Household energy storage power supply method and system based on solar energy

Through intelligent control units and predictive algorithms, real-time monitoring and optimization of solar panel output and household power demands is achieved, and efficient and stable power supply of solar energy storage systems is solved, which is a solution to the low power utilization efficiency and insufficient energy storage planning in the existing technology. question.

CN119093606AActive Publication Date: 2024-12-06TINJIN GUANGDIAN HUADIAN TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411200256.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-06
Estimated Expiration
2044-08-29

AI Technical Summary

Technical Problem

The existing solar household power supply system lacks effective energy storage solutions, resulting in low power utilization efficiency, unable to provide continuous and stable power output, and the control unit lacks intelligence, making it impossible to optimize power distribution and energy storage planning.

Method used

The intelligent control unit is used to monitor the household power usage and the output of solar panels in real time, estimate future electricity demand through predictive algorithms, conduct predictive charging and discharging management, and combine inverters and energy storage units to dynamically adjust the flow direction of the electricity.

Benefits of technology

It improves energy utilization, ensures efficient, safe and sustainable energy use, provides a convenient management experience, and reduces dependence on traditional power grids.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119093606A_ABST
    Figure CN119093606A_ABST
Patent Text Reader

Abstract

The invention provides a household energy storage power supply method and system based on solar energy. The method comprises the following steps: collecting solar energy by using a solar cell panel and converting the solar energy into direct current; the direct current is converted into alternating current through an inverter so as to be used by household equipment of a target user, and the direct current is stored in an electric energy storage unit; the intelligent control unit is used for monitoring the electric power use condition of household equipment, the output electric energy power of the solar cell panel and the weather condition in real time; a predictive algorithm is adopted, the future electric energy demand is estimated according to the electric power use condition, the output electric energy power and the weather condition, and predictive charging and discharging management is carried out on the electric energy storage unit. According to the invention, intelligent control, data prediction, real-time monitoring and adaptive management are integrated, and efficient, safe and sustainable energy use is ensured. The innovations not only improve the utilization rate of energy, but also provide convenient management experience for users, and lay a foundation for future energy system development.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] As the global energy crisis and environmental pollution become increasingly serious, solar energy as a clean and renewable energy source has attracted widespread attention and application. Solar power generation systems use solar panels to convert sunlight into electrical energy for use in homes, businesses, and industries. However, solar power generation is affected by weather and day-night changes, resulting in unstable output power and the problem of power waste. Therefore, how to efficiently use solar energy to generate electricity and store energy to provide stable and reliable power supply has become a research focus.

[0003] Traditional household power supply systems usually rely on the power grid. Although they can be supplemented by solar power generation systems, they still need to rely on the power grid when solar energy is unstable. This not only has low energy utilization efficiency and high costs, but also cannot provide stable power supply during power outages or power grid failures. Therefore, developing efficient energy storage power supply systems 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 home power supply systems have the following defects in application:

[0005] Traditional solar power supply systems usually do not have effective energy storage solutions. Electricity is wasted when there is excess solar energy during the day, and needs to rely on the power grid when there is insufficient energy at night or on cloudy days, which reduces energy utilization efficiency. Since solar power generation is affected by weather and day and night changes, even with basic energy storage devices, existing systems cannot provide continuous and stable power output, and it is difficult to ensure the continuity of household electricity use. In addition, many existing systems are not equipped with highly intelligent control units, cannot monitor and adjust the output and storage of electricity in real time, lack the ability to optimize scheduling, resulting in low efficiency in power distribution. Most of the existing control units only perform simple charging and discharging management, lack predictions 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, an object of the present invention is to provide a household energy storage and power supply method and system based on solar energy.

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

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

[0009] Use solar panels to collect solar energy and convert it into direct current electricity;

[0010] Converting the DC power into AC power through an inverter for use by the target user's home devices, and storing the DC power in an energy storage unit;

[0011] Using an intelligent control unit to monitor in real time the power usage of the household equipment, the output power of the solar panel and the weather conditions;

[0012] A predictive algorithm is used to estimate future power demand based on the power usage, the output power and the weather conditions, and predictive charging and discharging management of the power storage unit is performed.

[0013] Preferably, the solar panel is arranged on the roof of the building where the target user is located; the calculation formula of the output electric 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, f(T,γ,θ) is the comprehensive correction function of the 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 function, T actual is the current temperature, T ref is the reference temperature, β is the temperature loss coefficient; f γ (γ)=1-k γ ·γ;f γ (γ) is the dust coverage correction function, γ is the dust coverage degree, k γ is the dust coverage influence coefficient; f θ (θ) = cos(θ); f θ (θ) is the illumination angle correction function, and θ is the angle between the incident light and the surface of the solar panel.

[0014] Preferably, the dust coverage degree is obtained by:

[0015] An image acquisition device is arranged at the solar panel; the image acquisition device is used to acquire a surface image of the solar panel;

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

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

[0018] The characteristic image is input into a constructed dust coverage degree detection model to obtain the dust coverage degree.

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

[0020] Taking each pixel in the surface image as the center, taking a neighborhood;

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

[0022] A smoothing denoising model is constructed 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 x in the corresponding neighborhood, ▽u mean (x) is the mean pixel 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 of the neighborhood centered on pixel x;

[0023] The surface image is denoised using the smoothing denoising model to obtain the denoised image.

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

[0025] Calculate the smoothing value of each pixel using the smoothing denoising model;

[0026] All pixel points whose smoothing values ​​are greater than the denoising threshold are denoised using a mean filtering method to obtain the denoised image.

[0027] Preferably, a predictive algorithm is used to estimate future power demand based on the power usage, the output power and the weather conditions, and predictive charging and discharging management of the power storage unit is performed, including:

[0028] Obtaining a preset power usage data set, an output power data set, and a weather condition data set;

[0029] Construct an initial convolutional neural network;

[0030] The initial convolutional neural network is trained according to the power usage data set, the output electric energy power data set and the weather condition data set to obtain a trained first classifier, a second classifier and a third classifier;

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

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

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

[0034] The electric energy prediction data is used to perform predictive charging and discharging management on the electric energy storage unit.

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

[0036] Define the maximum capacity B of the energy storage unit max 、Minimum working power of the energy storage unit B min , the amount of electricity B(t) of the energy storage unit at time t;

[0037] The objective function is constructed with the optimization goal of minimizing the power usage of the power grid during the forecast period; the formula of the objective function is: Minimize∑ t GridPower(t)·Δt; where, Among them, 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 power change formula is: Among them, η charge is the charging efficiency of the preset electric energy storage unit;

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

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

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

[0042] A current collection module is used to collect solar energy using a solar panel and convert it into direct current;

[0043] A storage module, used to convert the direct current into alternating current through an inverter for use by the target user's household equipment, and store the direct current in an electric energy storage unit;

[0044] A monitoring module, for monitoring the power usage of the household equipment, the output power of the solar panel and the weather conditions in real time using an intelligent control unit;

[0045] The management module is used to adopt a predictive algorithm to estimate future power demand based on the power usage, the output power and the weather conditions, and to perform predictive charging and discharging management of the power storage unit.

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

[0047] The present invention provides a method and system for household energy storage and power supply based on solar energy, the method comprising: using solar panels to collect solar energy and convert it into direct current; converting the direct current into alternating current through an inverter for use by household devices of target users, and storing the direct current in an electric energy storage unit; using an intelligent control unit to monitor the power usage of the household devices, the output power of the solar panels and weather conditions in real time; using a predictive algorithm to estimate future power demand based on the power usage, the output power and the weather conditions, and perform predictive charging and discharging management on the electric energy storage unit. The present invention integrates intelligent control, data prediction, real-time monitoring and adaptive management to ensure efficient, safe and sustainable energy use. These innovations not only improve energy utilization, but also provide users with a convenient management experience, laying the foundation for the development of future energy systems. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0049] Figure 1A flow chart of a method provided by an embodiment of the present invention;

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

[0051] Figure 3 A schematic diagram of the system structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

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

[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0055] Figure 1 A flow chart of a method provided by an embodiment of the present invention, such as Figure 1 As shown, the present invention provides a household energy storage power supply method based on solar energy, comprising:

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

[0057] Step 200: converting the DC power into AC power through an inverter for use by the target user's household devices, and storing the DC power in an energy storage unit;

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

[0059] Step 400: using a predictive algorithm to estimate future power demand based on the power usage, the output power and the weather conditions, and performing predictive charging and discharging management on the power storage unit.

[0060] Preferably, the solar panel is arranged on the roof of the building where the target user is located; the calculation formula of the output electric 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, f(T,γ,θ) is the comprehensive correction function of the 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 function, T actual is the current temperature, T ref is the reference temperature, β is the temperature loss coefficient; f γ (γ)=1-k γ γ; f γ (γ) is the dust coverage correction subfunction, γ is the dust coverage degree, k γ is the dust coverage influence coefficient; f θ (θ) = cos(θ); f θ (θ) is the illumination angle correction 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 : DC power output by solar panels (unit: W).

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

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

[0065] η PV :Basic photoelectric conversion efficiency of solar panels (unit: dimensionless)

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

[0067] Detailed explanation of f(T,γ,θ):

[0068] T: Temperature. Usually high temperature will reduce the efficiency of solar panels.

[0069] γ: Dust coverage. Dust reduces the absorption of light energy.

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

[0071] Specifically, the efficiency of the solar panel in this embodiment will change with the temperature. Therefore, this embodiment uses a linear or nonlinear correction model, as described by the following formula:

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

[0073] in:

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

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

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

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

[0078] f γ (γ)=1-k γ γ

[0079] in:

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

[0081] k γ : Dust coverage influence coefficient is determined based on experimental data and is generally taken as 0.01-0.03.

[0082] Lighting angle correction (θ):

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

[0084] f θ (θ) = cos(θ)

[0085] in:

[0086] θ: The 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 effect of temperature on conversion efficiency, this embodiment can make real-time adjustments in actual operation to ensure the highest efficiency. And by monitoring the dust coverage state and making adjustments, the negative impact of dust on solar power generation efficiency can be reduced. Finally, by optimizing the incident angle of light, the energy loss caused by the angle of light can be reduced. This embodiment not only takes into account a variety of actual influencing factors, but also provides a more scientific way for system design and control, making the output power of solar panels more reliable and efficient.

[0092] Preferably, the dust coverage degree is obtained by:

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

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

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

[0096] The characteristic image is input into a constructed dust coverage degree detection model to obtain the dust coverage degree.

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

[0098] Taking each pixel in the surface image as the center, taking a neighborhood;

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

[0100] A smoothing denoising model is constructed according to the pixel feature value; the formula of the smoothing denoising model is: in, 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 neighborhood centered on pixel x;

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

[0102] In practical applications, this embodiment can set a denoising threshold according to the smoothing value of the pixel point, and at the same time, perform mean filtering on all the pixels in the noise interval to obtain the median pixel point, and then use the median pixel point to replace the values ​​of all the pixels in the neighborhood, so as to obtain the denoised historical working image. The original filtering algorithm, such as the mean filtering algorithm, performs mean processing on the pixels in each neighborhood on the original image, so the processed image will become blurred, while this embodiment can find the noise points on the image by using the smoothing denoising model, and then perform mean filtering on the corresponding noise points to smooth out the noise points in the image while maximally maintaining the original information of the image, so that dust can be accurately identified.

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

[0104] The input layer is used to input an image. The input is a denoised feature image with a size of H×W×C (for example, 224×224×3).

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

[0106] Pooling layer, add a pooling layer (such as maximum pooling) after each convolutional layer. The pooling layer uses a 2×2 window with a step size of 2 to reduce the size of the feature map.

[0107] The flattening layer flattens the multi-dimensional convolutional feature map into a one-dimensional vector and is usually added before the fully connected layer.

[0108] Fully connected layers, multiple fully connected layers (Dense Layers) are used for further feature extraction and classification. The number of output nodes is set according to the number of classifications of dust coverage (for example, if it is divided into mild, moderate, severe, etc., the number of output nodes can be 3).

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

[0110] Furthermore, the loss function of this embodiment selects a loss function suitable for each task (such as cross entropy loss) to perform model training. The optimizer uses an optimizer such as Adam or SGD to optimize model parameters.

[0111] Furthermore, in the training process, this embodiment uses data enhancement techniques (such as rotation, scaling, flipping, etc.) 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 comprises:

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

[0114] All pixel points whose smoothing values ​​are greater than the denoising threshold are denoised using a mean filtering method to obtain the denoised image.

[0115] Preferably, a predictive algorithm is used to estimate future power demand based on the power usage, the output power and the weather conditions, and predictive charging and discharging management of the power storage unit is performed, including:

[0116] Obtaining a preset power usage data set, an output power data set, and a weather condition data set;

[0117] Construct an initial convolutional neural network;

[0118] The initial convolutional neural network is trained according to the power usage data set, the output electric energy power data set and the weather condition data set to obtain a trained first classifier, a second classifier and a third classifier;

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

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

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

[0122] The electric energy prediction data is used to perform predictive charging and discharging management on the electric energy storage unit.

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

[0124] 1. Data preparation

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

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

[0127] 2. Constructing the initial convolutional neural network

[0128] ①CNN architecture design:

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

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

[0131] Pooling layer: A max pooling layer is added after the convolutional layer to reduce the feature dimension.

[0132] Fully connected layer: The convolution feature vector is passed into the fully connected layer and an activation function (such as ReLU) is used.

[0133] Output layer: Output categories or regression values ​​(such as classifying electricity usage types or predicting power and other related parameters, which can be set freely).

[0134] 3. Training CNN Classifier

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

[0136] 4. Cascade Classifier

[0137] The trained first classifier, second classifier and third classifier are cascaded to form a comprehensive classification network.

[0138] 5. Connecting LSTM Neural Network

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

[0140] 6. CNN-LSTM combination model

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

[0142] 7. Electricity forecast

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

[0144] 8. Predictive charge and discharge management

[0145] Use prediction data: manage the charge and discharge of the energy storage unit according to the power 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 to the energy storage unit.

[0146] 9. Model evaluation and optimization, use indicators such as mean square error (MSE) and mean absolute error (MAE) to evaluate the accuracy of the model. Adjust hyperparameters such as learning rate and batch size based on the model evaluation results, and train again to optimize model performance.

[0147] Through the above steps of this embodiment, a combined neural network model combining CNN and LSTM is implemented to effectively predict future power demand. This predictive charge and discharge management solution can significantly improve the efficiency and reliability of home energy storage systems.

[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 energy storage unit max 、Minimum working power of the energy storage unit B min , the amount of electricity B(t) of the energy storage unit at time t;

[0150] The objective function is constructed with the optimization goal of minimizing the power usage of the power grid during the forecast period; the formula of the objective function is: MinimizeΣ t GridPower(t)·Δt; where, Among them, 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;

[0151] Construct a power change formula; the power change formula is: Among them, η charge is the charging efficiency of the preset electric energy storage unit;

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

[0153] An optimal solution calculation is performed based on the objective function, the power change formula and the constraint conditions to perform predictive charge and discharge management.

[0154] Specifically, this embodiment uses an existing linear programming solver (such as Gurobi, CPLEX, etc.) to perform optimization and solving, and the specific steps are as follows:

[0155] 1. Install Gurobi and Gurobi Python interface. Make sure that the Gurobi optimization software and the corresponding Python interface are installed. You can download and install them from Gurobi's official website.

[0156] 2. Define the model parameters and variables. In the model, set the maximum capacity and minimum working power of the energy storage unit, 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 Gurobi's API to create the model and decision variables, including charging and discharging power.

[0158] 4. Define the objective function and constraints, and build them based on the previous optimization model.

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

[0160] Furthermore, after solving the charge and discharge management strategy obtained in this embodiment, the result analysis is performed:

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

[0162] 2. Make sure all constraints are met.

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

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

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

[0166] A current collection module is used to collect solar energy using a solar panel and convert it into direct current;

[0167] A storage module, used to convert the direct current into alternating current through an inverter for use by the target user's household equipment, and store the direct current in an electric energy storage unit;

[0168] A monitoring module, for monitoring the power usage of the household equipment, the output power of the solar panel and the weather conditions in real time using an intelligent control unit;

[0169] The management module is used to adopt a predictive algorithm to estimate future power demand based on the power usage, the output power and the weather conditions, and to perform predictive charging and discharging management of the power storage unit.

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

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

[0172] (2) The present invention uses a predictive algorithm to estimate future power demand based on historical data and real-time monitoring data. This forward-looking approach enables the system to manage charging and discharging in advance, reducing energy waste and risks. The present invention can also dynamically adjust the charging and discharging strategy based on the predicted data to ensure sufficient power supply during peak demand, and to charge during low demand to maintain a balance of power.

[0173] (3) The inverter of the present invention does not simply convert DC power into AC power, but also takes into account the state of the energy storage unit so as to perform efficient conversion at the appropriate time, which helps to improve the overall efficiency of the system. In addition, the present invention can also convert AC power into DC power when necessary to charge the energy storage unit, further optimizing energy use.

[0174] (4) The present invention uses the real-time power consumption, predicted power demand and solar energy output, and the intelligent control unit will adaptively adjust the power flow to ensure that the battery power is maintained within a reasonable range. The present invention can also set the priority to use solar energy instead of relying on the power grid, thereby improving self-sufficiency and reducing electricity costs.

[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. It also supports the access of multiple household devices to ensure the wide applicability and flexibility of the system.

[0176] (6) The present invention continuously collects and analyzes data, and the system can predict trends and further optimize management strategies. Users can view power usage and energy storage status in real time through the interface, which enhances user experience.

[0177] (7) The present invention reduces dependence on traditional fossil fuels by efficiently utilizing solar energy, thus contributing to environmental protection and complying with global sustainable development goals.

[0178] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0179] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A household energy storage power supply method based on solar energy, characterized in that: include: Use solar panels to collect solar energy and convert it into direct current electricity; Converting the DC power into AC power through an inverter for use by the target user's home devices, and storing the DC power in an energy storage unit; Using an intelligent control unit to monitor in real time the power usage of the household equipment, the output power of the solar panel and the weather conditions; A predictive algorithm is used to estimate future power demand based on the power usage, the output power and the weather conditions, and predictive charging and discharging management of the power storage unit is performed.

2. The method for household energy storage and power supply based on solar energy according to claim 1, characterized in that: The solar panel is arranged on the roof of the building where the target user is located; the calculation formula of the output electric 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, f(T,γ,θ) is the comprehensive correction function of the 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 function, T actual is the current temperature, T ref is the reference temperature, β is the temperature loss coefficient; f γ (γ)=1-k γ γ; f γ (γ) is the dust coverage correction function, γ is the dust coverage degree, k γ is the dust coverage influence coefficient; f θ (θ) = cos(θ); f θ (θ) is the illumination angle correction function, and θ is the angle between the incident light and the surface of the solar panel.

3. The solar energy-based household energy storage and power supply method according to claim 2, characterized in that: The dust coverage degree is obtained as follows: An image acquisition device is arranged at the solar panel; the image acquisition device is used to acquire a surface image of the solar panel; Denoising the surface image to obtain a denoised image; Segmenting the denoised image to obtain a feature image; The characteristic image is input into a constructed dust coverage degree detection model to obtain the dust coverage degree.

4. The method for household energy storage and power supply based on solar energy according to claim 3, characterized in that: Denoising the surface image to obtain a denoised image, comprising: Taking each pixel in the surface image as the center, taking a neighborhood; Calculate the pixel feature value of each pixel in the corresponding neighborhood; A smoothing denoising model is constructed according to the pixel feature value; the formula of the smoothing denoising model is: in, Represents the gradient value of pixel point x in the corresponding neighborhood, is the mean pixel 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 x; The surface image is denoised using the smoothing denoising model to obtain the denoised image.

5. The method for household energy storage and power supply based on solar energy according to claim 4, characterized in that: Denoising the surface image using the smoothing denoising model to obtain the denoised image, comprising: Calculate the smoothing value of each pixel using the smoothing denoising model; All pixel points whose smoothing values ​​are greater than the denoising threshold are denoised using a mean filtering method to obtain the denoised image.

6. The method for household energy storage and power supply based on solar energy according to claim 1, characterized in that: A predictive algorithm is used to estimate future power demand based on the power usage, the output power and the weather conditions, and predictive charging and discharging management of the power storage unit is performed, including: Obtaining a preset power usage data set, an output power data set, and a weather condition data set; Construct an initial convolutional neural network; The initial convolutional neural network is trained according to the power usage data set, the output electric energy power data set and the weather condition data set to obtain a trained first classifier, a second classifier and a third classifier; Cascade the trained classifiers to obtain a classification network; Connecting the trained LSTM neural network after the classification network to obtain a CNN-LSTM combined neural network model; Performing power forecasting on the power usage, the output power and the weather conditions according to the CNN-LSTM combined neural network model to obtain power forecasting data; the power forecasting data includes the estimated power consumption of the target user and the predicted output power of the solar panel; The electric energy prediction data is used to perform predictive charging and discharging management on the electric energy storage unit.

7. The method for household energy storage and power supply based on solar energy according to claim 6, characterized in that: Using the electric energy prediction data to perform predictive charge and discharge management on the electric energy storage unit includes: Define the maximum capacity B of the energy storage unit max 、Minimum working power of the energy storage unit B min , the amount of electricity B(t) of the energy storage unit at time t; The objective function is constructed with the minimization of the power usage of the power grid during the forecast period as the optimization goal; the formula of the objective function is: Minimize∑ t GridPower(t)·Δt; where, Among them, 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; Construct a power change formula; the power change formula is: Among them, η charge is the charging efficiency of the preset electric energy storage unit; Construct constraint conditions; the constraint condition formula is: B min ≥B(t)≤B max ; An optimal solution calculation is performed based on the objective function, the power change formula and the constraint conditions to perform predictive charge and discharge management.

8. A household energy storage power supply system based on solar energy, characterized in that: include: A current collection module is used to collect solar energy using a solar panel and convert it into direct current; A storage module, used to convert the direct current into alternating current through an inverter for use by the target user's household equipment, and store the direct current in an electric energy storage unit; A monitoring module, for monitoring the power usage of the household equipment, the output power of the solar panel and the weather conditions in real time using an intelligent control unit; The management module is used to adopt a predictive algorithm to estimate future power demand based on the power usage, the output power and the weather conditions, and to perform predictive charging and discharging management of the power storage unit.

Citation Information

Patent Citations

  • Isolated island microgrid real-time schedule energy management system

    CN105846418A

  • Optical storage power distribution method of comprehensive energy supply station

    CN117748609A

  • Cooperative energy management method and system for unmanned traveling vehicle in travel scenic area

    CN117996853A

  • Intelligent charging and discharging scheduling method and device and electronic equipment

    CN118017649A

  • Sensor module

    KR1020250007786A