Intelligent algorithm management method and system for electrical intelligent control switch

Abstract

The invention provides an intelligent algorithm management method and system for an electrical intelligent control switch, and relates to the technical field of intelligent power grids and electrical automation control, and the method comprises the steps: cleaning, synchronizing and storing multi-source heterogeneous data, and obtaining electrical quantity data; extracting the harmonic characteristics of the current through discrete Fourier transform, calculating the three-phase unbalance degree of the three-phase voltage, and fusing the characteristic vector of the current harmonic, the three-phase unbalance degree, the differential of the output power of the photovoltaic inverter and the state of the SOC of the lithium battery into a multi-modal characteristic tensor; constructing an electrical conflict graph to represent a harmonic interference relationship between devices, and calculating a photovoltaic cut-in angle, an energy storage charge-discharge rate and a switch on-off threshold through energy storage compensation decision processing; and calculating the PWM duty ratio of the IGBT driving instruction through edge calculation hardware acceleration processing, and finally generating and executing the IGBT driving instruction. According to the invention, real-time monitoring, intelligent regulation and optimal management of the electrical intelligent control switch are realized.

Description

Technical Field

[0001] This invention relates to the field of smart grid and electrical automation control technology, and more specifically, to a smart algorithm management method and system for intelligent electrical control switches. Background Technology

[0002] In modern power systems, the management and control of intelligent electrical switches are crucial for improving energy efficiency, ensuring power supply stability, and reducing operating costs. Currently, traditional electrical switch management relies primarily on fixed control strategies and manual inspections. This approach has several shortcomings when facing complex power grid environments and dynamic load changes. For example, traditional methods struggle to monitor and address electrical quality issues such as current harmonics and voltage imbalances in real time, and they also cannot flexibly adjust the charging and discharging strategies of energy storage systems based on real-time electricity prices and equipment status.

[0003] These problems lead to energy waste, shortened equipment lifespan, and low system operating efficiency. To address these issues, existing technologies typically employ simple threshold control or rule-based logic, but these methods lack flexibility and adaptability, and cannot effectively cope with complex power grid operating conditions. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent algorithm management method and system for intelligent electrical control switches to improve the aforementioned problems. To achieve the above objective, the technical solution adopted by this invention is as follows: In a first aspect, this application provides an intelligent algorithm management method for an electrical intelligent control switch, including: Collect multi-source heterogeneous data from intelligent control switches. The multi-source heterogeneous data includes electrical quantities, equipment quantities, environmental quantities, and policy quantities. The electrical quantities include three-phase voltage and current harmonics, the equipment quantities include photovoltaic inverter power and lithium battery SOC, the environmental quantities are temperature and humidity, and the policy quantities are time-of-use electricity prices. Clean, synchronize, and store the multi-source heterogeneous data to obtain the electrical quantity data. Based on the collected electrical quantity data, the harmonic characteristics of the current are extracted by discrete Fourier transform, and then the characteristic vector of the current harmonics is obtained. The three-phase unbalance of the three-phase voltage is calculated, and the characteristic vector of the current harmonics, the three-phase unbalance, the differential of the output power of the photovoltaic inverter, and the state of the lithium battery SOC are fused into a multi-modal characteristic tensor. Using multimodal feature tensors, an electrical conflict graph is constructed to characterize the harmonic interference relationship between devices. A neuro-evolutionary optimization algorithm is used, combined with a time-of-use pricing function, to dynamically evaluate the control weight of each device. By combining equipment control weights, lithium battery SOC status, and time-of-use pricing functions, the photovoltaic cut-in angle, energy storage charge / discharge rate, and switch on / off threshold are calculated through energy storage compensation decision processing, and a set of switch action parameters is generated. Based on the generated set of switching action parameters, the PWM duty cycle of the IGBT drive command is calculated through edge computing hardware acceleration processing. The IGBT temperature rise data is fed back in real time to adjust the switching on and off threshold. Finally, the IGBT drive command is generated and executed to realize real-time control of the intelligent switch.

[0005] Preferably, based on the collected electrical quantity data, the harmonic characteristics of the current are extracted through discrete Fourier transform to obtain the feature vector of the current harmonics. The three-phase unbalance of the three-phase voltage is calculated, and the feature vector of the current harmonics, the three-phase unbalance, the differential of the output power of the photovoltaic inverter, and the state of the lithium battery SOC are fused into a multimodal feature tensor, including: The current signal in the collected electrical quantity data is subjected to discrete Fourier transform to calculate the complex characteristics of the k-th harmonic, and the characteristic vector of the current harmonic is obtained through the complex characteristics. The obtained three-phase voltages are used to calculate the imbalance, and the three-phase imbalance degree is obtained. The eigenvectors of current harmonics, three-phase imbalance, the differential of the obtained photovoltaic inverter output power, and the state of lithium battery SOC are fused into a multi-mode characteristic tensor. The differential of the photovoltaic inverter output power is calculated from the photovoltaic inverter output power using a numerical differentiation method.

[0006] Preferably, the method of constructing an electrical conflict graph using multimodal feature tensors to characterize the harmonic interference relationship between devices, and employing a neuroevolutionary optimization algorithm combined with a time-of-use pricing function to dynamically evaluate the control weight of each device, includes: Using home appliances as nodes, the edge weights are the harmonic interference coefficients between devices; The multimodal feature tensor, inter-device harmonic interference coefficient, and time-of-use electricity price function are used as inputs. The device control weights are optimized through a neural evolution algorithm. The control weights of each device are output and optimized. The time-of-use electricity price function is the time-of-use electricity price function obtained by sorting the time-of-use electricity price. The optimized control weights of each device are normalized to obtain the device control weights. The normalization process includes a total weight sum of 1.

[0007] Preferably, by combining the equipment control weights, the state of the lithium battery's SOC, and the time-of-use electricity price function, and through energy storage compensation decision processing, the photovoltaic cut-in angle, energy storage charge / discharge rate, and switch on / off threshold are calculated, and a set of switch action parameters is generated, including: The electricity price information for the current time period is analyzed in the time-of-use pricing function, and the optimal energy storage state is calculated based on the electricity price information for the current time period. The optimal energy storage state for off-peak electricity price is 0.8, and the optimal energy storage state for peak electricity price is 0.3. Based on the equipment control weight, the state of lithium battery SOC, the optimal energy storage state, and the time-of-use electricity price function, energy storage supplementation decision processing is carried out, including photovoltaic cut-in angle calculation, energy storage charge and discharge rate calculation, and switch on / off threshold calculation. The results of the three calculations are combined to obtain the switch action parameter set.

[0008] Secondly, this application also provides an intelligent algorithm management system for an electrical intelligent control switch, including: The data acquisition module is used to collect multi-source heterogeneous data from the smart control switch. This data includes electrical quantities, equipment quantities, environmental quantities, and policy quantities. Electrical quantities include three-phase voltage and current harmonics, equipment quantities include photovoltaic inverter power and lithium battery SOC, environmental quantities include temperature and humidity, and policy quantities include time-of-use electricity pricing. The module cleans, synchronizes, and stores the multi-source heterogeneous data to obtain electrical quantity data. Fusion module: Based on the collected electrical quantity data, it extracts the harmonic features of the current through discrete Fourier transform, and then obtains the feature vector of the current harmonics. It calculates the three-phase unbalance of the three-phase voltage and fuses the feature vector of the current harmonics, the three-phase unbalance, the differential of the output power of the photovoltaic inverter, and the state of the lithium battery SOC into a multi-modal feature tensor. The evaluation module is constructed using multimodal feature tensors to build an electrical conflict graph to characterize the harmonic interference relationship between devices, and uses a neuro-evolutionary optimization algorithm combined with a time-of-use pricing function to dynamically evaluate the control weight of each device. Processing and generation module: It is used to combine the equipment regulation weight, the state of lithium battery SOC and the time-of-use electricity price function, and calculate the photovoltaic cut-in angle, energy storage charge and discharge rate and switch on and off threshold through energy storage compensation decision processing, and generate a set of switch action parameters; The generation control module is used to calculate the PWM duty cycle of the IGBT drive command based on the generated set of switching action parameters through edge computing hardware acceleration processing, provide real-time feedback of IGBT temperature rise data to adjust the switching on and off thresholds, and finally generate and execute the IGBT drive command to achieve real-time control of the intelligent switch.

[0009] Thirdly, this application also provides an intelligent algorithm management device for an electrical intelligent control switch, comprising: Memory, used to store computer programs; A processor is used to implement the intelligent algorithm management method for the electrical intelligent control switch when executing the computer program.

[0010] Fourthly, this application also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described intelligent algorithm management method based on an electrical intelligent control switch.

[0011] The beneficial effects of this invention are as follows: This invention integrates advanced technologies such as multi-source heterogeneous data acquisition, feature extraction and fusion, dynamic priority evaluation, energy storage compensation decision-making, and edge computing hardware acceleration to achieve real-time monitoring, intelligent control, and optimized management of intelligent electrical switches. This method can collect electrical quantities, equipment quantities, environmental quantities, and strategy quantities in real time, and dynamically adjust parameters such as switch on / off thresholds, energy storage charge / discharge rates, and photovoltaic cut-in angles through advanced data processing and intelligent algorithms, thereby maximizing energy utilization efficiency and economic benefits while ensuring stable system operation.

[0012] Compared with existing technologies, this invention has higher flexibility, adaptability and intelligence, and can effectively solve the problems existing in traditional methods, providing a brand-new solution for the intelligent management of power systems.

[0013] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a schematic diagram of the intelligent algorithm management method for the electrical intelligent control switch described in this embodiment of the invention; Figure 2 This is a schematic diagram of the intelligent algorithm management system for the electrical intelligent control switch described in this embodiment of the invention; Figure 3 This is a schematic diagram of the intelligent algorithm management device for the electrical intelligent control switch described in this embodiment of the invention.

[0016] In the diagram: 701, Acquisition module; 702, Fusion module; 703, Construction and evaluation module; 704, Processing and generation module; 705, Generation and control module; 800, Intelligent algorithm management device for electrical intelligent control switch; 801, Processor; 802, Memory; 803, Multimedia component; 804, I / O interface; 805, Communication component. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0018] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0019] Example 1:

[0020] This embodiment provides an intelligent algorithm management method for electrical intelligent control switches.

[0021] See Figure 1 The figure shows that the method includes steps S100, S200, S300, S400 and S500.

[0022] S100: Collects multi-source heterogeneous data from the intelligent control switch. The multi-source heterogeneous data includes electrical quantities, equipment quantities, environmental quantities, and policy quantities. The electrical quantities include three-phase voltage and current harmonics, the equipment quantities include photovoltaic inverter power and lithium battery SOC, the environmental quantities are temperature and humidity, and the policy quantities are time-of-use electricity prices. The multi-source heterogeneous data is cleaned, synchronized, and stored to obtain the electrical quantity data.

[0023] It is understood that the “data structure” in this embodiment describes the organization of multi-source heterogeneous data, which includes time series, matrix data and state vectors, and are the specific representations of electrical quantities, equipment quantities, environmental quantities and policy quantities mentioned in this step.

[0024] It should be noted that the electrical quantity data acquisition in this step involves using high-precision current transformers and voltage transformers to collect the instantaneous values ​​of the three-phase voltage at a sampling rate of 10kHz. The current signal I(t) is used, and the current harmonic distortion rate is calculated from the current signal using Fast Fourier Transform (FFT); while equipment quantity data acquisition involves collecting the output power of the photovoltaic inverter and the SOC status of the lithium battery through smart meters and sensors; among these, environmental quantity data acquisition involves collecting indoor temperature and humidity data through temperature and humidity sensors. And photovoltaic panel temperature; strategy quantity data acquisition is achieved by obtaining the time-of-use pricing function through communication with the grid management system. This includes electricity price information for peak, off-peak, and flat periods.

[0025] The data structure definition includes time series data, matrix data, and state vectors. The time series data consists of the instantaneous values ​​of the three-phase voltages. The data is stored as a floating-point array at 1ms intervals; the matrix data is the current harmonic spectrum represented as a 50×6 matrix, where the 6 columns represent the amplitude, phase and distortion rate of the 6 harmonic orders (3, 5, 7, 9, 11, 13); the state vector is the organization of equipment quantity and environmental quantity data, and is therefore a state vector.

[0026] Next, data preprocessing is performed, including data cleaning to remove outliers and noise from the collected data and fill in missing values; data synchronization to align data from different sources to a unified timestamp to ensure temporal consistency; and data storage to store the preprocessed data in a local database or cloud storage for subsequent processing. The final result is preprocessed multi-source heterogeneous data, including electrical quantities, equipment quantities, environmental quantities, and policy quantities, providing a foundation for subsequent feature extraction and analysis.

[0027] Therefore, the multi-source heterogeneous data acquisition and preprocessing in this step involves collecting and preprocessing multi-source data such as electrical quantities, equipment quantities, environmental quantities, and strategy quantities. This allows for a comprehensive understanding of the operating status of the intelligent control switch, providing a rich data foundation for subsequent intelligent decision-making. This enables the system to more accurately reflect the actual operating environment and supports the optimization of control strategies.

[0028] S200: Based on the collected electrical quantity data, the harmonic characteristics of the current are extracted through discrete Fourier transform, and then the characteristic vector of the current harmonics is obtained. The three-phase unbalance of the three-phase voltage is calculated. The characteristic vector of the current harmonics, the three-phase unbalance, the differential of the output power of the photovoltaic inverter, and the state of the lithium battery SOC are fused into a multi-modal characteristic tensor.

[0029] Understandably, in this step, the harmonic characteristics of the current are extracted by discrete Fourier transform, and the unbalance of the three-phase voltage is calculated. This invention can effectively identify electrical quality problems. Furthermore, these characteristics are fused with the differential of the output power of the photovoltaic inverter and the SOC state of the lithium battery to generate a multimodal feature tensor, which provides a comprehensive feature input for the calculation of the equipment control weight. The feature fusion method can capture more dimensional information and improve the system's perception capability and decision-making accuracy.

[0030] This step S200 includes S201, S202, and S203, wherein: S201. Perform Discrete Fourier Transform on the current signal in the collected electrical quantity data, calculate the complex characteristics of the k-th harmonic, and obtain the characteristic vector of the current harmonic through the complex characteristics. The calculation formula of the complex characteristics is as follows:

[0031] In the formula, For the first k The complex characteristics of the second harmonic, where N is the number of sampling points, I ; S202. Perform unbalance calculations on the obtained three-phase voltages to obtain the three-phase unbalance degree. S203. The characteristic vector of the current harmonics, the three-phase imbalance, the differential of the obtained photovoltaic inverter output power, and the state of the lithium battery SOC are fused into a multi-mode characteristic tensor. The differential of the photovoltaic inverter output power is calculated from the photovoltaic inverter output power using a numerical differentiation method. The calculation formula for the multi-mode characteristic tensor is as follows:

[0032] In the formula, Let H be the multimodal feature tensor and H be the harmonic eigenvector. For three-phase imbalance, This is the derivative of the output power of the photovoltaic inverter. This represents the SOC (State of Charge) state of the lithium battery.

[0033] S300 utilizes multimodal feature tensors to construct an electrical conflict graph to characterize the harmonic interference relationship between devices, and employs a neuro-evolutionary optimization algorithm combined with a time-of-use pricing function to dynamically evaluate the control weight of each device.

[0034] Understandably, in this step, an electrical conflict graph is constructed using multimodal feature tensors, and a neuroevolutionary optimization algorithm combined with a time-of-use pricing function is employed to dynamically evaluate equipment control weights. This allows for flexible adjustment of equipment priorities based on real-time operating conditions. This method not only considers harmonic interference between equipment but also incorporates economic factors, achieving optimized operating costs while ensuring power quality.

[0035] This step S300 includes S301, S302, and S303, wherein: S301. Taking household appliances as nodes, and the edge weights as the harmonic interference coefficients between devices, the formula for calculating the edge weights is as follows:

[0036] In the formula, This refers to the harmonic interference coefficient between equipment. λ The phase sensitivity coefficient, and respectively equipment i The k Second harmonic amplitude and phase; S302. Taking the multimodal feature tensor, inter-equipment harmonic interference coefficient, and time-of-use electricity price function as inputs, the device control weights are optimized using a neural evolutionary algorithm. The control weights of each device are output and optimized. The time-of-use electricity price function is the time-of-use electricity price function obtained by adjusting the time-of-use electricity price. The calculation formula for optimizing the device control weights is as follows:

[0037] In the formula, To optimize equipment control weights, It is a neuroevolutionary algorithm. These are the multimodal characteristic tensor, the inter-equipment harmonic interference coefficient, and the time-of-use electricity price function, respectively. It should be noted that the output of the control weights for each device... A larger value indicates priority in power supply. Furthermore, in this embodiment, time-of-use pricing information is extracted from the strategy quantity data obtained in step S100. Time-of-use pricing is typically given in time series format, for example: peak hour pricing. Cpeak Off-peak electricity price: Cvalley Electricity price during normal periods: Cflat Represent this electricity price information as a time-of-use pricing function. Cprice ( t ), specifically in the form of:

[0038] in, , and These represent the time ranges for the peak, valley, and plateau periods, respectively.

[0039] S303. Normalize the optimized control weights of each device to obtain the device control weights. The normalization process includes a total weight sum of 1.

[0040] S400, combining equipment control weights, lithium battery SOC status, and time-of-use pricing function, calculates photovoltaic cut-in angle, energy storage charge / discharge rate, and switch on / off threshold through energy storage compensation decision processing, and generates a set of switch action parameters.

[0041] Understandably, by combining equipment control weights, lithium battery SOC status, and time-of-use pricing functions in this step, the photovoltaic cut-in angle, energy storage charge / discharge rate, and switch on / off threshold can be dynamically calculated to generate a set of switch action parameters. Through this dynamic decision-making mechanism, the system can flexibly adjust the charging and discharging strategy of the energy storage system during different electricity price periods to maximize the economic benefits of the energy storage system while ensuring the stable operation of the system.

[0042] This step S400 includes S401 and S402, wherein: S401. Analyze the electricity price information of the current time period in the time-of-use electricity price function, and calculate the optimal energy storage state based on the electricity price information of the current time period. The optimal energy storage state during off-peak electricity price is 0.8, and the optimal energy storage state during peak electricity price is 0.3. S402. Based on the equipment control weight, lithium battery SOC state, optimal energy storage state, and time-of-use pricing function, energy storage replenishment decision processing is performed, including photovoltaic cut-in angle calculation, energy storage charge / discharge rate calculation, and switch on / off threshold calculation. The results of these three calculations are combined to obtain the switch action parameter set, the calculation formula of which is as follows:

[0043] In the formula, For the set of switch action parameters, For photovoltaic entry angle, For energy storage charge / discharge rate, This is the on / off threshold for the switch.

[0044] It should be noted that the formula for calculating the photovoltaic cut-in angle is as follows:

[0045] In the formula, For photovoltaic entry angle, For load power, For grid power, For inverter efficiency, This represents the maximum output power of the photovoltaic system. The formula for calculating the energy storage charge / discharge rate is as follows:

[0046] In the formula, For energy storage charge / discharge rate, This is the proportional control coefficient. These are the differential control coefficients. This represents the optimal energy storage state. This represents the current SOC state of the lithium battery. The rate of change of the equipment control weight. This is the differential control coefficient. This formula dynamically adjusts the energy storage charge / discharge rate through proportional and differential control to achieve the optimal energy storage state. The system is adjusted according to the rate of change of the equipment control weight to ensure that the system achieves the best balance between economy and stability.

[0047] The formula for calculating the switch on / off threshold is as follows:

[0048] In the formula, The on / off threshold of the switch. Rated voltage, For three-phase imbalance, γ for electricity Pressure compensation gain.

[0049] S500 calculates the PWM duty cycle of the IGBT drive command based on the generated set of switching action parameters through edge computing hardware acceleration processing, provides real-time feedback of IGBT temperature rise data to adjust the switching on / off threshold, and finally generates and executes the IGBT drive command to achieve real-time control of the intelligent switch.

[0050] It should be noted that the PWM duty cycle of the IGBT drive instruction is calculated based on the switching action parameter set generated in the above steps: and IGBT temperature rise data The data is then sent back to step S100 to dynamically adjust the switch on / off threshold: Deploy a lightweight NEAT model on a Raspberry Pi 4B to ensure a response latency of less than 50ms. This is based on the calculated PWM duty cycle. This generates and executes IGBT drive instructions to achieve real-time control of the smart switch. Through these optimizations, the source and usage of the time-of-use pricing function become clearer, ensuring the logical coherence and feasibility of the entire method.

[0051] Understandably, in this step, by deploying a lightweight model on edge computing devices such as the Raspberry Pi 4B, it is possible to achieve rapid IGBT drive instruction generation and real-time feedback control. This hardware acceleration not only reduces system response time but also improves the system's real-time performance and reliability, enabling it to adapt to rapidly changing power grid environments.

[0052] Example 2:

[0053] like Figure 2 As shown, this embodiment provides an intelligent algorithm management system for electrical intelligent control switches. See [link to relevant documentation]. Figure 2 The system includes: Acquisition module 701: Used to collect multi-source heterogeneous data of intelligent control switches, including electrical quantities, equipment quantities, environmental quantities, and policy quantities. The electrical quantities include three-phase voltage and current harmonics, the equipment quantities include photovoltaic inverter power and lithium battery SOC, the environmental quantities are temperature and humidity, and the policy quantities are time-of-use electricity prices. The multi-source heterogeneous data is cleaned, synchronized, and stored to obtain electrical quantity data. Fusion module 702: Based on the collected electrical quantity data, it extracts the harmonic features of the current through discrete Fourier transform, and then obtains the feature vector of the current harmonics, calculates the three-phase unbalance of the three-phase voltage, and fuses the feature vector of the current harmonics, the three-phase unbalance, the differential of the output power of the photovoltaic inverter, and the state of the lithium battery SOC into a multi-modal feature tensor. The evaluation module 703 is used to construct an electrical conflict graph using multimodal feature tensors to characterize the harmonic interference relationship between devices, and to dynamically evaluate the control weight of each device by using a neuro-evolutionary optimization algorithm combined with a time-of-use electricity price function. Processing and generation module 704: It is used to combine the equipment control weight, the state of lithium battery SOC and the time-of-use electricity price function, and through energy storage compensation decision processing, calculate the photovoltaic cut-in angle, energy storage charge and discharge rate and switch on / off threshold, and generate a set of switch action parameters. The generation control module 705 is used to calculate the PWM duty cycle of the IGBT drive command based on the generated set of switching action parameters through edge computing hardware acceleration processing, provide real-time feedback of IGBT temperature rise data to adjust the switching on / off threshold, and finally generate and execute the IGBT drive command to realize real-time control of the intelligent switch.

[0054] Specifically, the fusion module 702 includes: The first calculation unit is used to perform discrete Fourier transform on the current signal in the collected electrical quantity data, calculate the complex characteristics of the k-th harmonic, and obtain the characteristic vector of the current harmonic through the complex characteristics. The calculation formula of the complex characteristics is as follows:

[0055] In the formula, For the first k The complex characteristics of the second harmonic, where N is the number of sampling points, I ; The second calculation unit is used to perform unbalance calculations on the obtained three-phase voltages to obtain the three-phase unbalance degree. The third calculation unit is used to fuse the characteristic vector of current harmonics, three-phase imbalance, the differential of the obtained photovoltaic inverter output power, and the state of lithium battery SOC into a multimodal characteristic tensor. The differential of the photovoltaic inverter output power is calculated from the photovoltaic inverter output power using numerical differentiation methods. The calculation formula for its multimodal characteristic tensor is as follows:

[0056] In the formula, Let H be the multimodal feature tensor and H be the harmonic eigenvector. For three-phase imbalance, This is the derivative of the output power of the photovoltaic inverter. This represents the SOC (State of Charge) state of the lithium battery.

[0057] Specifically, the construction evaluation module 703 includes: Setting Unit: Used with home appliances as nodes and edge weights representing the harmonic interference coefficients between devices. The formula for calculating the edge weights is as follows:

[0058] In the formula, This refers to the harmonic interference coefficient between equipment. λ The phase sensitivity coefficient, and respectively equipment i The k Second harmonic amplitude and phase; The optimization unit takes the multimodal feature tensor, inter-device harmonic interference coefficient, and time-of-use electricity price function as input, optimizes the device control weights using a neuroevolutionary algorithm, and outputs the optimized control weights for each device. The time-of-use electricity price function is the time-of-use electricity price function obtained by adjusting the time-of-use electricity price. The calculation formula for optimizing the device control weights is as follows:

[0059] In the formula, To optimize equipment control weights, It is a neuroevolutionary algorithm. These are the multimodal characteristic tensor, the inter-equipment harmonic interference coefficient, and the time-of-use electricity price function, respectively. Processing unit: Used to normalize the optimized control weights of each device to obtain the device control weights. The normalization process includes a total weight sum of 1.

[0060] Specifically, the processing generation module includes: Analysis Unit: Used to analyze the electricity price information of the current time period in the time-of-use electricity price function, and calculate the optimal energy storage state based on the electricity price information of the current time period. The optimal energy storage state during off-peak electricity price is 0.8, and the optimal energy storage state during peak electricity price is 0.3. The combined unit is used for energy storage replenishment decision processing based on equipment control weights, lithium battery SOC status, optimal energy storage state, and time-of-use pricing function. This includes calculating the photovoltaic cut-in angle, energy storage charge / discharge rate, and switch on / off threshold. The results of these three calculations are combined to obtain the switch action parameter set, the calculation formula of which is as follows:

[0061] In the formula, For the set of switch action parameters, For photovoltaic entry angle, For energy storage charge / discharge rate, This is the on / off threshold for the switch.

[0062] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0063] Example 3:

[0064] Corresponding to the above method embodiments, this embodiment also provides an intelligent algorithm management device for an electrical intelligent control switch. The intelligent algorithm management device for an electrical intelligent control switch described below and the intelligent algorithm management method for an electrical intelligent control switch described above can be referred to in correspondence.

[0065] Figure 3 This is a block diagram illustrating an intelligent algorithm management device 800 for an electrical intelligent control switch, according to an exemplary embodiment. Figure 3 As shown, the intelligent algorithm management device 800 for the electrical intelligent control switch includes a processor 801 and a memory 802. The intelligent algorithm management device 800 also includes one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0066] The processor 801 controls the overall operation of the intelligent algorithm management device 800 for the intelligent electrical switch, to complete all or part of the steps in the aforementioned intelligent algorithm management method for the intelligent electrical switch. The memory 802 stores various types of data to support the operation of the intelligent algorithm management device 800. This data may include, for example, instructions for any application or method operating on the intelligent algorithm management device 800, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as keyboards, mice, or buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the intelligent algorithm management device 800 of the electrical intelligent control switch and other devices. Wireless communication includes, for example, Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or one or more combinations thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0067] In an exemplary embodiment, the intelligent algorithm management device 800 for the electrical intelligent control switch may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the aforementioned intelligent algorithm management method for the electrical intelligent control switch.

[0068] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, these program instructions implement the steps of the intelligent algorithm management method for the intelligent electrical control switch described above. For example, the computer-readable storage medium may be the memory 802 including program instructions described above. These program instructions may be executed by the processor 801 of the intelligent algorithm management device 800 for the intelligent electrical control switch to complete the intelligent algorithm management method for the intelligent electrical control switch described above.

[0069] Example 4:

[0070] Corresponding to the above method embodiments, this embodiment also provides a readable storage medium. The readable storage medium described below and the intelligent algorithm management method for an electrical intelligent control switch described above can be referred to and correspond to each other.

[0071] A computer program is stored on a readable storage medium, and when the computer program is executed by a processor, it implements the steps of the intelligent algorithm management method for the electrical intelligent control switch in the above method embodiment.

[0072] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0073] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0074] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A smart algorithm management method for an electrical intelligent control switch, characterized in that, include: Collect multi-source heterogeneous data from intelligent control switches. The multi-source heterogeneous data includes electrical quantities, equipment quantities, environmental quantities, and policy quantities. The electrical quantities include three-phase voltage and current harmonics, the equipment quantities include photovoltaic inverter power and lithium battery SOC, the environmental quantities are temperature and humidity, and the policy quantities are time-of-use electricity prices. Clean, synchronize, and store the multi-source heterogeneous data to obtain the electrical quantity data. Based on the collected electrical quantity data, the harmonic characteristics of the current are extracted by discrete Fourier transform, and then the characteristic vector of the current harmonics is obtained. The three-phase unbalance of the three-phase voltage is calculated, and the characteristic vector of the current harmonics, the three-phase unbalance, the differential of the output power of the photovoltaic inverter, and the state of the lithium battery SOC are fused into a multi-modal characteristic tensor. Using multimodal feature tensors, an electrical conflict graph is constructed to characterize the harmonic interference relationship between devices. A neuro-evolutionary optimization algorithm is used, combined with a time-of-use pricing function, to dynamically evaluate the control weight of each device. By combining equipment control weights, lithium battery SOC status, and time-of-use pricing functions, the photovoltaic cut-in angle, energy storage charge / discharge rate, and switch on / off threshold are calculated through energy storage compensation decision processing, and a set of switch action parameters is generated. Based on the generated set of switching action parameters, the PWM duty cycle of the IGBT drive command is calculated through edge computing hardware acceleration processing. The IGBT temperature rise data is fed back in real time to adjust the switching on and off threshold. Finally, the IGBT drive command is generated and executed to realize real-time control of the intelligent switch.

2. The intelligent algorithm management method for electrical intelligent control switches according to claim 1, characterized in that, Based on the collected electrical quantity data, the harmonic characteristics of the current are extracted through Discrete Fourier Transform, thereby obtaining the characteristic vector of the current harmonics. The three-phase unbalance of the three-phase voltage is calculated, and the characteristic vector of the current harmonics, the three-phase unbalance, the differential of the photovoltaic inverter output power, and the state of the lithium battery SOC are fused into a multimodal characteristic tensor, including: The current signal in the collected electrical quantity data is subjected to Discrete Fourier Transform to calculate the complex characteristics of the k-th harmonic, and the eigenvector of the current harmonic is obtained through the complex characteristics. The formula for calculating the complex characteristics is as follows: In the formula, For the first k The complex characteristics of the second harmonic, where N is the number of sampling points, I ; The obtained three-phase voltages are used to calculate the imbalance, and the three-phase imbalance degree is obtained. The eigenvectors of current harmonics, three-phase imbalance, the differential of the obtained photovoltaic inverter output power, and the state of lithium battery SOC are fused into a multimodal characteristic tensor. The differential of the photovoltaic inverter output power is calculated from the photovoltaic inverter output power using numerical differentiation methods. The calculation formula for the multimodal characteristic tensor is as follows: In the formula, Let H be the multimodal feature tensor and H be the harmonic eigenvector. For three-phase imbalance, The derivative of the output power of the photovoltaic inverter. This represents the SOC (State of Charge) state of the lithium battery.

3. The intelligent algorithm management method for electrical intelligent control switches according to claim 1, characterized in that, The method utilizes multimodal feature tensors to construct an electrical conflict graph to characterize the harmonic interference relationship between devices, and employs a neuroevolutionary optimization algorithm combined with a time-of-use pricing function to dynamically evaluate the control weight of each device, including: Taking home appliances as nodes and edge weights as the harmonic interference coefficients between devices, the formula for calculating the edge weights is as follows: In the formula, This refers to the harmonic interference coefficient between equipment. λ The phase sensitivity coefficient, and respectively equipment i The k Second harmonic amplitude and phase; Using multimodal feature tensors, inter-device harmonic interference coefficients, and time-of-use pricing functions as inputs, a neural evolutionary algorithm is used to optimize the device control weights. The output of each device's control weight is then optimized. The time-of-use pricing function is a time-of-use pricing function obtained by adjusting the time-of-use pricing. The calculation formula for optimizing the device control weights is as follows: In the formula, To optimize equipment control weights, It is a neuroevolutionary algorithm. These are the multimodal characteristic tensor, the inter-equipment harmonic interference coefficient, and the time-of-use electricity price function, respectively. The optimized control weights of each device are normalized to obtain the device control weights. The normalization process includes a total weight sum of 1.

4. The intelligent algorithm management method for electrical intelligent control switches according to claim 1, characterized in that, The process combines equipment control weights, lithium battery SOC status, and time-of-use pricing functions, and through energy storage compensation decision processing, calculates the photovoltaic cut-in angle, energy storage charge / discharge rate, and switch on / off threshold, generating a set of switch action parameters, including: The electricity price information for the current time period is analyzed in the time-of-use pricing function, and the optimal energy storage state is calculated based on the electricity price information for the current time period. The optimal energy storage state for off-peak electricity price is 0.8, and the optimal energy storage state for peak electricity price is 0.

3. Based on equipment control weights, lithium battery SOC status, optimal energy storage state, and time-of-use pricing function, energy storage replenishment decision processing is performed. This includes calculating the photovoltaic cut-in angle, energy storage charge / discharge rate, and switch on / off threshold. The results of these three calculations are combined to obtain the switch action parameter set, the calculation formula of which is as follows: In the formula, For the set of switch action parameters, For photovoltaic entry angle, For energy storage charge / discharge rate, This is the on / off threshold for the switch.

5. An intelligent algorithm management system for an electrical intelligent control switch, based on the intelligent algorithm management method for an electrical intelligent control switch as described in claim 1, characterized in that, include: The data acquisition module is used to collect multi-source heterogeneous data from the smart control switch. This data includes electrical quantities, equipment quantities, environmental quantities, and policy quantities. Electrical quantities include three-phase voltage and current harmonics, equipment quantities include photovoltaic inverter power and lithium battery SOC, environmental quantities include temperature and humidity, and policy quantities include time-of-use electricity pricing. The module cleans, synchronizes, and stores the multi-source heterogeneous data to obtain electrical quantity data. Fusion module: Based on the collected electrical quantity data, it extracts the harmonic features of the current through discrete Fourier transform, and then obtains the feature vector of the current harmonics. It calculates the three-phase unbalance of the three-phase voltage and fuses the feature vector of the current harmonics, the three-phase unbalance, the differential of the output power of the photovoltaic inverter, and the state of the lithium battery SOC into a multi-modal feature tensor. The evaluation module is constructed using multimodal feature tensors to build an electrical conflict graph to characterize the harmonic interference relationship between devices, and uses a neuro-evolutionary optimization algorithm combined with a time-of-use pricing function to dynamically evaluate the control weight of each device. Processing and generation module: It is used to combine the equipment regulation weight, the state of lithium battery SOC and the time-of-use electricity price function, and calculate the photovoltaic cut-in angle, energy storage charge and discharge rate and switch on and off threshold through energy storage compensation decision processing, and generate a set of switch action parameters; The generation control module is used to calculate the PWM duty cycle of the IGBT drive command based on the generated set of switching action parameters through edge computing hardware acceleration processing, provide real-time feedback of IGBT temperature rise data to adjust the switching on and off thresholds, and finally generate and execute the IGBT drive command to achieve real-time control of the intelligent switch.

6. The intelligent algorithm management system for the electrical intelligent control switch according to claim 5, characterized in that, The fusion module includes: The first calculation unit is used to perform discrete Fourier transform on the current signal in the collected electrical quantity data, calculate the complex characteristics of the k-th harmonic, and obtain the characteristic vector of the current harmonic through the complex characteristics. The calculation formula of the complex characteristics is as follows: In the formula, For the first k The complex characteristics of the second harmonic, where N is the number of sampling points, I ; The second calculation unit is used to perform unbalance calculations on the obtained three-phase voltages to obtain the three-phase unbalance degree. The third calculation unit is used to fuse the characteristic vector of current harmonics, three-phase imbalance, the differential of the obtained photovoltaic inverter output power, and the state of lithium battery SOC into a multimodal characteristic tensor. The differential of the photovoltaic inverter output power is calculated from the photovoltaic inverter output power using numerical differentiation methods. The calculation formula for its multimodal characteristic tensor is as follows: In the formula, Let H be the multimodal feature tensor and H be the harmonic eigenvector. For three-phase imbalance, The derivative of the output power of the photovoltaic inverter. This represents the SOC (State of Charge) state of the lithium battery.

7. The intelligent algorithm management system for the electrical intelligent control switch according to claim 5, characterized in that, The construction evaluation module includes: Setting Unit: Used with home appliances as nodes and edge weights representing the harmonic interference coefficients between devices. The formula for calculating the edge weights is as follows: In the formula, This refers to the harmonic interference coefficient between equipment. λ The phase sensitivity coefficient, and respectively equipment i The k Second harmonic amplitude and phase; The optimization unit takes the multimodal feature tensor, inter-device harmonic interference coefficient, and time-of-use electricity price function as input, optimizes the device control weights using a neuroevolutionary algorithm, and outputs the optimized control weights for each device. The time-of-use electricity price function is the time-of-use electricity price function obtained by adjusting the time-of-use electricity price. The calculation formula for optimizing the device control weights is as follows: In the formula, To optimize equipment control weights, It is a neuroevolutionary algorithm. These are the multimodal characteristic tensor, the inter-equipment harmonic interference coefficient, and the time-of-use electricity price function, respectively. Processing unit: Used to normalize the optimized control weights of each device to obtain the device control weights. The normalization process includes a total weight sum of 1.

8. The intelligent algorithm management system for the electrical intelligent control switch according to claim 5, characterized in that, The processing and generation module includes: Analysis Unit: Used to analyze the electricity price information of the current time period in the time-of-use electricity price function, and calculate the optimal energy storage state based on the electricity price information of the current time period. The optimal energy storage state during off-peak electricity price is 0.8, and the optimal energy storage state during peak electricity price is 0.

3. The combined unit is used for energy storage replenishment decision processing based on equipment control weights, lithium battery SOC status, optimal energy storage state, and time-of-use pricing function. This includes calculating the photovoltaic cut-in angle, energy storage charge / discharge rate, and switch on / off threshold. The results of these three calculations are combined to obtain the switch action parameter set, the calculation formula of which is as follows: In the formula, For the set of switch action parameters, For photovoltaic entry angle, For energy storage charge / discharge rate, This is the on / off threshold for the switch.

9. An intelligent algorithm management device for an electrical intelligent control switch, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the intelligent algorithm management method for the electrical intelligent control switch as described in any one of claims 1 to 4 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the intelligent algorithm management method for the electrical intelligent control switch as described in any one of claims 1 to 4.

Images