A cloud-edge-end collaborative regulation method and device of a zero-carbon household energy system, equipment and medium

Abstract

The application discloses a cloud-edge-device collaborative regulation method and device of a zero-carbon household energy system, equipment and medium, which is applied to a zero-carbon household energy system, the zero-carbon household energy system is deployed with a cloud end, an edge end and a device end, relates to the technical field of computers, and comprises the following steps: establishing a two-way feedback channel of the cloud end and the edge end and the edge end and the device end, modeling the uncertainty of power generation and power consumption prediction of the next day based on the cloud end, and constructing a day-ahead regulation model based on the obtained target scene and optimization target; solving the day-ahead regulation model, inputting the operation parameters of the day-ahead regulation scheme into an intra-day rolling correction model; the edge end determines the real-time regulation scheme of each device based on a preset real-time regulation algorithm, corrects the obtained intra-day regulation scheme, and the device end feeds back real-time operation parameters to the edge end and the cloud end, so that the cloud-edge-device collaborative regulation operation of the zero-carbon household energy system is performed. The fine and digital flexible regulation of the zero-carbon household energy system is realized.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a cloud-edge-device collaborative control method, device, equipment, and medium for a zero-carbon home energy system. Background Technology

[0002] Currently, distributed photovoltaics, energy storage batteries, heat pump air conditioners, and electric vehicles are widely used in urban and rural residential buildings, transforming buildings from traditional energy "consumers" into energy "producers, suppliers, storage providers, and consumers," creating a complex zero-carbon home energy system on the user side. This transformation has spurred new demands for home energy management: achieving economical, low-carbon, and intelligent management of home energy through the coordinated control of flexible resources such as energy storage batteries, heat pump air conditioners, and electric vehicles.

[0003] However, in practical engineering applications, the coordinated regulation of various flexible resources in a zero-carbon home energy system is mainly achieved by deploying a home energy management system on the user side. However, this technology currently only possesses basic functions such as data acquisition, visualization, and remote control. In terms of regulation strategies, it mostly adopts rule-based control strategies based on time-of-use pricing and maximizing photovoltaic self-consumption, lacking core functions such as user habit recognition, autonomous model parameter identification, flexible adaptive energy regulation, and online learning. Therefore, it cannot achieve refined, intelligent, and flexible regulation of a zero-carbon home energy system.

[0004] As can be seen from the above, how to achieve refined, intelligent, and flexible control of zero-carbon home energy systems is an urgent problem to be solved. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide a cloud-edge-device collaborative control method, device, equipment, and medium for a zero-carbon home energy system, capable of achieving refined, intelligent, and flexible control of the zero-carbon home energy system. The specific solution is as follows: Firstly, this application provides a cloud-edge-device coordinated control method for a zero-carbon home energy system, applied to the zero-carbon home energy system, which is deployed with a cloud, an edge, and device terminals, including: A first channel is established between the cloud and the edge, and a second channel is established between the edge and the device. A bidirectional feedback channel is constructed based on the first channel and the second channel. Based on the cloud and using scenario analysis, the uncertainty of the next day's power generation and consumption forecast is modeled by combining historical power generation data and historical power consumption data to construct various target scenarios. Optimization targets are constructed based on electricity cost, user comfort, photovoltaic self-consumption rate, and energy matching rate. A day-ahead control model is then constructed in conjunction with the target scenarios. Based on the cloud and using a genetic algorithm, the daytime regulation model is solved to obtain the daytime regulation scheme, and the operating parameters corresponding to the execution of the daytime regulation scheme are determined. The operating parameters are then input into the intraday rolling correction model to obtain the intraday regulation scheme. Based on the multi-dimensional real-time operation data of the zero-carbon home energy system collected at the edge, the priority order of the target flexible devices in the zero-carbon home energy system is determined based on the multi-dimensional real-time operation data, and a real-time control scheme is determined based on the priority order and in combination with the intraday control scheme. Based on the edge terminal and utilizing the bidirectional feedback channel, the real-time control scheme is transmitted to the device terminal, so that the device terminal executes the control commands corresponding to the real-time control scheme, thereby using the control commands to perform cloud-edge-device collaborative control operations on the zero-carbon home energy system. Optionally, based on the cloud and utilizing scenario analysis methods, combined with historical power generation data and historical electricity consumption data, the uncertainty of the next day's power generation and consumption forecast is modeled to construct various target scenarios. Optimization targets are constructed based on electricity costs, user comfort, photovoltaic self-consumption rate, and energy matching rate. A day-ahead control model is then constructed based on the target scenarios, including: Based on the cloud and using scenario analysis, combined with meteorological forecast data, historical photovoltaic power generation data and historical household electricity load data, the uncertainty of the next day's photovoltaic power generation and household electricity load prediction is modeled to construct various target scenarios; The optimization objectives are to minimize electricity costs, maximize user comfort, maximize photovoltaic self-consumption rate, and maximize energy matching rate. Based on the optimization objective and the target scenario, a day-ahead control model is constructed using the opportunity-constrained programming method.

[0006] Optionally, the step of solving the day-ahead regulation model based on the cloud and using a genetic algorithm to obtain the day-ahead regulation scheme includes: Based on the cloud and using a genetic algorithm, the daytime regulation model is optimized in multiple objectives to obtain a daytime regulation scheme including the first objective regulation time domain and the first objective regulation step size. Determine the operating parameters corresponding to the day-ahead control scheme for each flexible device in the zero-carbon home energy system; The operating parameters and the daily photovoltaic power generation forecast data are input into the intraday rolling correction model to obtain the intraday control scheme.

[0007] Optionally, the step of inputting the operating parameters and the daily photovoltaic power generation forecast data into the intraday rolling correction model to obtain the intraday control scheme includes: A rolling correction model is constructed using model predictive control. The operating parameters and the photovoltaic power generation forecast data for the day are input into the rolling correction model. The genetic algorithm is then used to solve the rolling correction model to obtain an intraday control scheme that includes the second target control time domain and the second target control step size. The second target control time domain and the second target control step size are obtained by simulating various electricity consumption / generation scenarios, which are the intraday control time domain and intraday control step size.

[0008] Optionally, determining the priority order of target flexible devices in the zero-carbon home energy system based on the multi-dimensional real-time operating data includes: Based on the multi-dimensional real-time operational data, the flexibility potential of each flexible device in the zero-carbon home energy system is determined. Determine whether the proportion of each of the aforementioned flexible potentials in the zero-carbon home energy system exceeds the target flexible proportion threshold, and based on the determination result, identify the flexible devices that exceed the target flexible proportion threshold as target flexible devices; The priority order of the target flexible equipment is determined based on the flexibility potential corresponding to the target flexible equipment.

[0009] Optionally, determining the real-time control plan based on the priority order and in conjunction with the intraday control plan includes: Based on the priority order, a rule-based control strategy for real-time response is determined, and the real-time control scheme is determined by combining the rule-based control strategy with the intraday control scheme.

[0010] Optional, also includes: Within the daily scheduling cycle, the intraday control scheme is used to modify the day-ahead control scheme, and the real-time control scheme is used to modify the intraday control scheme.

[0011] Secondly, this application provides a cloud-edge-device coordinated control device for a zero-carbon home energy system, applied to the zero-carbon home energy system, which is deployed with a cloud, an edge, and a device, including: The channel establishment module is used to establish a first channel between the cloud and the edge, and to establish a second channel between the edge and the device, and to construct a bidirectional feedback channel based on the first channel and the second channel; The regulation model construction module is used to model the uncertainty of the next day's power generation and consumption forecast based on the cloud and using scenario analysis method, combined with historical power generation data and historical power consumption data, in order to construct various target scenarios, construct optimization targets based on electricity cost, user comfort, photovoltaic self-consumption rate and energy matching rate, and construct the day-ahead regulation model in combination with the target scenarios; The regulation scheme determination module is used to solve the daytime regulation model based on the cloud and using a genetic algorithm to obtain the daytime regulation scheme, and to determine the operating parameters corresponding to the execution of the daytime regulation scheme. The operating parameters are then input into the intraday rolling correction model to obtain the intraday regulation scheme. The real-time scheme determination module is used to collect multi-dimensional real-time operation data of the zero-carbon home energy system from the edge terminal, determine the priority order of the target flexible devices in the zero-carbon home energy system based on the multi-dimensional real-time operation data, and determine the real-time control scheme based on the priority order and the intraday control scheme. The system control module is used to transmit the real-time control scheme to the device based on the edge terminal and using the bidirectional feedback channel, so that the device terminal can execute the control command corresponding to the real-time control scheme, and use the control command to perform cloud-edge-device collaborative control operation of the zero-carbon home energy system.

[0012] Thirdly, this application provides an electronic device, comprising: Memory, used to store computer programs; A processor is used to execute the computer program to implement the aforementioned cloud-edge-device collaborative control method for zero-carbon home energy systems.

[0013] Fourthly, this application provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned cloud-edge-device collaborative control method for a zero-carbon home energy system.

[0014] This application establishes a first channel between the cloud and the edge, and a second channel between the edge and the device. A bidirectional feedback channel is constructed based on the first and second channels. Based on the cloud and using scenario analysis, combined with historical power generation and consumption data, the uncertainty of next day's power generation and consumption forecasts is modeled to construct various target scenarios. Optimization targets are constructed based on electricity cost, user comfort, photovoltaic self-consumption rate, and energy matching rate. A day-ahead control model is then constructed based on the target scenarios. Based on the cloud and using a genetic algorithm, the day-ahead control model is solved to obtain a day-ahead control scheme and determine the corresponding scheme for execution. Operating parameters are input into the intraday rolling correction model to obtain an intraday control plan. Multi-dimensional real-time operating data of the zero-carbon home energy system is collected from the edge device. The priority order of target flexible devices in the zero-carbon home energy system is determined based on this multi-dimensional real-time operating data. A real-time control plan is determined based on this priority order and the intraday control plan. The real-time control plan is transmitted to the device via the edge device and the bidirectional feedback channel, so that the device executes the control commands corresponding to the real-time control plan, thereby using the control commands to perform cloud-edge-device collaborative control operations on the zero-carbon home energy system.

[0015] As can be seen from the above, this application first establishes a two-way feedback channel between the cloud and the edge, and between the edge and the device. Then, based on the cloud and using scenario analysis combined with historical data, it predicts the next day's power generation / consumption fluctuations to construct a target scenario covering all uncertainties. A day-ahead control model is built based on four core objectives: cost, comfort, photovoltaic integration, and energy matching. A genetic algorithm is used to solve the day-ahead control model to obtain the optimal day-ahead control scheme and determine the corresponding operating parameters. These operating parameters are then input into an intraday rolling correction model to generate an intraday control scheme. Multi-dimensional real-time operating data is collected, and the priority of target flexible devices is determined based on this data. A real-time control scheme is generated by combining the intraday scheme with the real-time control scheme. The real-time control scheme is fed back to the device through the two-way feedback channel at the edge, so that the device can execute the corresponding real-time control commands. In this way, by using real-time control commands to execute control management, a multi-timescale collaborative flexible control method at the day-ahead, intraday, and real-time scales is achieved, improving control speed and accuracy, thereby realizing intelligent flexible control of a zero-carbon home energy system. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0017] Figure 1 This application discloses a cloud-edge-device collaborative control method for a zero-carbon home energy system. Figure 2 This application discloses a specific cloud-edge-device collaborative control method for a zero-carbon home energy system; Figure 3 This is a schematic diagram of the cloud-edge-device collaborative control device for a zero-carbon home energy system disclosed in this application. Figure 4 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Currently, the main approach to achieving coordinated control of various flexible resources in zero-carbon home energy systems is through the deployment of home energy management systems on the user side. However, this technology only possesses basic functions such as data acquisition, visualization, and remote control. In terms of control strategies, it primarily employs rule-based control strategies based on time-of-use pricing and maximizing photovoltaic self-consumption, lacking core functions such as user habit recognition, autonomous model parameter identification, flexible adaptive energy control, and online learning. This makes it impossible to achieve refined, intelligent, and flexible control of zero-carbon home energy systems. Therefore, this application provides a cloud-edge-device coordinated control method for zero-carbon home energy systems. This method utilizes real-time control commands to execute control management, achieving coordinated flexible control across multiple time scales (day-ahead, intraday, and real-time), improving control speed and accuracy, and thus realizing intelligent and flexible control of zero-carbon home energy systems.

[0020] See Figure 1 As shown, this invention discloses a cloud-edge-device collaborative control method for a zero-carbon home energy system, applied to the zero-carbon home energy system, which is deployed with a cloud, an edge, and device terminals, including: Step S11: Establish a first channel between the cloud and the edge, and establish a second channel between the edge and the device, and construct a bidirectional feedback channel based on the first channel and the second channel.

[0021] In this embodiment, a bidirectional feedback channel is established between the cloud and the edge, and between the edge and the device, to achieve real-time data and command communication and ensure dynamic optimization of the control strategy. Specifically, the feedback channel from the cloud to the edge is used to issue global control strategies, optimized AI models, emergency control commands, and user-personalized settings, guiding the edge to conduct local control work. Simultaneously, based on edge feedback data, the global strategy is dynamically adjusted (e.g., peak-valley arbitrage parameter optimization) to adapt to changes in household electricity consumption habits. The feedback channel from the edge to the cloud is used to periodically report local control data, system operating status, trends in household load and photovoltaic output, and equipment anomaly records, providing support for cloud-based global strategy optimization, model iteration, and remote operation and maintenance. When problems arise that the edge cannot resolve (e.g., major equipment failures or grid anomalies), the issue is promptly reported to the cloud, which then formulates emergency strategies and pushes them to the edge. The feedback channel between the edge and the device is used to provide real-time feedback on device operating status, command execution results, and anomaly information (e.g., battery overheating or photovoltaic shading), providing a basis for real-time edge control and ensuring that control commands align with the actual operating status of the equipment.

[0022] S12. Based on the cloud and using scenario analysis, model the uncertainty of the next day's power generation and consumption forecast by combining historical power generation data and historical power consumption data, so as to construct various target scenarios, construct optimization targets based on electricity cost, user comfort, photovoltaic self-consumption rate and energy matching rate, and construct a day-ahead control model in combination with the target scenarios.

[0023] In this embodiment, based on the cloud and using scenario analysis, the uncertainty of users' historical photovoltaic power generation data and electricity load forecasts is modeled to construct k minimum number of target scenarios. These target scenarios cover uncertainties such as sunny / cloudy days, family members staying at home / going out, and peak / valley loads. Then, with the optimization objectives of minimizing electricity costs, maximizing user comfort, maximizing photovoltaic self-consumption rate, and maximizing energy matching rate, a day-ahead control model with a 24-hour control step size of 1 hour is built using the opportunity-constrained programming method and the target scenarios.

[0024] Specifically, the process involves modeling the uncertainty of next-day power generation and consumption forecasts based on the cloud and using scenario analysis, combined with historical power generation and consumption data, to construct various target scenarios. Optimization objectives are then established based on electricity costs, user comfort, photovoltaic self-consumption rate, and energy matching rate. Finally, a day-ahead control model is constructed based on these target scenarios. This includes: modeling the uncertainty of next-day photovoltaic power generation and household electricity load forecasts based on the cloud and using scenario analysis, combined with weather forecast data, historical photovoltaic power generation data, and historical household electricity load data, to construct various target scenarios; minimizing electricity costs, maximizing user comfort, maximizing photovoltaic self-consumption rate, and maximizing energy matching rate as optimization objectives; and constructing a day-ahead control model based on the optimization objectives and the target scenarios using a chance-constrained programming method.

[0025] Step S13: Based on the cloud and using a genetic algorithm, solve the daytime regulation model to obtain the daytime regulation scheme, determine the operating parameters corresponding to the execution of the daytime regulation scheme, and input the operating parameters into the intraday rolling correction model to obtain the intraday regulation scheme.

[0026] In this embodiment, after obtaining the day-ahead control model, a multi-objective optimization solution is performed on the day-ahead control model based on the cloud and using a genetic algorithm to obtain a day-ahead control scheme for the next 24 hours with a control step size of 1 hour. The day-ahead control scheme specifies the charging and discharging periods of the energy storage battery, the operation plan of the heat pump air conditioner / electric water heater / electric vehicle charging pile, and the photovoltaic self-consumption strategy. The operating parameters corresponding to the day-ahead control scheme for each flexible device in the zero-carbon home energy system are determined; the operating parameters may include the energy storage battery SOC (State of Charge), charging and discharging power, battery temperature, and the operating power, start-stop status, and set parameters of the air conditioner / water heater / electric vehicle / battery. Then, the operating parameters and the intraday photovoltaic power generation forecast data for the day are input into the intraday rolling correction model to obtain the intraday control scheme.

[0027] Specifically, the step of solving the day-ahead control model based on the cloud and using a genetic algorithm to obtain a day-ahead control scheme includes: performing multi-objective optimization on the day-ahead control model based on the cloud and using a genetic algorithm to obtain a day-ahead control scheme including a first objective control time domain and a first objective control step size; determining the operating parameters corresponding to the execution of the day-ahead control scheme by each flexible device in the zero-carbon home energy system; and inputting the operating parameters and the photovoltaic power generation forecast data for the day into the intraday rolling correction model to obtain an intraday control scheme.

[0028] It is understood that the intraday rolling correction model is a model determined based on the model predictive control method. The operating parameters and the photovoltaic power generation forecast data for the day are input into the intraday rolling correction model, and the genetic algorithm is used to solve the intraday rolling correction model to obtain an intraday control scheme including the second target control time domain and the second target control step size. The second target control time domain and the second target control step size are the optimal control time domain and the optimal control step size obtained through batch simulation. The second target control time domain can be 8 hours and the second target control step size can be 20 minutes, or they can be adjusted according to the actual situation.

[0029] Specifically, the step of inputting the operating parameters and the daily photovoltaic power generation forecast data into the intraday rolling correction model to obtain the intraday control scheme includes: constructing the intraday rolling correction model using a model predictive control method, inputting the operating parameters and the daily photovoltaic power generation forecast data into the intraday rolling correction model, and solving the intraday rolling correction model using the genetic algorithm to obtain an intraday control scheme including a second target control time domain and a second target control step size; wherein, the second target control time domain and the second target control step size are the intraday control time domain and intraday control step size obtained based on simulation of various electricity consumption / power generation scenarios.

[0030] Step S14: Collect multi-dimensional real-time operating data of the zero-carbon home energy system from the edge terminal, determine the priority order of the target flexible devices in the zero-carbon home energy system based on the multi-dimensional real-time operating data, and determine the real-time control scheme based on the priority order and the intraday control scheme.

[0031] In this embodiment, multi-dimensional real-time operational data of the zero-carbon home energy system is collected from the device layer at the edge. This multi-dimensional real-time operational data includes real-time photovoltaic output, energy storage battery SOC / charge / discharge power, operating status of air conditioners / electric water heaters / electric vehicles / batteries, indoor temperature and humidity, grid voltage / current, total household electricity load, and equipment anomaly information. In one specific implementation, the target flexible devices exceeding the target flexibility ratio threshold are air conditioners, water heaters, electric vehicles, and batteries. The real-time flexibility potential of these target flexible devices is quantified. This real-time flexibility potential includes adjustable power capacity, response speed, and adjustment range. The priority order of the target flexible devices is determined according to the magnitude of their real-time flexibility potential. The flexibility potential is directly proportional to the priority order. The target flexibility ratio threshold can be set according to actual conditions.

[0032] Specifically, determining the priority order of target flexible devices in the zero-carbon home energy system based on the multi-dimensional real-time operating data includes: determining the flexibility potential corresponding to each flexible device in the zero-carbon home energy system based on the multi-dimensional real-time operating data; determining whether the proportion of each flexibility potential in the zero-carbon home energy system exceeds a target flexibility proportion threshold, and determining the flexible devices that exceed the target flexibility proportion threshold as target flexible devices based on the determination result; and determining the priority order of the target flexible devices based on the flexibility potential corresponding to the target flexible devices.

[0033] It is understood that, based on the aforementioned priority order and in conjunction with the intraday control plan, a real-time response rule-based control strategy is constructed to generate a minute-level real-time control plan. Specifically, determining the real-time control plan based on the priority order and in conjunction with the intraday control plan includes: determining a real-time response rule-based control strategy based on the priority order, and using the rule-based control strategy in conjunction with the intraday control plan to determine the real-time control plan. Specifically, it also includes: within the daily scheduling cycle, using the intraday control plan to modify the previous day's control plan, and using the real-time control plan to modify the intraday control plan.

[0034] S15. Based on the edge terminal and using the bidirectional feedback channel, the real-time control scheme is transmitted to the device terminal so that the control command corresponding to the real-time control scheme is executed based on the device terminal, so as to use the control command to perform cloud-edge-device collaborative control operation of the zero-carbon home energy system.

[0035] In this embodiment, after obtaining the real-time control scheme, the instructions corresponding to the real-time control scheme are transmitted to the device end based on the edge terminal and using a bidirectional feedback channel. These instructions include, for example, instructions for adjusting the energy storage charging and discharging power, adjusting the flexible load start / stop / power, and optimizing photovoltaic consumption. This allows the device layer to execute the control based on the instructions and periodically transmit the real-time control results, device status, and abnormal information back to the cloud after the control is completed.

[0036] As can be seen from the above, this application first establishes a two-way feedback channel between the cloud and the edge, and between the edge and the device. Then, based on the cloud and using scenario analysis combined with historical data, it predicts the next day's power generation / consumption fluctuations to construct a target scenario covering all uncertainties. A day-ahead control model is built based on four core objectives: cost, comfort, photovoltaic integration, and energy matching. A genetic algorithm is used to solve the day-ahead control model to obtain the optimal day-ahead control scheme and determine the corresponding operating parameters. These operating parameters are then input into an intraday rolling correction model to generate an intraday control scheme. Multi-dimensional real-time operating data is collected, and the priority of target flexible devices is determined based on this data. A real-time control scheme is generated by combining this data with the intraday scheme. The real-time control scheme is then fed back to the device via the two-way feedback channel from the edge, enabling the device to execute the corresponding real-time control commands. In this way, by using real-time control commands to execute control management, it achieves refined, intelligent, and flexible control of the zero-carbon home energy system while realizing the user's goals of economical, low-carbon, flexible, and user-friendly electricity use.

[0037] Furthermore, to explain in detail the coordinated regulation at each level in a zero-carbon home energy system, see [link to relevant documentation]. Figure 2 As shown, this embodiment of the invention discloses a specific cloud-edge-device collaborative control method for a zero-carbon home energy system, applied to the zero-carbon home energy system, comprising: In this embodiment, the zero-carbon home energy system includes a device layer, a communication layer, a data layer, a cloud computing layer, an edge computing layer, an application layer, and a security layer. The device layer executes control commands and collects operational data. The communication layer is responsible for two-way / one-way communication between devices, the cloud, the edge, users, and the power grid. The data layer processes and stores data. The cloud computing layer and the edge computing layer perform optimization calculations. The application layer enables interaction and visualization between the cloud, the edge, and users. The security layer ensures the safe and reliable operation of the system while protecting the privacy of home users.

[0038] First, the equipment layer is the foundational terminal of a zero-carbon home energy system, responsible for data acquisition and execution of control commands. This includes: Energy production equipment: devices that provide clean electricity to the zero-carbon home energy system, including distributed photovoltaic power generation systems (composed of photovoltaic modules and inverters), where inverters collect real-time operating parameters such as voltage, current, and power generation; Energy storage and conversion equipment: devices in the zero-carbon home energy system capable of storing and releasing energy, including household battery systems. Household battery systems are equipped with their own energy management systems, autonomously collecting parameters such as battery SOC, charging and discharging power, and battery temperature, executing commands for charging and discharging, and grid-connected / off-grid switching, and possessing emergency power supply capabilities; Flexible load equipment: electrical appliances in the zero-carbon home energy system with flexible adjustment capabilities, including heat pump air conditioners (central air conditioning or split units, etc.), electric water heaters, washing machines, dryers, dishwashers, and electric vehicle charging stations. The equipment is equipped with IoT capabilities, enabling it to autonomously collect data on operating power, status, and set parameters. It can also respond to load adjustment commands, such as start / stop, power adjustment, and peak-shifting operation. Rigid load equipment refers to electrical appliances in a zero-carbon home energy system that lack flexible adjustment capabilities, including lighting, televisions, refrigerators, and range hoods. The device layer adopts standardized interface designs (such as Modbus, WiFi, and Bluetooth) to support plug-and-play functionality for various devices. It also embeds lightweight sensing modules to achieve real-time monitoring and anomaly warnings, such as battery overheating.

[0039] Understandably, the communication layer is the core channel connecting the device layer, edge layer, and cloud, responsible for high-speed, secure, and stable data transmission. It adopts a hybrid communication mode of WiFi, 4G / 5G, and Bluetooth, balancing economy and practicality. Specifically, WiFi / Bluetooth communication is used for short-range real-time data transmission between the edge and the device, suitable for home indoor scenarios, low-cost, and easy to deploy. It mainly transmits high-frequency real-time data (such as device operating parameters and power fluctuation data) to meet daily control needs. 4G / 5G communication is used for data transmission between the edge and the cloud, suitable for scenarios with insufficient WiFi coverage, such as rural and remote areas, ensuring remote data upload and cloud command issuance. It supports automatic switching to local storage when the network is down and data synchronization after network recovery. At the same time, the communication layer incorporates basic security technologies such as data encryption and identity authentication to ensure that private information such as household electricity data and device parameters are not leaked or tampered with, meeting the privacy protection needs of home scenarios.

[0040] Furthermore, the data layer is responsible for the aggregation, preprocessing, storage, and management of all relevant data related to zero-carbon home energy system equipment, environment, and personnel. This provides high-quality data support for control decisions, addresses issues such as heterogeneous multi-source data and data redundancy, and considers user scenario needs. Specifically, this includes: Edge data nodes: deployed on edge gateways, responsible for collecting real-time data from the device layer, performing preprocessing such as data cleaning, noise reduction, and compression, filtering redundant data, extracting key features (such as peak photovoltaic output and peak load periods), storing short-term (7-15 days) real-time data to reduce cloud data transmission pressure, and supporting local data storage and retrieval during network outages to ensure continuous system operation; Cloud nodes: aggregating preprocessed data from edge control gateways, storing long-term (1-5 years) historical data, control strategies, user settings, etc., using lightweight distributed storage technology to achieve secure data storage and efficient retrieval, and connecting to local power grid time-of-use pricing data, weather forecast data, and power grid interaction commands to support global optimization decisions. The data layer adopts a standardized data format to achieve the integration of multi-source data (equipment data, environmental data, load data, and electricity price data), builds a simple household energy data resource pool, provides data support for AI modeling and control optimization, and establishes a data classification management mechanism to prioritize the real-time processing of core data (such as energy storage SOC and electricity load).

[0041] In this embodiment, the cloud computing layer is deployed in the cloud, relying on powerful computing power and massive data to realize source load prediction, day-ahead-intraday global optimization and control, dynamic task allocation, fault diagnosis, incremental learning, and user and equipment management. Specifically, it includes: Source load prediction: Lightweight deep learning algorithms, such as CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory), are used, combined with local meteorological data and historical electricity consumption data, to train and iterate lightweight AI prediction models for distributed photovoltaic power generation prediction, household electricity load prediction, and domestic hot water load prediction, reducing the impact of prediction errors on system control; Day-ahead-intraday global optimization and control: Through day-ahead-intraday collaborative control, global optimization and control of system operation is achieved. The day-ahead scale (24-hour cycle, 1-hour step) employs a chance-constrained programming approach. Based on next-day photovoltaic output forecasts, household load forecasts, weather forecasts, and electricity price data, it formulates a day-ahead global control plan under constraints of user comfort and equipment safe operation. This plan includes energy storage charging and discharging periods and flexible load operation plans (such as charging during off-peak hours). The core objectives include minimizing daily electricity costs, maximizing peak-valley arbitrage profits, and maximizing photovoltaic self-consumption rate. The intraday scale (4-hour cycle, 30-minute step) uses a model predictive control algorithm to address mid-term load fluctuations and photovoltaic output deviations. It dynamically adjusts energy storage charging and discharging power and flexible load operation status. The core objective is to minimize output deviations, ensure household electricity stability, and avoid overcharging and discharging of energy storage. Dynamic task allocation: Based on task complexity and real-time requirements, control tasks are dynamically allocated to the cloud and edge. Local real-time control tasks for households (such as power fluctuation smoothing) are handled by the edge, while non-real-time tasks such as global planning and model training are handled by the cloud. This achieves optimal matching of computing resources and reduces cloud computing pressure and operating costs.

[0042] Furthermore, this includes: Incremental Learning: Incremental learning is applied to the cloud-based control module, enabling long-term model iteration and knowledge accumulation through small-batch, intermittent updates. The platform regularly aggregates operational data from photovoltaic, energy storage, air conditioning, and electric vehicles uploaded from the edge, and uses incremental learning to perform lightweight updates on the day-ahead and intraday optimized control models and source-load prediction models. Simultaneously, a historical sample playback mechanism is introduced to suppress catastrophic forgetting, preserving core operational patterns such as seasonal operating conditions and users' long-term electricity consumption habits. This learning method eliminates the need for full model retraining, adapts to cloud computing power characteristics, and can continuously adapt to slow time-varying characteristics such as equipment aging, seasonal changes, and user demand migration, continuously improving the economic efficiency and zero-carbon benefits of day-ahead scheduling plans, complementing edge-side online learning; User and Equipment Management: Unified management of user edge control gateways, terminal devices, and user accounts; real-time monitoring of the operating status of each user's system; support for user permission settings, remote adjustment of equipment parameters, and personalized configuration of control strategies; and provision of equipment maintenance reminders to meet the needs of large-scale deployment.

[0043] Understandably, the lightweight edge gateway deployed locally at the edge computing layer is designed to enable real-time local control, data processing, and autonomous operation even during network outages. This addresses pain points such as high latency in cloud-based control and unstable networks in home scenarios, adapting to the computing power needs of user scenarios. Key features include: Real-time data processing: Receiving high-frequency data collected from the device layer, combining it with preprocessing results from edge data nodes, and performing real-time analysis to quickly identify fluctuations in photovoltaic output, sudden load changes, and equipment anomalies (such as battery overheating or charging pile malfunctions), ensuring timely control; Real-time flexible control: Based on the response characteristics and real-time flexibility potential of different flexible resources such as home batteries, heat pump air conditioners, and electric vehicles, determining the priority of each flexible resource's real-time response, and establishing a real-time response control strategy for a zero-carbon home energy system that considers the priority of flexible resources. Based on this strategy, and using cloud-based day-to-day global control strategies (such as peak-valley arbitrage plans) combined with real-time household electricity consumption data, a real-time control scheme is determined to quickly smooth out fluctuations in photovoltaic output and sudden load changes (such as sudden air conditioner startup), adjust the emergency charging and discharging status of energy storage and the power of flexible loads. The core objective is to ensure the stability of household electricity voltage and frequency, prioritize the supply of rigid loads, and maximize photovoltaic absorption and peak-valley arbitrage benefits.

[0044] Furthermore, this includes: Online learning: Deployed at the edge control gateway, online learning leverages streaming real-time operational data to achieve dynamic iterative updates of the model, enabling rapid tracking of real-time operating condition changes in zero-carbon home energy systems. For scenarios such as random fluctuations in photovoltaic output, transient changes in indoor temperature, and sudden adjustments in user electricity consumption behavior, online learning performs real-time, sample-by-sample correction of photovoltaic and load forecasting models, HVAC parameter models, and energy storage operation models, simultaneously optimizing real-time control strategies. Within a second-level control cycle, online learning can complete model fine-tuning without a large amount of historical data, effectively ensuring the thermal comfort control accuracy of flexible air conditioning loads and the execution of safety constraints for energy storage charging and discharging. Even under network fluctuations or network outage autonomous mode, it can still maintain the real-time performance and reliability of system regulation, providing core support for precise local control at the platform edge. Network outage autonomy: When the edge end is disconnected from the cloud, the edge computing layer can rely on the local model and preset rule control algorithms to independently execute regulation tasks (such as prioritizing photovoltaic self-use and emergency power supply from energy storage) to maintain basic household electricity needs. After the network is restored, the data and regulation records are synchronized to the cloud to ensure system continuity and adapt to the reliability requirements of household electricity. Local safety monitoring: Real-time monitoring of equipment operation status and electricity safety. When anomalies are detected (such as battery overcharging, line overload, photovoltaic shading), local audible and visual warnings are immediately triggered, and emergency regulation measures are executed (such as stopping energy storage charging and disconnecting faulty loads), while reporting to the cloud to ensure household electricity safety. The edge computing layer adopts a lightweight architecture design, adapts to the limited computing power of edge gateways, deploys lightweight control algorithms, avoids complex calculations, reduces hardware costs, and supports remote algorithm upgrades to improve system scalability.

[0045] In this embodiment, the application layer serves as the interface for displaying the results of the control system and facilitating user interaction. It provides diverse, lightweight application services to home users and maintenance personnel, enabling visualization, operability, and traceability of the control process. Specifically, it includes: a data analysis module: statistically analyzing the operational data of the zero-carbon home energy system and outputting core indicators such as photovoltaic absorption rate, electricity cost savings, carbon emission reduction, and photovoltaic power generation self-consumption rate, providing data support for users to optimize their electricity consumption habits and for maintenance personnel to optimize control strategies; a user interaction module: providing lightweight interaction methods such as mobile apps and mini-programs, displaying real-time core information such as home photovoltaic power generation, energy storage SOC, electricity load, electricity bill statistics, and carbon emission reduction, supporting manual control (such as switching energy storage charging and discharging modes, and flexible load start / stop), personalized control strategy settings (such as enabling / disabling peak-valley arbitrage), and emergency power supply mode switching; and a comprehensive monitoring module: for maintenance personnel, displaying the real-time operating status of the zero-carbon home energy system, equipment anomaly information, and control command execution status, supporting anomaly alarms and fault location, enabling remote operation and maintenance of the user system, and reducing operation and maintenance costs.

[0046] Understandably, the security layer integrates security technologies such as identity authentication, data encryption, and access control to ensure the secure operation of the system. Specifically, this includes: employing data encryption and access control technologies to ensure the secure collection, transmission, and storage of private data such as household electricity usage data, device parameters, and user information, preventing data leakage, tampering, and loss; the communication layer: using SSL / TLS encrypted transmission and two-way authentication technologies to ensure secure data transmission; avoiding complex blockchain technology to reduce costs while ensuring that household data is not leaked or tampered with; employing access control and anomaly detection technologies to prevent unauthorized access and attacks; establishing a data backup and recovery mechanism to ensure data security and system continuity; and deploying lightweight security protection modules to avoid excessive consumption of computing power.

[0047] As can be seen from the above, this application reduces the uncertainty of photovoltaic power generation forecasting and load forecasting, as well as the impact of the control step size on the control results, based on the day-ahead, intraday, and real-time multi-timescale collaborative flexible control. This improves the speed, accuracy, and effectiveness of control, achieving refined flexible control. In practical engineering applications, a cloud-edge-device collaborative control mechanism has been established, clarifying the dynamic task allocation strategy of the cloud, edge, and device ends, thereby realizing the intelligent, digital, and smart flexible control of the zero-carbon home energy system.

[0048] Accordingly, see Figure 3 As shown, this application also provides a cloud-edge-device collaborative control device for a zero-carbon home energy system, applied to the zero-carbon home energy system, which is deployed with a cloud, an edge, and a device, including: The channel establishment module 11 is used to establish a first channel between the cloud and the edge, and to establish a second channel between the edge and the device, and to construct a bidirectional feedback channel based on the first channel and the second channel; The regulation model construction module 12 is used to model the uncertainty of the next day's power generation and power consumption forecast based on the cloud and using scenario analysis method, combined with historical power generation data and historical power consumption data, in order to construct various target scenarios, construct optimization targets based on electricity cost, user comfort, photovoltaic self-consumption rate and energy matching rate, and construct a day-ahead regulation model in combination with the target scenarios. The regulation scheme determination module 13 is used to solve the day-ahead regulation model based on the cloud and using a genetic algorithm to obtain the day-ahead regulation scheme, and to determine the operating parameters corresponding to the execution of the day-ahead regulation scheme. The operating parameters are then input into the intraday rolling correction model to obtain the intraday regulation scheme. The real-time scheme determination module 14 is used to collect multi-dimensional real-time operation data of the zero-carbon home energy system from the edge terminal, determine the priority order of the target flexible devices in the zero-carbon home energy system based on the multi-dimensional real-time operation data, and determine the real-time control scheme based on the priority order and in combination with the intraday control scheme. The system control module 15 is used to transmit the real-time control scheme to the device based on the edge terminal and using the bidirectional feedback channel, so that the device terminal can execute the control command corresponding to the real-time control scheme, and use the control command to perform cloud-edge-device collaborative control operation of the zero-carbon home energy system.

[0049] In some specific embodiments, the regulation model construction module 12 may specifically include: The target scenario construction unit is used to model the uncertainty of the next day's photovoltaic power generation and household electricity load forecast based on the cloud and using scenario analysis method, combined with meteorological forecast data, historical photovoltaic power generation data and historical household electricity load data, in order to construct each target scenario; The optimization objective determination unit is used to optimize the following objectives: minimizing electricity costs, maximizing user comfort, maximizing photovoltaic self-consumption rate, and maximizing energy matching rate. The day-ahead model building unit is used to build a day-ahead regulation model based on the optimization objective and the target scenario and using the chance-constrained programming method.

[0050] In some specific embodiments, the control scheme determination module 13 may specifically include: A multi-objective optimization solution unit is used to perform multi-objective optimization on the daytime regulation model based on the cloud and using a genetic algorithm to obtain a daytime regulation scheme including a first objective regulation time domain and a first objective regulation step size; An operating parameter determination unit is used to determine the operating parameters of each flexible device in the zero-carbon home energy system corresponding to the day-ahead control scheme. The intraday scheme determination submodule is used to input the operating parameters and the photovoltaic power generation forecast data for the day into the intraday rolling correction model to obtain the intraday control scheme.

[0051] In some specific implementations, the intraday plan determination submodule may specifically include: The intraday scheme determination unit is used to construct an intraday rolling correction model using model predictive control methods. The operating parameters and the photovoltaic power generation forecast data for the day are input into the intraday rolling correction model, and the genetic algorithm is used to solve the intraday rolling correction model to obtain an intraday control scheme including the second target control time domain and the second target control step size.

[0052] In some specific embodiments, the real-time scheme determination module 14 may specifically include: The flexibility potential determination unit is used to determine the flexibility potential of each flexible device in the zero-carbon home energy system based on the multi-dimensional real-time operating data. The target device determination unit determines whether the proportion of each of the aforementioned flexible potentials in the zero-carbon home energy system exceeds a target flexible proportion threshold, and determines the flexible devices that exceed the target flexible proportion threshold as target flexible devices based on the determination result. The priority order determination unit is used to determine the priority order of the target flexible device based on the flexibility potential corresponding to the target flexible device.

[0053] In some specific embodiments, the real-time scheme determination module 14 may specifically include: The real-time scheme determination unit is used to determine the rule control strategy for real-time response based on the priority order, and to determine the real-time control scheme by using the rule control strategy and combining it with the intraday control scheme.

[0054] In some specific embodiments, the cloud-edge-device coordinated control device of the zero-carbon home energy system may further include: The scheme correction unit is used to correct the day-ahead control scheme using the intraday control scheme within the daily scheduling cycle, and to correct the intraday control scheme using the real-time control scheme.

[0055] Furthermore, embodiments of this application also disclose an electronic device, Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the cloud-edge-device collaborative control method of the zero-carbon home energy system disclosed in any of the foregoing embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0056] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0057] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0058] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the cloud-edge-device collaborative control method of the zero-carbon home energy system executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0059] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned cloud-edge-device collaborative control method for a zero-carbon home energy system. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0060] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0061] 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.

[0062] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module 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.

[0063] 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.

[0064] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A cloud-edge-device coordinated control method for a zero-carbon home energy system, characterized in that, Applied to the zero-carbon home energy system, which is deployed at the cloud, edge, and device levels, the method includes: A first channel is established between the cloud and the edge, and a second channel is established between the edge and the device. A bidirectional feedback channel is constructed based on the first channel and the second channel. Based on the cloud and using scenario analysis, the uncertainty of the next day's power generation and consumption forecast is modeled by combining historical power generation data and historical power consumption data to construct various target scenarios. Optimization targets are constructed based on electricity cost, user comfort, photovoltaic self-consumption rate, and energy matching rate. A day-ahead control model is then constructed in conjunction with the target scenarios. Based on the cloud and using a genetic algorithm, the daytime regulation model is solved to obtain the daytime regulation scheme, and the operating parameters corresponding to the execution of the daytime regulation scheme are determined. The operating parameters are then input into the intraday rolling correction model to obtain the intraday regulation scheme. Based on the multi-dimensional real-time operation data of the zero-carbon home energy system collected at the edge, the priority order of the target flexible devices in the zero-carbon home energy system is determined based on the multi-dimensional real-time operation data, and a real-time control scheme is determined based on the priority order and in combination with the intraday control scheme. Based on the edge terminal and utilizing the bidirectional feedback channel, the real-time control scheme is transmitted to the device terminal, so that the device terminal executes the control command corresponding to the real-time control scheme, and uses the control command to perform cloud-edge-device collaborative control operation on the zero-carbon home energy system.

2. The cloud-edge-device coordinated control method for a zero-carbon home energy system according to claim 1, characterized in that, The method, based on the cloud and utilizing scenario analysis, combines historical power generation and consumption data to model the uncertainty of next day's power generation and consumption forecasts, constructing various target scenarios. Optimization targets are then built based on electricity costs, user comfort, photovoltaic self-consumption rate, and energy matching rate. Finally, a day-ahead control model is constructed based on these target scenarios, including: Based on the cloud and using scenario analysis, combined with meteorological forecast data, historical photovoltaic power generation data and historical household electricity load data, the uncertainty of the next day's photovoltaic power generation and household electricity load prediction is modeled to construct various target scenarios; The optimization objectives are to minimize electricity costs, maximize user comfort, maximize photovoltaic self-consumption rate, and maximize energy matching rate. Based on the optimization objective and the target scenario, a day-ahead control model is constructed using the opportunity-constrained programming method.

3. The cloud-edge-device coordinated control method for a zero-carbon home energy system according to claim 1, characterized in that, The process of solving the daytime regulation model based on the cloud and using a genetic algorithm to obtain the daytime regulation scheme includes: Based on the cloud and using a genetic algorithm, the daytime regulation model is optimized in multiple objectives to obtain a daytime regulation scheme including the first objective regulation time domain and the first objective regulation step size. Determine the operating parameters corresponding to the day-ahead control scheme for each flexible device in the zero-carbon home energy system; The operating parameters and the daily photovoltaic power generation forecast data are input into the intraday rolling correction model to obtain the intraday control scheme.

4. The cloud-edge-device coordinated control method for a zero-carbon home energy system according to claim 3, characterized in that, The step of inputting the operating parameters and the daily photovoltaic power generation forecast data into the intraday rolling correction model to obtain the intraday control scheme includes: A rolling correction model is constructed using model predictive control. The operating parameters and the photovoltaic power generation forecast data for the day are input into the rolling correction model. The genetic algorithm is then used to solve the rolling correction model to obtain an intraday control scheme that includes the second target control time domain and the second target control step size. The second target control time domain and the second target control step size are obtained by simulating various electricity consumption / generation scenarios, which are the intraday control time domain and intraday control step size.

5. The cloud-edge-device coordinated control method for a zero-carbon home energy system according to claim 1, characterized in that, Determining the priority order of target flexible devices in the zero-carbon home energy system based on the multi-dimensional real-time operating data includes: Based on the multi-dimensional real-time operational data, the flexibility potential of each flexible device in the zero-carbon home energy system is determined. Determine whether the proportion of each of the aforementioned flexible potentials in the zero-carbon home energy system exceeds the target flexible proportion threshold, and based on the determination result, identify the flexible devices that exceed the target flexible proportion threshold as target flexible devices; The priority order of the target flexible equipment is determined based on the flexibility potential corresponding to the target flexible equipment.

6. The cloud-edge-device coordinated control method for a zero-carbon home energy system according to claim 1, characterized in that, The process of determining the real-time control plan based on the priority order and in conjunction with the intraday control plan includes: Based on the priority order, a rule-based control strategy for real-time response is determined, and the real-time control scheme is determined by combining the rule-based control strategy with the intraday control scheme.

7. The cloud-edge-device coordinated control method for a zero-carbon home energy system according to any one of claims 1 to 6, characterized in that, Also includes: Within the daily scheduling cycle, the intraday control scheme is used to modify the day-ahead control scheme, and the real-time control scheme is used to modify the intraday control scheme.

8. A cloud-edge-device coordinated control device for a zero-carbon home energy system, characterized in that, Applied to the aforementioned zero-carbon home energy system, which is deployed at the cloud, edge, and device levels, including: The channel establishment module is used to establish a first channel between the cloud and the edge, and to establish a second channel between the edge and the device, and to construct a bidirectional feedback channel based on the first channel and the second channel; The regulation model construction module is used to model the uncertainty of the next day's power generation and consumption forecast based on the cloud and using scenario analysis method, combined with historical power generation data and historical power consumption data, in order to construct various target scenarios, construct optimization targets based on electricity cost, user comfort, photovoltaic self-consumption rate and energy matching rate, and construct the day-ahead regulation model in combination with the target scenarios; The regulation scheme determination module is used to solve the daytime regulation model based on the cloud and using a genetic algorithm to obtain the daytime regulation scheme, and to determine the operating parameters corresponding to the execution of the daytime regulation scheme. The operating parameters are then input into the intraday rolling correction model to obtain the intraday regulation scheme. The real-time scheme determination module is used to collect multi-dimensional real-time operation data of the zero-carbon home energy system from the edge terminal, determine the priority order of the target flexible devices in the zero-carbon home energy system based on the multi-dimensional real-time operation data, and determine the real-time control scheme based on the priority order and the intraday control scheme. The system control module is used to transmit the real-time control scheme to the device based on the edge terminal and using the bidirectional feedback channel, so that the device terminal can execute the control command corresponding to the real-time control scheme, and use the control command to perform cloud-edge-device collaborative control operation of the zero-carbon home energy system.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the cloud-edge-device collaborative control method for a zero-carbon home energy system as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store a computer program, wherein the computer program, when executed by a processor, implements the cloud-edge-device collaborative control method for a zero-carbon home energy system as described in any one of claims 1 to 7.

Images