Photovoltaic energy storage equipment power regulation method and device, equipment and storage medium

Abstract

The invention discloses a photovoltaic energy storage equipment power adjusting method and device, equipment and a storage medium, and relates to the technical field of photovoltaic energy storage, and the photovoltaic energy storage equipment power adjusting method comprises the steps: obtaining historical operation data and current environment data of photovoltaic energy storage equipment, and predicting a power prediction initial value of a future target time period based on the data; dividing a future target time period into three types of dynamic time periods, namely a high-income time period, a balance time period and a low-income time period, by combining a power prediction initial value, historical operation data and current environment data; then matching a corresponding target prediction model for each dynamic time period, and predicting an accurate power prediction value of each time period based on historical operation data and current environment data; and finally, generating a differentiated power regulation instruction according to the power predicted value of each dynamic time period, and controlling the energy storage module to execute charging, discharging or standby operation. According to the invention, the pre-judgment and all-time dynamic adaptive adjustment of the photovoltaic power are realized, and the accuracy and high efficiency of system scheduling can be guaranteed.

Description

Technical Field

[0001] This application relates to the field of photovoltaic energy storage technology, and in particular to power regulation methods, devices, equipment and storage media for photovoltaic energy storage devices. Background Technology

[0002] With the development of new energy technologies, photovoltaic power generation has been widely used due to its clean and renewable characteristics. However, due to the influence of environmental factors such as light intensity and temperature, the output power of photovoltaic power is intermittent.

[0003] To address this issue, related technologies employ photovoltaic (PV) energy storage systems to store excess PV energy and release it when PV power is insufficient. While this achieves power balance, it only charges the PV modules when their output exceeds load demand and discharges them when power is insufficient. This lack of advance prediction and dynamic adjustment of PV power results in low utilization of energy storage resources and poor returns. Therefore, effectively achieving advance prediction and dynamic adjustment of PV power has become an urgent problem to be solved. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for power regulation of photovoltaic energy storage equipment, in order to at least solve the problem of how to effectively predict and dynamically regulate photovoltaic power in the related art.

[0005] This application provides a power regulation method for photovoltaic energy storage devices, including: Acquire historical operating data and current environmental data of photovoltaic energy storage devices; Based on the historical operating data and current environmental data, the initial power prediction value of the photovoltaic energy storage device is predicted for the future target period. Based on the initial power forecast for the future target period, historical operating data, and current environmental data, the future target period is divided into multiple dynamic periods; wherein, the dynamic periods include high-yield periods, balanced periods, and low-yield periods; For any of the aforementioned dynamic time periods, based on the target prediction model corresponding to the dynamic time period, and according to the historical operating data and current environmental data, the predicted power value for the dynamic time period is predicted. Based on the power prediction values ​​for each dynamic time period, power adjustment commands are generated for each dynamic time period to control the energy storage module to perform charging, discharging, or standby operations; wherein, the photovoltaic energy storage device includes the energy storage module.

[0006] This application also provides a power regulation device for photovoltaic energy storage equipment, including: The acquisition module is used to acquire historical operating data and current environmental data of photovoltaic energy storage devices; The first prediction module is used to predict the initial power forecast value of the photovoltaic energy storage device in a future target period based on the historical operating data and current environmental data. The time period segmentation module is used to divide the future target time period into multiple dynamic time periods based on the initial power prediction value, historical operating data, and current environmental data; wherein, the dynamic time periods include high-yield time periods, balanced time periods, and low-yield time periods; The second prediction module is used to predict the power prediction value of any dynamic time period based on the target prediction model corresponding to the dynamic time period and according to the historical operating data and current environmental data. The power regulation module is used to generate power regulation commands for each dynamic period based on the predicted power values ​​for each dynamic period, so as to control the energy storage module to perform charging, discharging or standby operations; wherein, the photovoltaic energy storage device includes the energy storage module.

[0007] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any of the above-described photovoltaic energy storage device power regulation methods.

[0008] This application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of any of the above-described photovoltaic energy storage device power regulation methods.

[0009] In some embodiments of this application, based on historical operating data and current environmental data of the photovoltaic energy storage device, an initial power prediction value for the device in a future target period is first predicted. Then, based on this initial power prediction value, the future target period is divided into multiple dynamic periods, such as high-yield periods, balanced periods, and low-yield periods. Subsequently, for each dynamic period, a corresponding target prediction model is used to accurately predict the power prediction value for that period. Finally, corresponding power adjustment commands are generated based on the power prediction values ​​for each dynamic period to control the energy storage module to perform charging, discharging, or standby operations. In this way, advance prediction of photovoltaic power can be achieved through multi-step prediction, and dynamic adjustment of the energy storage module can be achieved through dynamic period division and precise prediction in different time periods. For example, during high-yield periods, the charging and discharging of the energy storage module can be specifically controlled to maximize returns; during balanced periods, power supply stability can be maintained; and during low-yield periods, ineffective charging and discharging losses can be reduced. This improves the utilization rate of energy storage resources and enhances system profitability. Thus, advance prediction and dynamic adjustment of photovoltaic power can be effectively achieved. Attached Figure Description

[0010] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A schematic flowchart of a photovoltaic energy storage device power regulation method provided for some embodiments of this application; Figure 2 A communication diagram of a photovoltaic energy storage device is provided for some embodiments of this application; Figure 3 A schematic diagram of a power regulation device for a photovoltaic energy storage device provided for some embodiments of this application; Figure 4 A schematic diagram of the modules of an electronic device provided for some embodiments of this application. Detailed Implementation

[0012] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0013] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0014] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] In some technical solutions, photovoltaic energy storage systems adopt a passive charge-discharge control architecture. This architecture controls the energy storage module to charge when the output power of the photovoltaic power generation module exceeds the load demand, and controls it to discharge when the photovoltaic output power is insufficient. However, this approach lacks advance prediction of photovoltaic power changes and does not dynamically adjust the system based on revenue targets. Therefore, how to effectively achieve advance prediction and dynamic adjustment of photovoltaic power has become an urgent problem to be solved.

[0016] In view of this, this application provides a power regulation method for photovoltaic energy storage devices, which can solve the above problems. The power regulation method for photovoltaic energy storage devices can be applied to photovoltaic energy storage devices. (See also...) Figure 1 This is a schematic flowchart of a photovoltaic energy storage device power regulation method provided in some embodiments of this application. Figure 1 The power regulation method for photovoltaic energy storage equipment includes the following steps: Step S101: Obtain historical operating data and current environmental data of the photovoltaic energy storage device.

[0017] Specifically, photovoltaic energy storage equipment refers to an integrated device with the ability to generate, store, and regulate photovoltaic power. It includes components such as photovoltaic power generation modules, energy storage modules, predictive control modules, linkage execution modules, and data acquisition modules, and can realize functions such as solar energy conversion, power storage, and charge and discharge linkage control.

[0018] Specifically, historical operating data refers to various historical data generated during the past operation of photovoltaic energy storage equipment, including but not limited to historical photovoltaic power data, historical charging load data, continuous peak power of energy storage, and historical meteorological data for the past 1-3 years. Among them, historical meteorological data includes light intensity, horizontal irradiance, and air temperature.

[0019] Specifically, the current environmental data includes real-time data and auxiliary forecast data. The real-time data includes real-time irradiance, ambient temperature, photovoltaic panel backsheet temperature, energy storage SOC (State of Charge), current charging load, and real-time electricity price signal. The auxiliary forecast data includes the weather forecast for the next 24 hours, photovoltaic module degradation coefficient, and grid acceptance capacity threshold.

[0020] Optionally, a 12-dimensional core feature vector is constructed based on historical operating data, real-time data, and auxiliary prediction data as the basis for subsequent data processing in this application. The 12-dimensional core feature vector includes the rate of change of illuminance, temperature gradient, historical power fluctuation coefficient, difference between current SOC and full charge threshold, charging load growth rate, peak-valley electricity price difference, photovoltaic module attenuation coefficient, grid acceptance capacity margin, equipment charging priority weight, short-term power prediction variance, seasonal feature factors, and holiday identifiers.

[0021] Step S102: Based on historical operating data and current environmental data, predict the initial power forecast of the photovoltaic energy storage device for the future target period.

[0022] Specifically, the future target period refers to the future time interval for which power forecasting and time period division are to be performed, and its duration can be flexibly adjusted according to grid dispatching needs and load fluctuation characteristics. The initial power forecast refers to the preliminary forecast result of photovoltaic power obtained for the future target period, providing a quantitative basis for subsequent dynamic time period division.

[0023] Understandably, the input historical operating data and current environmental data are first preprocessed by removing outliers and standardizing them, and then input into the preset basic prediction model to obtain the initial value of the photovoltaic power prediction for the future target period.

[0024] Step S103: Based on the initial power prediction value, historical operating data and current environmental data for the future target period, the future target period is divided into multiple dynamic periods; among which, the dynamic periods include high-yield periods, balanced periods and low-yield periods.

[0025] Specifically, dynamic time periods refer to time intervals whose boundaries and durations can be adjusted in real time, unlike fixed morning, noon, and evening time period divisions. High-yield periods refer to dynamic periods with high yield potential, where the goal is to maximize charging and discharging yield. Balanced periods refer to dynamic periods where yield potential and operational stability must be balanced, where the goal is to maintain a balance between photovoltaics, load, and energy storage to minimize curtailment losses. Low-yield periods refer to dynamic periods with low yield potential, where the goal is to control equipment losses and avoid ineffective charging and discharging.

[0026] Understandably, integrating and correlating multi-dimensional data from initial power forecasts, historical operating data, and current environmental data allows for the assessment of revenue potential across different sub-segments within the target future timeframe, resulting in three dynamic timeframes: high-revenue timeframes, balanced timeframes, and low-revenue timeframes. For instance, if the initial power forecast for the next four hours consistently exceeds 100kW and the current period falls within the grid peak electricity price range, it is classified as a high-revenue timeframe.

[0027] Step S104: For any dynamic time period, based on the target prediction model corresponding to the dynamic time period, predict the power prediction value of the dynamic time period according to historical operating data and current environmental data.

[0028] Specifically, the target prediction model refers to a dedicated prediction model tailored to the needs of each dynamic period, rather than a uniform, single model. The power prediction value refers to the accurate prediction result of the photovoltaic power output for each dynamic period, which is more accurate and more closely matches the actual power of the corresponding period.

[0029] Understandably, the first step is to clarify the requirements for each dynamic time period and complete the matching of the target prediction model; then, the 12-dimensional core feature vector is input into the corresponding target prediction model to perform accurate prediction and obtain the power prediction value for each dynamic time period.

[0030] Step S105: Based on the power prediction values ​​for each dynamic time period, generate power adjustment commands for each dynamic time period to control the energy storage module to perform charging, discharging, or standby operations; wherein, the photovoltaic energy storage device includes an energy storage module.

[0031] Specifically, power regulation commands are instructions used to guide energy storage modules to perform specific actions, including charging, discharging, and standby operations.

[0032] Specifically, an energy storage module refers to the core component of a photovoltaic energy storage device responsible for storing and releasing electrical energy. It includes sub-components such as energy storage battery packs, battery management systems (BMS), and bidirectional converters. It has the core functions of charging and storing electrical energy, discharging and releasing electrical energy, and standby and hibernation. It can realize flexible allocation of electrical energy by responding to power adjustment commands.

[0033] Specifically, photovoltaic energy storage equipment is an integrated device that combines a photovoltaic power generation module, an energy storage module, a predictive control module, a linkage execution module, a data acquisition module, and a communication module. The modules work together to ensure the accurate reception and execution of power regulation commands.

[0034] Understandably, the first step is to determine the direction of energy storage regulation for each period based on the power forecast and demand for each dynamic time period; then, the specific operation type of the energy storage module is determined, that is, to determine whether the energy storage module performs any operation such as charging, discharging or standby in each time period; finally, power regulation commands adapted to each time period are generated.

[0035] In summary, in the technical solutions of some embodiments of this application, based on the historical operating data and current environmental data of the photovoltaic energy storage device, an initial power prediction value for the device in a future target period is first predicted. Then, based on this initial power prediction value, the future target period is divided into multiple dynamic periods such as high-yield periods, balanced periods, and low-yield periods. Subsequently, for each dynamic period, a corresponding target prediction model is used to accurately predict the power prediction value for that period. Finally, corresponding power adjustment commands are generated based on the power prediction values ​​of each dynamic period to control the energy storage module to perform charging, discharging, or standby operations. In this way, advance prediction of photovoltaic power can be achieved through multi-step prediction, and dynamic adjustment of the energy storage module can be achieved through dynamic period division and precise prediction in different time periods. For example, during high-yield periods, the charging and discharging of the energy storage module can be specifically controlled to maximize returns; during balanced periods, power supply stability can be maintained; and during low-yield periods, ineffective charging and discharging losses can be reduced. This improves the utilization rate of energy storage resources and enhances system profitability. Thus, advance prediction and dynamic adjustment of photovoltaic power can be effectively achieved.

[0036] In some embodiments, step S103, which divides the future target time period into multiple dynamic time periods based on the initial power prediction value of the future target time period, includes: Step S1031: Divide the future target time period into multiple dynamic time periods according to a preset time interval; Step S1032: For any dynamic time period, determine the revenue coefficient for the dynamic time period based on the initial power prediction value, historical operating data and current environmental data. Step S1033: When the return coefficient of the dynamic period is greater than the first threshold, the dynamic period is regarded as a high-return period. Step S1034: When the return coefficient of the dynamic period is greater than the second threshold and not greater than the first threshold, the dynamic period is regarded as the equilibrium period. Step S1035: If the return coefficient of the dynamic period is not greater than the second threshold, the dynamic period is regarded as a low-return period.

[0037] Specifically, the preset time interval refers to the smallest time unit set in advance to divide the future target period. Its duration can be flexibly configured, such as 15 minutes, 30 minutes or 1 hour.

[0038] Specifically, the yield coefficient is a core indicator used to quantitatively assess the yield potential of each dynamic period. Its value directly reflects the level of yield that the photovoltaic energy storage system can obtain through charge and discharge linkage within the period.

[0039] Specifically, the first threshold and the second threshold are the criteria for distinguishing different benefit levels during different periods. The first threshold is higher than the second threshold. Both are determined based on historical operating data, current environmental data, and preset benefit targets. The first threshold is the dividing standard between high-return periods and balanced periods, and the second threshold is the dividing standard between balanced periods and low-return periods.

[0040] Understandably, the process begins by initially dividing the target time period into multiple short-cycle dynamic time periods through preset time intervals. For each dynamic time period, the initial power prediction value, historical operating data, and current environmental data are integrated to obtain the revenue coefficient for that period. Subsequently, the revenue coefficient is compared with preset first and second thresholds. If the revenue coefficient is greater than the first threshold, the dynamic time period is determined to be a high-revenue period. If the revenue coefficient is greater than the second threshold but not greater than the first threshold, it is determined to be a balanced period. If the revenue coefficient is not greater than the second threshold, it is determined to be a low-revenue period.

[0041] In the above embodiments, by dividing the future target time period according to a preset time interval, combining the initial power prediction value, historical operating data and current environmental data to determine the benefit coefficient of each dynamic time period, and classifying the time period type by comparing the first threshold and the second threshold, the benefit of each time period and the division of dynamic time periods can be realized, providing a logical basis for matching a dedicated prediction model and formulating differentiated charging and discharging strategies.

[0042] In some embodiments, step S104, for any dynamic time period, predicting the power forecast value for the dynamic time period based on the target prediction model corresponding to the dynamic time period and according to historical operating data and current environmental data, includes: Step S1041: When the dynamic period is a high-yield period, based on the first prediction model, predict the power forecast value of the high-yield period according to historical operating data and current environmental data. Step S1042: When the dynamic period is a balanced period, based on the second prediction model, predict the power forecast value of the balanced period according to historical operating data and current environmental data. Step S1043: When the dynamic period is a low-yield period, based on the third prediction model, predict the power forecast value for the low-yield period according to historical operating data and current environmental data. Step S1044: The target prediction model is divided into at least three types: the first prediction model, the second prediction model, and the third prediction model. The prediction accuracy of the first prediction model is higher than that of the second prediction model, and the prediction accuracy of the second prediction model is higher than that of the third prediction model.

[0043] Specifically, the first prediction model is a high-precision prediction model adapted for high-yield periods. It typically adopts a fusion architecture of a main model and a correction model. For example, an LSTM (Long Short-Term Memory) + Attention neural network is used as the main model, and an improved Kalman filter is used as the correction model. It has strong feature learning and error correction capabilities, ensuring optimal prediction accuracy.

[0044] Specifically, the second prediction model is a prediction model that is designed to be adapted to the power balance period, balancing accuracy and efficiency. It usually adopts a simplified neural network model, such as a GRU (Gated Recurrent Unit) neural network, which simplifies the feature input dimension to shorten the training cycle. While meeting the prediction accuracy required for power balance, it improves computational efficiency and reduces energy consumption.

[0045] Specifically, the third prediction model is an energy-saving prediction model adapted for low-yield periods. It typically uses a lightweight time-series prediction model, such as the ARIMA (AutoRegressive Integrated Moving Average Model), which only requires a small number of core features to complete the prediction. It has low algorithm complexity and low computational energy consumption, and can meet the basic prediction needs for low-yield periods.

[0046] Understandably, the process involves first identifying the type of the current dynamic period to be predicted, then calling the corresponding dedicated prediction model from the target prediction model set, and finally inputting preprocessed historical operational data and current environmental data into the model to calculate the power prediction value for the corresponding period. For example, if a dynamic period is determined to be a high-yield period, the first prediction model is called, inputting a 12-dimensional core feature vector, focusing on the feature data of three dimensions: the rate of change of light intensity, and the difference in electricity prices. The feature associations are learned through the LSTM+Attention main model, and then the error is corrected by an improved Kalman filter to output a high-precision power prediction value.

[0047] In the above embodiments, by clearly defining the dynamic time period type and matching a dedicated target prediction model for different time periods, and combining historical operating data and current environmental data to complete the power prediction for the corresponding time period, accurate adaptation of power prediction for each dynamic time period can be achieved, providing reliable data support for the subsequent generation of accurate differentiated linkage control commands.

[0048] In some embodiments, before step S105, which generates power adjustment commands for each dynamic period based on the power prediction values ​​for each dynamic period to control the energy storage module to perform charging, discharging, or standby operations, the method of this application further includes: Step a1: Determine the revenue value for each dynamic period based on the power prediction value and the revenue model for each dynamic period; wherein, the revenue model is used to verify whether the revenue reaches the optimal revenue in each dynamic period. Step a2: When the return value is less than the preset return threshold, adjust the prediction model parameters and / or correct the time period boundaries of each dynamic time period until the return value is not less than the preset return threshold. Step a3: When the revenue value is not less than the preset revenue threshold, the revenue value is determined to be the optimal revenue, and the step of generating power adjustment commands for each dynamic period based on the power prediction value of each dynamic period is executed to control the energy storage module to perform charging, discharging or standby operation.

[0049] Specifically, the revenue value refers to the comprehensive revenue quantification result of the period calculated based on the revenue model and combined with the power prediction value of each dynamic period, reflecting the actual revenue level that the photovoltaic energy storage system can obtain through charge and discharge linkage during the period.

[0050] Specifically, the preset revenue threshold refers to the revenue judgment benchmark determined based on historical operating data, current environmental data, and preset revenue targets. It is the core standard for distinguishing whether the revenue has met the target.

[0051] Understandably, the revenue model is first substituted with the predicted power values ​​for each time period to calculate the revenue value for each time period. Then, the calculated revenue value is compared with the preset revenue threshold to trigger subsequent differentiated operations. If the revenue value is less than the preset revenue threshold, an adjustment mechanism is triggered. This mechanism can either adjust the weights of the features in the corresponding prediction model to optimize the power prediction accuracy and improve the revenue value, or it can expand the revenue capture range by correcting the time period boundaries. After adjustment, the revenue value is recalculated until the revenue value is greater than the preset revenue threshold.

[0052] In the above embodiments, by calculating the revenue value based on the power prediction value of each dynamic time period before executing the power adjustment instruction generation step, comparing the revenue value with the preset revenue threshold, adjusting the prediction model parameters and / or correcting the time period boundary for scenarios that do not reach the threshold until the revenue reaches the target, and finally executing the subsequent instruction generation step, dynamic optimization of the revenue of each dynamic time period can be achieved, ensuring that subsequent scheduling instructions are generated based on the optimal revenue scenario.

[0053] In some embodiments, determining the revenue value for each dynamic period based on the power forecast value for each dynamic period includes: Step b1: Based on the power forecast values ​​for each dynamic period, determine the peak-valley price difference revenue, charging service fee revenue, curtailment loss, and equipment depreciation cost for each dynamic period. Step b2: Determine the revenue value for each dynamic period based on the peak-valley price difference revenue, charging service fee revenue, curtailment loss, and equipment depreciation cost for each dynamic period.

[0054] Specifically, peak-valley price difference revenue refers to the revenue obtained by a photovoltaic energy storage system by utilizing the difference between peak and valley electricity prices on the power grid through off-peak charging and peak-peak discharging modes. For example, the higher the peak-peak discharge power and the longer the discharge duration, the higher the peak-valley price difference revenue.

[0055] Specifically, charging service fee revenue refers to the revenue obtained by the system from providing charging services to external loads. The surplus of photovoltaic power during a period can be predicted by the power prediction value, thereby determining the scale of power that can be provided for charging services. Combined with the preset charging service unit price, the charging service fee revenue for that period can be calculated.

[0056] Specifically, curtailment loss refers to the economic loss caused by excess photovoltaic power being unable to be utilized due to reasons such as photovoltaic power exceeding energy storage capacity or lack of corresponding charging load demand.

[0057] Specifically, equipment loss cost refers to the economic cost corresponding to the losses generated by equipment such as energy storage modules, photovoltaic modules and bidirectional converters during operation over a period of time, including battery degradation loss and equipment energy consumption loss.

[0058] Understandably, the first step is to calculate all revenues and costs based on accurate power forecasts, and then calculate the final revenue value by deducting the revenues from the costs. For example, revenue value = peak-valley price difference revenue + charging service fee revenue - curtailment loss - equipment depreciation cost.

[0059] In the above embodiments, by accurately calculating the revenue from peak-valley price difference and charging service fees based on dynamic time-period power prediction values, as well as the costs of curtailment and equipment wear and tear, and then calculating the final revenue value by deducting the revenue from the costs, it can be ensured that the revenue value truly reflects the actual revenue level within the time period, providing accurate revenue data support for subsequent scheduling strategy optimization.

[0060] In some embodiments, step S105, which generates power adjustment commands for each dynamic time period based on the power prediction values ​​for each dynamic time period to control the energy storage module to perform charging, discharging, or standby operations, includes: Step S1051: When the dynamic period is a high-yield period and the high-yield period is within the off-peak electricity price range, generate an adjustment command for prioritizing the charging of the energy storage module. Step S1052: When the high-yield period falls within the peak electricity price range, an adjustment command is generated to prioritize the discharge of the energy storage module.

[0061] Specifically, off-peak electricity price ranges refer to periods when the electricity price is lower, typically corresponding to periods of low electricity demand, during which the cost of purchasing electricity is low. Peak electricity price ranges refer to periods when the electricity price is higher, typically corresponding to periods of high electricity demand, during which the revenue from selling electricity is high.

[0062] Understandably, the process involves first confirming that the current dynamic period is a high-yield period; then querying real-time grid electricity price information to determine whether the period falls within the off-peak or peak electricity price range; and finally matching the corresponding priority charging and discharging instructions based on the price range. For example, if a high-yield period is determined to fall within the peak electricity price range, an adjustment instruction is generated to discharge the energy storage module and prioritize power supply to the load, ensuring maximum profitability in this scenario.

[0063] In the above embodiments, by first confirming that the dynamic period is a high-yield period, then querying the real-time electricity price information of the power grid to determine the valley price or peak price range, and finally matching and generating corresponding priority charging and discharging adjustment instructions, the energy storage dispatch instructions for different electricity price scenarios in the high-yield period can be adapted, thereby improving the dispatch accuracy of photovoltaic energy storage systems in high-yield scenarios.

[0064] In some embodiments, step S105, which generates power adjustment commands for each dynamic time period based on the power prediction values ​​for each dynamic time period to control the energy storage module to perform charging, discharging, or standby operations, further includes: Step S1053: When the dynamic period is a balanced period, an adjustment command for direct photovoltaic power supply is generated, and the energy storage module is in standby mode. Step S1054: When the dynamic period is a low-yield period, an adjustment command is generated to limit the charging and discharging frequency of the energy storage module and reduce the power of the charging module.

[0065] Understandably, during balanced periods, a combination of direct photovoltaic power supply and energy storage backup is used to balance efficiency and stability; during low-yield periods, energy conservation and consumption reduction are focused on limiting energy storage operation and reducing module power, ultimately achieving precise matching between scheduling targets and operating states in different periods. For example, if a certain dynamic period is determined to be a balanced period, with the power forecast value stable at 50kW and the park's load demand stable at 50kW, then an instruction is generated to prioritize the direct supply of photovoltaic module output power to the park's load, while the energy storage module remains in standby mode.

[0066] In the above embodiments, by determining the dynamic time period type, adjustment instructions are generated for the balanced time period to directly power the photovoltaic system and for the energy storage module to be on standby, and for the low-yield time period to generate adjustment instructions to limit the charging and discharging frequency of the energy storage module and reduce the power of the charging module. This can achieve precise matching between the scheduling targets and operating status of different time periods, and improve the scheduling accuracy of the photovoltaic energy storage system in the balanced and low-yield time periods.

[0067] See also Figure 2 This is a communication diagram of a photovoltaic energy storage device provided in some embodiments of this application. Figure 2 In this context, environmental monitoring equipment refers to devices used to collect environmental parameters of the photovoltaic energy storage system, including but not limited to light sensors and temperature sensors. A photovoltaic inverter is a device that connects photovoltaic modules to the system's power link; its main function is to convert the direct current generated by the photovoltaic modules into usable or storeable alternating current. An energy storage system, or energy storage module, is the execution component responsible for storing and releasing electrical energy. A smart meter is a metering device used to measure electrical energy interaction data. The power grid / load is the energy consumption end. Data acquisition equipment is a data aggregation component, connected to various terminal sensing devices through specific communication interfaces. Local control equipment accurately sends generated power adjustment commands to the energy storage system via an RS485 wired bus. Cloud platforms and other platforms are core components for remote management and data processing of the system, deployed on remote servers, analyzing and processing received local data to generate remote control parameters, which are then sent to the local control equipment via 4G / 5G wireless communication links.

[0068] Corresponding to the power regulation method for photovoltaic energy storage devices, this application also provides a power regulation device for photovoltaic energy storage devices. (See also...) Figure 3 This is a schematic diagram of a power regulation device for a photovoltaic energy storage device provided in some embodiments of this application. Figure 3In this context, the power regulation device for photovoltaic energy storage equipment includes: The acquisition module 301 is used to acquire historical operating data and current environmental data of the photovoltaic energy storage device; The first prediction module 302 is used to predict the initial value of the power of the photovoltaic energy storage device in the future target period based on historical operating data and current environmental data. The time period segmentation module 303 is used to divide the future target time period into multiple dynamic time periods based on the initial power prediction value, historical operating data and current environmental data; among which, the dynamic time periods include high-yield time periods, balanced time periods and low-yield time periods; The second prediction module 304 is used to predict the power prediction value for any dynamic time period based on the target prediction model corresponding to the dynamic time period and according to historical operating data and current environmental data. The power regulation module 305 is used to generate power regulation commands for each dynamic period based on the power prediction value for each dynamic period, so as to control the energy storage module to perform charging, discharging or standby operation; wherein, the photovoltaic energy storage device includes the energy storage module.

[0069] In some embodiments, the time period segmentation module 303 includes: A dynamic time period division unit is used to divide the future target time period into multiple dynamic time periods according to a preset time interval; The revenue coefficient determination unit is used to determine the revenue coefficient for any given dynamic time period based on the initial power prediction value, historical operating data, and current environmental data. A high-yield period determination unit is used to identify a dynamic period as a high-yield period when the yield coefficient of the dynamic period is greater than a first threshold. The equilibrium period determination unit is used to determine the dynamic period as the equilibrium period when the revenue coefficient of the dynamic period is greater than the second threshold and not greater than the first threshold. The low-yield period determination unit is used to identify the dynamic period as a low-yield period when the yield coefficient of the dynamic period is not greater than a second threshold.

[0070] In some embodiments, the second prediction module 304 includes: The first prediction model unit is used to predict the power forecast value of the high-yield period based on the first prediction model and according to the historical operating data and the current environmental data when the dynamic period is a high-yield period. The second prediction model unit is used to predict the power forecast value of the balanced period based on the second prediction model and according to the historical operating data and the current environmental data when the dynamic period is a balanced period. The third prediction model unit is used to predict the power forecast value of the low-yield period based on the third prediction model and according to the historical operating data and the current environmental data when the dynamic period is a low-yield period. The prediction model differentiation unit is used to classify the target prediction model into at least three types: a first prediction model, a second prediction model, and a third prediction model. The prediction accuracy of the first prediction model is higher than that of the second prediction model, and the prediction accuracy of the second prediction model is higher than that of the third prediction model.

[0071] In some embodiments, the device further includes: The revenue value determination unit is used to determine the revenue value of each dynamic period based on the power prediction value of each dynamic period; wherein, the revenue model is used to verify whether the revenue in each dynamic period reaches the optimal revenue. The revenue value adjustment unit is used to adjust the prediction model parameters and / or correct the time period boundaries of each dynamic time period when the revenue value is less than a preset revenue threshold, until the revenue value is not less than the preset revenue threshold. The optimal benefit determination unit is used to determine that the benefit value is the optimal benefit when the benefit value is not less than a preset benefit threshold, and to execute the step of generating power adjustment commands for each dynamic period based on the power prediction values ​​of each dynamic period to control the energy storage module to perform charging, discharging or standby operation.

[0072] In some embodiments, the revenue value determination unit includes: The revenue factor determination subunit is used to determine the peak-valley price difference revenue, charging service fee revenue, curtailment loss and equipment depreciation cost for each dynamic period based on the power forecast value for each dynamic period. The revenue value determination subunit is used to determine the revenue value for each dynamic period based on the peak-valley price difference revenue, charging service fee revenue, curtailment loss, and equipment depreciation cost for each dynamic period.

[0073] In some embodiments, the power regulation module 305 includes: The off-peak electricity price generation and adjustment instruction unit is used to generate an adjustment instruction to prioritize charging the energy storage module when the dynamic period is a high-yield period and the high-yield period is within the off-peak electricity price range. The peak electricity price generation and adjustment instruction unit is used to generate an adjustment instruction to prioritize the discharge of the energy storage module when the high-yield period is within the peak electricity price range.

[0074] In some embodiments, the power regulation module 305 further includes: A balance period regulation instruction generation unit is used to generate regulation instructions for direct photovoltaic power supply when the dynamic period is a balance period, and the energy storage module is in standby mode; The low-yield period generation adjustment instruction unit is used to generate adjustment instructions that limit the charging and discharging frequency of the energy storage module and reduce the power of the charging module when the dynamic period is a low-yield period.

[0075] For a description of the features in the embodiment corresponding to the power regulation device of the photovoltaic energy storage equipment, please refer to the relevant description of the embodiment corresponding to the sample data processing method, which will not be repeated here.

[0076] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0077] See also Figure 4 The embodiments of this application also provide an electronic device, including a memory 10 and a processor 20, wherein the memory 10 stores a computer program and the processor 20 is configured to run the computer program to perform the steps in any of the above embodiments of the photovoltaic energy storage device power regulation method.

[0078] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above embodiments of the photovoltaic energy storage device power regulation method when running.

[0079] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0080] The embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the photovoltaic energy storage device power regulation method.

[0081] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above embodiments of the photovoltaic energy storage device power regulation method.

[0082] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0083] The power regulation method, apparatus, equipment, and storage medium of a photovoltaic energy storage device provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only intended to help understand the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A power regulation method for a photovoltaic energy storage device, characterized in that, The method includes: Acquire historical operating data and current environmental data of photovoltaic energy storage devices; Based on the historical operating data and current environmental data, the initial power prediction value of the photovoltaic energy storage device is predicted for the future target period. Based on the initial power forecast for the future target period, historical operating data, and current environmental data, the future target period is divided into multiple dynamic periods; wherein, the dynamic periods include high-yield periods, balanced periods, and low-yield periods; For any of the aforementioned dynamic time periods, based on the target prediction model corresponding to the dynamic time period, and according to the historical operating data and current environmental data, the power prediction value for the dynamic time period is predicted; Based on the power prediction values ​​for each dynamic time period, power adjustment commands are generated for each dynamic time period to control the energy storage module to perform charging, discharging, or standby operations; wherein, the photovoltaic energy storage device includes the energy storage module.

2. The power regulation method for photovoltaic energy storage equipment according to claim 1, characterized in that, The step of dividing the future target time period into multiple dynamic time periods based on the initial power prediction value of the future target time period includes: The future target time period is divided into multiple dynamic time periods according to a preset time interval; For any of the aforementioned dynamic time periods, the revenue coefficient for that dynamic time period is determined based on the initial power prediction value, historical operating data, and current environmental data. When the return coefficient of the dynamic period is greater than the first threshold, the dynamic period is regarded as a high-return period; When the return coefficient of the dynamic period is greater than the second threshold but not greater than the first threshold, the dynamic period is regarded as the balance period. If the return coefficient of the dynamic period is not greater than the second threshold, the dynamic period is designated as a low-return period.

3. The power regulation method for photovoltaic energy storage equipment according to claim 1, characterized in that, For any given dynamic time period, based on the target prediction model corresponding to that dynamic time period and according to the historical operating data and current environmental data, the prediction of the power forecast value for that dynamic time period includes: When the dynamic period is a high-yield period, based on the first prediction model, the power prediction value of the high-yield period is predicted according to the historical operating data and the current environmental data. When the dynamic period is a balanced period, based on the second prediction model, the power prediction value of the balanced period is predicted according to the historical operating data and the current environmental data. When the dynamic period is a low-yield period, based on the third prediction model, the power prediction value for the low-yield period is predicted according to the historical operating data and the current environmental data. The target prediction model is divided into at least three types: a first prediction model, a second prediction model, and a third prediction model. The prediction accuracy of the first prediction model is higher than that of the second prediction model, and the prediction accuracy of the second prediction model is higher than that of the third prediction model.

4. The power regulation method for photovoltaic energy storage equipment according to claim 1, characterized in that, Before generating power adjustment commands for each dynamic period based on the predicted power values ​​for each dynamic period to control the energy storage module to perform charging, discharging, or standby operation, the method further includes: Based on the power prediction value and revenue model for each dynamic period, the revenue value for each dynamic period is determined; wherein, the revenue model is used to verify whether the revenue reaches the optimal revenue in each dynamic period. When the revenue value is less than the preset revenue threshold, adjust the prediction model parameters and / or correct the time period boundaries of each dynamic time period until the revenue value is not less than the preset revenue threshold. When the revenue value is not less than the preset revenue threshold, the revenue value is determined to be the optimal revenue, and the step of generating power adjustment commands for each dynamic period based on the power prediction value of each dynamic period is executed to control the energy storage module to perform charging, discharging or standby operation.

5. The power regulation method for photovoltaic energy storage equipment according to claim 4, characterized in that, The step of determining the revenue value for each dynamic time period based on the power prediction value for each dynamic time period includes: Based on the power forecast values ​​for each dynamic period, determine the peak-valley price difference revenue, charging service fee revenue, curtailment loss, and equipment depreciation cost for each dynamic period. The revenue value for each dynamic period is determined based on the peak-valley price difference revenue, charging service fee revenue, curtailment loss, and equipment depreciation cost for each dynamic period.

6. The power regulation method for photovoltaic energy storage equipment according to claim 1, characterized in that, The step of generating power adjustment commands for each dynamic time period based on the predicted power values ​​for each dynamic time period to control the energy storage module to perform charging, discharging, or standby operations includes: When the dynamic period is a high-yield period and the high-yield period is within the off-peak electricity price range, an adjustment command is generated to prioritize charging the energy storage module. When the high-yield period falls within the peak electricity price range, an adjustment command is generated to prioritize the discharge of the energy storage module.

7. The power regulation method for photovoltaic energy storage equipment according to claim 6, characterized in that, The step of generating power adjustment commands for each dynamic time period based on the predicted power values ​​for each dynamic time period to control the energy storage module to perform charging, discharging, or standby operations includes: When the dynamic period is a balanced period, an adjustment command for direct photovoltaic power supply is generated, and the energy storage module is in standby mode. When the dynamic period is a low-yield period, adjustment commands are generated to limit the charging and discharging frequency of the energy storage module and reduce the power of the charging module.

8. A power regulation device for photovoltaic energy storage equipment, characterized in that, The device includes: The acquisition module is used to acquire historical operating data and current environmental data of photovoltaic energy storage devices; The first prediction module is used to predict the initial power forecast value of the photovoltaic energy storage device in a future target period based on the historical operating data and current environmental data. The time period segmentation module is used to divide the future target time period into multiple dynamic time periods based on the initial power prediction value, historical operating data, and current environmental data; wherein, the dynamic time periods include high-yield time periods, balanced time periods, and low-yield time periods; The second prediction module is used to predict the power prediction value of any dynamic time period based on the target prediction model corresponding to the dynamic time period and according to the historical operating data and current environmental data. A power regulation module is used to generate power regulation commands for each dynamic period based on the predicted power values ​​for each dynamic period, so as to control the energy storage module to perform charging, discharging or standby operations; wherein, the photovoltaic energy storage device includes the energy storage module.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the power regulation method for a photovoltaic energy storage device as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the power regulation method for a photovoltaic energy storage device as described in any one of claims 1 to 7.

Images