Intelligent control method and system for household photovoltaic energy storage equipment

Abstract

The invention discloses an intelligent control method and system for household photovoltaic energy storage equipment. The intelligent control method for the household photovoltaic energy storage equipment comprises the following steps: acquiring weather forecast information and acquiring operation data of the household photovoltaic energy storage equipment in real time; predicting to obtain a photovoltaic power generation power short-time prediction result, a user load power short-time prediction result and a net power consumption short-time prediction result; constructing a net power consumption prediction curve based on the net power consumption short-term prediction result; and when the state of charge of the energy storage battery reaches a preset upper limit threshold value and negative value regions meeting schedulable conditions exist in the net power consumption prediction curve, performing positive and negative area matching on each schedulable negative value region in the net power consumption prediction curve to determine whether to trigger an intelligent control strategy or not. Therefore, the intelligent control method for the household photovoltaic energy storage equipment can control the household photovoltaic energy storage equipment intelligently and accurately according to climate, the photovoltaic self-use rate is improved, and the phenomenon of light abandoning is reduced.

Description

Technical Field

[0001] The present application relates to the field of intelligent control of photovoltaic energy storage equipment, and specifically to an intelligent control method and system for household photovoltaic energy storage equipment. Background Art

[0002] With the transformation of the global energy mix and the rapid development of renewable energy, household photovoltaic energy storage systems are gaining increasing popularity. Typically consisting of a photovoltaic array, energy storage batteries, and a hybrid inverter, these systems store the electricity generated by photovoltaic power generation in the batteries and release it when needed to power user loads. Household photovoltaic energy storage systems play a vital role in increasing energy self-sufficiency, reducing electricity costs, and improving power reliability.

[0003] However, in areas with weak grid infrastructure and unstable grids, household PV energy storage systems are often configured to maintain a fully charged storage battery at all times, allowing them to serve as a backup uninterruptible power supply (UPS) during power outages. While this operational strategy ensures reliable power supply during grid failures, its integration with PV generation can lead to a serious phenomenon known as "abandonment." This refers to when PV power generation exceeds household electricity load, the excess clean energy cannot be effectively stored and is wasted, resulting in a significant waste of clean energy. This "abandonment" phenomenon not only reduces the economic benefits of household PV energy storage systems but also hinders the further development of renewable energy.

[0004] Current control strategies for household photovoltaic energy storage devices primarily rely on pre-set rules or thresholds to control the charging and discharging of storage batteries. For example, charging begins when the battery charge falls below a certain threshold and stops when it rises above a certain threshold. This approach is simple to implement, but suffers from low control accuracy and struggles to adapt to the complex and volatile nature of photovoltaic power generation and load fluctuations. In particular, in regions with variable climates and diverse user electricity consumption habits, simple threshold control strategies struggle to achieve optimal energy scheduling, leading to the continued prevalence of curtailed solar power.

[0005] Therefore, there is an urgent need for a more intelligent, efficient and reliable household energy storage system control method to improve the photovoltaic self-use rate and reduce the "abandoned light" phenomenon. Summary of the Invention

[0006] One advantage of the present application is that it provides an intelligent control method and system for household photovoltaic energy storage equipment, wherein the intelligent control method for household photovoltaic energy storage equipment can more intelligently and accurately control the household photovoltaic energy storage equipment according to the climate, thereby improving the photovoltaic self-use rate, reducing the "abandoned light" phenomenon, and improving the economy and reliability of users' electricity use.

[0007] According to one aspect of the present application, a method for intelligent control of a household photovoltaic energy storage device is provided, which includes the following steps: S110: obtaining weather forecast information and collecting operating data of the household photovoltaic energy storage device in real time, wherein the operating data includes photovoltaic power generation power, user load power and energy storage battery charge state.

[0008] S120: Based on the operating data and the weather forecast information, the photovoltaic power generation power, user load power and net power consumption within a future preset time window are predicted to obtain a short-term prediction result of the photovoltaic power generation power, a short-term prediction result of the user load power and a short-term prediction result of the net power consumption.

[0009] S130: Constructing a net power consumption prediction curve based on the short-term net power consumption prediction result.

[0010] S140: When the state of charge of the energy storage battery reaches a preset upper limit threshold and there is a negative area in the net power consumption forecast curve that meets the dispatchable conditions, positive and negative area matching is performed on each dispatchable negative area in the net power consumption forecast curve to determine whether to trigger the intelligent control strategy, wherein the dispatchable conditions are that the area of the negative area is greater than the preset area threshold or the duration of the negative area is greater than the preset time threshold or the absolute value of the minimum net power of the negative area is greater than the preset power threshold.

[0011] In one embodiment of the intelligent control method for household photovoltaic energy storage equipment described in the present application, step S140 includes the steps of: extracting the schedulable negative area from the net power consumption forecast curve; calculating the area of each of the schedulable negative areas; searching forward from the starting time of each of the schedulable negative areas to find a target positive area that meets the preset area matching conditions; when the target positive area is searched, triggering an intelligent control strategy, wherein the intelligent control strategy includes: controlling the energy storage battery to start discharging at the starting time of the target positive area and controlling the energy storage battery to start charging at the starting time of the schedulable negative area.

[0012] In one embodiment of the intelligent control method for household photovoltaic energy storage equipment described in the present application, a forward search is performed from the starting time of each of the schedulable negative value areas to find a target positive value area that meets the preset area matching condition, including the steps of: finding multiple candidate positive value areas that meet the preset area matching condition; and using dynamic programming or a branch and bound algorithm to screen out the best one from the multiple candidate positive value areas as the target positive value area.

[0013] In one embodiment of the intelligent control method for household photovoltaic energy storage equipment described in the present application, step S140, after searching forward from the starting time of each of the schedulable negative value areas to find a target positive value area that meets the preset area matching conditions, includes the steps of: when no target positive value area corresponding to the schedulable negative value area is found within the current future preset time window, matching the schedulable negative value area with the positive value area of another future preset time window for positive and negative areas.

[0014] In one embodiment of the intelligent control method for household photovoltaic energy storage equipment described in the present application, the schedulable negative area is extracted from the net power consumption forecast curve, including the steps of: extracting the original negative area from the net power consumption forecast curve, the area of the original negative area being greater than the super-large area threshold, and the super-large area threshold being greater than the preset area threshold; splitting the original negative area into multiple original negative areas; and extracting the schedulable negative area from the multiple original negative areas.

[0015] In one embodiment of the intelligent control method for household photovoltaic energy storage equipment described in the present application, the schedulable negative area is extracted from the net power consumption forecast curve, including the steps of: extracting multiple original negative areas from the net power consumption forecast curve, the area of the original negative areas being smaller than the preset area threshold; and merging the multiple original negative areas to obtain the schedulable negative area.

[0016] In one embodiment of the intelligent control method for household photovoltaic energy storage equipment described in the present application, step S140 includes the steps of: extracting the schedulable negative area from the net power consumption forecast curve; extracting the target positive area from the net power consumption forecast curve based on the positive-negative area dynamic balance analysis mechanism; when the target positive area is searched, triggering the intelligent control strategy, wherein the intelligent control strategy includes: controlling the energy storage battery to start discharging at the starting time of the target positive area and controlling the energy storage battery to start charging at the starting time of the schedulable negative area.

[0017] In one embodiment of the intelligent control method for household photovoltaic energy storage equipment described in the present application, a target positive area is extracted from the net power consumption forecast curve based on a positive-negative area dynamic balance analysis mechanism, including the steps of: sampling positive and negative areas from the net power consumption curve along the time series direction to obtain an initial negative sampling time series vector and an initial positive sampling time series vector; calculating a time window conforming phase correlation matrix based on the initial negative sampling time series vector and the initial positive sampling time series vector; calculating a two-dimensional full-time fluctuation adjustment factor and a weighting vector based on the initial negative sampling time series vector and the initial positive sampling time series vector; calculating the area of the optimized schedulable negative area and the area of the target positive area based on the two-dimensional full-time fluctuation adjustment factor, the weighting vector, the time window conforming phase correlation matrix, the initial negative sampling time series vector and the initial positive sampling time series vector to extract the target positive area from the net power consumption forecast curve based on the area of the target positive area.

[0018] In one embodiment of the intelligent control method for household photovoltaic energy storage equipment described in the present application, positive and negative value areas are sampled from the net power consumption curve along the timing direction to obtain an initial negative value sampling timing sequence vector and an initial positive value sampling timing sequence vector, including the steps of: sampling the schedulable negative value area from the net power consumption curve along the timing direction to obtain an initial negative value sampling timing sequence vector; extracting an initial positive value area from the net power consumption prediction curve; sampling the initial positive value area from the net power consumption curve along the timing direction to obtain an initial positive value sampling timing sequence vector, wherein the number of samples of the initial positive value area is the same as the number of samples of the schedulable negative value area.

[0019] In one embodiment of the intelligent control method for household photovoltaic energy storage equipment described in the present application, step S120 includes the steps of: using multiple candidate prediction models to process the operating data and the weather forecast information respectively to obtain a set of candidate photovoltaic power generation power short-term prediction results, a set of candidate user load power short-term prediction results, and a set of candidate net power consumption short-term prediction results; based on the set of candidate photovoltaic power generation power short-term prediction results, the set of candidate user load power short-term prediction results, and the set of candidate net power consumption short-term prediction results, calculating the photovoltaic power generation power short-term prediction results, the user load power short-term prediction results, and the net power consumption short-term prediction results.

[0020] According to another aspect of the present application, the present application proposes an intelligent control system for household photovoltaic energy storage equipment, which includes a processor, wherein the processor includes: a data acquisition module for obtaining weather forecast information and real-time collection of operating data of the household photovoltaic energy storage equipment, wherein the operating data includes photovoltaic power generation power, user load power and energy storage battery charge state; a prediction module for predicting the photovoltaic power generation power, user load power and net power consumption within a future preset time window based on the operating data and the weather forecast information to obtain a short-term prediction result of the photovoltaic power generation power, a short-term prediction result of the user load power and a short-term prediction result of the net power consumption; a net power consumption curve construction module, used to construct a net power consumption prediction curve based on the short-term net power consumption prediction result; a control strategy triggering module, used to perform positive and negative area matching on each schedulable negative area in the net power consumption prediction curve to determine whether to trigger an intelligent control strategy when the state of charge of the energy storage battery reaches a preset upper limit threshold and there is a negative area that meets the schedulable condition in the net power consumption prediction curve, wherein the schedulable condition is that the area of the negative area is greater than the preset area threshold or the duration of the negative area is greater than the preset time threshold or the absolute value of the minimum net power of the negative area is greater than the preset power threshold.

[0021] Further objectives and advantages of the present application will be fully reflected through understanding of the following description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0023] Figure 1 The figure illustrates a flow chart of an intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application.

[0024] Figure 2 The figure illustrates a flow chart of step S120 of the intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application.

[0025] Figure 3 The figure shows a flow chart of step S122 of the intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application.

[0026] Figure 4 Another flowchart of step S122 of the intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application is shown.

[0027] Figure 5 The figure shows a flow chart of step S140 of the intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application.

[0028] Figure 6 The figure shows a flow chart of step S141A of the intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application.

[0029] Figure 7 Another flowchart of step S141A of the intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application is shown.

[0030] Figure 8 The figure illustrates a flow chart of step S143A of the intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application.

[0031] Figure 9 Another flowchart of step S140 of the intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application is shown.

[0032] Figure 10 Another flowchart of step S142B of the intelligent control method for household photovoltaic energy storage equipment according to an embodiment of the present application is shown.

[0033] Figure 11 The figure shows a structural block diagram of an intelligent control system for household photovoltaic energy storage equipment according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described herein.

[0035] It is understood that the term "a" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "a" should not be understood as limiting the number. "Multiple" means greater than or equal to two.

[0036] Although ordinal numbers such as "first," "second," and the like will be used to describe various components, these are not intended to limit those components. The terms are used solely to distinguish one component from another. For example, a first component could be referred to as a second component, and similarly, a second component could be referred to as a first component without departing from the teachings of the present disclosure. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0037] The terms used herein are for the purpose of describing various embodiments only and are not intended to be limiting. As used herein, the singular is intended to include the plural, unless the context clearly indicates otherwise. It will also be understood that the terms "including" and / or "having" when used in this specification specify the presence of a stated feature, number, operation, component, element, or combination thereof, and do not preclude the presence or addition of one or more other features, numbers, operations, components, elements, or combinations thereof.

[0038] As mentioned above, current control strategies for household photovoltaic energy storage devices primarily rely on pre-set rules or thresholds to control the charging and discharging of storage batteries. For example, charging begins when the battery charge falls below a certain threshold and stops when it rises above a certain threshold. This approach is simple to implement, but suffers from low control accuracy and struggles to adapt to the complex and volatile nature of photovoltaic power generation and load fluctuations. In particular, in regions with variable climates and diverse user electricity consumption habits, simple threshold control strategies struggle to achieve optimal energy scheduling, leading to the continued prevalence of curtailed solar power.

[0039] Therefore, there is an urgent need for a more intelligent, efficient and reliable household energy storage system control method to improve the photovoltaic self-use rate and reduce the "abandoned light" phenomenon.

[0040] Based on this, this application proposes an intelligent control method and system for household photovoltaic energy storage equipment, aiming to provide a more refined and intelligent control strategy. By predicting the photovoltaic power generation power and user load power in the future, a net power consumption curve is constructed. In addition, an innovative positive and negative area matching algorithm is proposed and applied. Combined with a trigger mechanism based on the grid status, the energy storage battery status and the schedulable time period, the charging and discharging behavior of the energy storage battery is intelligently scheduled to overcome the shortcomings of the existing technology. The intelligent control method and system for household photovoltaic energy storage equipment can maximize the proportion of self-use of photovoltaic power generation while prioritizing the reliability of users' electricity use in the event of grid failures, significantly reduce the phenomenon of "abandoned light", and improve the economy and reliability of users' electricity use.

[0041] Accordingly, if Figures 1 to 10 As shown, the intelligent control method of household photovoltaic energy storage equipment according to the embodiment of the present application is explained. Figure 1As shown, the intelligent control method for household photovoltaic energy storage equipment includes the following steps: S110: obtaining weather forecast information and real-time collection of operating data of the household photovoltaic energy storage equipment, wherein the operating data includes photovoltaic power generation power, user load power and energy storage battery state of charge; S120: predicting photovoltaic power generation power, user load power and net power consumption within a future preset time window based on the operating data and the weather forecast information to obtain a short-term prediction result of photovoltaic power generation power, a short-term prediction result of user load power and a short-term prediction result of net power consumption; S130: constructing a net power consumption prediction curve based on the short-term prediction result of net power consumption; S140: when the energy storage battery state of charge reaches a preset upper threshold and there is a negative value area in the net power consumption prediction curve that meets the dispatchable condition, performing positive and negative area matching on each dispatchable negative value area in the net power consumption prediction curve to determine whether to trigger an intelligent control strategy, wherein the dispatchable condition is that the area of the negative value area is greater than a preset area threshold, or the duration of the negative value area is greater than a preset time threshold, or the absolute value of the minimum net power of the negative value area is greater than a preset power threshold.

[0042] Specifically, in step S110, weather forecast information is obtained and real-time operating data of household photovoltaic energy storage devices is collected. Specifically, real-time operating data of household photovoltaic energy storage devices is collected, including but not limited to: photovoltaic power generation power P_pv(t), user load power P_load(t), energy storage battery state of charge (SOC), grid status, etc. The data collection frequency can be set as needed, for example, every 1 minute or every 15 minutes.

[0043] In step S120, based on the operating data and the weather forecast information, the photovoltaic power generation, user load power, and net power consumption within a preset future time window are predicted to obtain short-term photovoltaic power generation prediction results, short-term user load power prediction results, and short-term net power consumption prediction results. Specifically, multiple candidate prediction models can be used to predict the operating data of the household photovoltaic energy storage system within the preset future time window.

[0044] Accordingly, in one embodiment of the present application, Figure 2 As shown, step S120 includes the steps of: S121, using multiple candidate prediction models to process the operating data and the weather forecast information respectively to obtain a set of candidate photovoltaic power generation power short-term prediction results, a set of candidate user load power short-term prediction results and a set of candidate net power consumption short-term prediction results; S122, based on the set of candidate photovoltaic power generation power short-term prediction results, the set of candidate user load power short-term prediction results and the set of candidate net power consumption short-term prediction results, calculating the photovoltaic power generation power short-term prediction results, the user load power short-term prediction results and the net power consumption short-term prediction results.

[0045] The set of candidate photovoltaic power generation short-term prediction results, the set of candidate user load power short-term prediction results and the set of candidate net power consumption short-term prediction results refer to the set of candidate photovoltaic power generation short-term prediction results, the set of candidate user load power short-term prediction results and the set of candidate net power consumption short-term prediction results within the future preset time window, respectively. It can be designed according to needs, for example, 1 hour, 2 hours, ..., 24 hours, ..., 25 hours, etc.

[0046] Predicting the operating data of household photovoltaic energy storage equipment within a preset future time window is the basis of intelligent control strategies, and its prediction accuracy directly affects the control effect. This application adopts a data-driven intelligent prediction method, using historical data and external information to learn the changing patterns of photovoltaic power generation and user load. Considering the prediction needs under different data volumes and application scenarios, this application adopts a strategy that integrates multiple prediction models for prediction. Among them, the multiple prediction models include but are not limited to: statistical prediction models, machine learning models, and deep learning models.

[0047] Accordingly, in one example of the present application, the multiple candidate prediction models include: statistical prediction models, machine learning models, and deep learning models. Each candidate prediction model can be selected according to demand. For example, the statistical prediction model can use ARIMA, Prophet, etc., which are suitable for scenarios with small amounts of data or high real-time requirements, and serve as the system's quick start and benchmark prediction model; the machine learning model can use XGBoost, LightGBM, RandomForest, SVR, etc., which are suitable for scenarios with moderate amounts of data and certain requirements for prediction accuracy, and can capture nonlinear relationships in the data. The deep learning model can use LSTM, GRU, TCN, Transformer, etc., which are suitable for scenarios with large amounts of data and extremely high requirements for prediction accuracy, and can deeply mine complex patterns and long-term dependencies in the data.

[0048] Accordingly, in an example of the present application, in step S121, based on the historical data collected in step S110 (including weather forecast information and real-time collected operating data of household photovoltaic energy storage equipment), a statistical prediction model is used to process the operating data and the weather forecast information to obtain a first candidate photovoltaic power generation short-term prediction result, a first candidate user load power short-term prediction result, and a first candidate net power consumption short-term prediction result, and a machine learning model is used to process the operating data and the weather forecast information to obtain a second candidate photovoltaic power generation short-term prediction result, a second candidate user load power short-term prediction result, and a second candidate net power consumption short-term prediction result, and a deep learning model is used to process the operating data and the weather forecast information to obtain a third candidate photovoltaic power generation short-term prediction result, a third candidate user load power short-term prediction result, and a third candidate net power consumption short-term prediction result, thereby obtaining a set of candidate photovoltaic power generation short-term prediction results, a set of candidate user load power short-term prediction results, and a set of candidate net power consumption short-term prediction results.

[0049] Each candidate photovoltaic power generation power short-term prediction result (i.e., the first candidate photovoltaic power generation power short-term prediction result or the second candidate photovoltaic power generation power short-term prediction result or the third candidate photovoltaic power generation power short-term prediction result) includes the future preset time window Every minute or every The candidate photovoltaic power generation power prediction result of each candidate user load power prediction result (i.e., the first candidate user load power short-term prediction result or the second candidate user load power short-term prediction result or the third candidate user load power short-term prediction result) includes the future preset time window Every minute or every The candidate user load power prediction result of each candidate net power consumption short-term prediction result (i.e., the first candidate net power consumption short-term prediction result or the second candidate net power consumption short-term prediction result or the third candidate net power consumption short-term prediction result) includes the future preset time window Every minute or every Candidate net electricity consumption forecast results for each minute.

[0050] The set of candidate photovoltaic power generation power short-time prediction results includes the first candidate photovoltaic power generation power short-time prediction result, the second candidate photovoltaic power generation power short-time prediction result and the third candidate photovoltaic power generation power short-time prediction result; the set of candidate user load power short-time prediction results includes the first candidate user load power short-time prediction result, the second candidate user load power short-time prediction result and the third candidate user load power short-time prediction result; the candidate net power consumption short-time prediction results include the first candidate net power consumption short-time prediction result, the second candidate net power consumption short-time prediction result and the third candidate net power consumption short-time prediction result.

[0051] The intelligent control method for household photovoltaic energy storage equipment can adaptively select and switch different types of prediction models according to the amount of data accumulated during actual operation time, and continuously optimize model parameters using technologies such as online learning and transfer learning to ensure that the prediction module can maintain optimal prediction accuracy throughout the entire life cycle of the system. The specific model selection and switching strategies will be described in detail in the specific implementation methods. It is worth emphasizing that the core innovation of the present invention lies in the positive and negative area matching control strategy of the back-end, and the specific prediction algorithm is not a limitation of the present invention. Any prediction method that can provide future photovoltaic power generation power and user load power prediction results can be applied to this application.

[0052] In one embodiment of the present application, the final short-term prediction result is obtained by weighting the prediction results of multiple candidate prediction models. Figure 3 As shown, step S122 includes the steps of: S1221A, evaluating the multiple candidate prediction models to obtain multiple model evaluation results; S1222A, determining the weight value of each candidate photovoltaic power generation short-term prediction result in the set of candidate photovoltaic power generation short-term prediction results based on the multiple model evaluation results to obtain a set of first weight values; S1223A, calculating the weighted sum of the set of candidate photovoltaic power generation short-term prediction results based on the set of first weight values to obtain the photovoltaic power generation short-term prediction result.

[0053] In step S1221A, the multiple candidate prediction models are evaluated to obtain multiple model evaluation results. Specifically, the adaptability of the multiple candidate prediction models to their application scenarios can be evaluated based on parameters such as the weather forecast information input into the candidate prediction models and the amount of data collected in real time from the operating data of household photovoltaic energy storage equipment, expected prediction accuracy, expected prediction real-time performance, and expected prediction time length, and the adaptability is used as the multiple model evaluation results.

[0054] In another embodiment of the present application, the prediction result of a candidate prediction model with higher credibility is selected from the prediction results of multiple candidate prediction models as the final short-term prediction result. Figure 4 As shown, step S122 includes the steps of: S1221B, evaluating the multiple candidate prediction models to obtain multiple model evaluation results; S1222B: selecting the candidate photovoltaic power generation short-term prediction result of the candidate prediction model corresponding to the best model evaluation result from the set of candidate photovoltaic power generation short-term prediction results as the photovoltaic power generation short-term prediction result.

[0055] The calculation method of the short-term prediction result of the user load power can refer to the calculation method of the short-term prediction result of the photovoltaic power generation power.

[0056] Accordingly, in one embodiment of the present application, step S122, after step S1221A, further includes the following steps: S1224A, determining the weight values of each candidate user load power short-term prediction result in the set of user load power short-term prediction results based on multiple model evaluation results to obtain a set of second weight values; and S1225A, calculating the weighted sum of the set of candidate user load power short-term prediction results based on the set of second weight values to obtain the user load power short-term prediction result. Steps S1224A and S1225A may be performed before step S1222A, after step S1223A, or in parallel with steps S1222A and S1223A, respectively.

[0057] In another embodiment of the present application, step S122 further includes, after step S1221B, step S1223B of selecting, from the set of candidate user load power short-term prediction results, the candidate user load power short-term prediction result corresponding to the candidate prediction model with the best model evaluation result as the photovoltaic power generation power short-term prediction result. Step S1223B may be performed before step S1222B, after step S1222B, or in parallel with step S1222B.

[0058] The short-term prediction result of net power consumption can be calculated based on the short-term prediction result of volt power generation and the short-term prediction result of user load power. Specifically, the short-term prediction result of net power consumption is equal to the sum of the short-term prediction result of user load power pload(t) and the short-term prediction result of volt power generation Ppv(t).

[0059] In step S130, a net power consumption prediction curve is constructed based on the net power consumption short-term prediction result. Specifically, the net power consumption short-term prediction result includes the future preset time window Every minute or every The net power consumption forecast result of the minute, accordingly, the future preset time window can be obtained from the short-term net power consumption forecast result The time series of multiple net power consumption forecast results within the future preset time window is constructed The net power consumption prediction curve intuitively reflects the energy supply and demand status of the system in the future and is the basis for the subsequent positive and negative area matching algorithm.

[0060] In step S140, when the state of charge of the energy storage battery reaches a preset upper limit threshold and there is a negative area that meets the dispatchable conditions in the net power consumption prediction curve, positive and negative area matching is performed on each dispatchable negative area in the net power consumption prediction curve to determine whether to trigger the intelligent control strategy.

[0061] In practice, when a power outage is detected, the intelligent control system of the household photovoltaic energy storage system immediately enters backup power mode, discharging the energy storage battery to power the user's load until the grid is restored or the battery's state of charge (SOC) reaches a preset lower threshold, SOC_min. This power outage backup mode has the highest priority, ensuring that users' basic electricity needs are met during a grid failure.

[0062] When the grid detects power or restores, the intelligent control system of the household PV energy storage device first charges the energy storage battery at maximum power until the state of charge (SOC) reaches the preset upper threshold SOC_max. Incoming calls prioritize charging the energy storage battery, preparing for subsequent "abandoned solar" utilization and backup power mode.

[0063] When the energy storage battery is fully charged (SOC=SOC_max) and there is a schedulable period, the positive and negative area matching is performed on each schedulable negative area in the net power consumption forecast curve to determine whether to trigger the intelligent control strategy. If the negative area meets one of the following conditions, it indicates that the negative area is schedulable and can be used as a "schedulable negative area": (1) the area of the negative area A_neg(i) is greater than the preset area threshold A_min, the duration of the negative area (t_i_end-t_i_start) is greater than the preset time threshold T_min, or the absolute value of the minimum net power of the negative area |P_net_min| is greater than the preset power threshold P_min. The specific values of the preset area threshold A_min, the preset time threshold T_min and the preset power threshold P_min can be optimized and set according to parameters such as the energy storage battery capacity, charge and discharge rate, and user electricity usage habits. "Schedulable period" refers to the time period that can be scheduled for charging the energy storage battery. "Schedulable period" is the time period corresponding to the "schedulable negative area". By defining dispatchable periods, the intelligent control system for household photovoltaic energy storage devices does not constantly run the positive and negative area matching algorithm. Instead, it intelligently activates the control strategy only when the storage battery is fully charged and the potential for future "abandonment" is predicted, avoiding unnecessary energy dispatch. This triggering mechanism enables this application to better balance photovoltaic consumption and uninterruptible power supply (UPS) functions, prioritizing user power reliability during grid failures while maximizing photovoltaic self-use during normal grid operation, better meeting the actual needs of users in developing countries.

[0064] If, after the energy storage battery is fully charged, the predicted net power consumption curve does not contain any negative areas that meet the dispatchable conditions, the intelligent control of the household photovoltaic energy storage device will remain in the monitoring state and will not implement the intelligent control strategy until the next control cycle arrives. When a positive and negative area matching is performed on each dispatchable negative area in the predicted net power consumption curve and a target positive area that meets the preset area matching conditions is found, the intelligent control strategy is triggered.

[0065] Accordingly, if Figure 5As shown, step S140 includes the following steps: S141A, extracting the schedulable negative area from the net power consumption forecast curve; S142A, calculating the area of each schedulable negative area; S143A, searching forward from the starting time of each schedulable negative area to find a target positive area that meets the preset area matching condition; S144A, when the target positive area is found, triggering the intelligent control strategy, wherein the intelligent control strategy includes: controlling the energy storage battery to start discharging at the starting time of the target positive area and controlling the energy storage battery to start charging at the starting time of the schedulable negative area. Accordingly, the present application does not continuously run the positive and negative area matching algorithm, but intelligently starts the control strategy based on preset trigger conditions (for example, searching for the target positive area) to achieve on-demand control and energy-saving operation, while giving priority to ensuring the reliability of users' electricity use in the event of a grid failure.

[0066] Step S141A: Extract the dispatchable negative area from the net power consumption forecast curve. Specifically, if a single negative area is too large, multiple positive areas may be required to match it. In this case, the large negative area can be split into multiple small negative areas for positive and negative area matching, ensuring that each of the split sub-negative areas can find a suitable match. If a single negative area is too small, multiple small negative areas can be merged and then matched with the positive area for positive and negative area matching.

[0067] Accordingly, in one embodiment of the present application, Figure 6 As shown, step S141A includes the steps of: S141A1A, extracting the original negative area from the net power consumption forecast curve, the area of the original negative area is greater than the super large area threshold, and the super large area threshold is greater than the preset area threshold; S141A2A, splitting the original negative area into multiple original negative areas; S141A3A, extracting the schedulable negative area from the multiple original negative areas.

[0068] In another embodiment of the present application, Figure 7 As shown, step S141A includes the steps of: S141A1B, extracting multiple original negative regions from the net power consumption forecast curve, wherein the area of the original negative region is smaller than the preset area threshold; S141A2B, merging the multiple original negative regions to obtain the schedulable negative region.

[0069] In step S142A, the area of each of the schedulable negative value regions is calculated. Specifically, for each of the schedulable negative value regions Calculate its area , the area represents the electric energy that can be used to charge the energy storage battery in the negative area, wherein the dispatchable negative area The area calculation formula is as follows: ;in, represents the area of the schedulable negative region, Indicates the starting time of the original negative value area; Indicates the end time of the original negative value area; Indicates the charging efficiency of the energy storage battery; The function value representing the net electricity consumption forecast curve; express In actual calculations, the integral can be approximated by numerical integration or numerical summation. .

[0070] The dispatchable conditions are that the area of the negative region is greater than a preset area threshold, the duration of the negative region is greater than a preset time threshold, or the absolute value of the minimum net power of the negative region is greater than a preset power threshold.

[0071] In step S143A, a search is performed from the start time of each of the schedulable negative value areas forward to find a target positive value area that meets the preset area matching condition. Specifically, in one embodiment of the present application, the preset area matching condition is: the area of the target positive value area is close to or equal to the ratio of the area of the schedulable negative value area to the discharge efficiency of the energy storage battery, that is, ;in, Indicates the area of the target positive region; Indicates the discharge efficiency of the energy storage battery, which is less than or equal to 1; wherein the target positive area The area calculation formula is as follows: ;in, represents the area of the target positive region, Indicates the starting time of the target positive area; Indicates the end time of the target positive value area. In actual calculation, the integral can be approximated by numerical integration or numerical summation. .

[0072] In one embodiment of the present application, in step S143A, one or more candidate positive regions that meet the preset area matching condition are found, so that the total area of the positive regions meets the preset area matching condition; a dynamic programming or branch and bound algorithm is used to screen out the best one from the multiple candidate positive regions as the target positive region.

[0073] Accordingly, in one embodiment of the present application, Figure 8 As shown, step S143A includes the steps of: S143A1, finding multiple candidate positive regions that meet the preset area matching conditions; and S143A2, using dynamic programming or branch and bound algorithm to screen out the best one from the multiple candidate positive regions as the target positive region.

[0074] If no target positive area corresponding to the dispatchable negative area is found within the future preset time window, cross-period matching is considered: an attempt is made to match the current negative area with a positive area in a more distant future time period (beyond the current future preset time window). This requires the use of forecast information on a longer time scale (for example, re-forecasting photovoltaic and load for a longer time range in the future). If a match is still not found, the photovoltaic surplus power in the negative area is not stored for the time being, and a matching attempt is made in the subsequent rolling control cycle. The algorithm continues to search backward for the next negative area.

[0075] Accordingly, in one embodiment of the present application, in step S140, after searching forward from the starting time of each of the schedulable negative value areas to find the target positive value area that meets the preset area matching conditions, it also includes step: S145A, when no target positive value area corresponding to the schedulable negative value area is found in the current future preset time window, the schedulable negative value area is matched with the positive value area of another future preset time window for positive and negative areas.

[0076] In step S144A, when the target positive area is found, an intelligent control strategy is triggered. The intelligent control strategy includes controlling the energy storage battery to begin discharging at the start of the target positive area and controlling the energy storage battery to begin charging at the start of the schedulable negative area. Specifically, the energy storage battery is controlled to begin discharging at the start of the target positive area, and the discharge power can be dynamically adjusted based on the matching area and time, so as to discharge the target positive area as much as possible at the start of the schedulable negative area. The energy storage battery is controlled to begin charging at the start of the schedulable negative area to store surplus photovoltaic power in the energy storage battery.

[0077] It is worth mentioning that the schedulable negative area may be obtained through splitting and merging operations, and the target positive area may be screened from multiple candidate positive areas. That is, the positive area and the negative area have significant asymmetric characteristics in the timing window in the timing direction. Therefore, in order to reduce the asymmetric significance error rate of the positive and negative area matching, a positive-negative area dynamic balance analysis mechanism is introduced.

[0078] First, for the determined schedulable replication area, the net power consumption in the net power consumption prediction curve is sampled along the time series direction, for example, recorded as , and for the target positive area obtained by the search, the same number of samples is sampled to obtain .

[0079] Then for the negative value sampling time series vector and the positive sampling time series vector , the calculation time window conforms to the phase correlation matrix: ; Thus, the time window is consistent with the phase correlation matrix The significant correlation fluctuations in the time window-positive and negative power consumption asymmetric dimensions under time series represent the dynamic matching relationship between the dispatchable negative and positive areas in time series, which can better capture the significant characteristics of positive and negative asymmetric fluctuations than direct area matching.

[0080] Then, the instantaneous load standard deviation is used as the fluctuation adjustment factor and integrated along the time series path. Here, it can be approximated by summation to obtain the two-dimensional full-time fluctuation adjustment factor: ; That is, through the nonlinear fluctuation adjustment factor To control the full-time fluctuation adjustment sensitivity and construct the weighted vector , which is suitable for predicting sudden changes in net electricity consumption.

[0081] Finally, the matching optimization of the positive and negative area is performed as follows: ;in ,and .

[0082] That is, in the positive-negative area dynamic balance analysis mechanism based on the net electricity consumption forecast value, for the asymmetric characteristics of the timing window significance of the positive surplus and the reverse deficit in the time series, by accurately capturing the positive and negative asymmetric fluctuation significance characteristics and adjusting and correcting the full-time fluctuation under the time series path integral, the local overmatch or local undermatch of the fluctuation phase is compensated, thereby establishing an asymmetric significance timing coupling relationship of the positive and negative areas, and solving the problem of inaccurate area matching error rate between the schedulable negative area and the target positive area.

[0083] Accordingly, in one embodiment of the present application, Figure 9 As shown, step S140 includes the following steps: S141B, extracting the schedulable negative area from the net power consumption forecast curve; step S142B, extracting the target positive area from the net power consumption forecast curve based on the positive-negative area dynamic balance analysis mechanism; step S143B, when the target positive area is searched, triggering the intelligent control strategy, wherein the intelligent control strategy includes: controlling the energy storage battery to start discharging at the starting moment of the target positive area and controlling the energy storage battery to start charging at the starting moment of the schedulable negative area.

[0084] like Figure 10As shown, step S142B includes the steps of: S1421B, sampling positive and negative areas from the net power consumption curve along the timing direction to obtain an initial negative sampling timing sequence vector and an initial positive sampling timing sequence vector; S1422B, calculating a time window conforming to a phase correlation matrix based on the initial negative sampling timing sequence vector and the initial positive sampling timing sequence vector; S1423B, calculating a two-dimensional full-time fluctuation adjustment factor and a weighting vector based on the initial negative sampling timing sequence vector and the initial positive sampling timing sequence vector; S1424B, calculating the area of the optimized schedulable negative area and the area of the target positive area based on the two-dimensional full-time fluctuation adjustment factor, the weighting vector, the time window conforming to the phase correlation matrix, the initial negative sampling timing sequence vector and the initial positive sampling timing sequence vector to extract the target positive area from the net power consumption prediction curve based on the area of the target positive area.

[0085] In step S1421B, positive and negative regions are sampled from the net power consumption curve along the time series direction to obtain an initial negative sampling time series vector and an initial positive sampling time series vector. Specifically, the schedulable negative region is sampled from the net power consumption curve along the time series direction to obtain an initial negative sampling time series vector; an initial positive region is extracted from the net power consumption forecast curve; and the initial positive region is sampled from the net power consumption curve along the time series direction to obtain an initial positive sampling time series vector.

[0086] The initial negative value sampling time series vector is expressed as: , Represents the number of samples. The initial positive sampling time series vector is expressed as: .

[0087] In step S1422B, the time window conformance phase correlation matrix is calculated using the following formula: ;in, Indicates that the time window conforms to the phase correlation matrix; It indicates that the time window conforms to the Kronecker product of the phase correlation matrix and the initial positive sampling time series sequence vector.

[0088] In step S1423B, the dual-dimensional full-time fluctuation adjustment factor and the weighting vector are calculated using the following formula: ;in, represents the first dimension full-time fluctuation adjustment factor in the dual-dimensional full-time fluctuation adjustment factor; represents the dual-dimensional full-time fluctuation adjustment factor in the dual-dimensional full-time fluctuation adjustment factor; represents the weight vector; Indicates the sampling sequence number, which is a positive integer.

[0089] In step S1424B, the area of the schedulable negative region and the area of the positive region are calculated using the following formula: ;in, Represents the optimized negative sampling time series vector; Represents the optimized positive sampling time series vector; Represents the area of the schedulable negative region after optimization; Represents the area of the target positive region; represents the reciprocal of the dual-dimensional full-time fluctuation adjustment factor; express and The result of the "XOR" operation; express and The "XOR" operation result is the same as Kronecker product; express and The result of the "XOR" operation is express and The result of the "XOR" operation; ,and .

[0090] It is worth mentioning that in order to adapt to the dynamic changes of photovoltaic power generation and user load, this application adopts a rolling control strategy. For control cycle , loop through the positive and negative area matching of step S140, i.e. Time period, based on the latest power consumption forecast curve, regenerate the future preset time window control strategy, but only the previous one is executed each time Control strategy within a time period. For example, when the control period Hours, future preset time window At every hour, the intelligent control system of the household photovoltaic energy storage device re-forecasts the photovoltaic power generation, user load power, and net power consumption for the next two hours. Based on the latest short-term forecast results of photovoltaic power generation, user load power, and net power consumption, it generates a control strategy for the next two hours. However, it only executes the control strategy for the next hour, leaving the remaining control strategy for the next control cycle. Through rolling control, the intelligent control system of the household photovoltaic energy storage device can promptly adjust the control strategy based on the latest forecast information, improving the real-time and flexibility of control, more effectively responding to fluctuations in photovoltaic power generation and user load power, and reducing the adverse effects of forecast errors.

[0091] The reason for using rolling control strategy is that only the first The time period control strategy is because for the prediction of time series data, the prediction accuracy of closer data points is usually higher, that is, predicting data in the near future is usually more accurate than predicting data in the far future. In this application, the predicted data points can be weighted according to their distance from the current moment. The closer the predicted value is to the current moment, the greater the weight of its error in the loss function of the candidate prediction model. Therefore, the candidate prediction model will pay more attention to the accuracy of recent predictions. This strategy ensures the real-time and accuracy of control, and can adjust the control behavior in time according to the latest prediction results, thereby more effectively responding to fluctuations in photovoltaic power generation and load.

[0092] In order to more clearly illustrate the execution process of the intelligent control strategy in a control cycle, this section uses the control cycle Hours, predicted duration Taking hours as an example, the execution steps and logic of the intelligent control strategy in one control cycle are described in detail.

[0093] Step 1: Obtain weather forecast information and collect real-time operating data of household photovoltaic energy storage equipment, wherein the operating data includes photovoltaic power generation, user load power and energy storage battery charge state.

[0094] Step 2: At each hour (e.g., 9:00, 10:00, 11:00, ...), the intelligent control system of the household photovoltaic energy storage device calculates the future preset time window based on the operating data and the weather forecast information. The photovoltaic power generation, user load power, and net power consumption within the hour are predicted to obtain short-term photovoltaic power generation, user load power, and net power consumption forecast results. Specifically, different types of candidate prediction models such as Prophet, XGBoost, and TCN can be adaptively selected based on the data volume of the operating data and weather forecast information, or other data, and online updates and candidate prediction model switching can be performed to ensure prediction accuracy.

[0095] Step 3: Based on the future preset time window The short-term forecast results of net electricity consumption within the hour are used to build a future preset time window Net electricity consumption forecast curve within the hour; among them, the future preset time window The short-term forecast results of net electricity consumption within an hour include the net electricity consumption forecast results for each minute (or other time intervals).

[0096] Step 4: When the state of charge of the energy storage battery reaches a preset upper threshold and there is a negative area that meets the dispatchable conditions in the net power consumption forecast curve, the positive and negative area matching algorithm is executed through the method of the above steps S141A to S144A or the method of the above steps S141B to S143B, and a detailed energy storage battery charging and discharging intelligent control strategy is generated for the next 2 hours. The core idea of the positive and negative area matching algorithm is to find a suitable positive area to match each dispatchable negative area within the future prediction time window, so that the total area of the positive area is as close as possible to or equal to the ratio of the area of the negative area to the discharge efficiency of the energy storage battery (taking into account the energy conversion efficiency). The control strategy is in minutes, indicating the charge and discharge status (charging, discharging or standby) and power of the energy storage battery at each moment in the next 2 hours. Special case handling includes cases where the negative area is too large or too small, and the strategies of splitting the negative area and merging the negative area are used for optimization.

[0097] During the execution of the energy storage battery charging and discharging intelligent control strategy, although a detailed intelligent control strategy for the next two hours is generated, only the intelligent control strategy for the next hour is executed. For example, at 9:00 a.m., an intelligent control strategy for 9:00-11:00 a.m. is generated, but only the intelligent control strategy for 9:00-10:00 a.m. is actually executed. After the 9:00-10:00 a.m. time period ends, even if the control strategy for 10:00-11:00 a.m. generated at 9:00 a.m. has not yet been executed, a new control strategy for the next two hours is predicted and generated at 10:00 a.m., and the new strategy for 10:00-11:00 a.m. is executed, and so on. This rolling control method ensures the real-time and flexibility of the control strategy, allowing timely adjustments based on the latest forecast information.

[0098] Repeat steps 1-4 at every hour to achieve rolling update and execution of intelligent control strategy. If the function value of the predicted net power consumption curve is always positive (P_net(t) ≥ 0), indicating that "curtailment" will not occur in the future, monitoring will continue without controlling it until the next control cycle arrives. Only when "curtailment" is predicted to be possible in the future will the positive and negative area matching algorithm be triggered to generate and execute the intelligent control strategy.

[0099] Based on the mechanism of the intelligent control method of household photovoltaic energy storage equipment, this application proposes an intelligent control system for household photovoltaic energy storage equipment. Figure 11 To describe the intelligent control system of the household photovoltaic energy storage equipment in the embodiment of the present application.

[0100] Figure 11 The figure shows a block diagram of an intelligent control system for household photovoltaic energy storage equipment according to an embodiment of the present application.

[0101] like Figure 11 As shown, the intelligent control system of the household photovoltaic energy storage device includes a processor 100.

[0102] The processor 100 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the intelligent control system of the household photovoltaic energy storage device to perform desired functions.

[0103] The processor 100 includes a data acquisition module 11 , a prediction module 12 , a net power consumption curve construction module 13 and a control strategy triggering module 14 .

[0104] The data acquisition module 11 is used to obtain weather forecast information and collect real-time operating data of household photovoltaic energy storage equipment, wherein the operating data includes photovoltaic power generation, user load power and energy storage battery state of charge; the prediction module 12 is used to predict the photovoltaic power generation, user load power and net power consumption within a future preset time window based on the operating data and the weather forecast information to obtain a short-term prediction result of photovoltaic power generation, a short-term prediction result of user load power and a short-term prediction result of net power consumption; the net power consumption curve construction module 13 is used to construct a net power consumption prediction curve based on the short-term prediction result of net power consumption; the control strategy triggering module 14 is used to perform positive and negative area matching on each schedulable negative area in the net power consumption prediction curve to determine whether to trigger an intelligent control strategy when the energy storage battery state of charge reaches a preset upper threshold and there is a negative area in the net power consumption prediction curve that meets the schedulable condition, wherein the schedulable condition is that the area of the negative area is greater than a preset area threshold, or the duration of the negative area is greater than a preset time threshold, or the absolute value of the minimum net power in the negative area is greater than a preset power threshold.

[0105] In one embodiment of the present application, the data acquisition module is also used to acquire the state of the power grid.

[0106] In one embodiment of the present application, the prediction module 12 includes a multi-model preliminary prediction module and a prediction result determination module. The multi-model preliminary prediction module is used to use multiple candidate prediction models to process the operating data and the weather forecast information respectively to obtain a set of candidate photovoltaic power generation power short-term prediction results, a set of candidate user load power short-term prediction results, and a set of candidate net power consumption short-term prediction results; the prediction result determination module is used to calculate the photovoltaic power generation power short-term prediction result, the user load power short-term prediction result, and the net power consumption short-term prediction result based on the set of candidate photovoltaic power generation power short-term prediction results, the set of candidate user load power short-term prediction results, and the set of candidate net power consumption short-term prediction results.

[0107] In one example of the present application, the multiple candidate prediction models include: a statistical prediction model, a machine learning model, and a deep learning model.

[0108] In one embodiment of the present application, the prediction result determination module includes a model evaluation unit, a weight value determination unit, and a result calculation unit. The model evaluation unit is used to evaluate the multiple candidate prediction models to obtain multiple model evaluation results; the weight value determination unit is used to determine the weight value of each candidate photovoltaic power generation short-term prediction result in the set of candidate photovoltaic power generation short-term prediction results based on the multiple model evaluation results to obtain a set of first weight values; and the result calculation unit is used to calculate the weighted sum of the set of candidate photovoltaic power generation short-term prediction results based on the set of first weight values to obtain the photovoltaic power generation short-term prediction result.

[0109] In one embodiment of the present application, the weight value determination unit is further used to determine the weight value of each candidate user load power short-time prediction result in the set of user load power short-time prediction results based on multiple model evaluation results to obtain a set of second weight values; the result calculation unit is also used to calculate the weighted sum of the set of candidate user load power short-time prediction results based on the set of second weight values to obtain the user load power short-time prediction result.

[0110] In one embodiment of the present application, the prediction result determination module includes a model evaluation unit and a result calculation unit. The model evaluation unit is configured to evaluate the multiple candidate prediction models to obtain multiple model evaluation results; and the result calculation unit is configured to select, from the set of candidate photovoltaic power generation short-term prediction results, the candidate photovoltaic power generation short-term prediction result of the candidate prediction model corresponding to the candidate with the best model evaluation result as the photovoltaic power generation short-term prediction result.

[0111] In one embodiment of the present application, the result calculation unit is also used to select the candidate user load power short-time prediction result of the candidate prediction model corresponding to the best model evaluation result from the set of candidate user load power short-time prediction results as the photovoltaic power generation power short-time prediction result.

[0112] In one embodiment of the present application, the control strategy triggering module 14 includes a schedulable negative region extraction unit, a schedulable negative region area calculation unit, a positive and negative area matching unit, and a strategy execution unit. The schedulable negative region extraction unit is used to extract the schedulable negative region from the net power consumption forecast curve; the schedulable negative region area calculation unit is used to calculate the area of each schedulable negative region; the positive and negative area matching unit is used to search forward from the starting time of each schedulable negative region to find a target positive region that meets the preset area matching condition; the strategy execution unit is used to trigger the intelligent control strategy when the target positive region is searched, wherein the intelligent control strategy includes: controlling the energy storage battery to start discharging at the starting time of the target positive region and controlling the energy storage battery to start charging at the starting time of the schedulable negative region.

[0113] In one embodiment of the present application, the schedulable negative area extraction unit is further used to extract the original negative area from the net power consumption forecast curve, the area of the original negative area is greater than the super large area threshold, and the super large area threshold is greater than the preset area threshold; split the original negative area into multiple original negative areas; and extract the schedulable negative area from the multiple original negative areas.

[0114] In another embodiment of the present application, the dispatchable negative area extraction unit is further used to extract multiple original negative areas from the net power consumption forecast curve, and the area of the original negative area is smaller than the preset area threshold; and the multiple original negative areas are merged to obtain the dispatchable negative area.

[0115] In one embodiment of the present application, the positive and negative area matching unit is used to find multiple candidate positive regions that meet preset area matching conditions; and use dynamic programming or branch and bound algorithm to screen out the best one from the multiple candidate positive regions as the target positive region.

[0116] In one embodiment of the present application, the control strategy triggering module 14 further includes an inter-period matching unit. The inter-period matching unit is configured to, when no target positive area corresponding to the schedulable negative area is found within the current future preset time window, perform positive and negative area matching between the schedulable negative area and a positive area in another future preset time window.

[0117] In one embodiment of the present application, the control strategy triggering module 14 includes a schedulable negative region extraction unit, a positive-negative area matching unit, and a strategy execution unit. The schedulable negative region extraction unit is used to extract the schedulable negative region from the net power consumption forecast curve; the positive-negative area matching unit is used to extract the target positive region from the net power consumption forecast curve based on the positive-negative area dynamic balance analysis mechanism; the strategy execution unit is used to trigger an intelligent control strategy when the target positive region is found, wherein the intelligent control strategy includes: controlling the energy storage battery to start discharging at the start time of the target positive region and controlling the energy storage battery to start charging at the start time of the schedulable negative region.

[0118] The positive and negative area matching unit includes a schedulable negative area sampling unit, an initial positive area extraction unit, an initial positive area sampling unit, a correlation matrix calculation unit, an adjustment parameter unit, and a target positive area extraction unit. The schedulable negative area sampling unit is used to sample the schedulable negative area from the net power consumption curve along the time sequence direction to obtain an initial negative sampling time sequence vector, wherein the initial negative sampling time sequence vector is expressed as: , represents the number of samples; the initial positive region extraction unit is used to extract the initial positive region from the net power consumption prediction curve; the initial positive region sampling unit is used to sample the initial positive region from the net power consumption curve along the time series direction to obtain an initial positive sampling time series sequence vector, wherein the initial positive sampling time series sequence vector is expressed as: ; The correlation matrix calculation unit is used to calculate the time window phase correlation matrix based on the initial negative sampling time series vector and the initial positive sampling time series vector; the adjustment parameter unit calculates the two-dimensional full-time fluctuation adjustment factor and the weighting vector based on the initial negative sampling time series vector and the initial positive sampling time series vector; the target positive area extraction unit is used to calculate the area of the optimized schedulable negative area and the area of the target positive area based on the two-dimensional full-time fluctuation adjustment factor, the weighting vector, the time window phase correlation matrix, the initial negative sampling time series vector and the initial positive sampling time series vector to extract the target positive area from the net power consumption forecast curve based on the area of the target positive area.

[0119] In one embodiment of the present application, the processor 100 further includes a scroll control module configured to cycle steps S110 to S140 of the intelligent control method for household photovoltaic energy storage equipment with a preset control period as the control period.

[0120] In one embodiment of the present application, the intelligent control system for the household photovoltaic energy storage device includes a photovoltaic array 10, an energy storage battery 20, a hybrid inverter 30, an edge computing device 40, and a cloud server 70. The energy storage battery 20 is connected between the photovoltaic array 10 and the hybrid inverter 30. The hybrid inverter 30 is connected between the energy storage battery 20 and the power grid 50. The power grid 50 is connected to a user load 60. The edge computing device 40 is connected between the photovoltaic array 10 and the energy storage battery 20. The processor 100 is disposed in the edge computing device 40. The cloud server 70 is connected to the edge computing device 40, the energy storage battery 20, and the hybrid inverter 30.

[0121] The photovoltaic array 10 utilizes the photovoltaic effect of solar panels to convert light energy into electrical energy, which is then used to power the energy storage battery 20. The hybrid inverter 30 converts direct current (DC) into alternating current (AC), enabling the electrical energy from the energy storage battery 20 to power user loads 60 via the power grid 50. The edge computing device 40 switches and adjusts the operating state of the energy storage battery 20 via the processor 100, supplying the energy storage battery 20's electrical energy to the user loads 60 and sending excess electrical energy to the energy storage battery 20 for storage. The cloud server 70 monitors the photovoltaic array 10, the energy storage battery 20, and the hybrid inverter 30 via a remote network. In one embodiment of the present application, the edge computing device 40 is a low-cost embedded computing platform that can be easily integrated into the intelligent control system of existing household photovoltaic energy storage systems without replacing existing hardware. As the intelligent control core, the edge computing device 40 interacts with the hybrid inverter 30 and the cloud server 70 via a communication connection for data exchange and command transmission, enabling local intelligent control and cloud-based collaborative optimization. This architecture reflects the characteristics of software and hardware decoupling and easy upgrade and transformation of this application.

[0122] In summary, the intelligent control method and system for household photovoltaic energy storage equipment are described. The intelligent control method for household photovoltaic energy storage equipment does not use traditional rules or threshold control. Instead, it accurately predicts future photovoltaic power generation and user load, pre-determines the risk of "abandonment" in advance, and uses an innovative positive and negative area matching algorithm to accurately match photovoltaic power generation surplus periods (negative areas) with user power demand periods (positive areas). This achieves refined intelligent scheduling of the charging and discharging behavior of the energy storage battery, can maximize the storage of surplus photovoltaic power in the battery, and formulate an optimal charging and discharging control strategy to release it during peak user power consumption periods, thereby significantly reducing the "abandonment" phenomenon, improving the self-use rate and power reliability of photovoltaic power generation, and ensuring power supply. The introduction of prediction makes the control strategy more forward-looking and predictive, and can better cope with the volatility of photovoltaic power generation and load, achieving more refined energy scheduling. In the event of a power outage, the intelligent control method for household photovoltaic energy storage equipment can seamlessly switch to backup power mode, with the battery providing users with a reliable power supply and ensuring the continuous operation of users' critical loads.

[0123] It is worth emphasizing that this application maximizes photovoltaic self-use while prioritizing the reliability of user electricity supply, which is more in line with the actual needs of users in developing countries. Specifically, this application innovatively proposes an intelligent triggering mechanism based on the schedulable period. Only when the battery is fully charged (SOC=SOC_max) and it is predicted that "abandonment" may occur in the future, the positive and negative area matching algorithm is intelligently activated. This triggering mechanism enables this application to maximize photovoltaic self-use while prioritizing the reliability of user electricity supply, avoiding unnecessary energy scheduling.

[0124] To address the prediction challenges faced by varying data volumes and application scenarios, and to improve the environmental adaptability and robustness of the intelligent control system for household photovoltaic energy storage equipment, this application innovatively employs an adaptive prediction model fusion strategy and a rolling control mechanism. This intelligent control system for household photovoltaic energy storage equipment adaptively selects the optimal prediction model based on the data volume and uses rolling control to promptly adjust the control strategy based on the latest prediction information, ensuring that the intelligent control system for household photovoltaic energy storage equipment maintains optimal operating performance under a variety of complex and uncertain operating conditions.

[0125] The intelligent control method for household photovoltaic energy storage equipment adopts a fully automatic intelligent control strategy. It can intelligently determine whether to start the positive and negative area matching algorithm based on the power grid status, the battery charge state, and the net power consumption prediction curve, and automatically generate the optimal charging and discharging control strategy without manual intervention, thereby lowering the user's usage threshold and improving the system's ease of use and intelligence level.

[0126] The positive and negative area matching algorithm used in this application has relatively low computational complexity, does not require high computing power from edge computing devices, and is easy to deploy and apply in household energy storage systems with limited computing resources. For example, during the experiment, the intelligent control method for household photovoltaic energy storage equipment ran perfectly in the edge computing chip RK3566.

[0127] The intelligent control system for household photovoltaic energy storage equipment adopts a flexible system architecture that is easy to expand and upgrade. The processor can be easily integrated into existing household energy storage systems without replacing the original hardware equipment. Only a set of low-cost edge computing devices and the deployment of the corresponding software system are required to achieve intelligent upgrades and transformations. This greatly reduces the upgrade cost and deployment difficulty, and has outstanding engineering application value.

[0128] The above description of the present application and its embodiments is non-limiting. The drawings show only one embodiment of the present application, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the inventive purpose of this application, designs a structure and embodiment similar to this technical solution without creatively designing, they shall fall within the scope of protection of this application.

Claims

1. An intelligent control method for household photovoltaic energy storage equipment, characterized in that: The method includes the following steps: S110: obtaining weather forecast information and collecting operating data of household photovoltaic energy storage equipment in real time, wherein the operating data includes photovoltaic power generation power, user load power and state of charge of the energy storage battery; S120: predicting the photovoltaic power generation power, user load power and net power consumption within a future preset time window based on the operating data and the weather forecast information to obtain a short-term prediction result of photovoltaic power generation power, a short-term prediction result of user load power and a short-term prediction result of net power consumption; S130: constructing a net power consumption prediction curve based on the short-term prediction result of net power consumption; S140: when the state of charge of the energy storage battery reaches a preset upper limit threshold and there is a negative value area that meets the dispatchable condition in the net power consumption prediction curve, performing positive and negative area matching on each dispatchable negative value area in the net power consumption prediction curve to determine whether to trigger an intelligent control strategy, wherein the dispatchable condition is that the area of the negative value area is greater than the preset area threshold, or the duration of the negative value area is greater than the preset time threshold, or the absolute value of the minimum net power of the negative value area is greater than the preset power threshold.

2. The intelligent control method for household photovoltaic energy storage equipment according to claim 1, characterized in that: Step S140 includes the steps of: extracting the schedulable negative value area from the net power consumption forecast curve; calculating the area of each of the schedulable negative value areas; searching forward from the start time of each of the schedulable negative value areas to find a target positive value area that meets a preset area matching condition; When the target positive area is searched, an intelligent control strategy is triggered, wherein the intelligent control strategy includes: controlling the energy storage battery to start discharging at the start time of the target positive area and controlling the energy storage battery to start charging at the start time of the schedulable negative area.

3. The intelligent control method for household photovoltaic energy storage equipment according to claim 2, characterized in that: Searching forward from the start time of each of the schedulable negative value areas to find a target positive value area that meets the preset area matching condition, including the steps of: finding multiple candidate positive value areas that meet the preset area matching condition; Dynamic programming or branch-and-bound algorithm is used to select the best one from multiple candidate positive value regions as the target positive value region.

4. The intelligent control method for household photovoltaic energy storage equipment according to claim 2, characterized in that: Step S140, after searching forward from the starting time of each of the schedulable negative value areas to find a target positive value area that meets the preset area matching conditions, includes the steps of: when no target positive value area corresponding to the schedulable negative value area is found within the current future preset time window, matching the schedulable negative value area with the positive value area of another future preset time window for positive and negative areas.

5. The intelligent control method for household photovoltaic energy storage equipment according to claim 1, characterized in that: Extracting the dispatchable negative value area from the net power consumption forecast curve includes the following steps: extracting an original negative value area from the net power consumption forecast curve, wherein the area of the original negative value area is greater than an ultra-large area threshold, and the ultra-large area threshold is greater than a preset area threshold; splitting the original negative value area into multiple original negative value areas; The schedulable negative value region is extracted from the plurality of original negative value regions.

6. The intelligent control method for household photovoltaic energy storage equipment according to claim 1, characterized in that: Extracting the dispatchable negative value area from the net power consumption forecast curve includes the following steps: extracting a plurality of original negative value areas from the net power consumption forecast curve, wherein the area of the original negative value area is smaller than the preset area threshold; A merging operation is performed on the multiple original negative value regions to obtain the schedulable negative value region.

7. The intelligent control method for household photovoltaic energy storage equipment according to claim 1, characterized in that: Step S140 includes the steps of: extracting the dispatchable negative area from the net power consumption forecast curve; extracting the target positive area from the net power consumption forecast curve based on a positive-negative area dynamic balance analysis mechanism; When the target positive area is searched, an intelligent control strategy is triggered, wherein the intelligent control strategy includes: controlling the energy storage battery to start discharging at the start time of the target positive area and controlling the energy storage battery to start charging at the start time of the schedulable negative area.

8. The intelligent control method for household photovoltaic energy storage equipment according to claim 7, characterized in that: Extracting a target positive area from the net power consumption forecast curve based on a positive-negative area dynamic balance analysis mechanism includes the following steps: sampling positive and negative areas from the net power consumption curve along a time series direction to obtain an initial negative sampling time series sequence vector and an initial positive sampling time series sequence vector; calculating a time window conforming phase correlation matrix based on the initial negative sampling time series sequence vector and the initial positive sampling time series sequence vector; and calculating a two-dimensional full-time fluctuation adjustment factor and a weighting vector based on the initial negative sampling time series sequence vector and the initial positive sampling time series sequence vector. Based on the two-dimensional full-time fluctuation adjustment factor, the weighting vector, the time window phase correlation matrix, the initial negative sampling time series vector and the initial positive sampling time series vector, the area of the optimized schedulable negative area and the area of the target positive area are calculated to extract the target positive area from the net power consumption forecast curve based on the area of the target positive area.

9. The intelligent control method for household photovoltaic energy storage equipment according to claim 1, characterized in that: Sampling positive and negative regions from the net power consumption curve along the time series direction to obtain an initial negative sampling time series vector and an initial positive sampling time series vector, comprising the steps of: sampling the schedulable negative region from the net power consumption curve along the time series direction to obtain an initial negative sampling time series vector; extracting an initial positive region from the net power consumption prediction curve; The initial positive region is sampled from the net power consumption curve along a timing direction to obtain an initial positive sampling timing sequence vector, wherein the number of samples in the initial positive region is the same as the number of samples in the schedulable negative region.

10. An intelligent control system for household photovoltaic energy storage equipment, characterized in that: The system comprises a processor, the processor comprising: a data acquisition module for acquiring weather forecast information and real-time collection of operating data of household photovoltaic energy storage equipment, wherein the operating data includes photovoltaic power generation power, user load power and energy storage battery state of charge; a prediction module for predicting photovoltaic power generation power, user load power and net power consumption within a future preset time window based on the operating data and the weather forecast information to obtain a short-term prediction result of photovoltaic power generation power, a short-term prediction result of user load power and a short-term prediction result of net power consumption; a net power consumption curve construction module for constructing a net power consumption prediction curve based on the short-term prediction result of net power consumption; and a control strategy triggering module for performing positive and negative area matching on each schedulable negative area in the net power consumption prediction curve to determine whether to trigger an intelligent control strategy when the energy storage battery state of charge reaches a preset upper threshold and there is a negative area in the net power consumption prediction curve that meets a schedulable condition, wherein the schedulable condition is that the area of the negative area is greater than a preset area threshold, or the duration of the negative area is greater than a preset time threshold, or the absolute value of the minimum net power in the negative area is greater than a preset power threshold.

Images