module's operating condition feature vector and the standard feature vector corresponding to each operating condition in the preset operating condition library. This yields a similarity value (ranging from 0 to 1, with values ​​closer to 1 indicating higher matching accuracy) between the module and each operating condition. The preset operating condition library includes five categories: idle, light load, heavy load, fault, and standby. The module selects the maximum similarity value and uses the operating condition corresponding to this maximum value as the current module's operating condition. After determining the operating condition of each module, the module's operating condition is matched against preset performance rules. These rules define the allocation relationship between different operating conditions and performance weights. Based on the matching results, the module's corresponding performance weight is determined (e.g., the performance weight for the fault condition is 0.9 to ensure full-load operation and fault protection of the core module; the performance weight for the light load condition is 0.5 to balance performance and power consumption; and the performance weight for the idle or standby condition is 0.3 to prioritize power optimization strategies).

[0047] By determining the performance weights of each module based on the feature vectors of each operating condition, the decision model can independently adjust the balance strategy between performance and power consumption of each module according to its current operating condition, thereby achieving differentiated weight allocation according to module requirements and ensuring that the control decisions of each module are accurately matched with its actual needs.

[0048] In some embodiments, the performance weights and operating condition feature vectors corresponding to each module are used to evaluate the action value of a number of preset power control actions to obtain several evaluation values. Specifically, this includes: for each module, inputting the operating condition feature vector and performance weights of that module into a preset decision model to evaluate the action value of a number of preset control actions. The decision model adopts a deep Q-network model. The deep Q-network model calculates the action value component of the current action in the current module state through its internal Q-value evaluation function, and performs a weighted summation of the action value components of all modules to obtain the evaluation value of the power control action; repeating the above process until the evaluation values ​​of all power control actions are calculated.

[0049] It should be noted that the decision-making model adopts a deep Q-network reinforcement learning model. When constructing it, the state space is defined with the total power consumption and load matching degree as the core, and the action space is defined with module frequency reduction, interface switching, etc. The weighted composite reward function with performance weight and power consumption weight (the value is 1 minus the difference of the performance weight) is designed, with the principle of "performance guarantee first, power consumption optimization second". The model is trained by offline pre-training and online fine-tuning. The offline pre-training is based on historical operating condition data and simulated operating condition data, and the online fine-tuning updates the model parameters based on the actual operation effect.

[0050] For example, the training process of a deep Q-network model specifically includes: collecting historical working condition data and simulated working condition data as training samples, performing offline pre-training on the deep Q-network model, and deploying the deep Q-network model to the edge intelligent decision-making module after the offline pre-training is completed.

[0051] In some embodiments, the power consumption control actions are screened using the evaluation values ​​to obtain a target power consumption control scheme. Specifically, this includes: comparing the evaluation values ​​of all power consumption control actions and selecting the power consumption control action with the largest evaluation value as a candidate action; obtaining the current operating condition and fault status of the low-voltage switchgear; if the current low-voltage switchgear is in a fault condition or a suspected fault condition, determining whether the candidate action can guarantee the full-load operation and fault protection function of the core module; if the candidate action meets the requirements, determining the candidate action as the target power consumption control scheme; if the candidate action does not meet the requirements, selecting the action with the second largest evaluation value from the remaining power consumption control actions and performing feasibility verification again until a power consumption control action that meets the requirements is obtained; if the current low-voltage switchgear is in a normal operating condition, directly selecting the power consumption control action with the largest evaluation value as the target power consumption control scheme.

[0052] It should be noted that the target power consumption control scheme includes at least the control target value of each module. The control target value includes at least one of the following: frequency reduction target value, sleep target value, wake-up target value, and full load operation target value.

[0053] In some embodiments, controlling the power consumption of the low-voltage switchgear based on the target power consumption control scheme specifically includes: generating a power supply adjustment command according to the target power consumption control scheme; sending the power supply adjustment command to the power management module of the low-voltage switchgear, so that the power management module adjusts the power supply of each module in the low-voltage switchgear according to the power supply adjustment command, thereby realizing the power consumption control of the low-voltage switchgear. Specifically, the MCU Core (microcontroller core) within the multi-core heterogeneous processing module generates power adjustment instructions based on the target power consumption control scheme and sends these instructions to the dynamic power management module. Upon receiving the power adjustment instructions, the dynamic power management module adjusts the operating voltage and current output to each module through a high-efficiency DC-DC or AC-DC converter circuit. For modules requiring frequency reduction, the operating voltage is appropriately reduced to control the operating current. For modules requiring sleep mode, the power supply is cut off or a low-power standby voltage is provided. For modules requiring wake-up or full-load operation, the rated power supply voltage and rated power supply current are restored. Each module responds synchronously to power supply changes and automatically completes its own power consumption adjustment. Specifically, the MCU Core and DSP Core within the multi-core heterogeneous processing module will perform automatic frequency reduction, the AFE Core will shut down non-core signal processing channels, the multi-source synchronous acquisition module will shut down non-critical acquisition channels and reduce the acquisition frequency of core channels, the multi-modal anti-interference communication module will shut down the 4G, 5G, and Ethernet communication interfaces and retain only the low-power narrowband communication interface, and the distributed secure storage module will enter a low-power sleep mode and reduce the flash memory read / write frequency.

[0054] By generating power supply adjustment commands based on the target power consumption control scheme, the decision results can be transformed into executable control commands, realizing a complete closed loop from decision-making to execution. The power supply adjustment commands are sent to the power management module, which adjusts the power supply of each module according to the commands. This directly controls the actual power consumption state of each module, ensuring that the decision results are accurately executed and avoiding inaccurate control due to execution deviations, thereby improving the final accuracy of power consumption control.

[0055] In some embodiments, after controlling the low-voltage cabinet to perform power consumption regulation based on the target power consumption regulation scheme, the method further includes: after the power consumption regulation is completed, collecting the actual operating power consumption values ​​of each module in the low-voltage cabinet; calculating the regulation deviation value of each module based on the actual operating power consumption value and the regulation target value corresponding to each module in the target power consumption regulation scheme; determining whether each regulation deviation value is greater than a preset threshold, and if so, generating a fine-tuning instruction based on each regulation deviation value, so as to control the power management module to adjust the power supply of each module in the low-voltage cabinet according to the fine-tuning instruction, thereby realizing the power consumption regulation of the low-voltage cabinet. Specifically, after power consumption regulation is completed, the operating voltage and current of each module in the low-voltage cabinet are re-acquired by the multi-source synchronous acquisition module, and the actual power consumption of each module is calculated based on the re-acquired voltage and current values. For each module, the regulation target value corresponding to the module in the target power consumption regulation scheme is obtained. The actual power consumption of the module is subtracted from the regulation target value and the absolute value is taken, then divided by the sum of the regulation target values ​​of all modules to calculate the regulation deviation value of the module. It is then determined whether the regulation deviation value of each module is greater than the preset deviation threshold (e.g., 5%). If the regulation deviation value of any module is greater than the preset threshold, a fine-tuning instruction is generated based on the regulation deviation value of the module and sent to the dynamic power management module so that the dynamic power management module can make a secondary adjustment to the power supply of the module according to the fine-tuning instruction until the regulation deviation value of the module meets the requirements. If the regulation deviation values ​​of all modules are not greater than the preset threshold, the power consumption regulation is determined to be successful and the current power supply parameters are maintained.

[0056] In some embodiments, the relevant formulas following the control of the low-voltage switchgear for power consumption regulation based on the target power consumption regulation scheme further include: Formula for calculating the control deviation value: ; In the formula, This represents the control deviation value of the i-th module; This represents the actual power consumption of the i-th module. This represents the control target value of the i-th module; This represents the sum of the target values ​​for all module adjustments.

[0057] After power consumption regulation is completed, the actual power consumption of each module is collected to obtain real feedback data after regulation, providing a basis for evaluating the regulation effect. Based on the actual power consumption of each module and the regulation target value in the target power consumption regulation scheme, the regulation deviation value of each module is calculated, which can quantify the gap between the actual regulation effect of each module and the expected target, and accurately locate the regulation deviation. It is determined whether each regulation deviation value is greater than the preset threshold, and when the condition is met, a fine-tuning command is generated to control the power management module to readjust the power supply. The regulation deviation can be corrected in time, forming a closed-loop feedback optimization mechanism, and the accuracy of subsequent power consumption regulation is continuously improved through multiple iterations.

[0058] For example, the multi-source synchronous acquisition module is also used to perform adaptive control of the acquisition channels, specifically including: the multi-source synchronous acquisition module responds to the power supply adjustment of the dynamic power management module, and when the system is idle or in standby mode, puts non-critical acquisition channels (such as the ambient temperature and humidity acquisition channel) into sleep mode, retaining only the core power consumption parameter acquisition channels (such as the module operating voltage acquisition channel and the module operating current acquisition channel), and reducing the acquisition frequency from nanosecond-level synchronous sampling to millisecond-level sampling; when the system is under heavy load or in fault condition, it wakes up all acquisition channels and restores nanosecond-level synchronous sampling to ensure the comprehensiveness and real-time nature of power consumption data; the multi-source synchronous acquisition module performs preliminary filtering on the acquired data, and transmits it through the SPI high-speed interface or I... ² The high-speed C interface transmits core data to the multi-core heterogeneous processing module in real time, while non-critical data in the hibernation channel is paused, reducing communication power consumption.

[0059] For example, the multimodal anti-interference communication module is used to perform instruction transmission and adaptive control of the communication interface. Specifically, it includes: receiving power adjustment instructions from the multi-core heterogeneous processing module through a low-power narrowband communication interface, synchronously forwarding the instructions to the dynamic power management module, and feeding back the instruction reception confirmation signal to the MCUCore; responding to the power adjustment of the dynamic power management module, the multimodal anti-interference communication module adjusts the working state of the communication interface according to the operating conditions. When the low-voltage cabinet is in an idle or standby state, it shuts down the 4G communication interface, 5G communication interface, and Ethernet interface, retaining only the low-power narrowband interface. The system employs a narrowband communication interface and reduces the communication frequency. When the low-voltage switchgear is under light load, it wakes up the Wi-Fi interface or power line communication interface as needed and maintains low-speed transmission. When the low-voltage switchgear is under heavy load or fault conditions, it wakes up all communication interfaces and increases the transmission rate to ensure the real-time transmission of power supply adjustment commands and fault signals. The multi-modal anti-interference communication module collects the operating power consumption of its various communication interfaces in real time and transmits it to the multi-core heterogeneous processing module to provide data for calculating the total system power consumption. When adjusting the status of the communication interfaces, the core functions of the national cryptographic algorithm anti-interference protocol are retained to ensure the security of power supply adjustment command transmission.

[0060] For example, the distributed secure storage module is used to perform classified storage and redundant backup of power consumption data. Specifically, the distributed secure storage module receives power consumption data (including real-time power consumption values, theoretical optimal power consumption values, operating temperatures, operating condition feature vectors, performance weights, and target power consumption control schemes for each module) transmitted by the multi-core heterogeneous processing module, classifies it according to real-time power consumption data, power consumption adjustment results, historical power consumption strategies, and fault power consumption data, and stores it in an independent area of ​​NAND flash memory (NAND gate flash memory); the distributed secure storage module performs triple redundancy backup of power consumption data under fault conditions, combining ECC (Error Correcting Code) error correction technology and blockchain storage ledger to ensure the integrity and immutability of power consumption data; the distributed secure storage module uses a hash index algorithm to retrieve power consumption data, and feeds back the historical power consumption adjustment effects and the optimal power consumption value under the same operating conditions to the edge intelligent decision-making module to provide data support for power consumption strategy optimization; when the system is idle, the distributed secure storage module automatically cleans up expired non-critical power consumption data, releases storage space, and reduces the continuous operating power consumption of the storage module.

[0061] For example, the edge intelligent decision-making module is also used to perform strategy self-optimization, specifically including: the edge intelligent decision-making module periodically retrieves the full-process data of historical power consumption adjustment (including operating condition type, target power consumption control scheme, control execution result, power consumption optimization rate, and performance guarantee status) from the distributed secure storage module, and incorporates it into the training dataset of the reinforcement learning adaptive decision-making model; the model retrains the dataset based on the principle of "performance guarantee first, power consumption optimization second", and adjusts the model's decision parameters and action value evaluation weights in real time to address the deviation problem and strategy adaptability problem of power consumption adjustment under different operating conditions. At the same time, it continuously iterates the training by combining new operating condition data from actual field operation, so that the power consumption adjustment strategy generated by the model continuously conforms to the actual operating needs of the low-voltage switchgear.

[0062] For example, the dynamic power management module is also used to perform multi-power input adaptive switching and over-power protection. Specifically, the dynamic power management module automatically switches the power supply mode according to the system power consumption requirements and power status. When the low-voltage cabinet is in a low-power condition (such as an idle condition or a standby condition), it prioritizes using the backup battery to supply power with a small current, reducing the conversion power consumption of the AC main power supply or DC main power supply. When the low-voltage cabinet is in a high-power condition (such as a heavy-load condition or a fault condition), it switches to the AC main power supply or DC main power supply to ensure power supply. When the system power consumption exceeds the rated threshold, the dynamic power management module automatically triggers the over-power protection mechanism, cutting off the power supply step by step from non-core modules to non-critical functions of core modules, and at the same time sending an over-power alarm signal to the edge intelligent decision module to ensure the normal operation of the system's core functions, namely fault protection and main circuit monitoring.

[0063] By collecting electrical parameters and operating temperatures from several modules in the low-voltage switchgear, this method provides an independent operating condition information basis for each module, laying the foundation for improved control accuracy from the data source. Based on the electrical parameters of each module, the real-time power consumption value and load matching degree of each module are calculated, accurately quantifying the current power consumption status and load matching degree of each module. This provides precise data support for developing differentiated power consumption control strategies for different modules, ensuring control accuracy. Based on the load matching degree and operating temperature of each module, the theoretical optimal power consumption value of each module is calculated. This allows for the calculation of independent optimal power consumption targets for different modules based on their load characteristics and temperature conditions, achieving refined target setting according to module requirements. This avoids control deviations caused by uniform targets and improves the accuracy of control based on module requirements. The real-time power consumption value, theoretical optimal power consumption value, and operating temperature are input into a preset decision model for feature fusion processing, obtaining the operating condition feature vector of each module. This allows the multi-dimensional information of each module to be fused into a feature representation of its individual operating state, enabling the decision model to accurately... This invention distinguishes the operating conditions of different modules to avoid misjudgments in control due to information loss or confusion, thereby improving control accuracy. Based on the feature vectors of each operating condition, the performance weights corresponding to each module are determined. This allows the decision model to independently adjust its performance and power consumption balance strategy according to the current operating condition of each module, achieving differentiated weight allocation according to module requirements and ensuring that the control decisions of each module accurately match its actual needs. The performance weights and operating condition feature vectors of each module are used to evaluate the action value of several preset power consumption control actions, resulting in several evaluation values. These values ​​can be combined with the performance weights and operating conditions of each module to independently quantify and evaluate its candidate control actions, achieving differentiated and accurate evaluation according to module requirements. This avoids control inaccuracies caused by uniform evaluation standards and improves control accuracy. The evaluation values ​​are used to screen each power consumption control action to obtain a target power consumption control scheme. Based on this scheme, the low-voltage cabinet is controlled for power consumption control. The optimal control action can be independently selected from numerous candidate actions for each module, forming an adaptive control scheme for the individual needs of each module. Ultimately, this achieves high-precision on-demand power consumption control of each module in the low-voltage cabinet. This application can improve the control accuracy of low-voltage cabinets when controlling power consumption according to the needs of internal modules.

[0064] See Figure 2 Based on the above method embodiments, corresponding device embodiments are provided; An embodiment of the present invention provides a power consumption control device for a low-voltage switchgear, comprising a first module 100, a second module 200, and a third module 300; The first module 100 is used to collect electrical parameters and operating temperature of several modules in the low-voltage cabinet; The second module 200 is used to calculate the real-time power consumption value and load matching degree of each module based on the electrical parameters of each module, and to calculate the theoretical optimal power consumption value of each module based on the load matching degree and the operating temperature of each module. The third module 300 is used to input the real-time power consumption values, the theoretical optimal power consumption values, and the operating temperatures into a preset decision model for feature fusion processing to obtain the operating condition feature vectors of each module. Based on the operating condition feature vectors, the performance weights corresponding to each module are determined. The performance weights and operating condition feature vectors of each module are used to evaluate the action value of a number of preset power consumption control actions to obtain a number of evaluation values. The evaluation values ​​are used to filter the power consumption control actions to obtain a target power consumption control scheme, and the power consumption of the low-voltage switchgear is controlled based on the target power consumption control scheme.

[0065] The first module collects electrical parameters and operating temperatures from several modules in the low-voltage switchgear, providing independent operating condition information for each module to support subsequent power consumption control based on module requirements. This data-driven approach lays the foundation for improved control accuracy. The second module calculates real-time power consumption and load matching for each module based on its electrical parameters, precisely quantifying the current power consumption status and load matching degree of each module. This provides accurate data support for developing differentiated power consumption control strategies for different modules, ensuring control accuracy. The third module calculates the theoretical optimal power consumption for each module based on its load matching degree and operating temperature. This allows for the calculation of independent optimal power consumption targets for different modules based on their load characteristics and temperature conditions, enabling refined target setting based on module requirements. This avoids control deviations caused by uniform targets and improves the accuracy of control based on module requirements. The fourth module inputs the real-time power consumption, theoretical optimal power consumption, and operating temperature into a preset decision model for feature fusion processing, obtaining the operating condition feature vector for each module. This integrates the multi-dimensional information of each module into a feature representation of its individual operating state, enabling decision-making... The model can accurately distinguish the differences in operating conditions of different modules, avoiding misjudgments in regulation due to information loss or confusion, thereby improving regulation accuracy. Based on the feature vectors of each operating condition, the model determines the performance weights corresponding to each module, allowing the decision model to independently adjust its performance and power consumption balance strategy according to the current operating condition of each module. This achieves differentiated weight allocation based on module requirements, ensuring that the regulation decisions of each module accurately match its actual needs. The model uses the performance weights and operating condition feature vectors of each module to evaluate the action value of several preset power consumption regulation actions, obtaining several evaluation values. It can then independently quantify and evaluate candidate regulation actions based on the performance weights and operating conditions of each module, achieving differentiated and accurate evaluation based on module requirements. This avoids regulation inaccuracies caused by uniform evaluation standards, improving regulation accuracy. Finally, the model uses the evaluation values ​​to screen each power consumption regulation action to obtain a target power consumption regulation scheme. Based on this scheme, it controls the low-voltage cabinet for power consumption regulation. It can independently select the optimal regulation action for each module from numerous candidate actions, forming an adaptive regulation scheme for the individual needs of each module, ultimately achieving high-precision on-demand power consumption regulation of each module in the low-voltage cabinet.

[0066] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can realize the power consumption control method of a low-voltage switchgear provided by any of the above-described method embodiments of the present invention.

[0067] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0068] Based on the above-described embodiment of a power consumption control method for a low-voltage switchgear, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a power consumption control method for a low-voltage switchgear according to any embodiment of the present invention.

[0069] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0070] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0071] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0072] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute a power consumption control method for a low-voltage switchgear as described in any of the above-described method embodiments of the present invention.

[0073] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0074] Based on the above-described method embodiments, another embodiment of the present invention provides a computer program product, including a computer program or instructions, which, when executed by a communication device, implements a power consumption control method for a low-voltage switchgear.

[0075] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A power consumption control method for a low-voltage switchgear, characterized in that, include: Collect electrical parameters and operating temperatures of several modules in the low-voltage switchgear; Based on the electrical parameters of each module, the real-time power consumption value and load matching degree of each module are calculated, and based on the load matching degree and operating temperature of each module, the theoretical optimal power consumption value of each module is calculated. The real-time power consumption values, theoretical optimal power consumption values, and operating temperatures are input into a preset decision model for feature fusion processing to obtain the operating condition feature vectors of each module. Based on the operating condition feature vectors, the performance weights corresponding to each module are determined. The performance weights and operating condition feature vectors of each module are used to evaluate the action value of several preset power control actions to obtain several evaluation values. The evaluation values ​​are used to filter the power control actions to obtain a target power control scheme, and the power consumption of the low-voltage switchgear is controlled based on the target power control scheme.

2. The power consumption control method for low-voltage switchgear as described in claim 1, characterized in that, The determination of the performance weights for each module based on the feature vectors of each operating condition specifically includes: For each module, the cosine similarity is calculated between the working condition feature vector corresponding to the current module and the standard feature vector corresponding to each working condition in the preset working condition library to obtain several similarity values. Select the maximum value from all the similarity values, and take the working condition corresponding to the maximum value as the current operating condition of the module; Each of the aforementioned operating conditions is matched with preset performance rules to determine the performance weight corresponding to each module.

3. The power consumption control method for low-voltage switchgear as described in claim 1, characterized in that, The calculation of the theoretical optimal power consumption value for each module, based on the load matching degree and operating temperature corresponding to each module, specifically includes: For each module, the operating temperature is matched with a preset state matching rule to obtain the device state correction coefficient corresponding to the current module; The module type of the current module is matched with the preset type matching rules to obtain the module function coefficient corresponding to the current module; Based on the load matching degree, the module function coefficient, the equipment state correction coefficient, and the obtained module rated power consumption, the theoretical optimal power consumption value is calculated.

4. The power consumption control method for low-voltage switchgear as described in claim 1, characterized in that, The step of inputting the real-time power consumption values, the theoretical optimal power consumption values, and the operating temperatures into a preset decision model for feature fusion processing to obtain the operating condition feature vectors of each module specifically includes: Based on the aforementioned real-time power consumption values, the total system power consumption of the low-voltage switchgear is calculated. Based on the real-time power consumption values ​​of each module and the total power consumption of the system, the power consumption ratio of each module is calculated. The total power consumption of the system, the power consumption ratio of each module, the operating temperature, and the theoretical optimal power consumption value are normalized to obtain the normalized value of the total power consumption of the system, the normalized value of the power consumption ratio of each module, the normalized value of the operating temperature, and the normalized value of the theoretical optimal power consumption. For each module, the normalized value of the total power consumption of the system, the normalized value of the power consumption ratio corresponding to the current module, the normalized value of the operating temperature, and the normalized value of the theoretical optimal power consumption are integrated to obtain the operating condition feature vector corresponding to the current module.

5. The power consumption control method for a low-voltage switchgear as described in claim 1, characterized in that, The calculation of the real-time power consumption and load matching degree of each module based on the electrical parameters of each module specifically includes: Based on the voltage and current values ​​in each of the electrical parameters, the real-time power consumption value corresponding to each module is calculated. Based on the real-time power consumption value and the preset rated power consumption value of each module, the load matching degree of each module is calculated.

6. The power consumption control method for a low-voltage switchgear as described in claim 1, characterized in that, The control of the low-voltage switchgear for power consumption regulation based on the target power consumption regulation scheme specifically includes: Based on the target power consumption control scheme, a power supply adjustment command is generated; The power supply adjustment command is sent to the power management module of the low-voltage cabinet, so that the power management module adjusts the power supply of each module in the low-voltage cabinet according to the power supply adjustment command, thereby realizing the power consumption control of the low-voltage cabinet.

7. The power consumption control method for a low-voltage switchgear as described in any one of claims 1-6, characterized in that, After controlling the low-voltage switchgear to regulate power consumption based on the target power consumption regulation scheme, the method further includes: After power consumption regulation is completed, the actual power consumption of each module in the low-voltage cabinet is collected. Based on the actual operating power consumption value and the control target value corresponding to each module in the target power consumption control scheme, the control deviation value of each module is calculated. Each of the aforementioned control deviation values ​​is determined to be greater than a preset threshold. If the threshold is met, a fine-tuning instruction is generated based on each of the aforementioned control deviation values. The power management module is then controlled to adjust the power supply of each module in the low-voltage cabinet according to the fine-tuning instruction, thereby achieving power consumption control of the low-voltage cabinet.

8. A power consumption control device for a low-voltage switchgear, characterized in that, It includes Module 1, Module 2, and Module 3; The first module is used to collect electrical parameters and operating temperature of several modules in the low-voltage switchgear; The second module is used to calculate the real-time power consumption value and load matching degree of each module based on the electrical parameters of each module, and to calculate the theoretical optimal power consumption value of each module based on the load matching degree and the operating temperature of each module. The third module is used to input the real-time power consumption values, the theoretical optimal power consumption values, and the operating temperatures into a preset decision model for feature fusion processing to obtain the operating condition feature vectors of each module. Based on the operating condition feature vectors, the module determines the performance weights corresponding to each module. The module uses the performance weights and operating condition feature vectors to evaluate the action value of a number of preset power control actions to obtain several evaluation values. The module uses the evaluation values ​​to filter the power control actions to obtain a target power control scheme, and controls the low-voltage switchgear to control power consumption based on the target power control scheme.

9. A terminal device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation of a power consumption control method for a low-voltage switchgear as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device or apparatus containing the computer-readable storage medium to perform a power consumption control method for a low-voltage switchgear as described in any one of claims 1 to 7.

Images