Electricity utilization scheduling strategy generation system and method of photovoltaic energy storage equipment

Abstract

The invention discloses a power utilization scheduling strategy generation system and method for photovoltaic energy storage equipment, and relates to the technical field of electronic power, and the system comprises an electricity price obtaining module, a station information collection module, a power generation prediction module, a load prediction module, a charging and discharging constraint module and a strategy generation module. The electricity price acquisition module acquires electricity price information; the site information acquisition module acquires equipment real-time information of photovoltaic energy storage equipment; the power generation prediction module predicts power generation information; the load prediction module predicts load information; the charging and discharging constraint module generates a charging and discharging constraint condition according to the configured peak clipping information, the charging and discharging information and the power utilization strategy preference information; and the strategy generation module determines an optimal power utilization scheduling strategy according to the electricity price information, the equipment real-time information, the power generation prediction information, the load prediction information and the charging and discharging constraint conditions. According to the invention, the real-time performance and accuracy of the data required when the power utilization scheduling strategy is generated can be ensured, and the accuracy of the power utilization scheduling strategy is further ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic power, and particularly to a system and method for generating an electricity consumption scheduling strategy for a photovoltaic energy storage device. Background Art

[0002] With the continuous improvement of people's concept of green environmental protection, the cost per kilowatt-hour of photovoltaic energy storage devices has been continuously decreasing, and photovoltaic energy storage devices are accepted and purchased by more people. In different regions and at different times, electricity prices are often different, and there are relatively large differences in electricity prices every day, every hour, or even every 5 minutes. Therefore, by scheduling the photovoltaic power generation amount, the source of load power, and the battery charging and discharging time, the price difference can be effectively utilized to adjust the time period and amount of buying and selling electricity, so as to obtain benefits.

[0003] The existing electricity consumption scheduling methods usually first obtain electricity prices, predict photovoltaic power generation, and predict loads, and then optimize the electricity consumption strategies for each time period based on the TOU mode (time-of-use electricity mode), or perform power limitations for each time period based on the energy flow. Since the generation of electricity consumption scheduling strategies involves the acquisition, generation, and interaction of multiple parties' data, and has high requirements for the accuracy and real-time performance of the data, the existing methods cannot ensure the real-time performance and accuracy of each data, and the existing methods do not consider the electricity consumption scheduling requirements of different users and different scenarios, resulting in a low accuracy of the finally obtained electricity consumption scheduling strategy, which cannot meet the user's electricity consumption expectations and achieve the maximum benefit. Summary of the Invention

[0004] An embodiment of the present invention provides a system for generating an electricity consumption scheduling strategy for a photovoltaic energy storage device, which is used to realize the generation of an electricity consumption scheduling strategy throughout the whole process of data acquisition, prediction, and strategy generation, and generate an electricity consumption scheduling strategy based on the electricity consumption scheduling requirements of different users and different scenarios, improve the real-time performance and accuracy of the data required for generating the electricity consumption scheduling strategy, and then ensure the accuracy of the electricity consumption scheduling strategy, meet the user's electricity consumption expectations and achieve the maximum benefit; the system for generating an electricity consumption scheduling strategy for a photovoltaic energy storage device includes: an electricity price acquisition module, a site information collection module, a power generation prediction module, a load prediction module, a charge and discharge constraint module, and a strategy generation module; the electricity price acquisition module, the site information collection module, the power generation prediction module, the load prediction module, the charge and discharge constraint module are connected to the strategy generation module; Among them, the electricity price acquisition module is used to acquire electricity price information; The site information collection module is used to collect the real-time information of the photovoltaic energy storage device; the real-time information of the device includes at least one of the real-time SOC value, real-time power generation information, real-time load information, and real-time temperature of the photovoltaic energy storage device; The power generation prediction module is used to predict the power generation prediction information of the photovoltaic energy storage device by using a power generation prediction model; The load prediction module is used to predict the load prediction information of the environment where the photovoltaic energy storage device is located by using a load prediction model; The charge-discharge constraint module is used to configure peak shaving information, charge-discharge information, and power consumption strategy preference information, and generate charge-discharge constraint conditions according to the peak shaving information, the charge-discharge information, and the power consumption strategy preference information; The strategy generation module is used to determine an optimal power consumption scheduling strategy according to the electricity price information, the device real-time information, the power generation prediction information, the load prediction information, and the charge-discharge constraint conditions.

[0005] In one embodiment, the electricity price acquisition module includes a first electricity price unit, a second electricity price unit, a third electricity price unit, a fourth electricity price unit, and an electricity price output unit: Among them, the first electricity price unit is used to obtain wholesale electricity price information from each power grid system and generate user electricity price information according to the wholesale electricity price information; The second electricity price unit is used to obtain retailer electricity price information from each retailer system; The third electricity price unit is used to collect the electricity price information configured by the user; The fourth electricity price unit is used to obtain first preferential electricity price information from each power grid system and / or second preferential electricity price information from each retailer system, and generate designated user preferential electricity price information according to the first preferential electricity price information and / or the second preferential electricity price information; The electricity price output unit is used to output the final user electricity price information according to at least one of the user electricity price information generated by the first electricity price unit, the retailer electricity price information obtained by the second electricity price unit, the electricity price information configured by the user collected by the third electricity price unit, and the designated user preferential electricity price information generated by the fourth electricity price unit.

[0006] In one embodiment, the first electricity price unit generates user electricity price information according to the wholesale electricity price information, specifically including: calculating the buy electricity price in the user electricity price information according to the buy electricity price calculation algorithm, in accordance with the preset buy electricity ratio information and buy electricity tax information, and combining the wholesale electricity price information; calculating the sell electricity price in the user electricity price information according to the sell electricity price calculation algorithm, in accordance with the preset sell electricity ratio information and sell electricity tax information, and combining the wholesale electricity price information.

[0007] In one embodiment, the power consumption scheduling strategy generation system of the photovoltaic energy storage device further includes: a meteorological actual measurement collector and a meteorological prediction collector; the meteorological actual measurement collector and the meteorological prediction collector are respectively connected to the power generation prediction module and the load prediction module; Among them, the meteorological actual measurement collector is used to collect the meteorological actual measurement data of the photovoltaic energy storage device; The meteorological prediction collector is used to collect the meteorological forecast data of the photovoltaic energy storage device.

[0008] In one embodiment, the power generation prediction module includes an irradiance optimizer, a first feature extraction unit, a power generation prediction model group, and a first result output unit; Among them, the irradiance optimizer is used to optimize the meteorological forecast data for a future specified time period collected by the meteorological prediction collector by using the historical meteorological actual measurement data collected by the meteorological actual measurement collector and the historical meteorological forecast data collected by the meteorological prediction collector, so as to obtain optimized meteorological forecast data; The first feature extraction unit is used to extract the first feature data of the optimized meteorological forecast data; The power generation prediction model group is used to predict the power generation prediction information of the photovoltaic energy storage device in a future specified time period according to the first feature data; The first result output unit is used to process the power generation prediction information of the photovoltaic energy storage device in a future specified time period predicted by the power generation prediction model group, and generate the final power generation prediction information of the photovoltaic energy storage device.

[0009] In one embodiment, the power generation prediction model group includes a plurality of power generation prediction models with different structures, and the structure of each power generation prediction model is any one of a deep learning model, a machine learning model, and a large model; Each power generation prediction model outputs the power generation prediction information of the photovoltaic energy storage device in a future specified time period predicted by itself according to the first feature data.

[0010] In one embodiment, the load prediction module includes a second feature extraction unit, a load prediction model group, and a second result output unit; Among them, the second feature extraction unit is used to extract the second feature data of the meteorological forecast data for a future specified time period collected by the meteorological prediction collector; The load prediction model group is used to predict the load prediction information of the environment where the photovoltaic energy storage device is located in a future specified time period according to the second feature data; The second result output unit is used to process the load prediction information of the environment where the photovoltaic energy storage device is located in a future specified time period predicted by the load prediction model group, and generate the final load prediction information of the environment where the photovoltaic energy storage device is located.

[0011] In one embodiment, the load prediction model group includes a plurality of load prediction models with different structures, and the structure of each load prediction model is any one of a deep learning model, a machine learning model, and a large model; Each load prediction model outputs load prediction information for the environment where the photovoltaic energy storage device is located in a future specified time period according to the second feature data.

[0012] In one embodiment, the charge-discharge constraint module includes: a peak shaving information configuration unit, a charge-discharge configuration unit, a power consumption strategy preference configuration unit, and a constraint condition generation unit; Among them, the peak shaving information configuration unit is used to configure peak shaving information, and the peak shaving information includes the peak power and the stored electricity SOC value for each date and each time period; The charge-discharge configuration unit is used to configure charge-discharge information, and the charge-discharge information includes the minimum charging SOC and the maximum discharging SOC for each specified time period; The power consumption strategy preference configuration unit is used to configure power consumption strategy preference information, and the power consumption strategy preference information includes charge-discharge modes with various degrees of aggressiveness; The constraint condition generation unit is used to generate charging constraint conditions according to the peak shaving information, the charge-discharge information, and the power consumption strategy preference information.

[0013] In one embodiment, the strategy generation module includes a strategy generation model group, a simulation unit, and a screening unit; Among them, the strategy generation model group is used to generate multiple power consumption scheduling strategies according to the electricity price information, the device real-time information, the power generation prediction information, the load prediction information, and the charge-discharge constraint conditions; The simulation unit is used to simulate each power consumption scheduling strategy to obtain a simulation result; The screening unit is used to screen the optimal power consumption scheduling strategy according to the simulation results of each power consumption scheduling strategy.

[0014] In one embodiment, the strategy generation model group includes multiple strategy generation models with different structures, and the structure of each strategy generation model is a reinforcement learning model or an operations research optimization model; Each strategy generation model generates a power consumption scheduling strategy according to the electricity price information, the device real-time information, the power generation prediction information, the load prediction information, and the charge-discharge constraint conditions.

[0015] An embodiment of the present invention further provides a method for generating a power consumption scheduling strategy for a photovoltaic energy storage device, which is used to realize the generation of a power consumption scheduling strategy throughout the whole process of data acquisition, prediction, and strategy generation, and generate a power consumption scheduling strategy based on the power consumption scheduling requirements of different users and different scenarios, improve the real-time performance and accuracy of the data required for generating the power consumption scheduling strategy, and then ensure the accuracy of the power consumption scheduling strategy, meet the user's power consumption expectations, and achieve the maximization of benefits; this method is applied to the power consumption scheduling strategy generation system of the above-mentioned photovoltaic energy storage device, and this method includes: The electricity price acquisition module acquires electricity price information; The site information collection module collects the real-time device information of the photovoltaic energy storage device; the real-time device information includes at least one of the real-time SOC value, real-time power generation information, real-time load information, and real-time temperature of the photovoltaic energy storage device; The power generation prediction module uses a power generation prediction model to predict the power generation prediction information of the photovoltaic energy storage device; The load prediction module uses a load prediction model to predict the load prediction information of the environment where the photovoltaic energy storage device is located; The charge and discharge constraint module configures peak shaving information, charge and discharge information, and power consumption strategy preference information, and generates charge and discharge constraint conditions according to the peak shaving information, the charge and discharge information, and the power consumption strategy preference information; The strategy generation module determines an optimal power consumption scheduling strategy according to the electricity price information, the real-time device information, the power generation prediction information, the load prediction information, and the charge and discharge constraint conditions.

[0016] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for generating a power consumption scheduling strategy for a photovoltaic energy storage device is implemented.

[0017] An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for generating a power consumption scheduling strategy for a photovoltaic energy storage device is implemented.

[0018] An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the above-mentioned method for generating a power consumption scheduling strategy for a photovoltaic energy storage device is implemented.

[0019] The power consumption scheduling strategy generation system for a photovoltaic energy storage device provided by an embodiment of the present invention includes: a power price acquisition module, a site information collection module, a power generation prediction module, a load prediction module, a charge and discharge constraint module, and a strategy generation module; the power price acquisition module, the site information collection module, the power generation prediction module, the load prediction module, and the charge and discharge constraint module are connected to the strategy generation module. In the embodiment of the present invention, the power price information can be obtained in real time through the power price acquisition module, the real-time device information of the photovoltaic energy storage device is collected through the site information collection module, the power generation information of the photovoltaic energy storage device is predicted through the power generation prediction module, the load information of the photovoltaic energy storage device is predicted through the load prediction module, the user demand configuration information of the user is obtained through the charge and discharge constraint module and charge and discharge constraint conditions are generated, and the strategy generation module determines the optimal power consumption scheduling strategy based on the above data. In this way, the power consumption scheduling strategy generation system for the photovoltaic energy storage device in the embodiment of the present invention supports the generation of power consumption scheduling strategies throughout the entire process from data acquisition, prediction, and strategy generation, and through the charge and discharge constraint module, the generation of power consumption scheduling strategies can be realized based on the power consumption scheduling requirements of different users and different scenarios, which can ensure the real-time and accuracy of the data required for generating power consumption scheduling strategies, and further ensure the accuracy of the power consumption scheduling strategy, meet the user's power consumption expectations, and maximize the benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0021] In the drawings: Figure 1 is a structural diagram of a power consumption scheduling strategy generation system for a photovoltaic energy storage device in an embodiment of the present invention; Figure 2 is a structural diagram of a power price acquisition module in an embodiment of the present invention; Figure 3 is a structural diagram of a power generation prediction module in an embodiment of the present invention; Figure 4 is a structural diagram of a load prediction module in an embodiment of the present invention; Figure 5 is a structural diagram of a charge and discharge constraint module in an embodiment of the present invention; Figure 6 is a structural diagram of a strategy generation module in an embodiment of the present invention; Figure 7 is a flowchart of a power consumption scheduling strategy generation method for a photovoltaic energy storage device in an embodiment of the present invention. Detailed implementation manners

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer and more understandable, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Herein, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but not to limit the present invention.

[0023] In the description of this specification, the terms "include", "comprise", "have", "contain", etc. are all open-ended terms, that is, they are intended to include but not limited to. The description with reference to terms such as "one embodiment", "one specific embodiment", "some embodiments", "for example", etc. means that the specific features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. The step sequences involved in each embodiment are used to schematically illustrate the implementation of the present application, and the step sequences are not limited and can be adjusted appropriately as needed.

[0024] After research, it is found that the existing power consumption scheduling methods for photovoltaic energy storage devices usually first obtain electricity prices, predict photovoltaic power generation, and predict loads, and then optimize the power consumption strategies for each time period based on the TOU mode (time-of-use power consumption mode), or perform power limit for each time period based on the energy flow. Since the generation process of the power consumption scheduling strategy needs to involve the acquisition, generation, and interaction of multiple parties' data, and has high requirements for the accuracy and real-time performance of the data, the existing power consumption scheduling strategy generation methods cannot ensure the real-time performance and accuracy of each data, resulting in a low accuracy of the finally obtained power consumption scheduling strategy.

[0025] Moreover, neither of these two power consumption scheduling methods takes into account the power consumption scheduling requirements in different users and different scenarios. For example, when optimizing the power consumption strategies for each time period based on the TOU mode, algorithms such as reinforcement learning and operations research optimization are mostly used to obtain better strategy combinations, but this method cannot control the charge and discharge power within the planned range, resulting in overcharging or over-discharging; when performing power limit for each time period based on the energy flow, the energy flow is optimized using the method of reinforcement learning or operations research optimization, which has extremely high requirements for the accuracy of photovoltaic power generation and load prediction, has a high tolerance for errors, and is prone to error accumulation. At the same time, the special settings of some users, such as peak shaving, backup power, charging pile scenarios, etc. will affect the priority of the energy flow in their scenarios, resulting in unexpected control results.

[0026] Based on this, an embodiment of the present invention provides a system for generating an electricity consumption scheduling strategy for a photovoltaic energy storage device. This system for generating an electricity consumption scheduling strategy for a photovoltaic energy storage device can obtain data in real time and accurately throughout the entire process of data acquisition, prediction, and strategy generation. Moreover, it can generate an electricity consumption scheduling strategy based on the electricity consumption scheduling requirements of different users and different scenarios, improving the accuracy of electricity consumption scheduling and achieving maximum benefits.

[0027] Figure 1 It is a structural diagram of a system for generating an electricity consumption scheduling strategy for a photovoltaic energy storage device provided by an embodiment of the present invention. As Figure 1 shown, this system for generating an electricity consumption scheduling strategy for a photovoltaic energy storage device includes: an electricity price acquisition module 1, a site information collection module 2, a power generation prediction module 3, a load prediction module 4, a charge and discharge constraint module 5, and a strategy generation module 6; the electricity price acquisition module 1, the site information collection module 2, the power generation prediction module 3, the load prediction module 4, and the charge and discharge constraint module 5 are connected to the strategy generation module 6; Among them, the electricity price acquisition module 1 is used to obtain electricity price information; The site information collection module 2 is used to collect the real-time device information of the photovoltaic energy storage device; the real-time device information includes at least one of the real-time SOC value, real-time power generation information, real-time load information, and real-time temperature of the photovoltaic energy storage device; among them, the real-time load information of the photovoltaic energy storage device can be the real-time load information of the environment where the photovoltaic energy storage device is located, that is, the real-time electricity consumption information of the household or industrial and commercial park where the photovoltaic energy storage device is installed; The power generation prediction module 3 is used to predict the power generation prediction information of the photovoltaic energy storage device by using a power generation prediction model; The load prediction module 4 is used to predict the load prediction information of the environment where the photovoltaic energy storage device is located by using a load prediction model; among them, the environment where the photovoltaic energy storage device is located can be the household or industrial and commercial park where the photovoltaic energy storage device is installed.

[0028] The charge and discharge constraint module 5 is used to configure peak shaving information, charge and discharge information, and electricity consumption strategy preference information, and generate charge and discharge constraint conditions according to the peak shaving information, charge and discharge information, and electricity consumption strategy preference information; The strategy generation module 6 is used to determine the optimal electricity consumption scheduling strategy according to the electricity price information, device real-time information, power generation prediction information, load prediction information, and charge and discharge constraint conditions.

[0029] The power consumption scheduling strategy generation system of the photovoltaic energy storage device provided by the embodiment of the present invention includes: a power price acquisition module, a site information acquisition module, a power generation prediction module, a load prediction module, a charge and discharge constraint module, and a strategy generation module; the power price acquisition module, the site information acquisition module, the power generation prediction module, the load prediction module, the charge and discharge constraint module are connected to the strategy generation module. In the embodiment of the present invention, the power price information can be obtained in real time through the power price acquisition module, the real-time device information of the photovoltaic energy storage device is collected through the site information acquisition module, the power generation information of the photovoltaic energy storage device is predicted through the power generation prediction module, the load information of the photovoltaic energy storage device is predicted through the load prediction module, the user demand configuration information of the user is obtained through the charge and discharge constraint module and the charge and discharge constraint conditions are generated, and the strategy generation module determines the optimal power consumption scheduling strategy based on the above data. In this way, the power consumption scheduling strategy generation system of the photovoltaic energy storage device in the embodiment of the present invention supports the generation of the power consumption scheduling strategy throughout the whole process from data acquisition, prediction to strategy generation, and through the charge and discharge constraint module, the generation of the power consumption scheduling strategy can be realized based on the power consumption scheduling requirements under different users and different scenarios, which can ensure the real-time and accuracy of the data required for the generation of the power consumption scheduling strategy, and then ensure the accuracy of the power consumption scheduling strategy, meet the user's power consumption expectations and realize the maximization of benefits.

[0030] In the field of photovoltaic energy storage power generation, there are many types of power prices, and the power prices are also different, including various retailer power prices, power prices of the power grid system, etc. Therefore, in order to provide accurate power consumption scheduling strategies for users, it is necessary to ensure the real-time and accuracy of the power price information obtained by the power price acquisition module; based on this, the embodiment of the present invention provides a solution for obtaining power prices in multiple dimensions.

[0031] Figure 2 It is the structural diagram of the power price acquisition module provided by the embodiment of the present invention. As Figure 2 shown, the above-mentioned power price acquisition module 1 may specifically include: a first power price unit 11, a second power price unit 12, a third power price unit 13, a fourth power price unit 14, and a power price output unit 15: Among them, the first power price unit 11 is used to obtain the wholesale power price information from each power grid system and generate user power price information according to the wholesale power price information; The second power price unit 12 is used to obtain the retailer power price information from each retailer system; The third power price unit 13 is used to collect the power price information configured by the user; The fourth power price unit 14 is used to obtain the first preferential power price information from each power grid system and / or the second preferential power price information from each retailer system, and generate the designated user preferential power price information according to the first preferential power price information and / or the second preferential power price information; The electricity price output unit 15 is used to output the final user electricity price information based on at least one of the user electricity price information generated by the first electricity price unit, the retailer electricity price information obtained by the second electricity price unit, the electricity price information configured by the user collected by the third electricity price unit, and the specified user preferential electricity price information generated by the fourth electricity price unit.

[0032] In specific implementation, the above-mentioned first electricity price unit 11 can be docked with each power grid system to obtain the wholesale electricity price information from each power grid system in real time or regularly, and generate user electricity price information based on the wholesale electricity price information. Specifically, the wholesale electricity price information is the clearing wholesale price announced by each power grid system; the user electricity price information can include the electricity purchase price information and the electricity selling price information. Among them, the electricity purchase price information refers to the price when the user purchases electricity from the power grid system, and the electricity selling price information refers to the price when the user sells the electricity obtained from photovoltaic power generation to the power grid system. In specific applications, the user electricity price information can be formed by weighting the wholesale electricity price in a proportional or fixed value manner.

[0033] In one embodiment, the above-mentioned first electricity price unit 11 generates user electricity price information based on the wholesale electricity price information. Specifically, it can include: calculating the electricity purchase price in the user electricity price information according to the electricity purchase price calculation algorithm, in accordance with the preset electricity purchase ratio information and electricity purchase tax information, and combining the wholesale electricity price information; calculating the electricity selling price in the user electricity price information according to the electricity selling price calculation algorithm, in accordance with the preset electricity selling ratio information and electricity selling tax information, and combining the wholesale electricity price information.

[0034] In specific implementation, the above-mentioned electricity purchase ratio information, electricity purchase tax information, electricity selling ratio information, and electricity selling tax information can be filled in by the user through the user interface provided by the first electricity price unit, or can be automatically generated by the first electricity price unit according to information such as the region where the user is located and the electricity buying and selling rules in that region. There is no limitation here.

[0035] In specific implementation, according to the electricity purchase price calculation algorithm, to calculate the electricity purchase price, it can be achieved through the following formula: Electricity purchase price = (1 + input item 1) × wholesale electricity price + input item 2; Among them, input item 1 is the electricity purchase ratio information, input item 2 is the electricity purchase tax information, and the electricity purchase tax information can be a fixed value.

[0036] According to the electricity selling price calculation algorithm, to calculate the electricity selling price, it can be achieved through the following formula: Electricity selling price = (1 + input item 3) × wholesale electricity price + input item 4; Among them, input item 3 is the electricity selling ratio information, input item 4 is the electricity selling tax information, and the electricity selling tax information can be a fixed value.

[0037] In specific implementation, the above-mentioned second electricity price unit 12 can be connected to each retailer system to obtain retailer electricity price information from each retailer system in real time or regularly for customers to select. Specifically, the retailer electricity price information refers to the price at which an electricity sales company or electricity retailer sells electricity to end-users (such as residential, commercial, and industrial users).

[0038] In specific implementation, the above-mentioned third electricity price unit 13 can provide a user configuration interface to collect the electricity price information configured by the user. Specifically, the user can set the electricity price for each time period according to information such as hours, minutes, days, weeks, and months through the user configuration interface, and the third electricity price unit collects the time-of-use electricity price information set by the user.

[0039] In specific implementation, the above-mentioned fourth electricity price unit 14 can also be connected to each power grid system and each retailer system. The fourth electricity price unit can generate specified user preferential electricity price information according to the first preferential electricity price information of each power grid system and / or the second preferential electricity price information of each retailer system. For example, due to the active electricity trading in some areas, there may be sudden preferential package time periods. Therefore, the fourth electricity price unit can obtain real-time first preferential electricity price information and second preferential electricity price information from each power grid system and each retailer system through the interface, and automatically set the target preferential time period and price for users in this area according to the first preferential electricity price information and the second preferential electricity price information.

[0040] In specific implementation, the above-mentioned electricity price output unit 15 can output the final user electricity price information according to at least one of the user electricity price information generated by the first electricity price unit, the retailer electricity price information obtained by the second electricity price unit, the user-configured electricity price information collected by the third electricity price unit, and the specified user preferential electricity price information generated by the fourth electricity price unit. Specifically, for example, when the user is a specified preferential user and the user has configured time-of-use electricity prices, the time-of-use electricity prices of the user electricity price information generated by the first electricity price unit or the retailer electricity price information obtained by the second electricity price unit can be modified according to the user-configured time-of-use electricity price information and the specified user preferential electricity price information to better meet the user's needs; another example is that when the user is a specified preferential user and the user has not configured time-of-use electricity prices, it can also be to only modify the time-of-use electricity prices of the user electricity price information generated by the first electricity price unit or the retailer electricity price information obtained by the second electricity price unit according to the specified user preferential electricity price information, or when the user is not a specified preferential user but the user has configured time-of-use electricity prices, it can be to only modify the time-of-use electricity prices of the user electricity price information generated by the first electricity price unit or the retailer electricity price information obtained by the second electricity price unit according to the user-configured electricity price information, etc. The electricity price output unit sends the final user electricity price information to the policy generation module 6.

[0041] In summary, the above electricity price acquisition module provides a channel for acquiring multi-dimensional electricity price information. By docking with each platform, electricity price information can be acquired in real time and accurately. At the same time, the electricity price information can be corrected based on the actual needs of users, and thus an accurate power consumption scheduling strategy can be provided for users.

[0042] In specific implementation, the above site information acquisition module 2 acquires the real-time device information of the photovoltaic energy storage device. Among them, the real-time device information may include at least one of the real-time SOC value, real-time power generation information, real-time load information, and real-time temperature of the photovoltaic energy storage device. This real-time device information is used for subsequent generation of power consumption strategies to improve the accuracy of power consumption scheduling strategies.

[0043] In specific implementation, when the power generation prediction module uses the power generation prediction model to predict the power generation prediction information of the photovoltaic energy storage device, or when the load prediction module uses the load prediction model to predict the load prediction information, meteorological data is needed for prediction. Therefore, in one embodiment, the power consumption scheduling strategy generation system of the photovoltaic energy storage device may further include: a meteorological actual measurement collector and a meteorological prediction collector; the meteorological actual measurement collector and the meteorological prediction collector are respectively connected to the power generation prediction module and the load prediction module; Among them, the meteorological actual measurement collector is used to collect the meteorological actual measurement data of the photovoltaic energy storage device; The meteorological prediction collector is used to collect the meteorological forecast data of the photovoltaic energy storage device.

[0044] In specific implementation, the meteorological actual measurement collector can regularly collect the meteorological actual measurement data of the location where the photovoltaic energy storage device is located (the longitude and latitude of the photovoltaic energy storage device's station yard); the meteorological prediction collector is used to obtain the meteorological forecast data of the location where the photovoltaic energy storage device is located from each meteorological forecast platform. Among them, the meteorological actual measurement data and the meteorological forecast data include but are not limited to irradiance information, temperature, cloud cover, wind speed, etc.

[0045] Figure 3 This is the structural diagram of the power generation prediction module provided by the embodiment of the present invention. As Figure 3 shown, the power generation prediction module 3 may include: an irradiance optimizer 31, a first feature extraction unit 32, a power generation prediction model group 33, and a first result output unit 34; Among them, the irradiance optimizer 31 is used to optimize the meteorological forecast data for a future specified time period collected by the meteorological prediction collector by using the historical meteorological actual measurement data collected by the meteorological actual measurement collector and the historical meteorological forecast data collected by the meteorological prediction collector, so as to obtain the optimized meteorological forecast data; The first feature extraction unit 32 is used to extract the first feature data of the optimized meteorological forecast data; The power generation prediction model group 33 is used to predict the power generation prediction information of the photovoltaic energy storage device in a future specified time period according to the first feature data; The first result output unit 34 is used to process the power generation prediction information of the photovoltaic energy storage device in a specified future time period predicted by the power generation prediction model group, and generate the final power generation prediction information of the photovoltaic energy storage device.

[0046] In one embodiment, the above-mentioned power generation prediction model group 33 may include multiple power generation prediction models 331-33N with different structures, and the structure of each power generation prediction model is any one of a deep learning model, a machine learning model, and a large model; Each power generation prediction model outputs the power generation prediction information of the photovoltaic energy storage device in a specified future time period predicted by itself according to the first feature data.

[0047] In specific implementation, during the prediction process of the power generation information of the photovoltaic energy storage device, the irradiance information in the meteorological data is one of the most important factors affecting the power generation of photovoltaic power generation. The photovoltaic cell module needs sunlight irradiation to be converted into electric energy. Therefore, solar irradiance is crucial for the generation of electric energy and the performance of the photovoltaic system. Therefore, the above-mentioned power generation prediction module 3 specifically further includes an irradiance optimizer 31. The irradiance optimizer can be an artificial intelligence model, and uses historical meteorological measured data and historical meteorological forecast data to optimize the irradiance information in the meteorological forecast data for a specified future time period.

[0048] In specific implementation, in order to further improve the accuracy of the power generation prediction model prediction, the power generation prediction model group can be configured with multiple power generation prediction models with different structures. The structure of the power generation prediction model can be a deep learning model, a machine learning model, or a large model. For example, the power generation prediction model group can be composed of 3 deep learning models, 3 machine learning models, and 2 large models. In the embodiment of the present invention, the number of power generation prediction models in the power generation prediction model group is not limited and can be set according to specific needs. Before applying the power generation prediction module, each power generation prediction model can be trained in advance using historical power generation prediction information and historical power generation information in its corresponding historical time period; during the process of training the model, a clustering learning algorithm can be used to preprocess the training data.

[0049] In specific implementation, the above-mentioned first result output unit processes the power generation prediction information of the photovoltaic energy storage device in a specified future time period predicted by each power generation prediction model. The processing method can be to calculate the average value or weighted value of the prediction results of multiple power generation prediction models to generate the final power generation prediction information. Among them, the power generation prediction information can include the photovoltaic power generation amount or the power generation power.

[0050] In this way, by using multiple power generation prediction models to predict the power generation information of the photovoltaic energy storage device at the same time, the accuracy of the power generation prediction model can be improved, more accurate power generation prediction information can be obtained, and thus the accuracy of the power consumption scheduling strategy can be ensured.

[0051] Figure 4 This is the structural diagram of the load prediction module provided by the embodiment of the present invention. As Figure 4 shown, the load prediction module 4 may include a second feature extraction unit 41, a load prediction model group 42, and a second result output unit 43; Among them, the second feature extraction unit 41 is used to extract the second feature data of the meteorological forecast data in a specified future time period collected by the meteorological prediction collector; The load prediction model group 42 is used to predict the load prediction information of the environment where the photovoltaic energy storage device is located in a specified future time period according to the second feature data; The second result output unit 43 is used to process the load prediction information of the environment where the photovoltaic energy storage device is located in a specified future time period predicted by the load prediction model group, and generate the final load prediction information of the environment where the photovoltaic energy storage device is located.

[0052] In one embodiment, the load prediction model group 42 may include multiple load prediction models 441-44N with different structures, and the structure of each load prediction model is any one of a deep learning model, a machine learning model, and a large model; Each load prediction model outputs the load prediction information of the environment where the photovoltaic energy storage device is located in a specified future time period predicted by itself according to the second feature data.

[0053] Specifically, in order to further improve the accuracy of the load prediction model prediction, the load prediction model group may include multiple load prediction models with different structures. The structure of the load prediction model may be a deep learning model, a machine learning model, or a large model. For example, the load prediction model group may be composed of 3 deep learning models, 3 machine learning models, and 2 large models. In the embodiment of the present invention, the number of load prediction models in the load prediction model group is not limited and can be set according to specific requirements. Before applying the load prediction module, each load prediction model can be trained in advance using meteorological forecast data and historical load information in its corresponding historical time period; during the process of training the model, a clustering learner can be used to preprocess the training data.

[0054] Specifically, the above-mentioned second result output unit processes the load prediction information of the environment where the photovoltaic energy storage device is located in a specified future time period predicted by each load prediction model. The processing method may be to calculate the average value or weight of the prediction results of multiple load prediction models to generate the final load prediction information. Among them, the load prediction information may include load power or usage.

[0055] In this way, by simultaneously using multiple load prediction models to predict the load information of the environment where the photovoltaic energy storage device is located, the accuracy of the load prediction model can be improved, more accurate load prediction information can be obtained, and further the accuracy of the power consumption scheduling strategy can be ensured.

[0056] Figure 5 The following is the structural diagram of the charge and discharge constraint module provided by the embodiment of the present invention. As Figure 5 shown, the above-mentioned charge and discharge constraint module 5 may include: a peak shaving information configuration unit 51, a charge and discharge configuration unit 52, a power consumption strategy preference configuration unit 53, and a constraint condition generation unit 54; Among them, the peak shaving information configuration unit 51 is used to configure peak shaving information, and the peak shaving information includes the peak power and the stored electricity SOC value for each date and each time period; The charge and discharge configuration unit 52 is used to configure charge and discharge information, and the charge and discharge information includes the minimum charge SOC and the maximum discharge SOC for each specified time period; The power consumption strategy preference configuration unit 53 is used to configure power consumption strategy preference information, and the power consumption strategy preference information includes various degrees of aggressive charge and discharge modes; The constraint condition generation unit 54 is used to generate charge constraint conditions according to the peak shaving information, the charge and discharge information, and the power consumption strategy preference information.

[0057] In specific implementation, in the peak shaving information configuration unit 51, the user can set the peak power and the stored electricity SOC value by date and time period.

[0058] In specific implementation, in the charge and discharge configuration unit 52, the user can set the minimum charge SOC and the maximum discharge SOC for the specified time period according to his / her daily power consumption plan.

[0059] In specific implementation, in the power consumption strategy preference configuration unit 53, various degrees of aggressive charge and discharge modes are preset. The charge and discharge modes may include a conservative mode, a revenue-self-use balance mode, a revenue maximization mode, etc. For example, the conservative mode may be a mode of not selling electricity to the grid; the revenue-self-use balance mode is a mode in which electricity is preferentially used for self-use, but part of the electricity will be sold at appropriate times during periods with higher electricity prices; the revenue maximization mode is a mode in which battery charging and discharging are performed in scenarios with revenue. The user can select the corresponding charge and discharge mode according to his / her own needs.

[0060] In specific implementation, the constraint condition generation unit 54 can automatically generate corresponding charging constraint conditions according to the above-mentioned peak shaving information, charge and discharge information, and power consumption strategy preference information through an artificial intelligence algorithm, and perform automated dynamic management that meets safety and economy. For example, if the user configures the minimum charging SOC during a specified period, then the artificial intelligence algorithm is used to select periods with lower electricity prices to gradually charge to the minimum charging SOC; if the user configures the maximum discharging SOC during a specified period, then the artificial intelligence algorithm is used to select periods with higher electricity prices to gradually discharge to the maximum discharging SOC.

[0061] In this way, during the generation process of the power consumption scheduling strategy, the user can configure their power consumption scheduling requirements through the charge and discharge constraint module, and then generate a power consumption scheduling strategy based on the power consumption scheduling requirements of different users and different scenarios, ensuring the accuracy of the power consumption scheduling strategy and improving user satisfaction.

[0062] Figure 6 The structure diagram of the strategy generation module provided by the embodiment of the present invention is as Figure 6 shown. Specifically, the strategy generation module 6 can include a strategy generation model group 61, a simulation unit 62, and a screening unit 63; Among them, the strategy generation model group 61 is used to generate multiple power consumption scheduling strategies according to electricity price information, device real-time information, power generation prediction information, the load prediction information, and charge and discharge constraint conditions; The simulation unit 62 is used to simulate each power consumption scheduling strategy to obtain a simulation result; The screening unit 63 is used to screen the optimal power consumption scheduling strategy according to the simulation results of each power consumption scheduling strategy.

[0063] In one embodiment, the strategy generation model group 61 can include multiple strategy generation models 611-61N with different structures, and the structure of each strategy generation model is a reinforcement learning model or an operations research optimization model; Each strategy generation model generates a power consumption scheduling strategy according to electricity price information, device real-time information, power generation prediction information, load prediction information, and charge and discharge constraint conditions.

[0064] In specific implementation, to ensure the provision of accurate power consumption scheduling strategies, the strategy generation model group can be set with multiple strategy generation models of different structures. The structure of the strategy generation model can be a reinforcement learning model in the field of artificial intelligence or an operations research optimization model in the field of mathematical models. For example, the strategy generation model group can be composed of 3 reinforcement learning models and 3 operations research optimization models. In the embodiments of the present invention, the number of strategy generation models in the strategy generation model group is not limited and can be set according to specific requirements. Before applying the strategy generation model, each strategy generation model can be trained using historical data. Each trained strategy generation model can generate a power consumption scheduling strategy based on the above-mentioned electricity price information, device real-time information, power generation prediction information, load prediction information, and charge and discharge constraint conditions.

[0065] In specific implementation, the simulation unit 62 can use a physical simulation method for simulating future strategies to simulate the power consumption scheduling strategies generated by each strategy generation model, and obtain simulation results. The simulation results can include the system state and benefits at the end of a future specified time period. Specifically, by running a simulation program, each power consumption scheduling strategy can be simulated to obtain the system state and benefits at the end of a future specified time period. The screening unit 63 can select the optimal power consumption scheduling strategy for execution and distribution according to each simulation result.

[0066] In summary, for the above power consumption scheduling strategy generation system of the photovoltaic energy storage device, the real-time and accuracy of the data are ensured in each step of data acquisition and prediction required for the power consumption scheduling strategy, and through the charge and discharge constraint module, the generation of power consumption scheduling strategies can be realized based on the power consumption scheduling requirements of different users and different scenarios, thereby ensuring the accuracy of the power consumption scheduling strategy.

[0067] In the embodiments of the present invention, a method for generating a power consumption scheduling strategy for a photovoltaic energy storage device is also provided, as described in the following embodiments. Since the principle of solving problems by this method is similar to that of the above power consumption scheduling strategy generation system of the photovoltaic energy storage device, the implementation of this method can refer to the implementation of the power consumption scheduling strategy generation system of the photovoltaic energy storage device, and the repeated parts will not be elaborated.

[0068] Figure 7 is a flowchart of a method for generating a power consumption scheduling strategy for a photovoltaic energy storage device provided by an embodiment of the present invention. This method is applied to the above power consumption scheduling strategy generation system of the photovoltaic energy storage device, as Figure 7 shown, this method includes: Step 701, the electricity price acquisition module acquires electricity price information; Step 702, the site information collection module collects the real-time device information of the photovoltaic energy storage device; the real-time device information includes at least one of the real-time SOC value, real-time power generation information, real-time load information, and real-time temperature of the photovoltaic energy storage device; Step 703, the power generation prediction module uses the power generation prediction model to predict the power generation prediction information of the photovoltaic energy storage device; Step 704, the load prediction module uses the load prediction model to predict the load prediction information of the environment where the photovoltaic energy storage device is located; Step 705, the charge and discharge constraint module configures peak shaving information, charge and discharge information, and power consumption strategy preference information, and generates charge and discharge constraint conditions according to the peak shaving information, the charge and discharge information, and the power consumption strategy preference information; Step 706, the strategy generation module determines the optimal power consumption scheduling strategy according to the electricity price information, the real-time device information, the power generation prediction information, the load prediction information, and the charge and discharge constraint conditions.

[0069] In one embodiment, the above step 701 may specifically include, in the electricity price acquisition module: The first electricity price unit obtains the wholesale electricity price information from each power grid system, and generates user electricity price information according to the wholesale electricity price information; The second electricity price unit is used to obtain the retailer electricity price information from each retailer system; The third electricity price unit is used to collect the electricity price information configured by the user; The fourth electricity price unit is used to obtain the first preferential electricity price information from each power grid system and / or the second preferential electricity price information from each retailer system, and generate the designated user preferential electricity price information according to the first preferential electricity price information and / or the second preferential electricity price information; The electricity price output unit is used to output the final user electricity price information according to at least one of the user electricity price information generated by the first electricity price unit, the retailer electricity price information obtained by the second electricity price unit, the user-configured electricity price information collected by the third electricity price unit, and the designated user preferential electricity price information generated by the fourth electricity price unit.

[0070] In one embodiment, the first electricity price unit generates user electricity price information according to the wholesale electricity price information, which may specifically include: calculating the buy electricity price in the user electricity price information according to the buy electricity price calculation algorithm, in accordance with the preset buy electricity ratio information and buy electricity tax information, and combining the wholesale electricity price information; calculating the sell electricity price in the user electricity price information according to the sell electricity price calculation algorithm, in accordance with the preset sell electricity ratio information and sell electricity tax information, and combining the wholesale electricity price information.

[0071] In one embodiment, the above method further includes: the meteorological measurement collector collects the meteorological measurement data of the photovoltaic energy storage device; The meteorological prediction collector collects the meteorological forecast data of the photovoltaic energy storage device.

[0072] In one embodiment, step 703 above may specifically include, in the power generation prediction module: The irradiation optimizer optimizes the meteorological forecast data for a future specified time period collected by the meteorological prediction collector by using the historical meteorological measurement data collected by the meteorological measurement collector and the historical meteorological forecast data collected by the meteorological prediction collector, to obtain optimized meteorological forecast data; The first feature extraction unit extracts the first feature data of the optimized meteorological forecast data; The power generation prediction model group is used to predict the power generation prediction information of the photovoltaic energy storage device in a future specified time period according to the first feature data; The first result output unit is used to process the power generation prediction information of the photovoltaic energy storage device in a future specified time period predicted by the power generation prediction model group, and generate the final power generation prediction information of the photovoltaic energy storage device.

[0073] In one embodiment, the power generation prediction model group includes a plurality of power generation prediction models with different structures, and the structure of each power generation prediction model is any one of a deep learning model, a machine learning model, and a large model; Each power generation prediction model outputs the power generation prediction information of the photovoltaic energy storage device in a future specified time period predicted by itself according to the first feature data.

[0074] In one embodiment, step 704 above may specifically include, in the load prediction module: The second feature extraction unit is used to extract the second feature data of the meteorological forecast data for a future specified time period collected by the meteorological prediction collector; The load prediction model group is used to predict the load prediction information of the environment where the photovoltaic energy storage device is located in a future specified time period according to the second feature data; The second result output unit is used to process the load prediction information of the environment where the photovoltaic energy storage device is located in a future specified time period predicted by the load prediction model group, and generate the final load prediction information of the environment where the photovoltaic energy storage device is located.

[0075] In one embodiment, the load prediction model group includes a plurality of load prediction models with different structures, and the structure of each load prediction model is any one of a deep learning model, a machine learning model, and a large model; Each load prediction model outputs the load prediction information of the environment where the photovoltaic energy storage device is located in a future specified time period predicted by itself according to the second feature data.

[0076] In one embodiment, step 705 above may specifically include, in the charge and discharge constraint module: The peak shaving information configuration unit configures peak shaving information, which includes the peak power and stored electricity SOC values for each date and each time period; The charge and discharge configuration unit configures charge and discharge information, which includes the minimum charging SOC and the maximum discharging SOC for each specified time period; The power consumption strategy preference configuration unit configures power consumption strategy preference information, which includes charge and discharge modes with various degrees of aggressiveness; The constraint condition generation unit generates charging constraint conditions based on the peak shaving information, charge and discharge information, and power consumption strategy preference information.

[0077] In one embodiment, the above step 706 may specifically include, in the strategy generation module: The strategy generation model group generates multiple power consumption scheduling strategies based on electricity price information, device real-time information, power generation prediction information, load prediction information, and charge and discharge constraint conditions; The simulation unit simulates each power consumption scheduling strategy to obtain simulation results; The screening unit screens the optimal power consumption scheduling strategy according to the simulation results of each power consumption scheduling strategy.

[0078] In one embodiment, the strategy generation model group includes multiple strategy generation models with different structures, and the structure of each strategy generation model is a reinforcement learning model or an operations research optimization model; Each strategy generation model generates a power consumption scheduling strategy based on electricity price information, device real-time information, power generation prediction information, load prediction information, and charge and discharge constraint conditions.

[0079] In summary, the above method for generating a power consumption scheduling strategy for a photovoltaic energy storage device takes into account various conditions, including but not limited to electricity price information, device real-time information (measured photovoltaic power generation, measured load power consumption, measured SOC, measured temperature, battery power, etc.), power generation prediction information, load prediction information, charge and discharge constraint conditions (peak shaving power limit, peak shaving SOC, charging target for the target time period, battery power selling limit, quantification of user aggressiveness, loss, cost per kilowatt-hour, etc.). Considering from multiple aspects, the power consumption scheduling strategy is generated based on the power consumption scheduling requirements of different users and different scenarios to ensure the accuracy of the power consumption scheduling strategy.

[0080] It should be noted that in the above method for generating a power consumption scheduling strategy for a photovoltaic energy storage device, the implementation order of steps 701 - 705 can be carried out simultaneously or sequentially, and the specific order is not limited.

[0081] An embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method for generating an electricity consumption scheduling strategy of the above photovoltaic energy storage device is implemented.

[0082] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for generating an electricity consumption scheduling strategy of the above photovoltaic energy storage device is implemented.

[0083] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer conversion program is executed by a processor, the method for generating an electricity consumption scheduling strategy of the above photovoltaic energy storage device is implemented.

[0084] The electricity consumption scheduling strategy generation system of the photovoltaic energy storage device provided by the embodiment of the present invention includes: a electricity price acquisition module, a site information collection module, a power generation prediction module, a load prediction module, a charge and discharge constraint module, and a strategy generation module; the electricity price acquisition module, the site information collection module, the power generation prediction module, the load prediction module, the charge and discharge constraint module are connected to the strategy generation module. In the embodiment of the present invention, the electricity price information can be obtained in real time through the electricity price acquisition module, the real-time information of the photovoltaic energy storage device can be collected through the site information collection module, the power generation information of the photovoltaic energy storage device can be predicted through the power generation prediction module, the load information of the photovoltaic energy storage device can be predicted through the load prediction module, the user demand configuration information of the user can be obtained through the charge and discharge constraint module and the charge and discharge constraint conditions can be generated, and the strategy generation module determines the optimal electricity consumption scheduling strategy based on the above data. In this way, the electricity consumption scheduling strategy generation system of the photovoltaic energy storage device in the embodiment of the present invention supports the generation of the electricity consumption scheduling strategy throughout the whole process from data acquisition, prediction to strategy generation, and through the charge and discharge constraint module, the generation of the electricity consumption scheduling strategy can be realized based on the electricity consumption scheduling requirements under different users and different scenarios, which can ensure the real-time and accuracy of the data required for the generation of the electricity consumption scheduling strategy, and then ensure the accuracy of the electricity consumption scheduling strategy, meet the user's electricity consumption expectations and realize the maximization of benefits.

[0085] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a depth such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0087] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0089] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A system for generating a power dispatching strategy for photovoltaic energy storage equipment, characterized in that: include: An electricity price acquisition module, a site information acquisition module, a power generation prediction module, a load prediction module, a charge and discharge constraint module and a strategy generation module; the electricity price acquisition module, the site information acquisition module, the power generation prediction module, the load prediction module, the charge and discharge constraint module are connected to the strategy generation module; Wherein, the electricity price acquisition module is used to obtain electricity price information; The site information collection module is used to collect real-time equipment information of the photovoltaic energy storage device; the real-time equipment information includes at least one of the real-time SOC value, real-time power generation information, real-time load information, and real-time temperature of the photovoltaic energy storage device; The power generation prediction module is used to predict the power generation prediction information of the photovoltaic energy storage device using a power generation prediction model; The load prediction module is used to predict the load prediction information of the environment in which the photovoltaic energy storage device is located using a load prediction model; The charge and discharge constraint module is used to configure peak shaving information, charge and discharge information and power usage strategy preference information, and generate charge and discharge constraint conditions according to the peak shaving information, the charge and discharge information and the power usage strategy preference information; The strategy generation module is used to determine the optimal power scheduling strategy based on the electricity price information, the real-time equipment information, the power generation forecast information, the load forecast information and the charging and discharging constraints.

2. The system according to claim 1, characterized in that The electricity price acquisition module includes a first electricity price unit, a second electricity price unit, a third electricity price unit, a fourth electricity price unit and an electricity price output unit: The first electricity price unit is used to obtain wholesale electricity price information from each power grid system, and generate user electricity price information according to the wholesale electricity price information; The second electricity price unit is used to obtain retailer electricity price information from each retailer system; The third electricity price unit is used to collect electricity price information configured by the user; The fourth electricity price unit is used to obtain the first preferential electricity price information from each power grid system and / or obtain the second preferential electricity price information from each retailer system, and generate the designated user preferential electricity price information according to the first preferential electricity price information and / or the second preferential electricity price information; The electricity price output unit is used to output final user electricity price information based on at least one of the user electricity price information generated by the first electricity price unit, the retailer electricity price information acquired by the second electricity price unit, the user-configured electricity price information collected by the third electricity price unit, and the designated user preferential electricity price information generated by the fourth electricity price unit.

3. The system according to claim 2, characterized in that The first electricity price unit generates user electricity price information based on the wholesale electricity price information, specifically including: according to the electricity purchase price calculation algorithm, in accordance with the preset electricity purchase ratio information and electricity purchase tax information, combined with the wholesale electricity price information, calculating the electricity purchase price in the user electricity price information; according to the electricity selling price calculation algorithm, in accordance with the preset electricity selling ratio information and electricity selling tax information, combined with the wholesale electricity price information, calculating the electricity selling price in the user electricity price information.

4. The system according to claim 1, characterized in that The power dispatch strategy generation system of the photovoltaic energy storage device also includes: a meteorological measurement collector and a meteorological forecast collector; the meteorological measurement collector and the meteorological forecast collector are respectively connected to the power generation forecast module and the load forecast module; Wherein, the meteorological measurement collector is used to collect the meteorological measurement data of the photovoltaic energy storage device; The weather forecast collector is used to collect weather forecast data of the photovoltaic energy storage device.

5. The system according to claim 4, characterized in that The power generation prediction module includes an irradiation optimizer, a first feature extraction unit, a power generation prediction model group and a first result output unit; The irradiation optimizer is used to optimize the weather forecast data for a future specified time period collected by the weather forecast collector using the historical weather measured data collected by the weather measured collector and the historical weather forecast data collected by the weather forecast collector to obtain optimized weather forecast data; The first feature extraction unit is used to extract first feature data of the optimized weather forecast data; The power generation prediction model group is used to predict the power generation prediction information of the photovoltaic energy storage device in a future specified time period according to the first characteristic data; The first result output unit is used to process the power generation prediction information of the photovoltaic energy storage device in the future specified time period predicted by the power generation prediction model group to generate final power generation prediction information of the photovoltaic energy storage device.

6. The system according to claim 5, characterized in that The power generation prediction model group includes a plurality of power generation prediction models with different structures, and the structure of each power generation prediction model is any one of a deep learning model, a machine learning model, and a large model; Each power generation prediction model outputs the power generation prediction information of the photovoltaic energy storage equipment predicted by each model in the future specified time period according to the first characteristic data.

7. The system according to claim 4, characterized in that The load forecasting module includes a second feature extraction unit, a load forecasting model group, and a second result output unit; Wherein, the second feature extraction unit is used to extract the second feature data of the weather forecast data of the future specified time period collected by the weather forecast collector; The load prediction model group is used to predict the load prediction information of the environment where the photovoltaic energy storage device is located in a specified time period in the future according to the second characteristic data; The second result output unit is used to process the load forecast information of the environment in which the photovoltaic energy storage device is located in a future specified time period predicted by the load forecast model group, and generate final load forecast information of the environment in which the photovoltaic energy storage device is located.

8. The system according to claim 7, characterized in that The load forecasting model group includes a plurality of load forecasting models with different structures, and the structure of each load forecasting model is any one of a deep learning model, a machine learning model, and a large model; Each load prediction model outputs the load prediction information of the environment in which the photovoltaic energy storage device is located in a future specified time period according to the second characteristic data.

9. The system according to claim 1, characterized in that The charging and discharging constraint module includes: a peak shaving information configuration unit, a charging and discharging configuration unit, a power consumption strategy preference configuration unit and a constraint condition generation unit; The peak shaving information configuration unit is used to configure peak shaving information, and the peak shaving information includes peak power and power storage SOC value for each date and time period; The charge and discharge configuration unit is used to configure charge and discharge information, wherein the charge and discharge information includes a minimum charge SOC value and a maximum discharge SOC value in each specified time period; The power usage strategy preference configuration unit is used to configure power usage strategy preference information, wherein the power usage strategy preference information includes charging and discharging modes of multiple aggressiveness; The constraint condition generating unit is used to generate charging constraint conditions according to the peak shaving information, the charging and discharging information and the power usage strategy preference information.

10. The system according to claim 1, wherein: The strategy generation module includes a strategy generation model group, a simulation unit, and a screening unit; The strategy generation model group is used to generate multiple power dispatch strategies according to the electricity price information, the real-time equipment information, the power generation forecast information, the load forecast information and the charging and discharging constraint conditions; The simulation unit is used to simulate each power dispatching strategy to obtain simulation results; The screening unit is used to screen the optimal power scheduling strategy according to the simulation result of each power scheduling strategy.

11. The system according to claim 10, characterized in that The strategy generation model group includes a plurality of strategy generation models with different structures, and the structure of each strategy generation model is a reinforcement learning model or an operations optimization model; Each strategy generation model generates a power dispatch strategy based on electricity price information, equipment real-time information, power generation forecast information, load forecast information and charging and discharging constraints.

12. A method for generating a power dispatching strategy for a photovoltaic energy storage device, characterized in that: The method applied to the power dispatch strategy generation system of the photovoltaic energy storage device according to any one of claims 1 to 11 comprises: The electricity price acquisition module acquires electricity price information; The site information collection module collects the real-time information of the photovoltaic energy storage device; the real-time information of the device includes at least one of the real-time SOC value, real-time power generation information, real-time load information, and real-time temperature of the photovoltaic energy storage device; The power generation prediction module predicts power generation prediction information of the photovoltaic energy storage device using a power generation prediction model; The load prediction module uses a load prediction model to predict the load prediction information of the environment in which the photovoltaic energy storage device is located; The charge and discharge constraint module configures peak shaving information, charge and discharge information and power usage strategy preference information, and generates charge and discharge constraint conditions according to the peak shaving information, the charge and discharge information and the power usage strategy preference information; The strategy generation module determines the optimal power dispatching strategy according to the electricity price information, the real-time equipment information, the power generation forecast information, the load forecast information and the charging and discharging constraint conditions.

13. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for generating a power scheduling strategy for photovoltaic energy storage equipment according to claim 12 is implemented.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating a power scheduling strategy for a photovoltaic energy storage device according to claim 12 is implemented.

15. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the method for generating a power scheduling strategy for a photovoltaic energy storage device according to claim 12 is implemented.

Images