Power generation management method of embedded photovoltaic module and electronic equipment

Abstract

The invention discloses a power generation management method of an embedded photovoltaic module and electronic equipment, and relates to the related field of light-to-electricity supervision, and the method comprises the steps: carrying out the power tracking of the embedded photovoltaic module according to a power generation state data set of the embedded photovoltaic module, a power generation electric energy data set is determined, and a historical power utilization data set of the embedded photovoltaic module is called to carry out power utilization prediction, so that power utilization demand prediction information is obtained to carry out energy management, and a power generation management strategy is formulated to carry out charge and discharge analysis on the embedded photovoltaic module; and generating an electric energy management feedback signal, sending the electric energy management feedback signal to a remote management terminal to respond and update a power generation management strategy, and generating a power generation management optimization strategy to perform intelligent power generation management on the embedded photovoltaic module. The technical problems of low energy utilization rate, unreasonable power utilization allocation and poor energy storage management efficiency in the power generation process are solved, and the technical effects of preferentially meeting the power utilization requirement of key equipment, intelligently releasing stored redundant electric energy, improving the energy utilization rate and power supply reliability and performing intelligent management are achieved.

Description

Technical Field

[0001] This application relates to the field of optoelectronic conversion supervision, and particularly to a power generation management method and an electronic device for embedded photovoltaic modules. Background Art

[0002] With the development of renewable energy technologies, due to their high integration and strong aesthetics, embedded photovoltaic modules are gradually applied to doors, windows, curtain walls, and building frames, becoming an important part of green buildings. However, in actual use, the power generation management of such photovoltaic modules still faces various challenges. First, since photovoltaic power generation is greatly affected by factors such as light intensity and weather changes, the power generation is volatile, and it is difficult for traditional management methods to achieve real-time regulation, resulting in low power generation utilization efficiency. Second, embedded photovoltaic modules are usually connected to multiple electrical equipment in buildings, such as door and window control, indoor lighting, and air conditioning. Without an efficient power consumption priority scheduling strategy, it may cause insufficient power supply for critical equipment or waste of electric energy. In addition, the excess generated electric energy needs to be stored through energy storage devices to meet the power consumption requirements at night or under low light conditions. However, the charge and discharge strategies of existing energy storage systems are usually in a fixed mode, which fails to fully consider the real-time power consumption demand and power generation volatility, and is prone to inefficient operation or excessive loss of energy storage devices. Summary of the Invention

[0003] This application provides a power generation management method and an electronic device for embedded photovoltaic modules, which solve the technical problems of low energy utilization efficiency, unreasonable power consumption allocation, and poor energy storage management efficiency during the power generation process of embedded photovoltaic modules, and achieve the technical effects of preferentially meeting the power consumption needs of critical equipment, efficiently storing and intelligently releasing excess electric energy, significantly improving the energy utilization efficiency and power supply reliability of the photovoltaic system, and simultaneously realizing the intelligent management of the energy system.

[0004] This application provides a power generation management method for embedded photovoltaic modules, including: performing real-time power generation sensing on the embedded photovoltaic modules through a sensor device group to obtain a power generation status data set of the embedded photovoltaic modules; performing power tracking on the embedded photovoltaic modules according to the power generation status data set to determine a power generation electric energy data set; retrieving the historical power consumption data set of the embedded photovoltaic modules for power consumption prediction to obtain power consumption demand prediction information; performing energy management on the power generation electric energy data set according to the power consumption demand prediction information to formulate a power generation management strategy; simulating and executing the power generation management strategy to perform charge and discharge analysis on the embedded photovoltaic modules, generating an electric energy management feedback signal, sending the electric energy management feedback signal to a remote management terminal for response, updating the power generation management strategy according to the response result, and generating a power generation management optimization strategy to perform intelligent power generation management on the embedded photovoltaic modules.

[0005] In a possible implementation manner, power tracking is performed on the embedded photovoltaic module according to the power generation status data set to determine a power generation electric energy data set, and the following processing is performed: output voltage data and output current data are extracted based on the power generation status data set; perturbation calculation is performed through the output voltage data and the output current data to obtain output power data; power fluctuation tracking is performed on the embedded photovoltaic module according to the output power data to determine a plurality of periodic fluctuation points; power comparison is performed according to the plurality of periodic fluctuation points, and calculation is performed in combination with the sampling period according to the comparison result to obtain the power generation electric energy data set.

[0006] In a possible implementation manner, the historical power consumption data set of the embedded photovoltaic module is retrieved for power consumption prediction to obtain power consumption demand prediction information, and the following processing is performed: the historical data record log of the embedded photovoltaic module is traversed for power consumption analysis, and the historical power consumption data set is retrieved; the historical power consumption data set is arranged in sequence according to the power consumption time sequence to construct a continuous power consumption time series; power consumption capture is performed on the historical power consumption data set according to the continuous power consumption time series to generate a long-term power consumption dependence coefficient; power consumption capture is performed on the historical power consumption data set according to the continuous power consumption time series to generate a short-term power consumption dependence coefficient; prediction analysis is performed according to the long-term power consumption dependence coefficient and the short-term power consumption dependence coefficient to generate the power consumption demand prediction information.

[0007] In a possible implementation manner, prediction analysis is performed according to the long-term power consumption dependence coefficient and the short-term power consumption dependence coefficient to generate the power consumption demand prediction information, and the following processing is performed: the long-term power consumption dependence coefficient is mapped to the historical power consumption data set for prediction training to generate long-term power consumption prediction data; the short-term power consumption dependence coefficient is mapped to the historical power consumption data set for prediction training to generate short-term power consumption prediction data; the long-term power consumption prediction data and the short-term power consumption prediction data are cross-combined according to the continuous power consumption time series, and backpropagation is performed according to the combination result to generate a plurality of power consumption weight values; calculation is performed on the combination result according to the plurality of power consumption weight values to generate a plurality of time windows, and the plurality of time windows have a plurality of power consumption prediction results; demand analysis is performed on the plurality of power consumption prediction results according to the plurality of time windows to obtain the power consumption demand prediction information.

[0008] In a possible implementation manner, perform energy management on the generated power dataset according to the power consumption demand prediction information, formulate a power generation management strategy, and execute the following processing: Use the power consumption demand prediction information as a power consumption critical value, traverse the generated power dataset according to the power consumption critical value for power consumption analysis, and set power consumption demand constraint conditions; Define power consumption priorities based on the multiple power consumption weight values, match the power consumption demand prediction information with the generated power dataset according to the power consumption priorities, and generate a power consumption power list; Slice the power consumption power list to generate multiple time slices, perform state transitions according to the multiple time slices, and generate multiple energy storage state information sets; Perform dynamic programming according to the multiple energy storage state information sets in combination with the multiple time slices to formulate the power generation management strategy.

[0009] In a possible implementation manner, slice the power consumption power list to generate multiple time slices, perform state transitions according to the multiple time slices, and generate multiple energy storage state information sets, and execute the following processing: Randomly extract based on the multiple time slices to obtain a first time slice and a second time slice. The first time slice and the second time slice are adjacent, and the first time slice is the previous time slice of the second time slice; Traverse the power consumption power list based on the first time slice for matching to obtain the first power data of the first time slice, perform energy storage calculation according to the first power data, and obtain the energy storage state information set of the first time slice; Perform energy storage transfer calculation on the second time slice according to the energy storage state information set of the first time slice to generate the energy storage state information set of the second time slice, and iterate in this way. Stop traversing after completing the multiple time slices to obtain the multiple energy storage state information sets.

[0010] In a possible implementation manner, simulate the execution of the power generation management strategy to perform charge and discharge analysis on the embedded photovoltaic module, generate a power management feedback signal, and execute the following processing: Perform power fluctuation analysis based on the power generation management strategy to determine the power fluctuation range; Perform dynamic simulation according to the power generation management strategy based on the power fluctuation range to obtain dynamic photovoltaic power generation simulation data; Determine whether the dynamic photovoltaic power generation simulation data is greater than or equal to the power consumption demand prediction information; If the dynamic photovoltaic power generation simulation data is greater than or equal to the power consumption demand prediction information, calculate the charging power and generate a charging power parameter; If the dynamic photovoltaic power generation simulation data is less than the power consumption demand prediction information, calculate the discharging power and generate a discharging power parameter; Perform energy storage feedback according to the charging power parameter and the discharging power parameter to generate a strategy adjustment suggestion; Add the strategy adjustment suggestion to the power management feedback signal.

[0011] The present application also provides an electronic device, including: a memory for storing executable instructions; and a processor for implementing a power generation management method for an embedded photovoltaic module when executing the executable instructions stored in the memory.

[0012] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0013] The power generation management method and the electronic device for the embedded photovoltaic module provided in the present application solve the technical problems of low energy utilization rate, unreasonable power allocation, and poor energy storage management efficiency during the power generation process of the embedded photovoltaic module, achieving the technical effects of preferentially meeting the power consumption requirements of key devices, efficiently storing and intelligently releasing surplus electric energy, significantly improving the energy utilization rate and power supply reliability of the photovoltaic system, and realizing the intelligent management of the energy system at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in the present application to illustrate the operations performed by the methods according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0015] Figure 1 It is a schematic flowchart of the power generation management method for the embedded photovoltaic module provided in the embodiment of the present application;

[0016] Figure 2 It is a schematic structural diagram of an electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The above description is only an overview of the technical solutions of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are given below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0019] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art of the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0020] The embodiments of this application provide a power generation management method for embedded photovoltaic modules, as Figure 1 shown, the method includes:

[0021] Step A100, performing real-time power generation sensing on the embedded photovoltaic modules through a sensor device group to obtain a power generation status data set of the embedded photovoltaic modules; first, performing sensing analysis according to the layout position information and layout environment information of the embedded photovoltaic modules to determine the sensor device layout conditions. The embedded photovoltaic modules can be photovoltaic modules embedded in doors and windows, frames, curtain walls, etc., and the sensor device group is deployed for sensing according to the sensor device layout conditions. The sensor device group includes a voltage sensor, a current sensor, an ambient light sensor, a temperature sensor, etc. A data sampling period (such as 1 second or 5 seconds) can be set, and key parameters such as the output voltage V, output current I, light intensity L, and module temperature T are collected regularly. Moreover, the sampling frequency in the sampling period can be adjusted according to the application scenario. At the same time, the output power is calculated according to the voltage and current collected in real time, and the collected raw data and the calculated power data are stored as a time series to form a power generation status data set. At the same time, the power generation status data set is stored in a database for historical record analysis and power generation performance evaluation, providing high-quality data support for intelligent power generation management and improving the operation efficiency and stability of the photovoltaic system.

[0022] Execute step A200, perform power tracking on the embedded photovoltaic module according to the power generation status data set, and determine the generated electric energy data set; in a possible implementation manner, step A200 further includes step A210, extract the output voltage data and output current data based on the power generation status data set; execute step A220, perform perturbation calculation through the output voltage data and the output current data to obtain the output power data; execute step A230, perform power fluctuation tracking on the embedded photovoltaic module according to the output power data to determine multiple periodic fluctuation points; execute step A240, perform power comparison according to the multiple periodic fluctuation points, and perform calculation in combination with the sampling period according to the comparison result to obtain the generated electric energy data set.

[0023] Extract the output voltage data V and output current data I from the power generation status data set to form a time series, that is, V = {V1, V2,..., V n}, I = {I1, I2,..., I n}, where n is the total number of data points within the sampling period. Further, according to the output voltage data and the output current data, calculate the output power P at each sampling point, that is, P t = V t × I t , t = 1, 2,..., n, and perform perturbation calculation through the output voltage data and the output current data. Within each sampling period, perform perturbation calculation on the power sequence P = {P1, P2,..., P n}, observe the power change trend, and the perturbation formula is: V new = V ref × △V; P new = V new × I; and compare P new with P ref . If P new > P ref , it indicates that the power increases, and continue to adjust V ref in the current direction. If P new < P ref , it indicates that the power decreases, and adjust V ref in the reverse direction. At the same time, record the power fluctuation points (local maximum and minimum values) within multiple periods, and sequentially determine whether the multiple periodic fluctuation points meet the stop condition. If the changes of the multiple periodic fluctuation points tend to be stable, stop the tracking.

[0024] Further, perform point-by-point comparison of the power data according to the multiple periodic fluctuation points (such as local maximum and minimum values), that is, △P = P max - P min; If △P exceeds the set threshold, mark this period as a high - volatility interval. In each sampling period, calculate the generated electrical energy according to the effective power determined by the fluctuation points, combined with the sampling period, that is, E t = P t ×T sample ; where, T sample is the sampling period, E t is the generated electrical energy at time t, and accumulate the generated electrical energy of all periods to form a generated - electrical - energy data set, providing solid data support for subsequent analysis and optimization.

[0025] Execute step A300 to retrieve the historical electricity - consumption data set of the embedded photovoltaic module for electricity - consumption prediction and obtain the electricity - demand prediction information; In a possible implementation, step A300 further includes step A310, traverse the historical data record log of the embedded photovoltaic module for electricity - consumption analysis and retrieve the historical electricity - consumption data set; Execute step A320, arrange the historical electricity - consumption data set in chronological order of electricity consumption to construct a continuous electricity - consumption time series; Execute step A330, traverse the historical electricity - consumption data set according to the continuous electricity - consumption time series for electricity - consumption capture to generate a long - term electricity - consumption dependence coefficient; Execute step A340, traverse the historical electricity - consumption data set according to the continuous electricity - consumption time series for electricity - consumption capture to generate a short - term electricity - consumption dependence coefficient; First, extract the historical electricity - consumption data set from the historical data record log of the embedded photovoltaic module. The data fields include timestamp, electricity - consuming equipment, electricity consumption, and environmental parameters. At the same time, perform normalization processing on the electricity consumption and map it to the [0, 1] interval to reduce the influence of magnitude differences, that is where D norm (t) is the normalized electricity consumption, and then arrange the historical electricity - consumption data in chronological order of timestamp to form a continuous time series S, that is, S = {D norm (t1), D norm (t2),..., D norm (t n )}.

[0026] Traversing the historical electricity - consumption data set according to the continuous electricity - consumption time series for electricity - consumption capture can be to first divide the historical data by a relatively large time window (such as days, weeks, months) to capture the long - term electricity - consumption trend, and then traverse the electricity - consumption data within each time window to calculate the average electricity consumption of each time window, that is where is the average electricity consumption, m is the number of data points within the window. Further, calculate the long - term electricity - consumption dependence coefficient, which represents the similarity between the current time window and the past electricity - consumption pattern, that is where C L is the long - term electricity - consumption dependence coefficient, and C LThe smaller it is, the higher the long-term stability of the identified electricity consumption pattern.

[0027] According to the continuous electricity consumption time series, traversing the historical electricity consumption dataset for electricity consumption capture can be to first divide the time series into smaller time windows (such as hourly or minute-level), capture short-term electricity consumption fluctuations, and then traverse the electricity consumption data within the short-term window to calculate the short-term electricity consumption dependence coefficient, representing short-term volatility, that is Among them, C S is the short-term electricity consumption dependence coefficient, is the average electricity consumption within the short-term exposure, k is the number of data points within the window, providing data support for subsequent power generation scheduling and energy storage optimization.

[0028] Execute step A350, and perform predictive analysis based on the long-term electricity consumption dependence coefficient and the short-term electricity consumption dependence coefficient to generate the electricity demand prediction information.

[0029] In a possible implementation manner, step A350 further includes step A351, mapping the long-term electricity consumption dependence coefficient to the historical electricity consumption dataset for predictive training to generate long-term electricity consumption prediction data; execute step A352, mapping the short-term electricity consumption dependence coefficient to the historical electricity consumption dataset for predictive training to generate short-term electricity consumption prediction data; execute step A353, cross-combine the long-term electricity consumption prediction data and the short-term electricity consumption prediction data according to the continuous electricity consumption time series, perform backpropagation according to the combination result to generate multiple electricity consumption weight values; execute step A354, calculate the combination result according to the multiple electricity consumption weight values to generate multiple time windows, and the multiple time windows have multiple electricity consumption prediction results; execute step A355, perform demand analysis based on the multiple electricity consumption prediction results according to the multiple time windows to obtain the electricity demand prediction information.

[0030] First, use the long-term electricity consumption dependence coefficient C L Segment the historical electricity consumption dataset (such as daily or weekly), construct a long-term electricity consumption dependence model according to the electricity consumption pattern characteristics of each time period, and select an algorithm suitable for capturing long-term trends such as linear regression or time series analysis model to use C L and the corresponding electricity consumption time series D(t) to train the model, input the long-term electricity consumption pattern characteristics of the future time window, and generate long-term electricity consumption prediction data.

[0031] Further use the short-term electricity consumption dependence coefficient C SDivide historical electricity consumption data into short - time windows (such as hours or minutes), extract short - term fluctuation characteristics, use short - term dependence characteristics and short - time window data, and combine with a recurrent neural network (such as LSTM) to train a short - term electricity consumption prediction model. Input the current short - term characteristic data to generate short - term electricity consumption prediction data.

[0032] Further, the cross - combination of the long - term electricity consumption prediction data and the short - term electricity consumption prediction data according to the continuous electricity consumption time series means aligning the long - term prediction data and the short - term prediction data according to the continuous electricity consumption time series, and for each time point, performing a weighted combination of the long - term and short - term prediction data. The weighted combination is a dynamically adjusted weight parameter, which can be optimized according to electricity consumption characteristics. Use the backpropagation algorithm to calculate the error and adjust the combination weight. Update the weight by minimizing the error to generate multiple electricity consumption weight values. Then divide the continuous time series into multiple time windows (for example, divide the next 24 hours into 24 windows by 1 hour), and within each time window, calculate the electricity consumption prediction result based on the combined electricity consumption data, that is, within each time window, use the combined data and the corresponding weight value to calculate the electricity consumption prediction result, and output the electricity consumption prediction results of multiple time windows.

[0033] Finally, based on the electricity consumption prediction results of each time window, perform demand classification, peak demand (such as electricity consumption exceeding a set threshold), low - valley demand (such as electricity consumption below a set threshold), analyze the electricity consumption characteristics of different devices or regions, provide support for subsequent scheduling optimization. On this basis, obtain electricity demand prediction information. The electricity demand prediction information can be used to predict the real - time electricity consumption demand of devices such as door and window control, lighting, and air - conditioning, provide a basis for power distribution, generate peak / low - valley classification and scheduling suggestions based on the prediction results, and support intelligent electricity management.

[0034] Execute step A400, perform energy management on the generated power data set according to the electricity demand prediction information, and formulate a power generation management strategy; in a possible implementation, step A400 further includes step A410, use the electricity demand prediction information as the electricity consumption critical value, traverse the generated power data set according to the electricity consumption critical value for electricity consumption analysis, and set electricity demand constraint conditions; execute step A420, define the electricity consumption priority based on the multiple electricity consumption weight values, match the electricity demand prediction information with the generated power data set according to the electricity consumption priority, and generate an electricity consumption power list; first, use the electricity demand prediction information as the electricity consumption critical value for each time window to determine whether the generated power can meet the demand, and then traverse the generated power data set based on the electricity consumption critical value and compare it with the electricity consumption critical value. If the generated power data set is greater than or equal to the electricity consumption critical value, it means that the generated power meets the electricity consumption demand. If the generated power data set is less than the electricity consumption critical value, it means that the generated power does not meet the electricity consumption demand and is correspondingly marked as an area with insufficient power. Define the electricity demand constraint conditions according to the comparison result. The electricity demand constraint conditions include the upper limit of electricity consumption (higher than the critical value), the condition for meeting the electricity consumption priority, etc.

[0035] Furthermore, defining the electricity consumption priority according to multiple electricity consumption weight values means setting the electricity consumption priority according to the importance of the equipment. Exemplarily, high-priority equipment (such as door and window control, lighting): the power supply demand is preferentially met; medium-priority equipment (such as air conditioners): the electric energy is allocated sub-optimally; low-priority equipment (such as non-critical equipment or energy storage): is considered last. Matching the electricity demand prediction information with the generated power data set according to the electricity consumption priority means matching the electricity demand prediction information with the generated power one by one according to the electricity consumption priority, and outputting an electricity consumption power list, including the equipment name, allocated power, and unmet demand.

[0036] Execute step A430 to slice the electricity consumption list to generate multiple time slices, and perform state transition according to the multiple time slices to generate multiple energy storage state information sets; in a possible implementation, step A430 further includes step A431, randomly extract based on the multiple time slices to obtain a first time slice and a second time slice, the first time slice and the second time slice are adjacent, and the first time slice is the previous time slice of the second time slice; execute step A432, traverse the electricity consumption list based on the first time slice for matching to obtain the first electricity data of the first time slice, perform energy storage calculation according to the first electricity data to obtain the energy storage state information set of the first time slice; execute step A433, perform energy storage transfer calculation on the second time slice according to the energy storage state information set of the first time slice to generate the energy storage state information set of the second time slice, and iterate in this way, stop traversing the multiple time slices, and obtain the multiple energy storage state information sets.

[0037] First, randomly extract a first time slice and a second time slice from the multiple time slices. It is required that the first time slice and the second time slice are adjacent, and the first time slice is the previous time slice of the second time slice. Each time slice includes an electricity consumption list, that is, electricity demand prediction data and power generation electricity allocation data, as well as energy storage state information, that is, the initial electricity of the energy storage device and the charge and discharge power.

[0038] Further traverse the electricity consumption list of the first time slice and match the power generation electricity with the electricity demand item by item. Among them, the electricity consumption that fails to meet the demand can be provided by the energy storage device. Then, according to the matching result of the electricity consumption, calculate the charge and discharge power of the energy storage device in the first time slice, which can be the photovoltaic power in the first time slice minus the sum of the power generation electricity allocation data at all times, obtain the charge and discharge power of the energy storage device in the first time slice and update the energy storage power. The charge and discharge power of the energy storage device in the first time slice can include the remaining energy storage power in the first time slice, the electricity demand satisfaction rate in the first time slice, etc.

[0039] Further transfer the energy storage state information of the first time slice to the second time slice as the initial energy storage state. First, traverse the electricity consumption list of the second time slice, match the power generation electricity with the electricity demand, and update the charge and discharge power of the energy storage device according to the energy storage state and the electricity demand, which can be the photovoltaic power in the second time slice minus the sum of the power generation electricity allocation data at all times, obtain the charge and discharge power of the energy storage device in the second time slice and update the energy storage power in the second time slice. The energy storage power in the second time slice can include the remaining energy storage power in the second time slice, the electricity demand satisfaction rate in the second time slice.

[0040] Finally, using the energy storage state information of the second time slice as the initial condition, the subsequent energy storage calculations and transfer processes are sequentially processed for the subsequent time slices. After traversing all the time slices, the iteration stops, and multiple energy storage state information sets are generated. The multiple energy storage state information sets include the energy storage state information sets of all time slices, that is, the energy storage power, charge and discharge power, and power consumption demand satisfaction rate of each time slice. The energy storage state is gradually calculated based on adjacent time slices, dynamically reflecting the operation of the energy storage device, providing comprehensive energy storage state information support for the subsequent power generation management strategy, and optimizing the system operation efficiency.

[0041] Execute step A440, and formulate the power generation management strategy through dynamic programming based on the multiple energy storage state information sets in combination with the multiple time slices.

[0042] Finally, the multiple energy storage state information sets are associated with the multiple time slices to maximize the energy storage utilization efficiency and the power supply satisfaction rate of key equipment, minimize the energy storage discharge loss and power waste, and use the dynamic programming algorithm to traverse all time slices and state information, including operations such as updating the energy storage charge and discharge plan and adjusting the power distribution of equipment priorities to formulate the power generation management strategy. The power generation management strategy may include the power distribution plan for each time window, the charge and discharge plan of the energy storage device, and the list of equipment with unmet power consumption demands, ensuring the efficient distribution of power generation power and energy storage management.

[0043] Next, execute step A500, simulate the execution of the power generation management strategy to perform charge and discharge analysis on the embedded photovoltaic modules, generate a power management feedback signal, send the power management feedback signal to the remote management terminal for response, and update the power generation management strategy according to the response result to generate an optimized power generation management strategy for intelligent power generation management of the embedded photovoltaic modules.

[0044] In a possible implementation manner, step A500 further includes step A510, performing power fluctuation analysis based on the power generation management strategy to determine the power fluctuation range; executing step A520, performing dynamic simulation according to the power fluctuation range by executing the power generation management strategy to obtain dynamic photovoltaic power generation simulation data; executing step A530, determining whether the dynamic photovoltaic power generation simulation data is greater than or equal to the power consumption demand prediction information; executing step A540, if the dynamic photovoltaic power generation simulation data is greater than or equal to the power consumption demand prediction information, calculating the charging power to generate a charging power parameter; executing step A550, if the dynamic photovoltaic power generation simulation data is less than the power consumption demand prediction information, calculating the discharge power to generate a discharge power parameter; executing step A560, performing energy storage feedback according to the charging power parameter and the discharge power parameter to generate a strategy adjustment recommendation; executing step A570, adding the strategy adjustment recommendation to the power management feedback signal.

[0045] First, the power fluctuation analysis based on the power generation management strategy refers to extracting the current power generation management strategy and power consumption demand prediction information, obtaining photovoltaic power generation data, and further subtracting the maximum power generation from the minimum power generation of the historical photovoltaic power generation data based on the historical photovoltaic power generation data to analyze the power fluctuation range and its fluctuation trend, which may include an upward trend, a downward trend, and a stable trend.

[0046] Further, simulating the dynamic power generation in the future time period based on the power fluctuation range combined with the current photovoltaic power generation data refers to the sum of the photovoltaic charge and discharge power and the fluctuation amount of the power generation, and comparing the simulated dynamic photovoltaic power generation data with the power consumption demand prediction information to determine whether the simulated dynamic photovoltaic power generation data is greater than or equal to the power consumption demand prediction information. If the simulated dynamic photovoltaic power generation data is greater than or equal to the power consumption demand prediction information, it is considered that the power generation meets the power consumption demand, and the charging power of the surplus electric energy is calculated to generate a charging power parameter for updating the energy storage device state. If the simulated dynamic photovoltaic power generation data is less than the power consumption demand prediction information, it is considered that the power generation is insufficient to meet the power consumption demand, and the discharge power of the energy storage device is calculated to generate a discharge power parameter for supplementing the power consumption demand.

[0047] Further, based on the charging power parameter and the discharge power parameter, the energy storage device state is updated, the current state of the energy storage device and the power consumption demand are analyzed, and a strategy adjustment recommendation is generated. The strategy adjustment recommendation may include, if the energy storage power is close to the upper limit, recommending reducing the charging power or adjusting the power generation energy distribution; if the energy storage power is close to the lower limit, recommending increasing the power generation or adjusting the power consumption priority. Devices such as door and window control, indoor lighting, and air conditioning can be preferentially powered, and the surplus electric energy is stored through the energy storage device for use at night or in low light. Finally, the strategy adjustment recommendation is added to the power management feedback signal, which may include adjustment recommendations such as the current energy storage state (power, charge and discharge power), adjusting the power generation distribution, and optimizing the operation of the energy storage device, to achieve the adaptive adjustment of power generation management.

[0048] Further, sending the power management feedback signal to the remote management terminal for response refers to parsing the content of the power management feedback signal by the remote management terminal, extracting the energy storage state information, power consumption demand satisfaction rate, and strategy adjustment recommendation, and responding to the power management feedback signal. The response process may include processing the feedback signal content according to a predefined rule engine, that is, if the energy storage power is close to the upper limit, reducing the charging power and optimizing the power consumption distribution; if the energy storage power is close to the lower limit, increasing the energy storage power generation and adjusting the power generation priority, and outputting the response result, including the updated power generation strategy adjustment plan.

[0049] Receive the response result through the embedded photovoltaic component management system, parse the new policy adjustment plan, that is, update the power generation management policy according to the response result, generate an optimized power generation management policy, which can include dynamically adjusting the priority of electrical equipment, giving priority to meeting the power demand of high-demand equipment, updating and optimizing the distribution of generated power, storing the optimized power generation management policy in the database, and outputting it to the energy management system for execution. Then, real-time monitor the photovoltaic power generation, energy storage status, and power consumption demand through sensor devices, dynamically adjust the policy according to the actual operation data to form a closed-loop optimization, and realize the real-time response of feedback signals and policy optimization through the bidirectional communication between the remote terminal and the embedded photovoltaic component.

[0050] The embodiment of this application solves the technical problems of low energy utilization rate, unreasonable power consumption allocation, and poor energy storage management efficiency during the power generation process of embedded photovoltaic components, and achieves the technical effects of giving priority to meeting the power demand of key equipment, efficiently storing and intelligently releasing excess electric energy, significantly improving the energy utilization rate and power supply reliability of the photovoltaic system, and at the same time realizing the intelligent management of the energy system.

[0051] Based on the foregoing embodiments, the embodiment of this application also provides an electronic device. When the processor of the electronic device is executed, it can implement the method described in any previous embodiment.

[0052] Figure 2 It is a schematic structural diagram of the electronic device provided by the embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiment of the present invention. Figure 2 The displayed electronic device is only an example and should not bring any limitations to the functions and usage scope of the embodiment of the present invention. The electronic device is presented in the form of a general computing device, and its components may include, but are not limited to, an input device 201, a processor 202, a memory 203, and an output device 204. Among them, the processor 202 can be one or more; the processor 202 executes various functional applications and data processing of the computer device by running software programs, instructions, and modules stored in the memory 203, that is, implements the power generation management method of the above-mentioned embedded photovoltaic component.

[0053] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the protection scope of this application. In some cases, the actions or steps recited in this application can be executed in a sequence different from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A power generation management method for an embedded photovoltaic module, characterized in that, The method includes: Performing real-time power generation sensing on the embedded photovoltaic module through a group of sensor devices to obtain a power generation status data set of the embedded photovoltaic module; Performing power tracking on the embedded photovoltaic module according to the power generation status data set to determine a generated electric energy data set; Retrieving a historical power consumption data set of the embedded photovoltaic module for power consumption prediction to obtain power consumption demand prediction information; Performing energy management on the generated electric energy data set according to the power consumption demand prediction information to formulate a power generation management strategy; Simulating and executing the power generation management strategy to perform charge and discharge analysis on the embedded photovoltaic module, generating an electric energy management feedback signal, sending the electric energy management feedback signal to a remote management terminal for response, updating the power generation management strategy according to the response result, and generating an optimized power generation management strategy to perform intelligent power generation management on the embedded photovoltaic module.

2. The power generation management method of the embedded photovoltaic module according to claim 1, characterized in that Performing power tracking on the embedded photovoltaic module according to the power generation status data set to determine a generated electric energy data set, the method including: Extracting output voltage data and output current data based on the power generation status data set; Performing perturbation calculation through the output voltage data and the output current data to obtain output power data; Performing power fluctuation tracking on the embedded photovoltaic module according to the output power data to determine multiple periodic fluctuation points; Performing power comparison according to the multiple periodic fluctuation points, and performing calculation in combination with the sampling period according to the comparison result to obtain the generated electric energy data set.

3. The power generation management method of the embedded photovoltaic module according to claim 1, characterized in that, Retrieving a historical power consumption data set of the embedded photovoltaic module for power consumption prediction to obtain power consumption demand prediction information, the method including: Traversing the historical data record log of the embedded photovoltaic module for power consumption analysis and retrieving the historical power consumption data set; Sequentially arranging the historical power consumption data set according to the power consumption time sequence to construct a continuous power consumption time series; Performing power consumption capture on the historical power consumption data set according to the continuous power consumption time series to generate a long-term power consumption dependence coefficient; Performing power consumption capture on the historical power consumption data set according to the continuous power consumption time series to generate a short-term power consumption dependence coefficient; Performing prediction analysis according to the long-term power consumption dependence coefficient and the short-term power consumption dependence coefficient to generate the power consumption demand prediction information.

4. The power generation management method of the embedded photovoltaic module according to claim 3, characterized in that, Performing prediction analysis according to the long-term power consumption dependence coefficient and the short-term power consumption dependence coefficient to generate the power consumption demand prediction information, the method including: Mapping the long-term power consumption dependence coefficient to the historical power consumption data set for prediction training to generate long-term power consumption prediction data; Mapping the short-term power consumption dependence coefficient to the historical power consumption data set for prediction training to generate short-term power consumption prediction data; Cross-combining the long-term power consumption prediction data and the short-term power consumption prediction data according to the continuous power consumption time series, and performing backpropagation according to the combination result to generate multiple power consumption weight values; Performing calculation on the combination result according to the multiple power consumption weight values to generate multiple time windows, and the multiple time windows have multiple power consumption prediction results; Performing demand analysis according to the multiple power consumption prediction results according to the multiple time windows to obtain the power consumption demand prediction information.

5. The power generation management method of the embedded photovoltaic module according to claim 4, wherein Perform energy management on the generated power dataset according to the predicted electricity demand information, and formulate a power generation management strategy. The method includes: Use the predicted electricity demand information as the electricity consumption threshold, traverse the generated power dataset according to the electricity consumption threshold for electricity consumption analysis, and set electricity demand constraint conditions; Define the electricity consumption priority based on the multiple electricity consumption weight values, match the predicted electricity demand information with the generated power dataset according to the electricity consumption priority, and generate an electricity consumption power list; Slice the electricity consumption power list to generate multiple time slices, perform state transitions according to the multiple time slices, and generate multiple energy storage state information sets; Perform dynamic programming according to the multiple energy storage state information sets combined with the multiple time slices to formulate the power generation management strategy.

6. The power generation management method of the embedded photovoltaic module according to claim 5, characterized in that, Slice the electricity consumption power list to generate multiple time slices, perform state transitions according to the multiple time slices, and generate multiple energy storage state information sets. The method includes: Randomly extract based on the multiple time slices to obtain a first time slice and a second time slice. The first time slice and the second time slice are adjacent, and the first time slice is the previous time slice of the second time slice; Traverse the electricity consumption power list based on the first time slice for matching, obtain the first power data of the first time slice, perform energy storage calculation according to the first power data, and obtain the energy storage state information set of the first time slice; Perform energy storage transfer calculation on the second time slice according to the energy storage state information set of the first time slice to generate the energy storage state information set of the second time slice, and perform iteration accordingly. Stop traversing the multiple time slices to obtain the multiple energy storage state information sets.

7. The power generation management method of the embedded photovoltaic module according to claim 1, characterized in that, Simulate the execution of the power generation management strategy to perform charge and discharge analysis on the embedded photovoltaic module, and generate an electric energy management feedback signal. The method includes: Perform power fluctuation analysis based on the power generation management strategy to determine the power fluctuation range; Execute the power generation management strategy for dynamic simulation according to the power fluctuation range to obtain dynamic photovoltaic power generation simulation data; Judge whether the dynamic photovoltaic power generation simulation data is greater than or equal to the predicted electricity demand information; If the dynamic photovoltaic power generation simulation data is greater than or equal to the predicted electricity demand information, calculate the charging power and generate a charging power parameter; If the dynamic photovoltaic power generation simulation data is less than the predicted electricity demand information, calculate the discharging power and generate a discharging power parameter; Perform energy storage feedback according to the charging power parameter and the discharging power parameter to generate a strategy adjustment suggestion; Add the strategy adjustment suggestion to the electric energy management feedback signal.

8. An electronic device, characterized in that, The electronic device includes: A memory for storing executable instructions; A processor for implementing the power generation management method of the embedded photovoltaic module according to any one of claims 1 to 7 when executing the executable instructions stored in the memory.

Images