Inverter control method and device, electronic equipment and storage medium

Abstract

The invention relates to an inverter control method and device, electronic equipment and a storage medium, and is applied to the technical field of power electronics, and the method comprises the steps: obtaining multi-source heterogeneous data affecting the load power demand; predicting load demand data within a preset duration based on the multi-source heterogeneous data; determining an adjustment strategy of an inverter according to the load demand data and / or the multi-source heterogeneous data; and adjusting the inverter according to the adjustment strategy so as to enable the output power of the inverter to meet the demand of the load.

Description

Technical Field

[0001] This application relates to the field of power electronics technology, and in particular to a control method, apparatus, electronic device and storage medium for an inverter. Background Technology

[0002] With the increasing popularity of renewable energy, photovoltaic systems are being used more and more widely in homes. A photovoltaic inverter is a key device that converts direct current (DC) generated by solar panels into alternating current (AC).

[0003] Most photovoltaic inverters in related technologies adopt a fixed operating mode, remaining operational during periods of ample sunlight or when household electricity demand is low or nonexistent. While this operating mode ensures stable system operation, it still consumes a certain amount of electricity, resulting in energy waste. Summary of the Invention

[0004] This application provides a control method, apparatus, electronic device, and storage medium for an inverter, to solve the problem of energy waste caused by inverters with fixed operating modes in the prior art.

[0005] According to a first aspect of the embodiments of this application, a control method for an inverter is provided, comprising:

[0006] Acquire multi-source heterogeneous data that affects load power demand;

[0007] Based on the multi-source heterogeneous data, predict the load demand data within a preset time period;

[0008] The inverter regulation strategy is determined based on the load demand data and / or the multi-source heterogeneous data.

[0009] The inverter is adjusted according to the adjustment strategy so that the output power of the inverter meets the requirements of the load.

[0010] Optionally, the inverter adjustment strategy is determined based on the load demand data, including:

[0011] Determine the dynamic change category to which the load demand data belongs;

[0012] When the dynamic change category is short-term fluctuation, the adjustment strategy includes at least one of the following: increasing the switching frequency of the inverter, switching the DC-DC topology mode to a specified topology, and increasing the power factor of the inverter;

[0013] When the dynamic change category is a long-term trend, the adjustment strategy includes at least one of the following: switching to the working mode corresponding to the working time period of the inverter, and adjusting the electronic components of the inverter according to the load demand data.

[0014] Optionally, the multi-source heterogeneous data includes the current operating power of the load;

[0015] Based on the aforementioned multi-source heterogeneous data, the inverter's regulation strategy is determined, including:

[0016] Based on the current operating power and the maximum operating power of the load, determine the load rate of the load;

[0017] When the load rate is less than a first preset value, the adjustment strategy includes at least one of the following: turning off the redundant power transistors in the inverter, starting the synchronous rectification topology, and controlling the inverter to switch to sleep mode;

[0018] When the load rate is less than a second preset value and greater than the first preset value, the adjustment strategy includes at least one of the following: reducing the switching frequency of the inverter to a first specified frequency, and activating soft switching;

[0019] When the load rate is greater than the second preset value, the adjustment strategy includes: increasing the switching frequency of the inverter to a second specified frequency;

[0020] Wherein, the first specified frequency is less than the second specified frequency, and the second preset value is greater than the first preset value.

[0021] Optionally, based on the load demand data and the multi-source heterogeneous data, a regulation strategy for the inverter is determined, including:

[0022] The load demand data and the multi-source heterogeneous data are used to determine the inverter's operating mode;

[0023] The control strategy corresponding to the operating mode is determined to be the adjustment strategy.

[0024] Optionally, after adjusting the inverter according to the adjustment strategy, the method further includes:

[0025] Obtain the execution result data of the load after the adjustment strategy is executed;

[0026] The adjustment strategy is adjusted based on the execution result data.

[0027] Optionally, the execution result data includes the load's junction temperature and conversion efficiency. Adjusting the regulation strategy based on the execution result data includes:

[0028] When the junction temperature is greater than the preset temperature, reduce the switching frequency in the regulation strategy and switch the operating mode to thermal balance mode.

[0029] If the conversion efficiency is less than the preset efficiency, adjust the PWM duty cycle in the adjustment strategy or switch the operating mode to DC-DC topology mode.

[0030] Optionally, predicting load demand data within a preset time period based on the multi-source heterogeneous data includes:

[0031] The multi-source heterogeneous data is input into a pre-trained prediction model, and the load demand data is output through the prediction model.

[0032] The prediction model is obtained by training on electricity consumption behavior based on sample running data and user behavior data.

[0033] According to a second aspect of the embodiments of this application, a control device for an inverter is provided, comprising:

[0034] The acquisition unit is used to acquire multi-source heterogeneous data that affects load power demand.

[0035] The prediction unit is used to predict load demand data within a preset time period based on the multi-source heterogeneous data;

[0036] The determining unit is used to determine the inverter's adjustment strategy based on the load demand data and / or the multi-source heterogeneous data;

[0037] A control unit is configured to adjust the inverter according to the adjustment strategy so that the output power of the inverter meets the requirements of the load.

[0038] According to a third aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor;

[0039] The memory is connected to the processor and is used to store programs;

[0040] The processor is used to implement the inverter control method as described in the first aspect by running the program in the memory.

[0041] According to a fourth aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the computer program is run by a processor, it implements the inverter control method as described in the first aspect.

[0042] According to a fifth aspect of the present application, a computer program product is provided, including computer program instructions that, when executed by a processor, cause the processor to perform the inverter control method as described in the first aspect.

[0043] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application acquires multi-source heterogeneous data affecting load power demand; predicts load demand data within a preset time period based on the multi-source heterogeneous data; determines an inverter adjustment strategy according to the load demand data and / or the multi-source heterogeneous data; and adjusts the inverter according to the adjustment strategy so that the inverter's output power meets the load demand. Thus, by utilizing load demand data predicted from the load demand and multi-source heterogeneous data of the load to adjust the inverter's operating parameters, dynamic adjustment of the inverter is achieved, thereby meeting the load demand in real time. This not only ensures stable system operation but also avoids energy waste. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0045] Figure 1 A flowchart of an inverter control method is provided for one embodiment of this application;

[0046] Figure 2 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0047] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and 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.

[0048] Exemplary Implementation Environment

[0049] The inverter control method according to embodiments of this application can be executed by electronic devices such as terminal devices or servers. Terminal devices can be user equipment (UE), mobile devices, user terminals, terminals, cellular phones, cordless phones, personal digital assistants (PDAs), handheld devices, computing devices, in-vehicle devices, wearable devices, etc. Servers can be independent physical servers, server clusters composed of multiple physical servers, or cloud servers capable of cloud computing. This method can be implemented by a processor calling computer-readable program instructions stored in memory. This application uses the execution of the inverter control method by a server as an example for explanation, but does not limit it.

[0050] Exemplary methods

[0051] Please see Figure 1 In one exemplary embodiment, a control method for an inverter is provided, comprising:

[0052] Step 101: Obtain multi-source heterogeneous data that affects load power demand.

[0053] In some embodiments, the load is affected by various factors during operation, such as the environment, power grid configuration, and user behavior. In this embodiment, the multi-source heterogeneous data includes: real-time monitoring of power grid load parameters by current / voltage sensors; synchronous collection of light intensity and load temperature by environmental sensors; and load operating status (such as load start / stop and load power requirements) obtained through smart home protocols (such as Zigbee).

[0054] After acquiring the raw data from the aforementioned sensors and smart home protocols, the raw data is preprocessed, including filtering (such as Kalman filtering for noise reduction) and normalization. The preprocessed data is then fused to obtain multi-source heterogeneous data.

[0055] It is understandable that the aforementioned loads can be electrical appliances used in smart homes, such as air conditioners, televisions, water heaters, etc.

[0056] Step 102: Predict load demand data within a preset time period based on the multi-source heterogeneous data.

[0057] In some embodiments, users' electricity consumption behavior is analyzed using multi-source heterogeneous data to predict load demand data in the future, which is then used as input for inverter regulation strategies.

[0058] In one optional embodiment, predicting load demand data within a preset time period based on the multi-source heterogeneous data includes:

[0059] The multi-source heterogeneous data is input into a pre-trained prediction model, and the load demand data is output through the prediction model.

[0060] The prediction model is obtained by training on electricity consumption behavior based on sample running data and user behavior data.

[0061] In some embodiments, the prediction model can be, but is not limited to, trained using a lightweight Long Short-Term Memory (LSTM) network model. By fusing multi-source heterogeneous data and using a lightweight LSTM model, real-time load demand prediction can be achieved at the edge.

[0062] LSTM models extract features from historical data (such as multi-source heterogeneous data over a past period), including periodic features (differences in electricity consumption between weekdays and holidays) and stochastic features (triggering patterns of sudden high-power events, such as oven startup). These extracted features are then used to predict load demand, thus obtaining load demand data.

[0063] The process of using an LSTM model for prediction can include:

[0064] Data acquisition: Integrating power grid, environmental, and user behavior data to obtain multi-source heterogeneous data;

[0065] Feature extraction: Extracting temporal, behavioral, and environmental features to obtain data features.

[0066] Model design: A lightweight LSTM model is adopted, which is suitable for edge deployment.

[0067] Real-time prediction: Input data features into the LSTM model for prediction. During the prediction process, a sliding window can be used to update and generate load prediction values ​​for a preset time period in the future.

[0068] The preset duration can be set based on actual conditions, such as the next 1 to 2 hours or the next day.

[0069] In an optional embodiment, the inverter control method further includes:

[0070] Obtain updated user behavior data;

[0071] The prediction model is optimized based on the updated data.

[0072] In some embodiments, during a user's electricity consumption, there may be situations where certain loads experience sudden power consumption or power outages. Based on this, incremental learning techniques can be used on the prediction model, allowing the model to be updated gradually as new data arrives, without retraining the entire model. Model parameters are updated using small batches of data or single samples to adapt to changes in the user's electricity consumption patterns.

[0073] Recent user electricity consumption data can be stored locally on the device, and the model can be updated periodically to capture new features of electricity consumption patterns. The range of input data for the model can be dynamically adjusted by using a sliding window or time series segmentation.

[0074] User behavior data can be obtained through the interactive interface, including user electricity consumption data and user policy adjustment data. User electricity consumption data can be obtained by users controlling the load to switch it on or off or adjusting load parameters (such as adjusting the air conditioner temperature) through voice or gesture control. User policy adjustment data can be obtained by users setting sleep time through the interactive interface.

[0075] Users can adjust strategy parameters through the interactive interface, and the system can optimize the weights of the local learning model accordingly.

[0076] Specifically, users can set the hibernation trigger threshold (such as entering deep hibernation when the power is less than 30W) through the visual panel.

[0077] Users issue commands via voice or gestures, which are then parsed by a Natural Language Processing (NLP) engine to indicate "enter power saving mode" and mapped to system hibernation policy parameters.

[0078] User-defined parameters (such as prioritizing energy efficiency or response speed) are input into the LSTM model training process to adjust prediction weights. For example, if the user frequently adjusts the dormancy threshold manually, the system automatically learns and optimizes the triggering conditions of the prediction model.

[0079] Furthermore, monthly inverter operating data (such as loss distribution and fault records) can be collected to trigger incremental learning of the LSTM model and optimize prediction and scheduling strategies. Additionally, abnormal inverter events (such as power transistor overheating) can be monitored, alarms can be pushed to user terminals, and automatic load reduction can be implemented.

[0080] Step 103: Determine the inverter adjustment strategy based on the load demand data and / or the multi-source heterogeneous data.

[0081] In some embodiments, multi-source heterogeneous data on household electricity consumption behavior and load dynamic changes are used, combined with load demand data output by a predictive model, to adaptively adjust the inverter hardware parameters and operating mode, thereby achieving dual optimization of power consumption and efficiency.

[0082] In an optional embodiment, determining the inverter's adjustment strategy based on the load demand data includes:

[0083] Determine the dynamic change category to which the load demand data belongs;

[0084] When the dynamic change category is short-term fluctuation, the adjustment strategy includes at least one of the following: increasing the switching frequency of the inverter, switching the DC-DC topology mode to a specified topology, and increasing the power factor of the inverter;

[0085] When the dynamic change category is a long-term trend, the adjustment strategy includes at least one of the following: switching to the working mode corresponding to the working time period of the inverter, and adjusting the electronic components of the inverter according to the load demand data.

[0086] In some embodiments, the dynamic change category of load demand data can be determined by the duration of load demand.

[0087] When the dynamic change category is short-term fluctuation, the duration of load demand is usually short, such as within one hour. Short-term fluctuations in electricity demand involve rapid changes, such as users starting or stopping high-power appliances (air conditioners, electric kettles, etc.). For such cases, load demand data needs to respond quickly, requiring high forecast accuracy and a small time window.

[0088] When the dynamic change category is a long-term trend, the duration of load demand is typically long, such as a day or longer. Long-term trends in electricity demand exhibit cyclical variations, such as peak electricity consumption periods in the morning and evening. In this case, load demand data changes relatively smoothly, and forecasts can be based on cyclical patterns in historical data.

[0089] Based on this, different types of dynamic changes correspond to real-time adjustments of hardware parameters and mode switching.

[0090] Specifically, when the dynamic change category is short-term fluctuation, the inverter can be adjusted as follows:

[0091] Switching frequency: When it is predicted that the load demand data will increase in the next few minutes, i.e., the load will suddenly increase, the switching frequency of pulse-width modulation (PWM) will be increased to the megahertz level to reduce dynamic response delay and ensure that the inverter can quickly adjust the output power.

[0092] DC-DC topology mode: Switch to a high-efficiency topology, such as a synchronous rectifier BUCK converter, to cope with instantaneous high power demand, optimize high power output, and ensure stable output voltage.

[0093] Power factor adjustment: Dynamically adjusts the power factor to optimize power quality, reduce harmonic distortion, and ensure the normal operation of electrical appliances.

[0094] When the dynamic change category is a long-term trend, the inverter can be adjusted as follows:

[0095] Operating mode switching: Different operating modes can be preset according to different times of the day. For example, during peak electricity consumption periods, switch to high-power output mode; during off-peak periods, switch to energy-saving mode to reduce energy waste.

[0096] Electronic component adjustment: Based on long-term load demand forecast data, dynamically adjust the parameters of capacitors and inductors in the inverter's electronic components to maintain output voltage stability and smooth transition.

[0097] Furthermore, based on long-term trend forecasts, the efficiency parameters of the inverter can be optimized, such as improving conversion efficiency, reducing standby power consumption, and adapting to expected long-term power demand.

[0098] In one alternative embodiment, the multi-source heterogeneous data includes the current operating power of the load;

[0099] Based on the aforementioned multi-source heterogeneous data, the inverter's regulation strategy is determined, including:

[0100] The load rate of the load is determined based on the current operating power and the maximum operating power of the load.

[0101] When the load rate is less than a first preset value, the adjustment strategy includes at least one of the following: turning off the redundant power transistors in the inverter, starting the synchronous rectification topology, and controlling the inverter to switch to sleep mode;

[0102] When the load rate is less than a second preset value and greater than the first preset value, the adjustment strategy includes at least one of the following: reducing the switching frequency of the inverter to a first specified frequency, and activating soft switching;

[0103] When the load rate is greater than the second preset value, the adjustment strategy includes: increasing the switching frequency of the inverter to a second specified frequency;

[0104] Wherein, the first specified frequency is less than the second specified frequency, and the second preset value is greater than the first preset value.

[0105] In some embodiments, the current operating power can be calculated from the real-time voltage and current of the load. The maximum operating power can be the sum of the rated power of all currently operating loads. The load factor is obtained by calculating the ratio of the current operating power to the maximum operating power of the load. Key hardware parameters (such as switching frequency and duty cycle) are automatically adjusted based on the real-time load factor, breaking the limitations of traditional fixed parameters. A dynamic trade-off is struck between reducing switching losses and improving conversion efficiency; for example, prioritizing power reduction under light loads and prioritizing efficiency under heavy loads.

[0106] Specifically, the load status can be graded based on the load rate. When the load rate is less than a first preset value, the load status is extremely light; when the load rate is greater than the first preset value but less than a second preset value, the load status is light; and when the load rate is greater than the second preset value, the load status is medium to high. The first and second preset values ​​can be set based on actual conditions; for example, the first preset value could be 10%, and the second preset value 30%. The first specified frequency can be, but is not limited to, in the kilohertz range, and the second specified frequency can be, but is not limited to, in the megahertz range.

[0107] In the case of extremely light load, synchronous rectification topology and dynamic sleep unit are enabled, and redundant power transistors are turned off.

[0108] Under light load conditions, reduce the switching frequency to the kilohertz level and enable soft switching (e.g., ZVS) to eliminate turn-off losses.

[0109] Under medium to high load conditions, the switching frequency is increased to the megahertz level to optimize dynamic response speed.

[0110] Furthermore, the load demand data includes load power variation, which represents the predicted power change of the load over a future period. The switching frequency can also be adjusted as follows:

[0111] Based on the load rate and predicted load changes, the optimal switching frequency f is dynamically calculated as follows: sw :

[0112]

[0113] Where P represents the current operating power, Pmax represents the maximum operating power, P / Pmax represents the load rate, α represents the dynamic compensation coefficient, and ΔPpred represents the predicted change in load power. min f max and f mid These represent the minimum, maximum, and median values ​​of the switching frequency, respectively. These are all factory-provided attributes of the inverter hardware and can be obtained directly.

[0114] Furthermore, when a load surge is detected (such as ΔP / Δt>100W / s), ZVS mode can be forcibly enabled to suppress voltage spikes.

[0115] Furthermore, by combining user behavior prediction and load inertia analysis, the system can proactively enter deep sleep mode during periods of no load, rather than relying on a fixed schedule. Predictive models can anticipate appliance startup events (such as timed water heater heating) and wake the system in advance, pre-setting the output power.

[0116] Hibernation conditions can be determined based on the current operating power of the current load. Hibernation is triggered if one of the following conditions is met: the current operating power is less than a first specified power (e.g., P≤50W); combined with the output of the prediction model, if there are no high-probability load events (e.g., P) within the next 30 minutes. pred <100W).

[0117] After the inverter enters sleep mode, a wake-up mechanism can be configured. The wake-up mechanism is triggered under one of the following conditions: when the LSTM model predicts a high-probability load event (confidence > 80%), the inverter system is woken up 10 seconds in advance and preset parameters are loaded; or it is woken up immediately through communication with an IoT device (such as a change in the status of a smart socket).

[0118] The sleep mode can also be tiered. In shallow sleep mode, non-critical peripherals (such as the display) are turned off, while the core control chip continues to operate. In deep sleep mode, only the RTC clock and low-power communication modules are retained, resulting in low static power consumption, typically less than 1 watt.

[0119] In an optional embodiment, determining the inverter's regulation strategy based on the load demand data and the multi-source heterogeneous data includes:

[0120] The load demand data and the multi-source heterogeneous data are used to determine the inverter's operating mode;

[0121] The control strategy corresponding to the operating mode is determined to be the adjustment strategy.

[0122] In some embodiments, the multi-source heterogeneous data includes the current operating power p of the load, the photovoltaic power output fluctuation rate σ, and the energy storage SOC, and the load demand data includes the load power change P. pred The operating modes include dynamic follow mode and peak optimization mode.

[0123] The inverter's operating mode can be arbitrated using fuzzy logic. For example, a membership function can be defined where, when P is low and σ is high, the membership tilts towards the "dynamic follow mode." If P... pred If there is a sudden increase and the energy storage SOC is greater than 80%, the "peak optimization mode" will be triggered.

[0124] In the dynamic follow mode, the adjustment strategy is to increase the PWM frequency to the megahertz level to track the load power curve in real time. In the peak optimization mode, the energy storage battery output is activated to limit the inverter's instantaneous power to less than or equal to 90% of the rated power, and the DC-DC converter is adjusted to buck-boost mode to adapt to sudden rises / falls in grid voltage.

[0125] It can also monitor the junction temperature of power devices and dynamically distribute the load to devices with lower temperatures to avoid local overheating.

[0126] It is understood that the above-described process of determining the inverter's regulation strategy based on the load demand data and / or the multi-source heterogeneous data can be combined to jointly determine the regulation strategy.

[0127] Step 104: Adjust the inverter according to the adjustment strategy so that the output power of the inverter meets the load requirements.

[0128] In some embodiments, the inverter's operating parameters are adjusted by utilizing load demand data that predicts load demand and multi-source heterogeneous load data, thereby achieving dynamic adjustment of the inverter. This enables the inverter to meet load demands in real time, ensuring stable system operation and preventing energy waste.

[0129] In an optional embodiment, after adjusting the inverter according to the adjustment strategy, the method further includes:

[0130] Obtain the execution result data of the load after the adjustment strategy is executed;

[0131] The adjustment strategy is adjusted based on the execution result data.

[0132] In some embodiments, the performance of the inverter hardware (such as efficiency and temperature rise) is fed back to the algorithm layer in real time to dynamically adjust the control strategy. The load distribution is dynamically adjusted according to the junction temperature of the power devices to avoid efficiency degradation caused by local overheating.

[0133] The execution result data may include, but is not limited to, the junction temperature of the load, switching losses, and conversion efficiency.

[0134] The junction temperature can be obtained in the following ways: First, with the load in a cold state (ambient temperature or case temperature known), apply a small measuring current to the load and measure the target thermistor parameter value. Let the load run under actual operating conditions for a period of time until it reaches thermal steady state. Quickly switch to measurement mode (apply the same small measuring current) and measure the target thermistor parameter value again. Calculate the current junction temperature based on a pre-calibrated "thermistor parameter value - junction temperature" curve or formula. Second, measure the case temperature using a thermocouple / resistance temperature detector (RTD) and calculate the thermal resistance. Install a thermocouple or RTD (such as PT100) in close contact with the load casing to measure the case temperature, and calculate the junction temperature Tj based on the load's thermal resistance parameter.

[0135] Where Tj=Tc+(Ptot*Rθjc), Tc represents the case temperature obtained from the above measurement, Ptot represents the total power consumption of the load, and Rθjc represents the junction-to-case thermal resistance provided in the load datasheet.

[0136] The total power dissipation of the load is the sum of conduction losses and switching losses. Load manufacturers typically provide curves or tables of single-cycle switching energy (turn-on energy Eon, turn-off energy Eoff) under specific test conditions (e.g., specific drain-source voltage Vds, collector-emitter voltage Vce, drain current Id, collector current Ic, gate-source voltage Vgs, base-emitter voltage Vge, junction temperature Tj, gate resistance Rg, etc.).

[0137] Based on the actual operating conditions (bus voltage, load current, drive resistance, junction temperature), approximate Eon and Eoff' are obtained by interpolation on the curve. Then, the switching loss P_sw = (Eon + Eoff) * f is calculated. sw .

[0138] Conversion efficiency can be obtained by calculating the ratio of output power to input power.

[0139] In an optional embodiment, the execution result data includes the junction temperature and conversion efficiency of the load, and adjusting the adjustment strategy based on the execution result data includes:

[0140] When the junction temperature is greater than the preset temperature, the switching frequency in the regulation strategy is reduced and the operating mode is switched to thermal balance mode.

[0141] If the conversion efficiency is less than the preset efficiency, adjust the PWM duty cycle in the adjustment strategy or switch the operating mode to DC-DC topology mode.

[0142] In some embodiments, if the junction temperature exceeds a safety threshold (e.g., 120°C), the switching frequency is reduced and a thermal equilibrium mode is triggered (the load is transferred to a device with a lower temperature). If the conversion efficiency is lower than a preset efficiency (e.g., 90%), the PWM duty cycle is dynamically adjusted or the DC-DC topology mode is switched.

[0143] The inverter control method proposed in this application employs a dynamic power consumption adjustment mechanism through collaborative design of the hardware and algorithm layers. The hardware layer utilizes a low-power DC-DC converter and an adaptive PWM drive circuit to adjust the switching frequency and conduction losses in real time according to the load status. The algorithm layer introduces a load prediction model to dynamically switch the inverter's operating mode (such as light-load energy-saving mode and full-load high-efficiency mode). By dynamically optimizing hardware parameters and linking algorithmic decisions, the contradiction between standby power consumption and efficiency is resolved.

[0144] A user electricity consumption behavior prediction model is built based on an LSTM neural network. By combining historical electricity consumption data (such as time periods and power fluctuations) and weather forecast information, a dynamic inverter control strategy is generated. For example, when a user preheats domestic hot water before getting out of bed, the inverter output power is adjusted in advance to match the load demand. This algorithm achieves localized learning through edge computing, avoiding cloud dependence and solving the real-time response problem in dynamic electricity consumption scenarios.

[0145] The inverter operates in three modes: "intelligent sleep," "dynamic follow," and "peak optimization." When there is no load, it enters sleep mode, maintaining only basic communication functions. Under low load conditions, it uses dynamic follow mode to match the load power curve. Under high load conditions or grid fluctuations, it activates peak optimization mode, combining with the energy storage system to smooth power fluctuations. This strategy achieves a balance between power consumption and efficiency across the entire load range through seamless switching between modes.

[0146] Exemplary device

[0147] Accordingly, this application also provides a control device for an inverter, including:

[0148] The acquisition unit is used to acquire multi-source heterogeneous data that affects load power demand.

[0149] The prediction unit is used to predict load demand data within a preset time period based on the multi-source heterogeneous data;

[0150] The determining unit is used to determine the inverter's adjustment strategy based on the load demand data and / or the multi-source heterogeneous data;

[0151] A control unit is configured to adjust the inverter according to the adjustment strategy so that the output power of the inverter meets the requirements of the load.

[0152] The inverter control device provided in this embodiment belongs to the same concept as the inverter control method provided in the above embodiments of this application. It can execute the method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the specific processing content of the inverter control method provided in the above embodiments of this application, and will not be repeated here.

[0153] The functions implemented by each unit in the control device of the inverter described above can be implemented by the same or different processors, and this application embodiment does not limit this.

[0154] It should be understood that each unit in the above device can be implemented by a processor calling software. For example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of each unit in the device. The processor can be a general-purpose processor, such as a CPU or microprocessor, and the memory can be internal or external to the device. Alternatively, the units in the device can be implemented as hardware circuits. By designing the hardware circuits, some or all of the unit functions can be implemented. The hardware circuits can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are implemented by designing the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a PLD, such as an FPGA, which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files to implement the functions of some or all of the above units. All units in the above device can be implemented entirely by a processor calling software, entirely by hardware circuits, or partially by a processor calling software with the remaining parts implemented by hardware circuits.

[0155] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, microprocessor, GPU, or DSP. In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented as an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to implement the functions of some or all of the above units. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, or DPU.

[0156] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0157] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a System-on-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0158] Exemplary electronic devices

[0159] Another embodiment of this application also provides an electronic device, see [link to relevant documentation] Figure 2 As shown, the device includes:

[0160] Memory 200 and processor 210;

[0161] The memory 200 is connected to the processor 210 and is used to store programs;

[0162] The processor 210 is used to implement the inverter control method disclosed in any of the above embodiments by running the program stored in the memory 200.

[0163] Specifically, the control equipment of the inverter may also include: a bus, a communication interface 220, an input device 230, and an output device 240.

[0164] The processor 210, memory 200, communication interface 220, input device 230, and output device 240 are interconnected via a bus. Among them:

[0165] A bus can include a pathway for transmitting information between various components of a computer system.

[0166] The processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0167] Processor 210 may include a main processor, as well as a baseband chip, modem, etc.

[0168] The memory 200 stores a program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0169] Input device 230 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0170] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0171] The communication interface 220 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0172] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the various steps of any inverter control method provided in the above embodiments of this application.

[0173] Exemplary computer program products and storage media

[0174] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the inverter control methods according to various embodiments of this application as described in any of the foregoing embodiments of this specification.

[0175] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0176] Furthermore, embodiments of this application may also be storage media storing a computer program, which is executed by a processor through steps in the inverter control method according to various embodiments of this application described above. Specifically, the following steps can be implemented:

[0177] Acquire multi-source heterogeneous data that affects load power demand;

[0178] Based on the multi-source heterogeneous data, predict the load demand data within a preset time period;

[0179] The inverter regulation strategy is determined based on the load demand data and / or the multi-source heterogeneous data.

[0180] The inverter is adjusted according to the adjustment strategy so that the output power of the inverter meets the requirements of the load.

[0181] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0182] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0183] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.

[0184] The modules and sub-modules in the apparatus and terminal in the various embodiments of this application can be merged, divided, and deleted according to actual needs.

[0185] It should be understood that the disclosed terminals, devices, and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the terminal embodiments described above are merely illustrative. For instance, the division of modules or sub-modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0186] The modules or submodules described as separate components may or may not be physically separate. The components that constitute a module or submodule may or may not be physical modules or submodules; that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules can be selected to achieve the purpose of this embodiment's solution, depending on actual needs.

[0187] Furthermore, the functional modules or sub-modules in the various embodiments of this application can be integrated into one processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into one module. The integrated modules or sub-modules described above can be implemented in hardware or in the form of software functional modules or sub-modules.

[0188] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0189] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0190] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0191] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A control method for an inverter, characterized in that, include: Acquire multi-source heterogeneous data that affects load power demand; Based on the multi-source heterogeneous data, predict the load demand data within a preset time period; The inverter regulation strategy is determined based on the load demand data and / or the multi-source heterogeneous data. The inverter is adjusted according to the adjustment strategy so that the output power of the inverter meets the requirements of the load.

2. The method according to claim 1, characterized in that, Determining the inverter's adjustment strategy based on the load demand data includes: Determine the dynamic change category to which the load demand data belongs; When the dynamic change category is short-term fluctuation, the adjustment strategy includes at least one of the following: increasing the switching frequency of the inverter, switching the DC-DC topology mode to a specified topology, and increasing the power factor of the inverter; When the dynamic change category is a long-term trend, the adjustment strategy includes at least one of the following: switching to the working mode corresponding to the working time period of the inverter, and adjusting the electronic components of the inverter according to the load demand data.

3. The method according to claim 1, characterized in that, The multi-source heterogeneous data includes the current operating power of the load; Based on the aforementioned multi-source heterogeneous data, the inverter's regulation strategy is determined, including: The load rate of the load is determined based on the current operating power and the maximum operating power of the load. When the load rate is less than a first preset value, the adjustment strategy includes at least one of the following: turning off the redundant power transistors in the inverter, starting the synchronous rectification topology, and controlling the inverter to switch to sleep mode; When the load rate is less than a second preset value and greater than the first preset value, the adjustment strategy includes at least one of the following: reducing the switching frequency of the inverter to a first specified frequency, and activating soft switching; When the load rate is greater than the second preset value, the adjustment strategy includes: increasing the switching frequency of the inverter to a second specified frequency; Wherein, the first specified frequency is less than the second specified frequency, and the second preset value is greater than the first preset value.

4. The method according to claim 1, characterized in that, Based on the load demand data and the multi-source heterogeneous data, the inverter adjustment strategy is determined, including: The load demand data and the multi-source heterogeneous data are used to determine the inverter's operating mode; The control strategy corresponding to the operating mode is determined to be the adjustment strategy.

5. The method according to claim 1, characterized in that, After adjusting the inverter according to the aforementioned adjustment strategy, the process further includes: Obtain the execution result data of the load after the adjustment strategy is executed; The adjustment strategy is adjusted based on the execution result data.

6. The method according to claim 5, characterized in that, The execution result data includes the load's junction temperature and conversion efficiency. Adjusting the regulation strategy based on the execution result data includes: When the junction temperature is greater than the preset temperature, the switching frequency in the regulation strategy is reduced and the operating mode is switched to thermal balance mode. If the conversion efficiency is less than the preset efficiency, adjust the PWM duty cycle in the adjustment strategy or switch the operating mode to DC-DC topology mode.

7. The method according to claim 1, characterized in that, Based on the multi-source heterogeneous data, load demand data within a preset time period is predicted, including: The multi-source heterogeneous data is input into a pre-trained prediction model, and the load demand data is output through the prediction model. The prediction model is obtained by training on electricity consumption behavior based on sample running data and user behavior data.

8. A control device for an inverter, characterized in that, include: The acquisition unit is used to acquire multi-source heterogeneous data that affects load power demand. The prediction unit is used to predict load demand data within a preset time period based on the multi-source heterogeneous data; The determining unit is used to determine the inverter's adjustment strategy based on the load demand data and / or the multi-source heterogeneous data; A control unit is configured to adjust the inverter according to the adjustment strategy so that the output power of the inverter meets the requirements of the load.

9. An electronic device, characterized in that, Including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the inverter control method as described in any one of claims 1 to 7 by running the program in the memory.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the inverter control method as described in any one of claims 1 to 7.

Images