A solar-based household energy storage and power supply method and system

Abstract

The present invention provides a household energy storage power supply method and system based on solar energy. The method includes: collecting solar energy by a solar panel and converting it into direct current; converting the direct current into alternating current through an inverter for use by household devices of a target user, and storing the direct current in an electrical energy storage unit; using an intelligent control unit to monitor in real time the power usage of household devices, the output power of the solar panel, and the weather conditions; adopting a predictive algorithm to estimate the future electrical energy demand based on the power usage, output power, and weather conditions, and performing predictive charge and discharge management on the electrical energy storage unit. The present invention integrates intelligent control, data prediction, real-time monitoring, and adaptive management, ensuring efficient, safe, and sustainable energy use. These innovations not only improve the energy utilization rate but also provide a convenient management experience for users, laying a foundation for the development of future energy systems.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage and power supply, and particularly to a household energy storage power supply method and system based on solar energy. Background Art

[0002] With the increasingly serious global energy crisis and environmental pollution problems, solar energy, as a clean and renewable energy source, has been widely concerned and applied. Solar power generation systems use solar panels to convert solar energy into electrical energy for use in household, commercial and industrial fields. However, solar power generation is affected by weather and day-night changes, resulting in unstable output electrical energy and also problems of electrical energy waste. Therefore, how to efficiently utilize solar energy for power generation and energy storage to provide stable and reliable power supply has become the focus of research.

[0003] Traditional household power supply systems usually rely on the power grid for power supply. Although electrical energy can be supplemented through solar power generation systems, they still need to rely on the power grid when solar energy is unstable. This not only has low electrical energy utilization efficiency and high costs, but also cannot provide stable power supply during power outages or power grid failures. Therefore, developing an efficient energy storage power supply system based on solar energy to achieve self-sufficient power supply for households has become a new development trend.

[0004] In the prior art, most solar household power supply systems have the following defects in application:

[0005] Traditional solar power supply systems usually do not have an effective energy storage solution. Electrical energy is wasted during the day when solar energy is excessive, and it needs to rely on the power grid at night or on cloudy days, reducing the energy utilization efficiency. Due to the influence of weather and day-night changes on solar power generation, even with basic energy storage devices, existing systems cannot provide continuous and stable power output, making it difficult to ensure the continuity of household electricity use. And many existing systems do not configure highly intelligent control units, cannot monitor and adjust the output and storage of electrical energy in real time, lack the ability of optimal scheduling, resulting in low electrical energy distribution efficiency. Most of the existing control units only perform simple charge and discharge management, lack the prediction of future electricity demand and weather forecasts, and cannot perform optimized energy scheduling and energy storage planning. Summary of the Invention

[0006] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide a household energy storage power supply method and system based on solar energy.

[0007] To achieve the above purpose, the present invention provides the following solutions:

[0008] A household energy storage power supply method based on solar energy, comprising:

[0009] Collecting solar energy using solar panels and converting it into direct current;

[0010] Convert the direct current into alternating current through an inverter for use by the household appliances of the target user, and store the direct current in the electrical energy storage unit;

[0011] Use the intelligent control unit to monitor the power consumption of the household appliances, the output power of the solar panels, and the weather conditions in real time;

[0012] Adopt a predictive algorithm to estimate the future electrical energy demand based on the power consumption, the output power, and the weather conditions, and perform predictive charge and discharge management on the electrical energy storage unit.

[0013] Preferably, the solar panels are installed on the roof of the building where the target user is located; the calculation formula for the output power of the solar panels is: P DC = A × E × η PV × f(T, γ, θ); where P DC is the output power of the solar panels, A is the effective area of the solar panels, E is the incident solar radiation intensity, η PV is the basic photoelectric conversion efficiency of the solar panels, and f(T, γ, θ) is the comprehensive correction function of the temperature T, dust coverage γ, and illumination angle θ factors; f(T, γ, θ) = f T (T) × f γ (γ) × f \θ (θ); where f T (T) = 1 - β · (T actual - T ref ); where f T (T) is the temperature correction sub-function, T actual is the current temperature, T ref is the reference temperature, and β is the temperature loss coefficient; f γ (γ) = 1 - k γ · γ; f γ (γ) is the dust coverage correction sub-function, γ is the dust coverage degree, and k γ is the dust coverage influence coefficient; f θ (θ) = cos(θ); f θ (θ) is the illumination angle correction sub-function, and θ is the angle between the incident light and the surface of the solar panels.

[0014] Preferably, the way to obtain the dust coverage degree is:

[0015] Set an image acquisition device at the solar panels; the image acquisition device is used to obtain the surface image of the solar panels;

[0016] Denoise the surface image to obtain a denoised image;

[0017] Segment the denoised image to obtain a feature image;

[0018] Input the feature image into the constructed dust coverage detection model to obtain the dust coverage.

[0019] Preferably, denoising the surface image to obtain a denoised image includes:

[0020] Take a neighborhood centered on each pixel point in the surface image;

[0021] Calculate the pixel feature value of each pixel point in the corresponding neighborhood;

[0022] Construct a smoothing denoising model according to the pixel feature value; the formula of the smoothing denoising model is: f(x) = 1 - exp(▽u(x) - ▽u mean (x) 2 - u(x) - u median (x)); where, ▽u(x) represents the gradient value of pixel point x in the corresponding neighborhood, ▽u mean (x) is the pixel mean value of the neighborhood centered on pixel point x, u(x) represents the pixel value of pixel point x, and u median (x) represents the pixel median value of the neighborhood centered on pixel point x;

[0023] Use the smoothing denoising model to denoise the surface image to obtain the denoised image.

[0024] Preferably, using the smoothing denoising model to denoise the surface image to obtain the denoised image includes:

[0025] Use the smoothing denoising model to calculate the smoothing value of each pixel point;

[0026] Denoise all pixel points with smoothing values greater than the denoising threshold using the mean filtering method to obtain the denoised image.

[0027] Preferably, adopt a predictive algorithm to estimate the future power demand based on the power usage situation, the output power of the electric energy, and the weather situation, and perform predictive charge and discharge management on the electric energy storage unit, including:

[0028] Obtain a preset power usage situation dataset, an output power of electric energy dataset, and a weather situation dataset;

[0029] Construct an initial convolutional neural network;

[0030] Train the initial convolutional neural network according to the power usage dataset, the output power dataset, and the weather dataset respectively to obtain the trained first classifier, second classifier, and third classifier;

[0031] Cascade the trained classifiers to obtain a classification network;

[0032] Connect the trained LSTM neural network after the classification network to obtain a CNN-LSTM combined neural network model;

[0033] Perform power prediction on the power usage, the output power, and the weather according to the CNN-LSTM combined neural network model to obtain power prediction data; the power prediction data includes the estimated power consumption of the target user and the predicted output power of the solar panel;

[0034] Use the power prediction data to perform predictive charge and discharge management on the energy storage unit.

[0035] Preferably, using the power prediction data to perform predictive charge and discharge management on the energy storage unit includes:

[0036] Define the maximum capacity B of the energy storage unit max and the minimum working power B of the energy storage unit min and the power B(t) of the energy storage unit at time t;

[0037] Construct an objective function with the minimization of the grid power usage during the prediction period as the optimization goal; the formula of the objective function is: Minimize∑ t GridPower(t)·Δt; where, where η discharge is the preset discharge efficiency of the energy storage unit, is the estimated power consumption of the target user at time t, is the predicted output power of the solar panel at time t;

[0038] Construct a power change formula; the formula of the power change formula is: where η charge is the preset charge efficiency of the energy storage unit;

[0039] Construct a constraint condition; the formula of the constraint condition is: B min ≥B(t)≤B max ;

[0040] Optimal solution calculation is performed according to the objective function, the power change formula, and the constraint conditions to perform predictive charge and discharge management.

[0041] A solar-based household energy storage power supply system, comprising:

[0042] A current acquisition module, configured to collect solar energy by a solar panel and convert it into direct current;

[0043] A storage module, configured to convert the direct current into alternating current through an inverter for use by household devices of a target user, and store the direct current in an electric energy storage unit;

[0044] A monitoring module, configured to use an intelligent control unit to monitor in real time the power usage of the household devices, the output power of the solar panel, and the weather conditions;

[0045] A management module, configured to adopt a predictive algorithm to estimate future power demand based on the power usage, the output power, and the weather conditions, and perform predictive charge and discharge management on the electric energy storage unit.

[0046] According to the specific embodiments provided by the present invention, the following technical effects are disclosed by the present invention:

[0047] The present invention provides a solar-based household energy storage power supply method and system. The method includes: collecting solar energy by a solar panel and converting it into direct current; converting the direct current into alternating current through an inverter for use by household devices of a target user, and storing the direct current in an electric energy storage unit; using an intelligent control unit to monitor in real time the power usage of the household devices, the output power of the solar panel, and the weather conditions; adopting a predictive algorithm to estimate future power demand based on the power usage, the output power, and the weather conditions, and performing predictive charge and discharge management on the electric energy storage unit. The present invention integrates intelligent control, data prediction, real-time monitoring, and adaptive management, ensuring efficient, safe, and sustainable energy use. These innovations not only improve the energy utilization rate but also provide users with a convenient management experience, laying a foundation for the development of future energy systems. Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1Flow chart of the method provided by the embodiment of the present invention;

[0050] Figure 2 Schematic diagram of the device connection provided by the embodiment of the present invention;

[0051] Figure 3 Schematic diagram of the system structure provided by the embodiment of the present invention. Detailed implementation manners

[0052] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0053] The purpose of the present invention is to provide a solar-based household energy storage power supply method, which can improve the energy utilization rate, provide users with a convenient management experience, and lay a foundation for the development of future energy systems.

[0054] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0055] Figure 1 Flow chart of the method provided by the embodiment of the present invention, as Figure 1 shown, the present invention provides a solar-based household energy storage power supply method, including:

[0056] Step 100: Collect solar energy using a solar panel and convert it into direct current;

[0057] Step 200: Convert the direct current into alternating current through an inverter for use by the household devices of the target user, and store the direct current in an electrical energy storage unit;

[0058] Step 300: Use an intelligent control unit to monitor the power usage of the household devices, the output power of the solar panel, and the weather conditions in real time;

[0059] Step 400: Adopt a predictive algorithm to estimate the future power demand based on the power usage, the output power, and the weather conditions, and perform predictive charge and discharge management on the electrical energy storage unit.

[0060] Preferably, the solar panel is arranged on the roof of the building where the target user is located; the calculation formula for the output power of the solar panel is: P DC = A × E × η PV×f(T, γ, θ); where P DC is the output power of the solar panel, A is the effective area of the solar panel, E is the incident solar radiation intensity, η PV is the basic photoelectric conversion efficiency of the solar panel, and f(T, γ, θ) is the comprehensive correction function of factors such as temperature T, dust coverage γ, and illumination angle θ; f(T, γ, θ) = f T (T) × f γ (γ) × f \θ (θ); where f T (T) = 1 - β·(T actual - T ref ); where f T (T) is the temperature correction sub-function, T actual is the current temperature, T ref is the reference temperature, and β is the temperature loss coefficient; f γ (γ) = 1 - k γ ·γ; f γ (γ) is the dust coverage correction sub-function, γ is the dust coverage degree, and k γ is the dust coverage influence coefficient; f θ (θ) = cos(θ); f θ (θ) is the illumination angle correction sub-function, and θ is the angle between the incident light and the surface of the solar panel.

[0061] Specifically, the formula of this embodiment is explained as follows:

[0062] P DC : The DC power output by the solar panel (unit: W).

[0063] A: The effective area of the solar panel (unit: m 2 ).

[0064] E: The incident solar radiation intensity (unit: W / m 2 ).

[0065] η PV : The basic photoelectric conversion efficiency of the solar panel (unit: dimensionless)

[0066] f(T, γ, θ): The comprehensive correction function of factors such as temperature (T), dust coverage (γ), and illumination angle (θ), used to dynamically adjust the efficiency.

[0067] Details of f(T, γ, θ):

[0068] T: Temperature. Generally, high temperature will reduce the efficiency of the solar panel.

[0069] γ: Dust coverage degree. Dust will reduce the absorption of light energy.

[0070] θ: Angle of illumination. The incident angle of sunlight has a significant impact on the effective utilization of solar energy.

[0071] Specifically, the efficiency of the solar panel in this embodiment varies with temperature. Therefore, a linear or non-linear correction model is used in this embodiment, which is described by the following formula:

[0072] f T (T) = 1 - β·(T actual - T ref ·

[0073] Where:

[0074] T actual : Current temperature (unit: °C).

[0075] T ref : Reference temperature, generally 25°C (unit: °C).

[0076] β: Temperature loss coefficient. Solar panels made of different materials have different β values, generally 0.004 - 0.006 / °C.

[0077] Dust coverage correction (γ): Dust coverage reduces the photoelectric conversion efficiency. The following correction formula can be used according to the dust coverage degree:

[0078] f γ (γ) = 1 - k γ ·γ

[0079] Where:

[0080] γ: Dust coverage degree (the specific value is obtained through an image acquisition device or estimation).

[0081] k γ : Dust coverage influence coefficient, determined according to experimental data, generally taking 0.01 - 0.03.

[0082] Illumination angle correction (θ):

[0083] The influence of the light incident angle on the efficiency can be corrected by the following formula:

[0084] f θ (θ) = cos(θ)

[0085] Where:

[0086] θ: Angle between the incident light and the surface of the solar panel (unit: degree)

[0087] Therefore, the comprehensive correction function can be expressed as:

[0088] f(T,γ,θ) = f T (T) × f γ (γ) × f \θ (θ)

[0089] Finally, the formula becomes:

[0090] P DC = A × E × η PV × (1 - β·(T actual - T ref )) × (1 - k γ ·γ) × cos(θ)

[0091] Furthermore, by considering the influence of temperature on the conversion efficiency in this embodiment, it can be adjusted in real time during actual operation to ensure the highest efficiency. And by monitoring the dust coverage status and making adjustments, the negative impact of dust on the solar power generation efficiency can be reduced. Finally, by optimizing the incident angle of light, the energy loss caused by the light angle can be reduced. This embodiment not only considers various actual influencing factors, but also provides a more scientific way for system design and control, making the output electric energy of the solar panel more reliable and efficient.

[0092] Preferably, the method for obtaining the dust coverage degree is as follows:

[0093] An image acquisition device is arranged at the solar panel; the image acquisition device is used to acquire the surface image of the solar panel;

[0094] Denoise the surface image to obtain a denoised image;

[0095] Segment the denoised image to obtain a feature image;

[0096] Input the feature image into the constructed dust coverage degree detection model to obtain the dust coverage degree.

[0097] Preferably, denoising the surface image to obtain a denoised image includes:

[0098] Take a neighborhood with each pixel point in the surface image as the center;

[0099] Calculate the pixel feature value of each pixel point in the corresponding neighborhood;

[0100] Construct a smoothing denoising model according to the pixel feature value; the formula of the smoothing denoising model is: Wherein, represents the gradient value of pixel point x in the corresponding neighborhood, is the pixel mean value of the neighborhood centered on pixel point x, u(x) represents the pixel value of pixel point x, u median(x) represents the median value of the pixels in the neighborhood centered on pixel point x;

[0101] The surface image is denoised using the smoothing denoising model to obtain the denoised image.

[0102] In practical applications, in this embodiment, the denoising threshold can be set according to the smoothing value of the pixel points. At the same time, all pixel points in the noise interval are subjected to mean filtering to obtain median pixel points, and then the values of all pixel points in the neighborhood are replaced with the median pixel points, so that the historical working image after denoising can be obtained. The original filtering algorithm, such as the mean filtering algorithm, performs mean processing on the pixel points in each neighborhood of the original image. Therefore, the processed image will become blurred. In this embodiment, by using the smoothing denoising model, the noise points on the image can be found, and then the corresponding noise points are subjected to mean filtering. While smoothing the noise points in the image, the original information of the image can be maximally preserved, so as to accurately identify the dust.

[0103] Specifically, the structure of the dust coverage detection model in this embodiment is as follows:

[0104] Input layer, used to input the image. The input is the denoised feature image, and its size is: H×W×C (for example, 224×224×3).

[0105] Convolutional layer, multiple convolutional layers are used to extract image features. The size of the convolutional kernel is 3×3 or 5×5, and the number of convolutional kernels usually starts from 64 and increases layer by layer (such as 64, 128, 256, etc.). The activation function is ReLU (Rectified Linear Unit)

[0106] Pooling layer, a pooling layer (such as max pooling) is added after every several convolutional layers. The pooling layer uses a 2×2 window and a stride of 2 to reduce the size of the feature map.

[0107] Flattening layer, which flattens the multi-dimensional convolutional feature map into a one-dimensional vector, usually added before the fully connected layer.

[0108] Fully connected layer, multiple fully connected layers (Dense Layers) are used for further feature extraction and classification. The number of output nodes is set according to the classification quantity of the dust coverage degree (for example, if it is divided into states such as slight, medium, and severe, the number of output nodes can be 3).

[0109] Output layer, using an activation function (such as softmax or sigmoid) to output the predicted probability or score of the dust coverage degree.

[0110] Furthermore, for the loss function of this embodiment, a loss function suitable for each task (such as cross-entropy loss) is selected for model training. Optimizers such as Adam or SGD are used to optimize the model parameters.

[0111] Furthermore, during the training process of this embodiment, data augmentation techniques (such as rotation, scaling, flipping, etc.) are used to enhance the generalization ability of the model. And this embodiment uses cross-validation or the method of dividing the training set and the validation set to evaluate the model to ensure its performance on different data sets.

[0112] Preferably, denoising the surface image using the smoothing denoising model to obtain the denoised image, including:

[0113] Calculating the smoothing value of each pixel point using the smoothing denoising model;

[0114] Denoising the pixel points with all smoothing values greater than the denoising threshold using the mean filtering method to obtain the denoised image.

[0115] Preferably, adopting a predictive algorithm to estimate the future power demand based on the power usage, the output power of the electrical energy, and the weather conditions, and performing predictive charge and discharge management on the electrical energy storage unit, including:

[0116] Obtaining a preset data set of power usage, a data set of output power of electrical energy, and a data set of weather conditions;

[0117] Constructing an initial convolutional neural network;

[0118] Respectively training the initial convolutional neural network according to the data set of power usage, the data set of output power of electrical energy, and the data set of weather conditions to obtain a trained first classifier, second classifier, and third classifier;

[0119] Cascading the trained classifiers to obtain a classification network;

[0120] Connecting a trained LSTM neural network after the classification network to obtain a CNN-LSTM combined neural network model;

[0121] Performing power prediction on the power usage, the output power of the electrical energy, and the weather conditions according to the CNN-LSTM combined neural network model to obtain power prediction data; the power prediction data includes the estimated power consumption of the target user and the predicted output power of the solar panel;

[0122] Performing predictive charge and discharge management on the electrical energy storage unit using the power prediction data.

[0123] Specifically, the specific implementation process of this embodiment is as follows:

[0124] 1. Data Preparation

[0125] ① Data acquisition: Acquire the preset power usage dataset, output power dataset, and weather condition dataset. The dataset should include historical data that can cover power usage and power output under different time periods and weather conditions.

[0126] ② Data preprocessing: Perform data cleaning to remove missing values and noise. Normalize or standardize the data to improve the model training efficiency. Divide the data into training set, validation set, and test set.

[0127] 2. Construct the initial convolutional neural network

[0128] ① CNN architecture design:

[0129] Input layer: Receive the feature maps of power usage, output power, and weather data.

[0130] Convolutional layer: Use several convolutional layers to extract features.

[0131] Pooling layer: Add a max pooling layer after the convolutional layer to reduce the feature dimension.

[0132] Fully connected layer: Pass the convolutional feature vectors into the fully connected layer and use an activation function (such as ReLU).

[0133] Output layer: Output the category or regression value (such as classifying power usage types or predicting relevant parameters such as power, which can be freely set).

[0134] 3. Train the CNN classifier

[0135] Training process: Use the power usage dataset, output power dataset, and weather condition dataset to train the CNN respectively. Use early stopping to avoid overfitting and set the validation set for monitoring.

[0136] 4. Cascade classifiers

[0137] Cascade the trained first classifier, second classifier, and third classifier to form a comprehensive classification network.

[0138] 5. Connect the LSTM neural network

[0139] The LSTM layer receives the output from the CNN and processes the time series data. In this embodiment, multiple LSTM layers and fully connected layers are added to improve the learning ability of the model and the accuracy of the output.

[0140] 6. CNN-LSTM combined model

[0141] Combine the output of the CNN with the input of the LSTM to form a combined CNN-LSTM model.

[0142] 7. Electric energy prediction

[0143] Run the model, and input the preprocessed power usage, output power, and weather conditions into the combined CNN-LSTM model for prediction. Obtain electric energy prediction data, including the estimated power consumption and the predicted output power of the solar panels.

[0144] 8. Predictive charge and discharge management

[0145] Use the prediction data: Perform charge and discharge management on the electric energy storage unit according to the electric energy prediction data. Exemplarily, the charge and discharge strategy of this embodiment is: when the predicted power consumption is higher than the actual output, discharge from the energy storage unit; when the actual output power is higher than the predicted power consumption, charge the electric energy storage unit.

[0146] 9. Model evaluation and optimization. Use metrics such as mean squared error (MSE) and mean absolute error (MAE) to evaluate the accuracy of the model. Adjust hyperparameters such as the learning rate and batch size according to the model evaluation results, and retrain to optimize the model performance.

[0147] Through the above steps of this embodiment, a combined neural network model integrating CNN and LSTM is implemented to effectively predict future electric energy demands. This predictive charge and discharge management scheme can significantly improve the efficiency and reliability of the household energy storage system.

[0148] Preferably, using the electric energy prediction data to perform predictive charge and discharge management on the electric energy storage unit includes:

[0149] Define the maximum capacity B of the electric energy storage unit max and the minimum working power level B of the electric energy storage unit min and the power level B(t) of the electric energy storage unit at time t;

[0150] Construct an objective function with the minimization of the grid power usage during the prediction period as the optimization goal; the formula of the objective function is: Minimize Σ t GridPower(t)·Δt; where, where η discharge is the preset discharge efficiency of the electric energy storage unit, is the estimated power consumption of the target user at time t, is the predicted output power of the solar panels at time t;

[0151] Construct the formula for power change; the formula for power change is as follows: where η charge is the preset charging efficiency of the electrical energy storage unit;

[0152] Construct the constraint conditions; the formula for the constraint conditions is: B min ≥B(t)≤B max ;

[0153] Perform optimal solution calculation according to the objective function, the formula for power change, and the constraint conditions to perform predictive charge and discharge management.

[0154] Specifically, in this embodiment, an existing linear programming solver (such as Gurobi, CPLEX, etc.) is used for optimization solution, and the specific steps are as follows:

[0155] 1. Install Gurobi and the Gurobi Python interface to ensure that the Gurobi optimization software and the corresponding Python interface have been installed. It can be downloaded and installed through the official website of Gurobi.

[0156] 2. Define the model parameters and variables. In the model, set the maximum capacity of the electrical energy storage unit, the minimum working power, as well as the estimated power consumption of the target user and the predicted output power of the solar panel.

[0157] 3. Create a Gurobi model, and use the API of Gurobi to create the model and decision variables, including the charging and discharging power.

[0158] 4. Define the objective function and the constraint conditions, and construct the objective function and the constraints according to the previous optimization model.

[0159] 5. Solve the model, use Gurobi to solve the optimization problem, and extract the results.

[0160] Furthermore, after obtaining the charge and discharge management strategy through solution in this embodiment, result analysis is carried out:

[0161] 1. Check whether the power exceeds the capacity range.

[0162] 2. Ensure that all constraint conditions are met.

[0163] If necessary, the objective function can be adjusted to optimize the charge and discharge strategy.

[0164] Through the above steps of this embodiment, it is possible to efficiently perform optimal solution calculation according to the objective function, the formula for power change, and the constraint conditions to execute predictive charge and discharge management.

[0165] Corresponding to the above method, the present embodiment also provides a household energy storage power supply system based on solar energy, including:

[0166] A current acquisition module, configured to collect solar energy by means of a solar panel and convert it into direct current electricity;

[0167] A storage module, configured to convert the direct current electricity into alternating current electricity through an inverter for use by household devices of a target user, and store the direct current electricity in an electric energy storage unit;

[0168] A monitoring module, configured to use an intelligent control unit to monitor in real time the power consumption of the household devices, the output power of the solar panel, and the weather conditions;

[0169] A management module, configured to adopt a predictive algorithm to estimate future electricity demand based on the power consumption, the output power of the electricity, and the weather conditions, and perform predictive charge and discharge management on the electric energy storage unit.

[0170] The beneficial effects of the present invention are as follows:

[0171] (1) The present invention can monitor in real time the power consumption of household devices, the solar output power, and the weather conditions, enabling the system to dynamically adjust its operation strategy to optimize energy use. By integrating data on power consumption, solar power generation, and weather conditions, a comprehensive system perspective is provided, and this integration helps to optimize overall energy management.

[0172] (2) The present invention adopts a predictive algorithm to estimate future electricity demand based on historical data and real-time monitoring data. This forward-looking approach enables the system to perform charge and discharge management in advance, reducing energy waste and risks. Moreover, the present invention can dynamically adjust the charge and discharge strategy according to the predicted data to ensure sufficient electricity supply during peak demand and charge during low demand to maintain the balance of the electricity quantity.

[0173] (3) The inverter of the present invention not only simply converts direct current electricity into alternating current electricity, but also takes into account the state of the energy storage unit to perform efficient conversion at an appropriate time, which helps to improve the overall efficiency of the system. In addition, the present invention can also convert alternating current electricity into direct current electricity when needed to charge the energy storage unit, further optimizing energy use.

[0174] (4) According to the real-time electricity quantity, predicted electricity demand, and solar output, the intelligent control unit of the present invention adaptively adjusts the electricity flow direction to ensure that the battery electricity quantity is maintained within a reasonable range. Moreover, the present invention can be set to preferentially use solar energy rather than relying on the power grid, enhancing the self-sufficiency ability and reducing electricity bills.

[0175] (5) The present invention can be expanded according to household needs, and more solar panels and energy storage units can be added to adapt to different usage scenarios. Moreover, it supports the access of various household devices, ensuring the wide applicability and flexibility of the system.

[0176] (6) By continuously collecting and analyzing data, the system of the present invention can perform trend prediction and further optimize management strategies. Users can view the power usage situation and energy storage status in real time through the interface, enhancing the user experience.

[0177] (7) By efficiently using solar energy, the present invention reduces the dependence on traditional fossil fuels, contributes to environmental protection, and conforms to the global sustainable development goals.

[0178] In this specification, each embodiment is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and reference can be made to the description in the method part for relevant parts.

[0179] In this article, specific examples are used to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, based on the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A solar-based household energy storage power supply method, characterized in that, Comprising: Collecting solar energy using a solar panel and converting it into direct current; Converting the direct current into alternating current through an inverter for use by the household appliances of the target user, and storing the direct current in an electrical energy storage unit; Using an intelligent control unit to monitor in real time the power consumption of the household appliances, the output power of the solar panel, and the weather conditions; Adopting a predictive algorithm to estimate the future electrical energy demand based on the power consumption, the output power, and the weather conditions, and obtaining electrical energy prediction data; Using the electrical energy prediction data to perform predictive charge and discharge management on the electrical energy storage unit; Using the electrical energy prediction data to perform predictive charge and discharge management on the electrical energy storage unit, including: Define the maximum capacity B of the electrical energy storage unit max , the minimum working power B of the electrical energy storage unit min , and the power B(t) of the electrical energy storage unit at time t; Construct an objective function with the goal of minimizing the grid power consumption during the prediction period; the formula of the objective function is: Minimize∑ t GridPower(t)·Δt; where, where, η discharge is the preset discharge efficiency of the electrical energy storage unit, is the estimated power consumption of the target user at time t, is the predicted output power of the solar panel at time t; Construct a power change formula; the power change formula is: where η charge is the preset charging efficiency of the electrical energy storage unit; Construct constraint conditions; the formula for the constraint conditions is: B min ≥B(t)≤B max ; Performing optimal solution calculation according to the objective function, the power change formula, and the constraint conditions for predictive charge and discharge management.

2. The method for household energy storage power supply based on solar energy according to claim 1, wherein, The solar panel is installed on the roof of the building where the target user is located; the calculation formula for the output power of the electric energy of the solar panel is: P DC = A × E × η PV × f(T, γ, θ); where P DC is the output power of the electric energy output by the solar panel, A is the effective area of the solar panel, E is the incident solar radiation intensity, η PV is the basic photoelectric conversion efficiency of the solar panel, and f(T, γ, θ) is the comprehensive correction function of the factors of temperature T, dust coverage γ, and illumination angle θ; f(T, γ, θ) = f T (T) × f γ (γ) × f \θ (θ); where f T (T) = 1 - β · (T actual - T ref ); where f T (T) is the temperature correction sub-function, T actual is the current temperature, T ref is the reference temperature, and β is the temperature loss coefficient; f γ (γ) = 1 - k γ · γ; f γ (γ) is the dust coverage correction sub-function, γ is the dust coverage degree, and k γ is the dust coverage influence coefficient; f θ (θ) = cos(θ); f θ (θ) is the illumination angle correction sub-function, and θ is the included angle between the incident light and the surface of the solar panel.

3. The household energy storage power supply method based on solar energy according to claim 2, wherein, The manner of obtaining the dust coverage degree is as follows: Setting an image acquisition device at the solar panel; the image acquisition device is used to acquire the surface image of the solar panel; Denosing the surface image to obtain a denoised image; Segmenting the denoised image to obtain a feature image; Inputting the feature image into a constructed dust coverage degree detection model to obtain the dust coverage degree.

4. The household energy storage power supply method based on solar energy according to claim 3, wherein Denosing the surface image to obtain a denoised image, including: Taking a neighborhood centered on each pixel point in the surface image; Calculating the pixel feature value of each pixel point in the corresponding neighborhood; Construct a smoothing and denoising model based on the pixel feature values; the formula of the smoothing and denoising model is: where represents the gradient value of pixel point x in the corresponding neighborhood, is the pixel mean of the neighborhood centered on pixel point x, u(x) represents the pixel value of pixel point x, and u median (x) represents the pixel median of the pixels in the neighborhood centered on pixel point x; Using the smoothing denoising model to denoise the surface image to obtain the denoised image.

5. The household energy storage power supply method based on solar energy according to claim 4, characterized in that Using the smoothing denoising model to denoise the surface image to obtain the denoised image, including: Using the smoothing denoising model to calculate the smoothing value of each pixel point; Denosing the pixel points with all smoothing values greater than the denoising threshold using the mean filtering method to obtain the denoised image.

6. The household energy storage power supply method based on solar energy according to claim 1, characterized in that Adopting a predictive algorithm to estimate the future electrical energy demand based on the power consumption, the output power, and the weather conditions, and obtaining electrical energy prediction data, including: Obtaining a preset power consumption data set, an output power data set, and a weather condition data set; Constructing an initial convolutional neural network; Respectively training the initial convolutional neural network according to the power consumption data set, the output power data set, and the weather condition data set to obtain a trained first classifier, a second classifier, and a third classifier; Cascading the trained classifiers to obtain a classification network; Connecting a trained LSTM neural network after the classification network to obtain a CNN-LSTM combined neural network model; Performing electrical energy prediction on the power consumption, the output power, and the weather conditions according to the CNN-LSTM combined neural network model to obtain electrical energy prediction data; the electrical energy prediction data includes the estimated power consumption of the target user and the predicted output power of the solar panel.

7. A household energy storage power supply system based on solar energy, characterized in that, Comprising: A current acquisition module for collecting solar energy using a solar panel and converting it into direct current; A storage module, which is used to convert the direct current into alternating current through an inverter for use by the household devices of the target user and store the direct current in an electrical energy storage unit; A monitoring module, which is used to use an intelligent control unit to monitor in real time the power consumption of the household devices, the output power of the solar panels, and the weather conditions; A management module, which is used to adopt a predictive algorithm to estimate the future electrical energy demand based on the power consumption, the output power of the electrical energy, and the weather conditions to obtain electrical energy prediction data, and use the electrical energy prediction data to perform predictive charge and discharge management on the electrical energy storage unit; Performing predictive charge and discharge management on the electrical energy storage unit by using the electrical energy prediction data includes: Define the maximum capacity B of the electrical energy storage unit max and the minimum working power B of the electrical energy storage unit min and the power B(t) of the electrical energy storage unit at time t; Construct an objective function with the minimization of the grid power consumption during the prediction period as the optimization goal; the formula of the objective function is: Minimize ∑ t GridPower(t)·Δt; where, where η discharge is the preset discharge efficiency of the electrical energy storage unit, is the estimated power consumption of the target user at time t, is the predicted output power of the solar panel at time t; Construct an electricity change formula; the electricity change formula is as follows: where η charge is the charging efficiency of a preset electric energy storage unit; Construct constraint conditions; the formula of the constraint conditions is: B min ≥B(t)≤B max ; Performing optimal solution calculation according to the objective function, the power change formula, and the constraint conditions to perform predictive charge and discharge management.

Images