Demand control method for photovoltaic energy storage power station and related products

Abstract

The application provides a demand control method for a photovoltaic energy storage power station, the photovoltaic energy storage power station comprising a photovoltaic assembly and an energy storage device; and the demand control method comprises the following steps: obtaining historical power supply data of the photovoltaic energy storage power station; predicting a production power load of the photovoltaic energy storage power station in a preset prediction period based on the historical power supply data; determining whether the production power load exceeds a preset production demand threshold; if yes, predicting whether there is a power supply shortage in a power use peak period of one or more power use statistical periods during the preset prediction period; and if there is a power supply shortage, selecting a charging time before the power use statistical period in which the power supply shortage exists, charging the energy storage device at the charging time, and configuring the energy storage device to discharge in the power use peak period of the power use statistical period in which the power supply shortage exists.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic energy storage technology, and in particular to a demand control method and related products for a photovoltaic energy storage power station. Background Technology

[0002] With the rapid development of science and technology and the continuous progress of society, people's living standards and consumption concepts have been constantly improved. At the same time, people are also facing a series of serious environmental pollution and climate deterioration problems, such as energy shortages, air pollution, and rising global temperatures. Therefore, the development and utilization of renewable energy sources has become a global focus. Solar energy, due to its low pollution and status as a renewable energy source, is widely used in photovoltaic power generation. However, because solar energy is affected by natural factors and is intermittent, fluctuating, and random, it is prone to power imbalances.

[0003] Currently, in existing technologies, the common approach to ensure the reliability of photovoltaic (PV) power generation systems is to equip them with energy storage systems. This is particularly prevalent in industrial parks, where such PV-energy storage systems are often deployed, or individual businesses voluntarily configure them to reduce electricity costs. Furthermore, to further guide businesses towards economical, efficient, and green electricity use, my country has issued a series of demand-based electricity policies. For example, monthly demand standards are issued to businesses; if a business exceeds these standards, the power grid company charges an additional fee on top of the electricity consumption. Existing PV-energy storage systems, during operation, use historical power supply data to predict user electricity consumption and the system's power supply, adjusting their operational strategies based on these predictions. However, while this can meet the electricity needs of enterprise users to some extent, the photovoltaic-energy storage system cannot predict in advance whether the electricity consumption of enterprise users will exceed the demand standard. If the capacity of the photovoltaic modules and energy storage batteries cannot meet the electricity demand of enterprise users during peak periods after the electricity consumption exceeds the demand standard, the photovoltaic-energy storage system will draw power from the grid, which will cause the electricity costs of enterprise users to rise sharply and reduce the user experience. Summary of the Invention

[0004] One object of the present invention is to provide a demand control method and related products for a photovoltaic energy storage power station that can solve at least one of the defects in the prior art.

[0005] A further objective of this invention is to effectively reduce the electricity costs of the powered devices and ensure a better user experience.

[0006] Specifically, this invention provides a demand control method for a photovoltaic energy storage power station, the photovoltaic energy storage power station including photovoltaic modules and energy storage devices; and,

[0007] Demand control methods include:

[0008] Obtain historical power supply data from photovoltaic energy storage power stations;

[0009] The power load of the photovoltaic energy storage power station is predicted within a preset prediction period based on historical power supply data.

[0010] Determine whether the power load exceeds the preset production demand threshold;

[0011] If so, predict whether there will be insufficient power supply during peak electricity consumption periods of one or more electricity consumption statistical cycles within a preset prediction period for photovoltaic modules;

[0012] If present, select a charging time before the power consumption statistics period with insufficient power supply, charge the energy storage device during the charging time, and configure the energy storage device to discharge during the peak power consumption period of the power consumption statistics period with insufficient power supply.

[0013] Furthermore, the charging time includes both photovoltaic charging time and mains charging time; and,

[0014] The steps of selecting a charging time before a power consumption period with insufficient power supply and charging the energy storage device during that time include:

[0015] Determine the photovoltaic charging time and the grid charging time, and use the photovoltaic modules and the grid to charge the energy storage device during the photovoltaic charging time and the grid charging time, respectively.

[0016] Furthermore, the steps for determining the photovoltaic charging time and the mains charging time include:

[0017] Based on the electricity revenue charging time model, a preset algorithm is used to solve for the time points when the photovoltaic power generation starts charging and the grid power generation starts charging when the electricity revenue is maximized. The electricity revenue charging time model is a function of the electricity revenue and the photovoltaic power generation start charging time and the grid power generation start charging time.

[0018] The time points at which the photovoltaic power starts charging and the time points at which the mains power starts charging, obtained from the solution, are respectively defined as the photovoltaic charging time and the mains power charging time.

[0019] Furthermore, the electricity revenue charging time model is as follows:

[0020] M = C1(t1) - C2(t2) - C3(t3),

[0021] Where M represents electricity revenue;

[0022] C1 is the discharge capacity of the energy storage device, t1 is the discharge time of the energy storage device, and C1(t1)=P1t1m1, P1 is the discharge power of the energy storage device, and m1 is the discharge electricity price of the energy storage device.

[0023] C2 represents the charging capacity using the photovoltaic modules, t2 represents the time when the photovoltaic system starts charging, and C2(t2) = P2t2m2, where P2 is the charging power using the photovoltaic modules, and m2 is the charging electricity price using the photovoltaic modules. T represents the temperature of the photovoltaic panel in the photovoltaic module, and G represents the temperature of the photovoltaic module. max T represents the maximum irradiance of the photovoltaic panel. noct The battery operating temperature of the energy storage device, t rise For sunrise time, t set For sunset time, t noon For noon, a, b, and k are correction coefficients;

[0024] C3 represents the charging capacity using the municipal power grid, t3 represents the start time of charging using the municipal power grid, and C3(t3) = P3t3m3, where P3 is the charging power of the energy storage device using the municipal power grid, and m3 is the charging electricity price of the energy storage device using the municipal power grid.

[0025] The default algorithm is the ant colony algorithm, with the following constraints: 0≤C1≤C, 0≤C2≤C, t1 is earlier than t3 and t3 is earlier than t2, and C is the energy storage capacity of the energy storage device.

[0026] Furthermore, during the step of charging the energy storage device within the charging time, and during the time between charging and discharging the energy storage device, the discharge of the energy storage device is limited.

[0027] Furthermore, the production demand threshold is determined based on the demand standards issued by the public grid dispatching department to the photovoltaic energy storage power station's power supply recipients.

[0028] Furthermore, the historical power supply data includes historical power supply volume for a preset historical statistical period; and,

[0029] The steps for predicting the power load of a photovoltaic energy storage power station within a preset prediction period based on historical power supply data include:

[0030] The historical power supply is classified according to the power supply volume of the preset historical statistical period to obtain the power supply volume of the standard working period and the power supply volume of the non-standard working period.

[0031] The LSTM model is used to predict the power load of production based on the power supply during the standard duty cycle and the power supply during the non-standard duty cycle.

[0032] Furthermore, historical power supply data includes peak electricity consumption during preset historical statistical periods; and,

[0033] The steps for predicting whether there will be a power shortage during peak electricity consumption periods of one or more electricity consumption statistical cycles within a preset prediction period include:

[0034] Predict the peak power generation of photovoltaic modules within a preset prediction period;

[0035] Based on historical peak electricity consumption, the power consumption of photovoltaic energy storage power stations during the peak period of the preset prediction cycle is predicted.

[0036] Determine whether peak-period power generation is greater than or equal to peak-period power consumption;

[0037] If not, it is determined that there is insufficient power supply for the photovoltaic modules during peak electricity consumption periods of one or more electricity consumption statistical cycles within the preset forecast period;

[0038] If so, it is confirmed that there is no power shortage during the peak electricity consumption period of one or more electricity consumption statistical periods within the preset prediction period.

[0039] Furthermore, the steps for predicting the peak power generation of photovoltaic modules within a preset prediction period include:

[0040] The weather forecasting model is used to predict weather data within a preset forecast period. The weather forecasting model includes at least one of the DGMR (Deep Generative Model for Rainfall) model and the WRF (Weather Research and Forecasting) model.

[0041] The output power of the corresponding photovoltaic modules during the peak electricity consumption period within the preset forecast cycle is determined based on weather data.

[0042] Peak-period power generation is calculated based on output power and the predicted peak sunshine duration of the photovoltaic modules. The predicted peak sunshine duration is the sunshine duration of the photovoltaic modules during the peak electricity consumption period within a preset prediction cycle.

[0043] The steps for predicting the peak electricity consumption of photovoltaic energy storage power stations during a preset prediction period based on historical peak electricity consumption include:

[0044] Based on historical peak electricity consumption, the LSTM (Long Short-Term Memory) model is used to predict peak electricity consumption.

[0045] In particular, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described demand control method for a photovoltaic energy storage power station.

[0046] In particular, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described demand control method for a photovoltaic energy storage power station.

[0047] In particular, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-described demand control method for a photovoltaic energy storage power station.

[0048] The demand control method for photovoltaic energy storage power stations of the present invention can effectively predict whether a power-supplying entity (such as a business user) will exceed its demand standard by setting a production demand threshold and predicting insufficient power supply from photovoltaic modules. Furthermore, it can store electrical energy using energy storage devices before demand exceeds the standard, and discharge any insufficient power supply during peak periods of the statistical period within a future preset prediction cycle. This effectively limits the occurrence of power-supplying entities drawing power from the grid during peak periods after demand exceeds the standard. Therefore, the demand control method for photovoltaic energy storage power stations of the present invention can effectively reduce the electricity costs of power-supplying entities and ensure a better user experience.

[0049] The computer program product of the present invention can implement the demand control method for the photovoltaic energy storage power station described above. Therefore, the computer program product of the present invention also possesses the beneficial technical effects that the demand control method for the photovoltaic energy storage power station described above can achieve.

[0050] The computer-readable storage medium of the present invention can implement the demand control method for the photovoltaic energy storage power station described above. Therefore, the computer-readable storage medium of the present invention also possesses the beneficial technical effects that the demand control method for the photovoltaic energy storage power station described above can achieve.

[0051] The computer device of the present invention can implement the demand control method for the photovoltaic energy storage power station described in the above embodiments. Therefore, the computer device of the present invention also possesses the beneficial technical effects that can be achieved by the demand control method for the photovoltaic energy storage power station described above.

[0052] The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments of the invention in conjunction with the accompanying drawings. Attached Figure Description

[0053] The following sections will describe some specific embodiments of the invention in detail by way of example and not limitation, with reference to the accompanying drawings. The same reference numerals in the drawings denote the same or similar parts or portions. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0054] Figure 1 This is a schematic flowchart of a demand control method for a photovoltaic energy storage power station according to an embodiment of the present invention;

[0055] Figure 2 This is a schematic diagram of the process of selecting a charging time and charging the energy storage device during the charging time in a demand control method for a photovoltaic energy storage power station according to an embodiment of the present invention.

[0056] Figure 3 This is a flowchart illustrating the process of predicting whether there is a power shortage during peak electricity consumption periods of one or more electricity consumption statistical cycles during a preset prediction period in a photovoltaic energy storage power station demand control method according to an embodiment of the present invention.

[0057] Figure 4 This is a schematic flowchart of a demand control method for a photovoltaic energy storage power station according to another embodiment of the present invention;

[0058] Figure 5 This is a schematic flowchart of a demand control method for a photovoltaic energy storage power station according to another embodiment of the present invention;

[0059] Figure 6 This is a structural block diagram of a computer program product according to an embodiment of the present invention;

[0060] Figure 7 This is a schematic structural block diagram of a computer-readable storage medium according to an embodiment of the present invention;

[0061] Figure 8 This is a structural block diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0062] In the description of this embodiment, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature, that is, include one or more of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. When a feature "includes or contains" one or more of the features it encompasses, unless otherwise specifically described, this indicates that other features are not excluded and may be further included.

[0063] Unless otherwise specified, all terms (including technical and scientific terms) used in the description of these embodiments have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0064] In the description of this embodiment, the use of the term "embodiment," etc., refers to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0065] The following is combined with Figures 1 to 5 The demand control method of the photovoltaic energy storage power station in this embodiment will be described in detail below.

[0066] Figure 1 This is a schematic flowchart of a demand control method for a photovoltaic energy storage power station according to an embodiment of the present invention. (Refer to...) Figure 1 In this embodiment, the demand control method for a photovoltaic energy storage power station includes photovoltaic modules and energy storage devices; and the demand control method may include:

[0067] Step S101: Obtain historical power supply data of the photovoltaic energy storage power station (historical power supply data may include historical power supply during a preset historical statistical period and historical peak electricity consumption during a preset historical statistical period).

[0068] Step S102: Predict the power load of the photovoltaic energy storage power station within a preset prediction period (e.g., 15 days) based on historical power supply data. This step may include steps S402 to S403 of the following embodiments.

[0069] Step S103: Determine whether the production power load exceeds the preset production demand threshold. If yes, proceed to step S104. If no, return to step S102 or step S101.

[0070] Step S104: Predict whether there is a power shortage during peak electricity consumption periods of one or more electricity consumption statistical periods (e.g., one or more days in 15 days) during the preset prediction period of the photovoltaic module; if so, proceed to step S105; if not, the photovoltaic energy storage power station can be configured to operate according to the preset peak shaving and valley filling strategy.

[0071] Step S105: Select a charging time before the power consumption statistics period with insufficient power supply, charge the energy storage device during the charging time, and configure the energy storage device to discharge during the peak power consumption period of the power consumption statistics period with insufficient power supply.

[0072] Because the demand control method of the photovoltaic energy storage power station in this embodiment can effectively predict whether the demand of the power supply target (such as enterprise users) will exceed the demand standard by setting the production demand threshold and predicting the insufficient power supply of photovoltaic modules, it can store electrical energy using energy storage devices before the demand standard is exceeded. Furthermore, it can discharge the insufficient power supply during the peak period of the statistical period when the power supply may exceed the demand standard in the future preset prediction period, thus effectively limiting the occurrence of the power supply target drawing power from the grid during peak periods after the power consumption exceeds the demand standard. Therefore, the demand control method of the photovoltaic energy storage power station in this embodiment can effectively reduce the electricity cost of the power supply target and ensure the user experience.

[0073] In this embodiment, the charging time may include photovoltaic charging time and mains charging time. Furthermore, referring to... Figure 2 The steps of selecting a charging time before a power usage statistical period with insufficient power supply and charging the energy storage device during that charging time may include:

[0074] Step S201 involves determining the photovoltaic charging time and the mains charging time, and then charging the energy storage device using the photovoltaic modules and the mains grid during the photovoltaic charging time and mains charging time, respectively. This step may include steps S410 to S412 of the following embodiments.

[0075] Understandably, since the charging rate of the municipal power grid for energy storage devices is much greater than that of photovoltaic modules, in order to enable the energy storage devices to complete charging quickly and respond rapidly to situations where the power supply targets may draw power from the municipal power grid during peak periods in the future, the municipal power grid and photovoltaic modules can be used together to charge the energy storage devices. This ensures that the energy storage devices can discharge during peak electricity consumption periods in the statistical period of insufficient power supply, further reducing the electricity costs for the power supply targets and ensuring the user experience.

[0076] In this embodiment, the discharge of the energy storage device is limited during the step of charging the energy storage device within the charging time, and during the time between charging and discharging the energy storage device.

[0077] It is understandable that by prohibiting the discharge of the energy storage device during charging and during the charging and discharging of the energy storage device, the electrical energy stored in the energy storage device can be fully provided to the power supply object during the peak electricity consumption period of the electricity consumption statistical period when the power supply is insufficient. This further avoids the situation where the power supply object draws power from the grid during the peak period after the electricity consumption exceeds the demand standard, thus ensuring the reduction of the power supply object's electricity cost.

[0078] In this embodiment, the production demand threshold can be determined based on the demand standard issued by the public grid dispatching department to the photovoltaic energy storage power station's power supply targets, thereby improving the accuracy of predicting whether the power supply targets (e.g., enterprise users) will exceed the demand standard. Specifically, the production demand threshold can be the sum of the demand standard and the power generation of the photovoltaic modules within the preset forecast period. Furthermore, the production demand threshold can also be determined based on the demand standard and other considerations, such that the production demand threshold is greater than, equal to, or less than the demand standard (or such that the production demand threshold is less than the sum of the demand standard and the power generation of the photovoltaic modules within the preset forecast period). This allows the photovoltaic energy storage power station to promptly predict when the power supply targets will draw power from the grid during peak hours after their electricity consumption exceeds the demand standard, and to promptly utilize energy storage devices to store electrical energy, thus preventing the power supply targets from drawing power from the grid during peak hours after their electricity consumption exceeds the demand standard.

[0079] In this embodiment, historical power supply data includes peak electricity consumption during a preset historical statistical period; and, referring to Figure 3 The steps for predicting whether there will be a power shortage during peak electricity consumption periods of one or more electricity consumption statistical periods within a preset prediction period include:

[0080] Step S301: Predict the peak power generation of the photovoltaic module within a preset prediction period. This step may include steps S405 to S407 of the following embodiments.

[0081] Step S302: Predict the peak electricity consumption of the photovoltaic energy storage power station's power supply targets during a preset prediction period based on historical peak electricity consumption. This step may include step S408 of the following embodiment.

[0082] Step S303: Determine whether the peak power generation is greater than or equal to the peak power consumption; if not, proceed to step S304; if yes, proceed to step S305.

[0083] Step S304: Determine that the photovoltaic modules experience insufficient power supply during peak electricity consumption periods of one or more electricity consumption statistical cycles within a preset prediction period.

[0084] Step S305: Determine that there is no power shortage during peak electricity consumption periods of one or more electricity consumption statistical cycles within a preset prediction period for the photovoltaic modules.

[0085] It is understandable that whether the power supply of the photovoltaic module is sufficient during peak periods can be determined by comparing the power generation of the photovoltaic module with the power consumption of the target device during peak periods. That is, step S104 of the above embodiment can be achieved through steps S301 to S305.

[0086] Figure 4This is a schematic flowchart of a demand control method for a photovoltaic energy storage power station according to another embodiment of the present invention. In this embodiment, the photovoltaic energy storage power station includes photovoltaic modules and an energy storage device; and, referring to... Figure 4 Demand control methods may include:

[0087] Step S401: Obtain historical power supply data of the photovoltaic energy storage power station (historical power supply data may include historical power supply volume for a preset historical statistical period).

[0088] Step S402: Classify the historical power supply according to the power supply volume of the preset historical statistical period to obtain the power supply volume of the standard working cycle and the power supply volume of the non-standard working cycle.

[0089] Step S403: Based on the power supply of the standard working cycle and the power supply of the non-standard working cycle, the LSTM model is used to predict the power load of production.

[0090] Step S404: Determine whether the production power load exceeds the preset production demand threshold. If yes, proceed to step S405. If no, return to step S402 or step S401.

[0091] Step S405: Use a preset weather forecast model to predict weather data within a preset forecast period.

[0092] Step S406: Determine the output power of the corresponding photovoltaic module during the peak electricity consumption period within the preset forecast cycle based on weather data.

[0093] Step S407: Calculate the peak power generation based on the output power and the peak sunshine duration of the photovoltaic module during the predicted period. The peak sunshine duration during the predicted period is the sunshine duration of the photovoltaic module during the peak electricity consumption period within the preset prediction period.

[0094] Step S408: Based on historical peak electricity consumption, use the LSTM model to predict peak electricity consumption.

[0095] Step S409: Determine whether the peak power generation is greater than or equal to the peak power consumption; if not, proceed to step S310; if yes, the photovoltaic energy storage power station can be configured to operate according to the preset peak shaving and valley filling strategy.

[0096] Step S410: Based on the electricity revenue charging time model, a preset algorithm is used to solve for the time points when the photovoltaic power generation starts charging and the mains power generation starts charging when the electricity revenue is maximized. The electricity revenue charging time model is a functional relationship between electricity revenue and the photovoltaic power generation start charging time and the mains power generation start charging time.

[0097] Step S411: Determine the time points when the photovoltaic power starts charging and the mains power starts charging, respectively, as the photovoltaic charging time and the mains power charging time.

[0098] Step S412: The energy storage device is charged using the photovoltaic modules and the mains power grid during the photovoltaic charging time and the mains power charging time, respectively.

[0099] Step S413: Configure the energy storage device to discharge during peak electricity consumption periods in the statistical cycle of insufficient power supply.

[0100] Understandably, in steps S410 to S412, the optimal (when the value of electricity revenue is maximized) time points for photovoltaic power generation to start charging and grid power generation to start charging are obtained by solving the electricity revenue charging time model. This allows the energy storage device to be fully charged as quickly as possible with the lowest electricity cost, thereby suppressing the occurrence of the power supply object drawing power from the grid during peak periods after the electricity consumption exceeds the demand standard. It can also further reduce the electricity cost of the power supply object and further ensure the user experience.

[0101] In step S410, the electricity consumption revenue charging time model is as follows:

[0102] M = C1(t1) - C2(t2) - C3(t3),

[0103] Where M represents electricity revenue;

[0104] C1 is the discharge capacity of the energy storage device, t1 is the discharge time of the energy storage device, and C1(t1)=P1t1m1, P1 is the discharge power of the energy storage device, and m1 is the discharge electricity price of the energy storage device.

[0105] C2 represents the charging capacity using photovoltaic modules, t2 represents the time when the photovoltaic system starts charging, and C2(t2) = P2t2m2, where P2 is the charging power using photovoltaic modules, and m2 is the charging electricity price using photovoltaic modules. For calculation purposes, m2 can be 0.00001 yuan per kilowatt-hour. T represents the temperature of the photovoltaic panel in the photovoltaic module, and G represents the temperature of the photovoltaic module. max T represents the maximum irradiance of the photovoltaic panel. noct The battery operating temperature of the energy storage device, t rise For sunrise time, t set For sunset time, t noon For noon, a, b, and k are correction coefficients, and k can be 0.3;

[0106] C3 represents the charging capacity using the municipal power grid, t3 represents the start time of charging using the municipal power grid, and C3(t3) = P3t3m3, where P3 is the charging power of the energy storage device using the municipal power grid, and m3 is the charging electricity price of the energy storage device using the municipal power grid.

[0107] The default algorithm is the ant colony algorithm, with the following constraints: 0≤C1≤C, 0≤C2≤C, t1 is earlier than t3 and t3 is earlier than t2, and C is the energy storage capacity of the energy storage device.

[0108] It is understandable that by setting the above parameters of the electricity revenue charging time model, the optimal (when the electricity revenue value is maximized) time points for photovoltaic power generation to start charging and grid power generation to start charging can be obtained.

[0109] In step S402, since the LSTM model is naturally suitable for capturing long-term dependencies and periodic patterns in sequence data, and thus has higher prediction accuracy for regular values, step S402 divides historical power supply into power supply for standard working cycles (e.g., typical working days for enterprise users, which can be Monday to Friday) and power supply for non-standard working cycles (e.g., special working days for enterprise users, such as Saturdays and Sundays when overtime production is carried out). This can effectively improve the accuracy of predicting production power load, thereby further improving the accuracy of predicting whether the power supply target (e.g., enterprise users) will exceed the demand standard. Furthermore, in step S408, the LSTM model can be used to predict peak-period power consumption and ensure the accuracy of peak-period power consumption prediction.

[0110] In step S405, the weather forecast model includes at least one of the DGMR model and the WRF model, so that step S405 can make the prediction of weather data and ensure the accuracy of the weather data prediction.

[0111] In step S405, the weather data may include weather type, such as sunny, cloudy, rainy, and partly cloudy. In step S406, the output power of the corresponding photovoltaic module during the peak electricity consumption period within a preset forecast period is determined based on the weather data. Specifically, this may include obtaining a preset correspondence between preset weather data (weather type) and preset solar irradiance (and ambient temperature, which can also be detected in real time), and obtaining the solar irradiance based on the weather data and the preset correspondence. Furthermore, the output power of a single string of photovoltaic modules can be calculated based on the ambient temperature and solar irradiance. The output power of the photovoltaic modules is also obtained based on the number of strings of photovoltaic modules in the photovoltaic energy storage power station (e.g., a product). The output power of a single string of photovoltaic modules is P = a + b × T × H + c × H + d × H. 2P is the output power of a single-string photovoltaic module, H is the solar irradiance, T is the temperature of the photovoltaic panel, and a, b, c, and d are correction factors. G max T represents the maximum irradiance of the photovoltaic panel. noct T represents the battery operating temperature of the energy storage device. a The ambient temperature is used. In step S407, the peak power generation is obtained by calculating (producting) the output power of the photovoltaic module and the peak sunshine duration during the forecast period.

[0112] In the above embodiments, after step S101 and before step S102, and / or after step S401 and before step S402, the demand control method may include: performing data preprocessing on historical power supply data (e.g., historical power supply and historical peak-period power consumption) (e.g., data cleaning to eliminate noise and outliers, handle missing values, unify data format, and remove duplicate data, ensuring data quality and avoiding interference from noise and outliers to the model; or, for example, feature extraction to extract key features, construct derived features, and extract time-series features, thereby improving the prediction accuracy of production power load and peak-period power consumption; and during feature extraction, dimensionality reduction processing can be performed on the data to improve the generalization ability of the model), to ensure the accuracy and efficiency of production power load and peak-period power consumption prediction.

[0113] In the above embodiments, after step S104, if the photovoltaic modules do not experience power shortages during peak electricity consumption periods in one or more electricity consumption statistical periods within a preset forecast period, and after step S409, if peak-period power generation is greater than or equal to peak-period power consumption, then the demand control method can execute the step of configuring the photovoltaic energy storage power station to operate according to a preset peak-shaving and valley-filling strategy. It should be understood that if the photovoltaic modules do not experience power shortages during peak electricity consumption periods in one or more electricity consumption statistical periods within a preset forecast period, or if peak-period power generation is greater than or equal to peak-period power consumption, it indicates that the power supply target will not exceed the demand standard within the preset forecast period. Therefore, the photovoltaic energy storage power station can be configured to execute normal peak-shaving and valley-filling policies to ensure the normal operation of the photovoltaic energy storage power station and guarantee the power supply target's electricity consumption.

[0114] Figure 5 This is a schematic flowchart of a demand control method for a photovoltaic energy storage power station according to another embodiment of the present invention. In this embodiment, the demand control method for the photovoltaic energy storage power station includes photovoltaic modules and an energy storage device; and, referring to... Figure 5 Demand control methods may include:

[0115] Step S501: Obtain historical charging and discharging data of the photovoltaic energy storage power station and relevant data of the energy storage power station during peak electricity consumption periods.

[0116] Step S502: Perform data preprocessing (data cleaning and feature extraction) on historical charging and discharging data and data related to peak electricity consumption.

[0117] Step S503: Construct a production load prediction model based on LSTM (Long Short-Term Memory Neural Network), and use the model to predict the future production load (i.e., the production power load in the above embodiment) to obtain electricity consumption data in the short and long term (specifically, it can include electricity consumption data for typical working days and special working days).

[0118] Step S504: Determine whether the production load has reached the required value (typical workday / special workday); if yes, proceed to step S505; if no, return to proceed to step S503 or step S501.

[0119] Step S505: Based on LSTM (Long Short-Term Memory Neural Network), construct an energy consumption model for peak electricity consumption energy storage power station, and use the model to predict the energy consumption during future peak electricity consumption periods to obtain peak-period energy consumption data (i.e., peak-period electricity consumption in the above embodiment).

[0120] Step S506: Based on the GAN adversarial neural network, DGMR (Deep Production Model for Rainfall Prediction) is used to construct a distributed photovoltaic power output prediction model, and this model is used to predict future photovoltaic power output to obtain photovoltaic power output data in the short and long term (i.e., peak power generation in the above embodiment); specifically including power output on sunny days and power output on rainy days.

[0121] Step S507: Determine whether the photovoltaic output can meet the energy consumption during future peak electricity demand; if not, proceed to step S508. If yes, proceed to step S509.

[0122] Step S508: Using an intelligent optimization algorithm, under the condition that the photovoltaic output meets the future peak electricity demand, the nearest charging time is found (e.g., the process from step S410 to step S411 in the above embodiment), allowing only charging and disallowing discharging. Step S510 can be executed after this step.

[0123] Step S509 involves using intelligent optimization algorithms to maximize the response to user needs (economical, efficient, and green) while ensuring that photovoltaic output meets future peak electricity demand. For example, a photovoltaic energy storage power station can be configured to operate according to a preset peak-shaving and valley-filling strategy. Step S510 can be executed after this step.

[0124] Step S510: Control the operation of the energy storage power station according to the corresponding strategy.

[0125] Because the demand control method of the photovoltaic energy storage power station in this embodiment can effectively predict whether the demand of the power supply target (such as enterprise users) will exceed the demand standard by setting the production demand threshold and predicting the insufficient power supply of photovoltaic modules, it can store electrical energy using energy storage devices before the demand standard is exceeded. Furthermore, it can discharge the insufficient power supply during the peak period of the statistical period when the power supply may exceed the demand standard in the future preset prediction period, thus effectively limiting the occurrence of the power supply target drawing power from the grid during peak periods after the power consumption exceeds the demand standard. Therefore, the demand control method of the photovoltaic energy storage power station in this embodiment can effectively reduce the electricity cost of the power supply target and ensure the user experience. Furthermore, step S101 of the above embodiments may include step S501 of this embodiment, step S102 of the above embodiments may include step S503 of this embodiment, step S103 of the above embodiments may include step S504 of this embodiment, step S104 of the above embodiments may include steps S505 to S507 of this embodiment, step S105 of the above embodiments may include step S508 of this embodiment, and the steps of configuring the photovoltaic energy storage power station to operate according to the preset peak shaving and valley filling strategy in the above embodiments may include step S509 of this embodiment. Moreover, each step in this embodiment can correspondingly achieve the beneficial technical effects of the corresponding steps in the foregoing embodiments, which will not be repeated here.

[0126] In this embodiment, typical workdays / special workdays can be determined based on the magnitude of electricity load. For example, if a company implements a two-day weekend, its electricity load will follow a pattern, cycling weekly, which is called a typical workday. However, in case of emergencies requiring overtime work on Saturdays and Sundays, there will also be electricity load on Saturdays and Sundays, which are called special workdays. Special workdays may also have a cycle, such as working overtime every other week. For emergencies, users can set them separately and manually input the demand value. Furthermore, since LSTM models are naturally suitable for capturing long-term dependencies and periodic patterns in sequential data, they have higher prediction accuracy for regular values. Therefore, distinguishing production load into typical workdays / special workdays can more accurately estimate production load.

[0127] In this embodiment, demand charge refers to the electricity fee charged to enterprises for exceeding the standard set by the power grid company. For example, if the power grid company issues a demand standard of 150 kWh to an enterprise, then when the enterprise's electricity consumption exceeds the standard, the power grid company will charge an additional fee for the excess electricity consumption in addition to the electricity fee charged according to the amount of electricity consumed, in order to encourage enterprises to use electricity as needed and ensure the stability of the power grid.

[0128] Therefore, the process in steps S503 to S508 can be understood as follows: For example, LSTM predicts that the total production load 15 days later will be 200 kWh, including 150 kWh of typical weekday load and 50 kWh of special weekday load. Assuming the energy storage capacity is 20 kWh and the set demand value is 180 kWh, the production load exceeds the demand by 20 kWh. At this time, based on the photovoltaic output, if the next 15 days are all sunny, the system will still perform peak shaving and valley filling as usual to meet the grid connection profit of enterprises. If the first 10 days are sunny, and the next 11 days are cloudy, then an intelligent algorithm can be used to calculate the optimal time for the power grid to be deactivated (i.e., after 10 days, no peak shaving or valley filling will be implemented, and all stored electricity will be used to address the capacity difference after 5 days, thus meeting the company's "excessive electricity demand" and avoiding drawing electricity from the grid during peak hours). More specifically, if the first 10 days are sunny, and the next 11 to 15 days are cloudy, then the energy storage device needs to be fully charged before the 11th day. Then, using an intelligent optimization algorithm or the electricity revenue charging time model described in the above embodiments, a preset algorithm can be used to find the optimal time to utilize the market. The optimal time for the power grid to charge the energy storage device and the optimal time for using photovoltaic modules to charge the energy storage device are as follows. For example, the optimal time for using photovoltaic modules to charge the energy storage device could be 10:35 AM on the 10th day, and the optimal time for using the municipal power grid to charge the energy storage device could be 1:00 PM or 9:00 PM on the 10th day. Therefore, the photovoltaic modules can be configured to start charging the energy storage device at 10:35 AM on the 10th day, and the municipal power grid can be used to charge the energy storage device at 1:00 PM or 9:00 PM on the 10th day. The device can then start discharging at 8:00 AM on the 11th day as planned.

[0129] In this embodiment, steps S509, S510, and / or the conventional operation strategy of the photovoltaic energy storage power station may specifically be: for example, charging the energy storage device using the municipal power grid at 8:00 PM on the first day, and configuring the energy storage device to discharge at 8:00 AM on the second day; charging the energy storage device using photovoltaic modules at 10:00 AM on the first day, and configuring the energy storage device to discharge at 4:00 PM on the same day.

[0130] In the aforementioned embodiments, the demand control method for photovoltaic energy storage power stations can be operated and applied to photovoltaic energy storage power stations by an EMS (Energy Management System).

[0131] The following is combined with Figure 6 The computer program product of this embodiment will be described in detail below. Figure 6 This is a schematic structural block diagram of a computer program product according to an embodiment of the present invention. (Refer to...) Figure 6 In this embodiment, the computer program product 10 includes a computer program 11, which, when executed by a processor, implements the demand control method of the photovoltaic energy storage power station described above.

[0132] The computer program product 10 of this embodiment can implement the demand control method for the photovoltaic energy storage power station described above. Therefore, the computer program product 10 of this embodiment also possesses the beneficial technical effects that the demand control method for the photovoltaic energy storage power station described above can achieve.

[0133] The following is combined with Figure 7 The computer-readable storage medium of this embodiment will be described in detail below. Figure 7 This is a schematic structural block diagram of a computer-readable storage medium according to an embodiment of the present invention, with reference to... Figure 7 In this embodiment, a computer program 11 is stored on the computer-readable storage medium 20. When the computer program 11 is executed by the processor, it implements the demand control method of the photovoltaic energy storage power station described in the above embodiment.

[0134] The computer-readable storage medium 20 of this embodiment can implement the demand control method for the photovoltaic energy storage power station described above. Therefore, the computer-readable storage medium 20 of this embodiment also possesses the beneficial technical effects that the demand control method for the photovoltaic energy storage power station described above can achieve.

[0135] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of instructions for implementing logical functions, and can be specifically implemented in any computer-readable storage medium 20 for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from an instruction execution system, apparatus or device).

[0136] For the purposes of this embodiment, the computer-readable storage medium 20 can be any means capable of containing, storing, communicating, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, the computer-readable storage medium 20 can even be paper or other suitable media on which a program can be printed, since a program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0137] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system.

[0138] The following is combined with Figure 8 The computer device of this embodiment will be described in detail below. Figure 8 This is a structural block diagram of a computer device according to an embodiment of the present invention, with reference to... Figure 8 In this embodiment, the computer device 30 includes a memory 31, a processor 32, and a computer program 11 stored in the memory 31. When the processor 32 executes the computer program 11, it implements the demand control method of the photovoltaic energy storage power station described above.

[0139] The computer device 30 of this embodiment can implement the demand control method for the photovoltaic energy storage power station described in the above embodiment. Therefore, the computer device 30 of this embodiment also possesses the beneficial technical effects that can be achieved by the demand control method for the photovoltaic energy storage power station described above.

[0140] Computer device 30 can be, for example, a server, desktop computer, laptop computer, tablet computer, or smartphone. In some examples, computer device 30 can be a cloud computing node. Computer device 30 can be described in the general context of computer system instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., that perform specific tasks or implement specific abstract data types. Computer device 30 can be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can reside on local or remote computing system storage media, including storage devices.

[0141] Computer device 30 may include a processor 32 adapted to execute stored instructions and a memory 31 that provides temporary storage space for the operation of instructions during operation. The processor 32 may be a single-core processor, a multi-core processor, a computing cluster, or any other configuration. The memory 31 may include random access memory (RAM), read-only memory, flash memory, or any other suitable storage system.

[0142] The processor 32 can be connected via a system interconnect (e.g., PCI, PCI-Express, etc.) to an I / O interface (input / output interface) suitable for connecting the computer device 30 to one or more I / O devices (input / output devices). I / O devices may include, for example, a keyboard and indicating devices, where indicating devices may include a touchpad or touchscreen, etc. I / O devices may be built into the computer device 30 or may be external devices connected to the computing device.

[0143] The processor 32 may also be linked via a system interconnect to a display interface suitable for connecting the computer device 30 to a display device. The display device may include a display screen that is a built-in component of the computer device 30. The display device may also include an external computer monitor, television, or projector connected to the computer device 30. Furthermore, a network interface controller (NIC) may be adapted to connect the computer device 30 to a network via a system interconnect. In some embodiments, the NIC may use any suitable interface or protocol (such as an Internet Minicomputer System Interface) to transmit data. The network may be a cellular network, a radio network, a wide area network (WAN), a local area network (LAN), or the Internet, etc. Remote devices may connect to the computing device via the network.

[0144] Therefore, those skilled in the art should recognize that although numerous exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications conforming to the principles of the present invention can be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Thus, the scope of the present invention should be understood and construed as covering all such other variations or modifications.

Claims

1. A demand control method for a photovoltaic energy storage power station, wherein the photovoltaic energy storage power station includes photovoltaic modules and energy storage devices; and, The demand control method includes: Obtain historical power supply data of the photovoltaic energy storage power station; Based on the historical power supply data, the production power load of the photovoltaic energy storage power station is predicted within a preset prediction period. Determine whether the power load exceeds a preset production demand threshold; If so, predict whether the photovoltaic module will experience power shortages during peak electricity consumption periods in one or more electricity consumption statistical cycles during the preset prediction period; If present, a charging time is selected before the power usage statistics period with insufficient power supply, and the energy storage device is charged during the charging time. The energy storage device is also configured to discharge during the peak power consumption period of the power usage statistics period with insufficient power supply.

2. The demand control method for a photovoltaic energy storage power station according to claim 1, wherein, The charging time includes both photovoltaic charging time and mains charging time; and... The step of selecting a charging time before the energy usage statistics period in which there is insufficient power supply, and charging the energy storage device during the charging time, includes: The photovoltaic charging time and the mains power charging time are determined, and the energy storage device is charged using the photovoltaic module and the mains power grid respectively during the photovoltaic charging time and the mains power charging time.

3. The demand control method for a photovoltaic energy storage power station according to claim 2, wherein, The step of determining the photovoltaic charging time and the mains charging time includes: Based on the electricity revenue charging time model, a preset algorithm is used to solve for the time points when the photovoltaic power generation starts charging and the mains power generation starts charging when the electricity revenue is maximized. The electricity revenue charging time model is a functional relationship between the electricity revenue and the photovoltaic power generation start charging time and the mains power generation start charging time. The time points at which the photovoltaic power starts charging and the time points at which the mains power starts charging, obtained from the solution, are respectively determined as the photovoltaic charging time and the mains power charging time.

4. The demand control method for a photovoltaic energy storage power station according to claim 3, wherein, The electricity revenue charging time model is as follows: M = C1(t1) - C2(t2) - C3(t3), Where M represents the electricity revenue; C1 is the discharge capacity of the energy storage device, t1 is the discharge time of the energy storage device, and C1(t1)=P1t1m1, where P1 is the discharge power of the energy storage device and m1 is the discharge electricity price of the energy storage device. C2 is the charging capacity using the photovoltaic module, t2 is the time when the photovoltaic module starts charging, and C2(t2) = P2t2m2, where P2 is the charging power using the photovoltaic module, m2 is the charging electricity price using the photovoltaic module, and... T is the temperature of the photovoltaic panel in the photovoltaic module, G max T represents the maximum irradiance of the photovoltaic panel. noct The battery operating temperature of the energy storage device, t rise For sunrise time, t set For sunset time, t noon For noon, a, b, and k are correction coefficients; C3 represents the charging capacity using the municipal power grid, t3 represents the start time of charging using the municipal power grid, and C3(t3) = P3t3m3, where P3 is the charging power of the energy storage device using the municipal power grid, and m3 is the charging electricity price of the energy storage device using the municipal power grid; furthermore, The preset algorithm is the ant colony algorithm, with the following constraints: 0≤C1≤C, 0≤C2≤C, t1 earlier than t3, and t3 earlier than t2, where C is the energy storage capacity of the energy storage device.

5. The demand control method for a photovoltaic energy storage power station according to claim 1, wherein, During the step of charging the energy storage device within the charging time, and during the time between charging and discharging the energy storage device, the discharge of the energy storage device is limited.

6. The demand control method for a photovoltaic energy storage power station according to claim 1, wherein, The production demand threshold is determined based on the demand standards issued by the public grid dispatching department to the power supply targets of the photovoltaic energy storage power station.

7. The demand control method for a photovoltaic energy storage power station according to claim 1, wherein, The historical power supply data includes the historical power supply volume for a preset historical statistical period; and, The step of predicting the power load of the photovoltaic energy storage power station within a preset prediction period based on the historical power supply data includes: The historical power supply is classified according to the power supply volume of the preset historical statistical period to obtain the power supply volume of the standard working period and the power supply volume of the non-standard working period. The production power load is predicted using an LSTM model based on the power supply during the standard working cycle and the power supply during the non-standard working cycle.

8. The demand control method for a photovoltaic energy storage power station according to claim 1, wherein, The historical power supply data includes the peak electricity consumption during a preset historical statistical period; and, The step of predicting whether there will be a power shortage during peak electricity consumption periods of one or more electricity consumption statistical periods during the preset prediction period includes: Predict the peak power generation of the photovoltaic module within the preset prediction period; Based on the historical peak electricity consumption, the photovoltaic energy storage power station predicts the peak electricity consumption of the power supply objects during the preset prediction period. Determine whether the peak period power generation is greater than or equal to the peak period power consumption; If not, it is determined that the photovoltaic module experiences insufficient power supply during peak electricity consumption periods of one or more electricity consumption statistical cycles during the preset prediction period; If so, it is determined that the photovoltaic module does not experience power shortages during peak electricity consumption periods in one or more electricity usage statistical cycles during the preset prediction period.

9. The demand control method for a photovoltaic energy storage power station according to claim 8, wherein, The step of predicting the peak power generation of the photovoltaic module within the preset prediction period includes: The weather data within the preset forecast period is predicted using a preset weather forecast model, wherein the weather forecast model includes at least one of the DGMR model and the WRF model. Based on the weather data, determine the output power of the corresponding photovoltaic module during the peak electricity consumption period within the preset forecast period; The peak-period power generation is calculated based on the output power and the predicted peak sunshine duration of the photovoltaic module, where the predicted peak sunshine duration is the sunshine duration of the photovoltaic module during the peak electricity consumption period within the preset prediction cycle; and... The step of predicting the peak electricity consumption of the photovoltaic energy storage power station's power supply targets during the preset prediction period based on the historical peak electricity consumption includes: Based on the historical peak electricity consumption, the peak electricity consumption is predicted using an LSTM model.

10. A computer program product comprising a computer program that, when executed by a processor, implements the demand control method for a photovoltaic energy storage power station as described in any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the demand control method for a photovoltaic energy storage power station according to any one of claims 1 to 9.

12. A computer device comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the demand control method for a photovoltaic energy storage power station according to any one of claims 1 to 9.

Images