Energy regulation and control method, system, equipment and program product

Abstract

The invention relates to the technical field of energy, in particular to an energy regulation and control method, system and device and a program product. The method comprises the following steps: acquiring vehicle end data related to a vehicle in a vehicle-to-home system, and acquiring home data related to home equipment in the vehicle-to-home system; on the basis of the vehicle end data, predicting vehicle end demand electric quantity required by vehicle traveling; based on the household data, predicting household required electric quantity required for operating household equipment; based on the vehicle end demand electric quantity and the family demand electric quantity, an equipment control instruction of the family equipment is generated, the equipment control instruction is used for controlling the running state of the family equipment, and the vehicle provides electric energy for running of the family equipment. According to the invention, vehicle end requirements and family requirements are effectively balanced, fine management is carried out on operation of family equipment, and the energy utilization efficiency from the vehicle to the family system is improved.

Description

Technical Field

[0001] This application relates to the field of energy technology, specifically to an energy regulation method, system, equipment, and program product. Background Technology

[0002] With the rapid development of electric vehicles (EVs) and energy internet technologies, vehicle-to-home (V2H) technology has become an important direction in the fields of smart grids and smart energy. V2H technology uses vehicle batteries as distributed energy storage units to achieve two-way interaction between vehicle and home energy systems: during off-peak hours, vehicles can connect to the grid for charging; during peak hours or when there is a power outage at home, the vehicle battery directly supplies power to the home, alleviating grid pressure and improving energy self-sufficiency. However, traditional V2H applications largely rely on grid coordination and are centered solely on household electricity demand, lacking refined management of vehicle battery discharge strategies. This leads to problems such as a significant risk of reduced vehicle range and potential for unreasonable energy distribution. Summary of the Invention

[0003] Based on the deficiencies and shortcomings of the existing technology, this application proposes an energy regulation method, system, equipment and program product that effectively balances vehicle-side demand and household demand, performs refined management of the operation of household equipment, and improves the energy utilization efficiency of the vehicle-to-home system.

[0004] According to a first aspect of this application, an energy regulation method is provided, comprising: acquiring vehicle-side data related to a vehicle in a vehicle-to-home system, and acquiring home data related to home devices in the vehicle-to-home system; predicting the vehicle-side power demand required for the vehicle to travel based on the vehicle-side data; predicting the home power demand required to operate the home devices based on the home data; and generating device control instructions for the home devices based on the vehicle-side power demand and the home power demand, wherein the device control instructions are used to control the operating state of the home devices, and the vehicle provides power for the operation of the home devices.

[0005] According to the energy regulation method provided in the first aspect of this application, the step of generating device control instructions for the home devices based on the vehicle-side power demand and the household power demand includes: generating operating strategies for the home devices at different priorities based on the vehicle-side power demand and the household power demand, wherein the higher the priority of the home device, the fewer the adjustable operating parameters of the home device; and generating device control instructions corresponding to each of the home devices based on the operating strategies.

[0006] According to the energy regulation method provided in the first aspect of this application, the vehicle-to-home system further includes an energy storage battery; the step of generating device control instructions for the home devices based on the vehicle's power demand and the home's power demand includes: calculating the vehicle's available power based on the vehicle's remaining power and the vehicle's power demand in the vehicle data; if the vehicle's available power is less than the home's power demand, generating a battery activation instruction for the energy storage battery, wherein the battery activation instruction is used to control the energy storage battery to provide power to the home devices; and generating the device control instructions for the home devices based on the energy storage battery's battery power.

[0007] According to the energy regulation method provided in the first aspect of this application, the vehicle-side data includes a historical vehicle-side data sequence within a historical time period; the step of predicting the vehicle-side electricity demand required for the vehicle trip based on the vehicle-side data includes: inputting the historical vehicle-side data sequence into a pre-trained vehicle demand prediction model, and having the vehicle demand prediction model output the vehicle-side electricity demand within the prediction time period, wherein the vehicle demand prediction model is trained on the basis of a long short-term memory network architecture.

[0008] According to the energy regulation method provided in the first aspect of this application, the step of predicting the household electricity demand required to operate the household equipment based on the household data includes: inputting the household data into a pre-trained household demand prediction model, and having the household demand prediction model output the household electricity demand of the household equipment during the prediction period, wherein the household demand prediction model is trained on an extreme gradient boosting tree architecture.

[0009] According to the energy regulation method provided in the first aspect of this application, after generating the device control instructions corresponding to each of the household devices based on the operating strategy, the method further includes: obtaining actual operating data of the household devices operating based on the device control instructions; adjusting the operating strategy based on the data deviation between the operating strategy and the actual operating data; and regenerating new device control instructions corresponding to each of the household devices based on the adjusted operating strategy.

[0010] According to the energy regulation method provided in the first aspect of this application, the vehicle-side data includes vehicle-side battery data, vehicle trip data, and / or vehicle-side load data; the household data includes device priority data, device operation data, device environment data, and user personalized operation data.

[0011] According to a second aspect of this application, a vehicle-to-home system is provided, comprising a vehicle and home appliances, wherein the vehicle provides electrical energy for the operation of the home appliances; the vehicle is configured to acquire vehicle-side data related to the vehicle in the vehicle-to-home system, and acquire home data related to the home appliances in the vehicle-to-home system, predict the vehicle-side power demand required for the vehicle's travel based on the vehicle-side data, predict the home power demand required for the operation of the home appliances based on the home data, and generate device control instructions for the home appliances based on the vehicle-side power demand and the home power demand; the home appliances are configured to adjust their operating state based on the device control instructions.

[0012] According to a third aspect of this application, an electronic device is provided, comprising: a memory and a processor; the memory being connected to the processor for storing a program; the processor being configured to implement the vehicle-to-home method as described in the first aspect by running the program in the memory.

[0013] According to a fourth aspect of this application, a computer program product is provided, including computer program instructions; said computer program instructions, when executed by a processor, cause the processor to perform the vehicle-to-home method as described in the first aspect.

[0014] This application acquires vehicle-side data related to the vehicle within a vehicle-to-home system, as well as household data related to household devices within the same system. Based on the vehicle-side data, it predicts the vehicle's power demand for travel. Based on the household data, it predicts the household power demand for operating the household devices. Based on both vehicle and household power demands, it generates device control commands for the household devices, whereby the device control commands control the operating status of the household devices, with the vehicle providing power to the devices. By processing the vehicle and household data separately, predicting the vehicle and household power demands respectively, and controlling the operating status of the household devices based on these demands, the application effectively balances vehicle and household needs, preventing issues such as insufficient vehicle range or excessive battery discharge. This achieves refined adjustments to the vehicle-to-home system and improves its energy efficiency. Attached Figure Description

[0015] 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.

[0016] Figure 1This is a schematic flowchart of a vehicle-to-home method provided in an embodiment of this application.

[0017] Figure 2 A block diagram of a vehicle-to-home device provided in an embodiment of this application.

[0018] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] 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.

[0020] Application Overview Further analysis of the problems existing in the V2H scenario in the current technology.

[0021] First, there is a conflict over energy allocation.

[0022] Traditional V2H technology focuses solely on household electricity demand, and excessive discharge can lead to accelerated vehicle battery wear or insufficient driving range for subsequent trips. Furthermore, in scenarios without a power grid, the linkage strategy between household devices and vehicle batteries is crude and cannot balance the dual goals of "household power saving" and "vehicle range assurance".

[0023] Second, dynamic prediction and real-time control are lacking.

[0024] The lack of accurate forecasting of future vehicle power demand leads to a disconnect between vehicle power dissipation plans and travel plans; the adjustment of home appliances relies on manual intervention and cannot automatically optimize operating modes based on the real-time status of the vehicle.

[0025] Third, multi-energy synergy is inefficient.

[0026] The lack of a coordinated scheduling mechanism between vehicle batteries, configurable home energy storage batteries, and home appliances results in low energy utilization. In grid-free scenarios, household electricity consumption relies entirely on vehicle batteries, which can easily lead to energy shortages or forced shutdowns of equipment due to sudden high energy demands such as prolonged operation of water heaters.

[0027] Fourth, the challenge of balancing device lifespan with user experience.

[0028] Traditional strategies do not dynamically adjust the vehicle battery discharge strategy based on the vehicle's State of Health (SOH), which accelerates battery aging with long-term use; when user comfort conflicts with energy-saving goals, there is a lack of adaptive optimization mechanisms, resulting in high resistance to strategy implementation.

[0029] Exemplary methods To address the problems existing in current vehicle-to-home (V2H) technology, this application provides an energy regulation method that can be implemented in the form of a software algorithm. In real time, the software algorithm of this method can run on any device with data processing capabilities, such as a vehicle local controller, a cloud server, or a smart mobile device. The scope of protection of this application is not limited to the type of device on which the software algorithm of this method is implemented.

[0030] In one embodiment, such as Figure 1 As shown, the process steps for implementing the energy regulation method include: Step 101: Obtain vehicle-related data in the vehicle-to-home system, and obtain home data related to home devices in the vehicle-to-home system.

[0031] In this embodiment, the vehicle-to-home (V2H) system includes a vehicle and home appliances. The vehicle includes an onboard battery that provides power to the vehicle; simultaneously, in the V2H system, the onboard battery in the vehicle can provide power to the home appliances. Vehicle-side data refers to various data related to the vehicle, such as battery state of charge (SOC), battery state of health (SOH), battery temperature, available charge / discharge power, and other onboard battery-related data; vehicle trip data such as vehicle driving mode, vehicle historical trips, and vehicle planned trips; and vehicle load data such as the load power of the vehicle's air conditioning, vehicle lights, and vehicle entertainment system.

[0032] In this embodiment, household appliances refer to electrical equipment used in a home, such as air conditioners, refrigerators, washing machines, microwave ovens, ovens, water heaters, and lighting fixtures. In a vehicle-to-home system, there are generally multiple household appliances, the specific types and quantities of which are determined based on actual circumstances. Household data refers to data related to household appliances, such as pre-configured device priorities, power consumption, operating modes, and set parameters for each appliance, environmental data related to the appliance's location (temperature, humidity, light intensity, weather conditions, etc.), and user preferences for personalized settings of each appliance.

[0033] In this embodiment, different types of data are stored in a reasonable manner. For example, vehicle data is stored in the form of SOC and SOH curves (timestamp + SOC value + SOH value) and charge / discharge records (timestamp + charge amount + discharge amount). Home data is stored in the form of device operation logs (timestamp + device ID + power + operating mode) and environmental data (timestamp + room temperature + humidity + light intensity). Both vehicle-side data and home data can be stored locally on the vehicle or in the cloud, depending on the actual situation and needs. For example, vehicle storage uses solid-state drives (SSDs) to store key data (permanently saved) and supports daily or monthly backups to the local storage; cloud storage uses encrypted uploads to a cloud server (requiring user authorization) and supports cross-device data synchronization (e.g., viewing via a mobile app).

[0034] Step 102: Based on vehicle-side data, predict the vehicle-side power demand required for vehicle travel.

[0035] In this embodiment, when the vehicle provides power to household devices via its onboard battery, the maximum power the vehicle can provide is fixed, and the onboard battery also needs to provide power for vehicle travel. If all the maximum power the vehicle can provide is supplied to household devices, it could easily lead to insufficient range for subsequent trips, and excessive discharge of the onboard battery could also easily exacerbate battery degradation. Therefore, based on vehicle-side data, the required power demand for travel is predicted in advance, and a rigid constraint is established to ensure the vehicle's range, avoiding the problem of household device power consumption preventing the vehicle's basic travel functions from being implemented.

[0036] Step 103: Based on household data, predict the household electricity demand required to operate household appliances.

[0037] In this embodiment, household appliance power consumption can be predicted in advance based on household data. Household power demand refers to the total power required for the operation of all household appliances. For some household appliances, such as air conditioners and water heaters, their operating status can be adjusted according to actual conditions and needs, thereby adjusting power consumption. Predicting the household appliance power demand in advance allows for better control of the operating status of each household appliance based on the effective power provided by the vehicle.

[0038] Step 104: Based on the vehicle's power demand and the household's power demand, generate device control instructions for the household devices. The device control instructions are used to control the operating status of the household devices, and the vehicle provides power for the operation of the household devices.

[0039] In this embodiment, the maturity of Internet of Things (IoT) technology provides a technological foundation for deep integration between vehicles and home devices. The vehicle, acting as a mobile "IoT platform," can acquire real-time vehicle data and home device data through communication modules such as onboard sensors, a Battery Management System (BMS), a Telematics Box (T-BOX), and 5G-C-V2X (5th Generation Mobile Communication Technology). This allows for localized decision-making through edge computing. Based on IoT technology, a bidirectional energy interaction control scheme between the vehicle and home devices is implemented, dynamically adjusting the operating status of the home devices.

[0040] In this embodiment, based on the vehicle's and household's power demand, device control commands are generated for each household device, flexibly adjusting their operating status. While ensuring vehicle range, this flexible energy allocation avoids energy waste and excessive consumption, improving energy efficiency.

[0041] In one embodiment, device control instructions for home devices are generated based on the vehicle's power demand and the household's power demand. This includes: generating operating strategies for home devices at different priorities based on the vehicle's power demand and the household's power demand, wherein the higher the priority of a home device, the fewer adjustable operating parameters it has; and generating device control instructions for each home device based on the operating strategies.

[0042] In this embodiment, priorities are pre-configured for multiple home devices, with higher priorities allowing for more adjustable operating parameters. When generating operating strategies for each home device based on the vehicle's and home's power demands, the strategies are dynamically adjusted according to the priorities. Each home device's operating strategy includes controlling one or more parameters such as whether the device is running, its operating mode, and real-time operating parameters. Optionally, priorities can be flexibly set based on user comfort needs, safety requirements, and specific device parameters.

[0043] For example, all household appliances are divided into three priority levels, corresponding to critical loads, adjustable loads, and non-essential loads, respectively. Critical loads have higher priority than adjustable loads, and adjustable loads have higher priority than non-essential loads. While ensuring vehicle range, if the power provided by the vehicle is sufficient to meet the operational needs of all household appliances, each appliance can operate according to its actual situation and requirements. If the power provided by the vehicle is insufficient to meet the operational needs of all household appliances, the power supply to each priority level is flexibly adjusted. Priority is given to ensuring the basic power consumption of critical loads such as refrigerators and security equipment, while limiting the power of non-critical loads such as air conditioners and water heaters. Non-essential loads such as washing machines and landscape lighting can also be shut down. This tiered and refined strategy for controlling the operation of household appliances not only ensures vehicle range but also minimizes the impact of insufficient power on user comfort and safety, thereby improving energy efficiency.

[0044] In this embodiment, "vehicle range assurance" serves as a constraint, and each household device is subject to tiered control, with separate operating strategies for each device. Specifically, available vehicle power = remaining vehicle power - required vehicle power (e.g., if remaining vehicle power SOC = 70% and required vehicle power SOC = 25%, then available vehicle power = 45%). Based on available vehicle power and the overall efficiency of household devices (e.g., energy storage battery conversion efficiency 90%), the maximum effective power available to household devices is calculated (e.g., 45% × 90% = 40.5%). For critical loads (e.g., refrigerator), a minimum operating power threshold is set (e.g., 50W to ensure basic cooling); for adjustable loads (e.g., air conditioner), a maximum operating power threshold is set (e.g., 1.5kW to limit redundant energy consumption); for non-essential loads (e.g., washing machine), operating condition thresholds are set (e.g., allowing startup only when available vehicle power > 60%).

[0045] In this embodiment, executable device control commands are generated based on the respective operating strategies of each household appliance. Specifically, for the optimized operating mode strategy for critical loads, the device control commands are used to adjust the refrigerator compressor start-stop cycle (e.g., extending it from 30 minutes to 60 minutes), reduce the average power (e.g., from 50W to 30W), and ensure that the adjusted power is not lower than the minimum threshold (e.g., ≥30W). For the dynamic power adjustment strategy for adjustable loads, the device control commands are used to dynamically adjust operating parameters according to available power (e.g., raising the air conditioner temperature by 2°C, power from 1.5kW to 1.2kW; lowering the target water temperature of the water heater from 60°C to 50°C, power from 2kW to 1.5kW); simultaneously, power is allocated according to the user's historical usage frequency (high-frequency devices are prioritized, e.g., air conditioner > water heater). For the delayed operation strategy for non-essential loads, the device control commands are used to control household appliances to start only when there is sufficient available power (e.g., allowing the washing machine to run when available power is >60%, otherwise delaying it until the vehicle is offline).

[0046] In this embodiment, after generating the operating strategies for each device, the operating strategies can be verified. Specifically, device health data (such as air conditioner minimum temperature ≥16℃), user comfort thresholds (temperature adjustment range ≤±2℃), and other information are predetermined. The system then calculates whether the total power consumption of the household devices after adjustment is ≤ the available power at the vehicle end (e.g., if the predicted total power consumption after adjustment is 2.5kW, and the available power at the vehicle end corresponds to a power of 1.125kW / h, then the adjustable load power needs to be reduced). Equipment health Verification and inspection of control policies Check if the temperature exceeds the equipment's allowable range (e.g., air conditioner minimum temperature ≥ 16℃). Perform user comfort verification, and evaluate the impact of the strategy on user comfort using a reinforcement learning model (e.g., if the temperature adjustment range is ≤ ±2℃, the verification is passed).

[0047] In this embodiment, the operating strategy is translated into specific device control commands to drive home devices to operate in optimized mode and provide feedback on the command execution results. Specifically, the operating strategy (e.g., "air conditioner set temperature 28℃") is converted into device control commands that home devices can recognize (e.g., "0x01 0x28" in Zigbee indicates temperature setting), and the transmission order of multiple device control commands is allocated according to device priority (critical loads are sent first, and non-essential load commands (e.g., washing machine) are sent last to avoid communication conflicts. If a device control command fails to be sent (e.g., device offline), it will automatically retry 3 times within 30 seconds. It supports multi-protocol compatibility (e.g., Zigbee 3.0, Bluetooth Mesh), adapts to different brands of home devices, and uses reasonable methods to communicate with various home devices. For example, it sends device control commands directly to smart devices through local IoT protocols (e.g., Zigbee 3.0). After receiving the device control commands, the smart devices adjust their operating status (e.g., air conditioner from 26℃ to 28℃) and collect actual operating data (current power, temperature) in real time through sensors for feedback. Older devices are controlled through smart socket relay (e.g., turning off the socket power to limit heating). The actual operating data of household appliances is transmitted back once per second (e.g., air conditioner power 1.0kW, water heater power 0W); the execution effect of the device control command is evaluated once every 5 minutes, comparing the actual operating data with the strategy target (e.g., the strategy requires the air conditioner power to be 1.2kW, but the actual power is 1.15kW), and calculating the "strategy execution deviation". If the deviation exceeds the threshold, the strategy correction is triggered.

[0048] In one embodiment, the vehicle-to-home system also includes an energy storage battery.

[0049] Based on the vehicle's power demand and the household's power demand, device control instructions for household devices are generated, including: calculating the available power on the vehicle based on the vehicle's remaining power and the vehicle's power demand data; if the available power on the vehicle is less than the household's power demand, generating a battery activation instruction for the energy storage battery, wherein the battery activation instruction is used to control the energy storage battery to provide power to the household devices; and generating device control instructions for the household devices based on the energy storage battery's battery level.

[0050] In this embodiment, a storage battery can be configured in the vehicle-to-home system, serving as a buffer layer between the vehicle and home devices. Vehicle data includes the vehicle's remaining battery power, which refers to the maximum amount of power the onboard battery can actually provide. The difference between the vehicle's remaining battery power and the required battery power is calculated as the available battery power, i.e.: Available power on the vehicle = Remaining power on the vehicle - Power required on the vehicle.

[0051] The available power at the vehicle end represents the maximum power the vehicle can provide to household devices. Comparing the available power at the vehicle end with the household's power demand, if the available power is greater than or equal to the demand, it indicates that the vehicle can provide enough power to meet the basic travel needs of all household devices, and the vehicle can directly supply power to each device. If the available power is less than the demand, it means that the vehicle, constrained by the basic range requirement, cannot provide sufficient power to all household devices. In this case, a battery activation command is used to activate the energy storage battery, which then supplies power to each household device, ensuring their normal operation. The energy storage battery does not participate in the energy regulation process as a buffer. Furthermore, the maximum power provided by the energy storage battery is still limited. Based on the battery's charge level, device control commands can be generated to flexibly adjust the operating status of household devices. For example, based on the priority of each household device, higher-priority devices can be prioritized for normal operation, thereby improving energy efficiency and ensuring a better and safer service experience for household devices under limited power conditions.

[0052] In one embodiment, device control instructions for home devices are generated based on the vehicle's power demand and the household's power demand, including: calculating the vehicle's available power based on the vehicle's remaining power and the vehicle's power demand in the vehicle data; if the vehicle's available power is less than the household's power demand, adjusting the operating status of the home devices under each priority based on their respective priorities.

[0053] In this embodiment, the lower the priority of a household device, the more adjustable operating parameters it has. Given the limited available power at the vehicle end, by adjusting these operating parameters, the power consumption of even lower-priority household devices is reduced first, achieving dynamic energy regulation and improving energy efficiency.

[0054] In one embodiment, the vehicle-side data includes a sequence of historical vehicle-side data within a historical time period.

[0055] Based on vehicle-side data, predict the vehicle-side electricity demand required for vehicle travel, including: inputting historical vehicle-side data sequences into a pre-trained vehicle demand prediction model, and outputting the vehicle-side electricity demand of the vehicle during the prediction period by the vehicle demand prediction model, wherein the vehicle demand prediction model is trained on the basis of a long short-term memory network architecture.

[0056] In this embodiment, the vehicle's electricity demand can be predicted using a vehicle demand prediction model based on historical vehicle data sequences. The historical period can be a pre-defined time period, such as the past 30 days. The historical vehicle data sequence consists of vehicle data from the past 30 days, including travel time, travel distance, driving mode, and other historical travel data. The vehicle demand prediction model trained on a Long Short-Term Memory (LSTM) network architecture is more suitable for time series prediction, thus making the predicted vehicle electricity demand more accurate.

[0057] In this embodiment, the vehicle demand prediction model outputs the vehicle's battery power demand during the prediction period, which is a period determined during the model training phase, for example, the next 24 hours. Optionally, the vehicle demand prediction model outputs the vehicle travel probability and vehicle battery power demand during the prediction period. For example, the prediction result includes a travel probability of 85% from 18:00 to 19:00, corresponding to a vehicle battery SOC ≥ 25%.

[0058] In this embodiment, the vehicle demand prediction model is continuously optimized by updating historical data and learning user behavior. Specifically, the continuously collected vehicle-side data and predicted vehicle-side power demand are constantly updated as the vehicle-side training sample data used to train the vehicle demand prediction model. Based on the continuously updated vehicle-side training sample data, the vehicle demand prediction model is continuously trained and optimized. In addition, personalized user historical operations (such as "always turn on the air conditioner at 7 pm" and "use the water heater on weekend mornings") are analyzed through clustering algorithms to extract personalized preferences (such as "elderly user mode: air conditioner temperature not lower than 26℃"). The comfort boundary is continuously updated, that is, the number and direction of the user's manual intervention strategy are recorded (such as the user repeatedly raising the air conditioner temperature), and the "comfort threshold" is dynamically adjusted (such as expanding the allowable temperature fluctuation range from ±2℃ to ±3℃).

[0059] Of course, based on vehicle-side data, other types of intelligent models or other prediction methods can be used to predict the vehicle's electricity demand for travel.

[0060] In one embodiment, predicting the household electricity demand required to operate household appliances based on household data includes: inputting household data into a pre-trained household demand prediction model, and having the household demand prediction model output the household electricity demand of household appliances during the prediction period, wherein the household demand prediction model is trained on an extreme gradient boosting tree architecture.

[0061] In this embodiment, the household data includes various types of data corresponding to multiple household devices. To improve the accuracy of household demand data prediction, an intelligent model prediction method is also adopted. Specifically, the household demand prediction model is trained on the basis of the extreme gradient boosting (XGBoost) architecture, which is more suitable for multi-feature regression prediction.

[0062] In this embodiment, the household demand forecasting model outputs the household electricity demand for household appliances within a forecast period. The forecast period is determined during the model training phase, for example, the forecast period is the next 24 hours. Optionally, the household electricity demand can be expressed as a household electricity load curve. For example, the household electricity demand is a household electricity load curve for the next 24 hours, with a time granularity of 15 minutes. The total electricity load within any time granularity can be determined from this household electricity load curve, for example, the total load from 18:00 to 18:15 is 2.5kW.

[0063] In this embodiment, the household demand prediction model is continuously optimized by updating historical data and learning user behavior. Specifically, the continuously collected household data and predicted household electricity demand are constantly updated as the household training sample data used to train the household demand prediction model. Based on the continuously updated household training sample data, the household demand prediction model is continuously trained and optimized. In addition, personalized user historical operations (such as "always turn on the air conditioner at 7 pm" and "use the water heater on weekend mornings") are analyzed through clustering algorithms to extract personalized preferences (such as "elderly user mode: air conditioner temperature not lower than 26℃"). The comfort boundary is continuously updated, that is, the number and direction of the user's manual intervention strategy are recorded (such as the user repeatedly raising the air conditioner temperature), and the "comfort threshold" is dynamically adjusted (such as expanding the allowable temperature fluctuation range from ±2℃ to ±3℃).

[0064] In one embodiment, after generating device control instructions for each home device based on the operating strategy, the method further includes: obtaining actual operating data of the home devices based on the device control instructions; adjusting the operating strategy based on the data deviation between the operating strategy and the actual operating data; and regenerating new device control instructions for each home device based on the adjusted operating strategy.

[0065] In this embodiment, after regulating the working status of each household device through device control commands, the real-time operating status of each household device can also be detected in real time, actual operating data can be collected, and compared with the initially determined operating strategy to determine whether there is a large deviation between the actual operating status of each household device and the expected operating status in the operating strategy. If there is a large deviation, the operating strategy is adjusted, new device control commands are regenerated, and dynamic regulation of household electricity consumption is achieved, further improving the energy regulation effect.

[0066] In one embodiment, vehicle-side data includes vehicle-side battery data, vehicle trip data, and / or vehicle-side load data; home-side data includes device priority data, device operation data, device environment data, and user-personalized operation data.

[0067] In this embodiment, various types of vehicle-side data can be collected and processed in appropriate ways. For example, vehicle-side battery data (such as SOC, SOH, battery temperature, available charge / discharge power, etc.) can be obtained through the vehicle's built-in BMS (Battery Management System) interface (such as CAN bus); vehicle trip data (such as destination distance, estimated departure / arrival time, driving mode, etc.) can be obtained through the vehicle navigation system (such as GPS or BeiDou Navigation Satellite System); and vehicle-side load data (such as the power of loads such as air conditioning, headlights, and entertainment systems) can be monitored through vehicle sensors (such as current / voltage sensors).

[0068] Furthermore, when collecting various vehicle-side data, the vehicle's hardware devices are used appropriately. For example, the vehicle's BMS interface uses a CAN bus (ISO 11898 standard) to connect to the vehicle battery, supporting real-time acquisition of SOC (range 0-100%), SOH (range 0-100%), battery temperature (range -40℃-85℃), and available charge / discharge power (range 0-100kW). The navigation module uses an integrated high-precision Global Positioning System (GPS) or Beidou chip (positioning accuracy ≤2.5m) to support the acquisition of vehicle trip data (destination coordinates, estimated travel time, driving mode). The vehicle power consumption monitoring unit uses deployed current and voltage sensors (accuracy ±0.5%) to monitor the real-time power of the vehicle's air conditioning (power range 500W-3kW), headlights (power range 20W-100W), and entertainment system (power range 10W-50W).

[0069] Furthermore, the collection frequency of various vehicle-side data can be determined according to actual conditions and needs. For example, vehicle-side battery data can be collected and updated once per second, vehicle-side trip data can be collected and updated once every 30 seconds, and vehicle-side load data can be collected and updated twice per second. Optionally, after initially collecting the raw vehicle-side data, a data preprocessing scheme can be adopted, such as filtering outliers (e.g., SOC mutation > 5% / s), to obtain vehicle-side data of higher quality.

[0070] In this embodiment, data collection and processing can be carried out in a reasonable manner for various types of household devices. For example, the priority of each household device can be marked by preset rules (e.g., critical loads: refrigerator, security system; adjustable loads: air conditioner, water heater; non-essential loads: washing machine, landscape lighting). A smart sensor network (e.g., Zigbee smart sockets, device status monitors) is deployed to collect device operating data (e.g., power, operating mode, set parameters). Environmental sensors (temperature, humidity, light sensors) are used to obtain environmental data (e.g., room temperature, humidity, light intensity). Weather forecast data (e.g., temperature, precipitation probability) can also be obtained through network communication devices to correct household electricity demand forecasts. By recording user historical operations (e.g., air conditioner temperature setting habits, water heater usage periods), user preferences (e.g., cold tolerance / cold sensitivity, energy-saving sensitivity) are analyzed to obtain personalized user operation data. The data collection frequency for various household devices can be determined according to actual conditions and needs. For example, device operating data is real-time dynamic data (collected and updated once per second), while environmental data is periodically updated (collected and updated once per minute).

[0071] Furthermore, when collecting data on various household devices, appropriate hardware is employed. For example, the smart sensor network utilizes Zigbee 3.0 smart sockets (supporting 16A current monitoring) and device status monitors (supporting operating mode recognition for devices such as air conditioners and water heaters), covering core household appliances (such as air conditioners, water heaters, refrigerators, and washing machines). The environmental sensor group employs SHT30 temperature and humidity sensors (accuracy ±0.3℃, ±2%RH) and BH1750 light sensors (accuracy ±20%), deployed in key areas such as the living room and bedrooms. The energy storage battery interface connects to the home energy storage system via an RS485 interface, collecting SOC (range 0-100%), charge / discharge efficiency (range 85%-95%), and SOH (range 0-100%) data. Historical operation records are stored through the Home Energy Management System (HEMS) or a user's mobile application (APP), recording user usage habits (e.g., "air conditioner on from 7 PM to 10 PM" and "water heater used on weekend mornings"). The weather forecast interface calls third-party application programming interfaces (APIs) (such as the China Meteorological Administration) to obtain temperature, humidity, and precipitation probability data for the next 24 hours. Indoor environmental monitoring uses deployed temperature and humidity sensors to collect real-time data on room temperature (accuracy ±0.5℃) and humidity (accuracy ±3%RH).

[0072] Furthermore, the priority of each household device can be automatically marked using a preset rule base (e.g., "power > 500W and continuous operation > 2h is adjustable load"), with priorities such as critical / adjustable / non-essential loads. For scattered sensor data, it is aggregated by device dimension (e.g., air conditioner power + set temperature + operating mode) to output a "Device Operating Status Table". For personalized user operation data, the K-means clustering algorithm is used to extract user preference tags (e.g., "cold-resistant: air conditioner minimum temperature 20℃" "energy-saving: water heater target water temperature 50℃").

[0073] In one embodiment, the software algorithm for implementing the energy regulation method defines the core modules and functional boundaries of the system, clarifies the data flow and interface relationships between modules, and better completes complex processing procedures.

[0074] In this embodiment, the software algorithm for implementing the energy regulation method is divided into a multi-source state perception module, a demand prediction module, a dynamic decision generation module, a precise execution control module, and a storage and optimization module. The multi-source state perception module is responsible for collecting vehicle-side data and household data. The demand prediction module, based on training sample data, constructs vehicle demand prediction models and household demand prediction models, outputting the vehicle-side and household power demand for the predicted time period, respectively. The dynamic decision generation module uses "vehicle range assurance" as a rigid constraint, combining vehicle-side and household power demand to generate tiered control operation strategies for household devices (critical load protection, adjustable load optimization, and unnecessary load limitation). The precise execution control module converts the operation strategies into device control commands that the devices can recognize, driving the operation of household devices and providing feedback on the execution results. The storage and optimization module stores historical data (including historical vehicle-side data, historical household datasets, historical vehicle-side power demand, and historical household power demand), continuously trains and optimizes the vehicle-side and household demand prediction models, and learns user preferences.

[0075] In this embodiment, interfaces between different modules are pre-designed to improve data transmission efficiency. Specifically, from the multi-source state perception module to the demand prediction module: vehicle-side data and household data (such as vehicle SOC, total household power, and room temperature) are transmitted via the "state vector" interface. From the demand prediction module to the dynamic decision generation module: vehicle-side power demand and household power demand are transmitted via the "prediction result" interface. From the dynamic decision generation module to the precise execution control module: tiered control operation strategies (such as air conditioner temperature setpoint and water heater heating period) are transmitted via the "strategy command" interface. From the precise execution control module to the storage and optimization module: actual operating data of household devices based on device control commands (such as actual air conditioner power and water heater energy consumption) are transmitted via the "execution feedback" interface.

[0076] This application acquires vehicle-side data related to the vehicle within a vehicle-to-home system, as well as household data related to household devices within the same system. Based on the vehicle-side data, it predicts the vehicle's power demand for travel. Based on the household data, it predicts the household power demand for operating the household devices. Based on both vehicle and household power demands, it generates device control commands for the household devices, whereby the device control commands control the operating status of the household devices, with the vehicle providing power to the devices. By processing the vehicle and household data separately, predicting the vehicle and household power demands respectively, and controlling the operating status of the household devices based on these demands, the application effectively balances vehicle and household needs, preventing issues such as insufficient vehicle range or excessive battery discharge. This achieves refined adjustments to the vehicle-to-home system and improves its energy efficiency.

[0077] Furthermore, by integrating multi-source state information from vehicle batteries, energy storage batteries, and household devices, a dynamic optimization model is constructed to maximize household energy self-sufficiency and reduce dependence on the power grid while ensuring the future electricity needs of vehicles.

[0078] Exemplary System Accordingly, this application also provides a vehicle-to-home system, including a vehicle and home appliances. The vehicle provides electrical energy for the operation of the home appliances. The vehicle is used to acquire vehicle-side data related to the vehicle in the vehicle-to-home system, and to acquire home data related to the home appliances in the vehicle-to-home system. Based on the vehicle-side data, it predicts the vehicle-side power demand required for vehicle travel. Based on the home data, it predicts the home power demand required for the operation of the home appliances. Based on the vehicle-side power demand and the home power demand, it generates device control commands for the home appliances. The home appliances are used to adjust their operating status based on the device control commands.

[0079] Specifically, the vehicle serves as the core control node of the V2H system, integrating vehicle-side data and household data to achieve localized decision-making for bidirectional energy interaction between the vehicle and the home. Based on the vehicle's and household's electricity demand, the vehicle dynamically adjusts its energy allocation strategy, eliminating the reliance on cloud scheduling in traditional V2H technology and resolving the core conflict between household energy conservation and vehicle range goals.

[0080] In one embodiment, the vehicle-to-home system also includes an energy storage battery.

[0081] The vehicle is used to calculate the available power at the vehicle end based on the vehicle's remaining power and the power demand at the vehicle end data. If the available power at the vehicle end is less than the household's power demand, a battery activation command for the energy storage battery is generated. Based on the battery power of the energy storage battery, device control commands for household devices are generated.

[0082] Energy storage batteries are used to provide power to home devices based on battery activation commands.

[0083] The vehicle-to-home system provided in this embodiment belongs to the same application concept as the vehicle-to-home method provided in the above embodiments of this application. It can apply the vehicle-to-home method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the specific processing content of the vehicle-to-home method provided in the above embodiments of this application, and will not be repeated here.

[0084] Exemplary device Accordingly, embodiments of this application also provide a vehicle-to-home device, such as... Figure 2 As shown, the device may include: The acquisition module 201 is used to acquire vehicle-related vehicle data in the vehicle-to-home system, and to acquire home data related to home devices in the vehicle-to-home system. The vehicle-side prediction module 202 is used to predict the vehicle-side power demand required for vehicle travel based on vehicle-side data. The household forecasting module 203 is used to predict the household electricity demand required to operate household appliances based on household data. The control module 204 is used to generate device control commands for home devices based on the vehicle's power demand and the household's power demand. The device control commands are used to control the operating status of the home devices, and the vehicle provides power to the home devices.

[0085] In one embodiment, the control module 204 is used to generate operating strategies for home devices of different priorities based on the vehicle's power demand and the home's power demand, wherein the higher the priority of the home device, the fewer adjustable operating parameters the home device has; and based on the operating strategies, generate device control instructions corresponding to each home device.

[0086] In one embodiment, the vehicle-to-home system also includes an energy storage battery; The control module 204 is used to calculate the available power at the vehicle end based on the vehicle's remaining power and the power demand at the vehicle end in the vehicle end data; if the available power at the vehicle end is less than the power demand at the household, it generates a battery activation command for the energy storage battery, wherein the battery activation command is used to control the energy storage battery to provide power to the household devices; and generates device control commands for the household devices based on the battery power of the energy storage battery.

[0087] In one embodiment, the vehicle-side data includes a sequence of historical vehicle-side data within a historical time period; The vehicle-side prediction module 202 is used to input historical vehicle-side data sequences into a pre-trained vehicle demand prediction model, and the vehicle demand prediction model outputs the vehicle-side electricity demand during the prediction period. The vehicle demand prediction model is trained on the basis of a long short-term memory network architecture.

[0088] In one embodiment, the household prediction module 203 is used to input household data into a pre-trained household demand prediction model, and the household demand prediction model outputs the household electricity demand of household devices during the prediction period. The household demand prediction model is trained on an extreme gradient boosting tree architecture.

[0089] In one embodiment, the control module 204 is further configured to generate device control instructions for each household device based on the operating strategy, obtain actual operating data of the household devices based on the device control instructions, adjust the operating strategy based on the data deviation between the operating strategy and the actual operating data, and regenerate new device control instructions for each household device based on the adjusted operating strategy.

[0090] In one embodiment, vehicle-side data includes vehicle-side battery data, vehicle trip data, and / or vehicle-side load data; home-side data includes device priority data, device operation data, device environment data, and user-personalized operation data.

[0091] The vehicle-to-home device provided in this embodiment belongs to the same application concept as the vehicle-to-home method provided in the above embodiments of this application. It can execute the vehicle-to-home method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the specific processing content of the vehicle-to-home method provided in the above embodiments of this application, and will not be repeated here.

[0092] Exemplary electronic devices This application also provides an electronic device, such as... Figure 3 As shown, the electronic device includes a memory 300 and a processor 301.

[0093] The memory 300 is connected to the processor 301 and is used to store programs.

[0094] The processor 301 is used to implement the vehicle-to-home method in the above embodiments by running the program stored in the memory 300.

[0095] Specifically, the aforementioned electronic device may also include: a communication interface 302, an input device 303, an output device 304, and a bus 305.

[0096] The processor 301, memory 300, communication interface 302, input device 303, and output device 304 are interconnected via a bus. Among them: Bus 305 may include a pathway for transmitting information between various components of a computer system.

[0097] Processor 301 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.

[0098] Processor 301 may include a main processor, as well as a baseband chip, modem, etc.

[0099] The memory 300 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 300 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.

[0100] Input device 303 may include a device for receiving data and information input by the user, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0101] Output device 304 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0102] The communication interface 302 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.

[0103] The processor 301 executes the program stored in the memory 300 and calls other devices, which can be used to implement the various steps of the vehicle-to-home method provided in the above embodiments of this application.

[0104] Exemplary computer program products and storage media 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 of the vehicle-to-home method described in the embodiments of this application.

[0105] 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.

[0106] Furthermore, embodiments of this application may also be storage media storing a computer program, which is executed by a processor of the steps in the vehicle-to-home method described in the embodiments of this application.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] The modules and sub-modules in the devices and terminals provided in the various embodiments of this application can be merged, divided, and deleted according to actual needs.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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 method of energy regulation, characterized by, The method comprises: acquiring vehicle-related vehicle-side data in a vehicle-to-home system and acquiring home-related home data in the vehicle-to-home system; based on the vehicle-side data, predicting vehicle-side demand power required for the vehicle to travel; based on the home data, predicting home demand power required for the home devices to operate; based on the vehicle-side demand power and the home demand power, generating device control instructions for the home devices, wherein the device control instructions are used to control the operating state of the home devices, and the vehicle provides power for the operation of the home devices.

2. The energy regulation method of claim 1, wherein, The method further comprises: based on the vehicle-side demand power and the home demand power, generating operating strategies for the home devices under respective priorities, wherein the higher the priority of the home devices, the fewer the adjustable operating parameters of the home devices; based on the operating strategies, generating the device control instructions corresponding to the respective home devices.

3. The energy regulation method of claim 1, wherein, The vehicle-to-home system further comprises an energy storage battery. The method further comprises: based on the vehicle-side data, calculating vehicle-side available power based on the vehicle remaining power and the vehicle-side demand power; if the vehicle-side available power is less than the home demand power, generating a battery activation instruction for the energy storage battery, wherein the battery activation instruction is used to control the energy storage battery to provide power for the home devices; based on the battery power of the energy storage battery, generating the device control instructions for the home devices.

4. The energy regulation method of claim 1, wherein, The vehicle-side data comprises a historical vehicle-side data sequence in a historical period. The method further comprises: inputting the historical vehicle-side data sequence into a pre-trained vehicle demand prediction model, and outputting the vehicle-side demand power of the vehicle in a prediction period by the vehicle demand prediction model, wherein the vehicle demand prediction model is trained based on a long short-term memory network architecture.

5. The energy regulation method of claim 1, wherein, The method further comprises: inputting the home data into a pre-trained home demand prediction model, and outputting the home demand power of the home devices in a prediction period by the home demand prediction model, wherein the home demand prediction model is trained based on an extreme gradient boosting tree architecture.

6. The energy regulation method of claim 2, wherein, The method further comprises: acquiring actual operating data of the home devices based on the device control instructions; adjusting the operating strategies based on the data deviation between the operating strategies and the actual operating data; based on the adjusted operating strategies, regenerating new device control instructions corresponding to the respective home devices.

7. The method of claim 1-6, wherein, The vehicle-side data comprises vehicle-side battery data, vehicle travel data, and / or vehicle-side load data. The home data includes device priority data, device operation data, device environment data, and user personalized operation data.

8. A vehicle-to-home system characterized by comprising: The vehicle provides electric energy for operation of the home device; The vehicle is configured to acquire vehicle-to-home system vehicle-related vehicle end data and vehicle-to-home system home device-related home data, predict vehicle end demand electric quantity required for vehicle travel based on the vehicle end data, predict home demand electric quantity required for operation of the home device based on the home data, and generate device control instructions for the home device based on the vehicle end demand electric quantity and the home demand electric quantity. The home device is configured to adjust an operation state based on the device control instructions.

9. An electronic device, comprising: The vehicle-to-home system comprises: a memory and a processor; the memory is connected to the processor and configured to store a program; the processor is configured to execute the program in the memory to implement the vehicle-to-home method according to any one of claims 1-7.

10. A computer program product, characterised in that, The computer program instructions, when executed by a processor, cause the processor to perform the vehicle-to-home method according to any one of claims 1-7. ​

Images