Energy storage operation mode switching method and apparatus, and storage medium and device

Through preset load and user electricity use behavior models, combined with large language models to generate energy storage scheduling strategies, the problems of single energy storage mode and interaction delay are solved, and multiple application mode switching and convenient interaction are realized, improving user experience.

WO2024227454A2PCT designated stage expired Publication Date: 2024-11-07SHANGHAI SIGEYUAN INTELLIGENT TECH CO LTD
View PDF 0 Cites 32 Cited by

Patent Information

Application Number
PCT/CN2024/101766
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-04-29
Filing Date
2024-06-26
Publication Date
2024-11-07

AI Technical Summary

Technical Problem

The existing energy storage mode is single and cannot be switched in time and effectively according to changes in application scenarios, resulting in poor experience and lack of convenient human-computer interaction methods, resulting in delayed information interaction.

Method used

By pre-setting the load prediction model and user electricity consumption behavior model, combining the large language model to generate energy storage scheduling strategies, including charging pile prediction strategies, heat pump prediction strategies, economic priority prediction strategies and off-grid priority prediction strategies, to realize multiple application modes switch and convenient information interaction.

Benefits of technology

It realizes setting different system performance maintenance strategies according to customer needs, improves user experience, and solves the problem of information interaction delay, providing flexible energy storage mode switching and convenient human-computer interaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024101766_07112024_PF_FP_ABST
    Figure CN2024101766_07112024_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of electric power allocation. Disclosed are an energy storage operation mode switching method and apparatus, and a storage medium and a device. The energy storage operation mode switching method comprises: presetting a first load prediction model; acquiring first user input information; inputting the first user input information into a model for learning, so as to generate a first user power utilization behavior model; inputting a prediction result of the first user power utilization behavior model and a prediction result of the first load prediction model into a model for learning, so as to generate a second load prediction model; and outputting an energy storage scheduling policy according to a result of second load prediction. The present invention solves the problems whereby existing energy storage modes are single, making it impossible to provide multiple application modes for a user to choose, and thus it is impossible to perform timely and effective switching according to changes in an application scenario, resulting in poor experience; moreover, there is a lack of a convenient human-machine interaction mode, resulting in delay in information interaction.
Need to check novelty before this filing date? Find Prior Art

Description

Energy storage operation mode switching method, device, storage medium and equipment Technical Field

[0001] The present invention relates to the field of power allocation technology, and in particular to a method, device, storage medium and equipment for switching energy storage operation modes. Background Art

[0002] With the development of social economy and the advancement of science and technology, energy shortage and environmental pollution have attracted more and more attention. In order to deal with this serious problem, people have increased their research and development of renewable energy. Photovoltaic microgrids based on solar energy have gradually become a research direction of renewable energy.

[0003] Solar-energy storage systems, also known as solar photovoltaic energy storage power generation systems, are power generation systems composed of photovoltaic equipment and energy storage devices. Existing energy storage models are limited in scope and fail to offer a variety of application modes for users to choose from. This makes it difficult to switch between them promptly and effectively based on changing application scenarios, resulting in a poor user experience. Furthermore, they lack convenient human-computer interaction, leading to information exchange delays. Currently, no effective solutions have been proposed to address these issues.

[0004] Summary of the Invention

[0005] Purpose of the invention: To provide a method, device, storage medium and equipment for switching energy storage operation modes to solve the above-mentioned problems existing in the prior art.

[0006] Technical solution: A method for switching energy storage operation modes, comprising:

[0007] S101. Presetting a first load forecasting model: receiving first data, where the first data includes photovoltaic forecast power, load forecast power data, actual sampled power data, daily electricity consumption schedule, meteorological data, electricity price forecast data, energy storage system capacity percentage data, parameters of each aggregation unit of the power station, and distribution network parameters; or inputting the first data into a neural network model for training to generate the first load forecasting model; or extracting entities from the first data and constructing a knowledge graph based on the mapping relationship between the entities and the load to generate the first load forecasting model;

[0008] S102: Obtain first user input information, where the first user input information includes voice input, QR code scanning, or text input;

[0009] S103: Inputting the first user input information into a large language model for learning to generate a first user electricity usage behavior model;

[0010] S104: Input the prediction result of the first user electricity consumption behavior model and the prediction result of the first load forecasting model into a large language model for learning to generate a second load forecasting model;

[0011] S105 , obtaining the operating data of the photovoltaic system and inputting it into the second load prediction model to obtain a second load prediction result, and outputting an energy storage scheduling strategy according to the second load prediction result.

[0012] Preferably, the energy storage scheduling strategy includes:

[0013] Charging pile prediction strategy, heat pump prediction strategy, economic priority prediction strategy and off-grid priority prediction strategy.

[0014] According to one embodiment of the present invention, the process of outputting a charging pile prediction strategy based on the result of the second load prediction includes:

[0015] Obtain data on photovoltaic power generation, photovoltaic predicted power, charging pile charging power, charging pile predicted power, and energy storage system capacity percentage;

[0016] Perform charging and discharging management based on the photovoltaic power generation, the photovoltaic predicted power, the charging pile charging power, the charging pile predicted power, and the state of charge of the energy storage system;

[0017] When the photovoltaic power generation power is greater than the charging power of the charging pile, and the state of charge of the energy storage system is less than the preset value A,

[0018] If it is during the peak electricity consumption period, photovoltaic power generation will charge the charging pile and the energy storage system. When the state of charge of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment will stop charging;

[0019] If it is in the high-use and low-use period, photovoltaic power generation will charge the charging pile, and at the same time, the excess photovoltaic power generation and the power grid will replenish the energy storage system. If the charge state of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment will stop charging.

[0020] According to one embodiment of the present invention, the data on photovoltaic power generation power, charging pile charging power and energy storage system capacity are obtained in real time through an energy controller, wherein the photovoltaic power generation power meter is the sum of the power generation efficiency of all photovoltaics in the substation area, the charging pile charging power meter is the sum of the charging efficiency of all charging piles in the substation area, and the energy storage system state of charge is the average value of the state of charge of each battery pack in the substation area.

[0021] According to one embodiment of the present invention, the process of outputting a heat pump prediction mode strategy based on the result of the second load prediction includes:

[0022] Obtain data on photovoltaic power generation power, photovoltaic predicted power, heat pump charging power, heat pump predicted power, and energy storage system capacity percentage, and perform charging and discharging management based on the relationship between the photovoltaic power generation power, photovoltaic predicted power, heat pump charging power, heat pump predicted power, and the energy storage system charge state.

[0023] According to one embodiment of the present invention, the process of outputting the economic priority forecasting strategy according to the result of the second load forecasting includes:

[0024] Calculate the peak-shaving costs of distributed photovoltaics with energy storage, including the opportunity cost of distributed photovoltaics, the cost of purchasing electricity when charging energy storage, and the operation and maintenance costs of energy storage;

[0025] Calculate the peak-shaving benefits of distributed photovoltaics with energy storage, including peak-shaving compensation benefits and energy storage electricity benefits;

[0026] Establish and analyze the economic benefit model of distributed photovoltaics with energy storage providing peak load regulation. Based on the model constraints, maximize the model's objective function to calculate the economic benefits of distributed photovoltaics with energy storage participating in peak load regulation.

[0027] Based on the peak-shaving costs, peak-shaving benefits and the economic benefits of distributed photovoltaics with energy storage participating in peak-shaving, a distributed photovoltaic peak-shaving control strategy with energy storage is formulated.

[0028] In particular, the present invention further provides an energy storage operation mode switching device, characterized by comprising:

[0029] A preset module, used for presetting a first load forecasting model;

[0030] An input module, configured to obtain first user input information;

[0031] a first learning module, configured to input the first user input information into a large language model for learning, and generate a first user electricity usage behavior model;

[0032] a second learning module, configured to input the prediction result of the first user electricity consumption behavior model and the prediction result of the first load forecasting model into a large language model for learning, so as to generate a second load forecasting model;

[0033] The output module obtains the working data of the photovoltaic system and inputs it into the second load forecasting model to obtain the result of the second load forecast, and is used to output the energy storage scheduling strategy according to the result of the second load forecast.

[0034] According to one embodiment of the present invention, the energy storage scheduling strategy includes:

[0035] Charging pile prediction strategy, heat pump prediction strategy, economic priority prediction strategy and off-grid priority prediction strategy.

[0036] According to one embodiment of the present invention, the process of outputting a charging pile prediction strategy based on the result of the second load prediction includes:

[0037] Obtain data on photovoltaic power generation, photovoltaic predicted power, charging pile charging power, charging pile predicted power, and energy storage system capacity percentage;

[0038] Perform charging and discharging management based on the photovoltaic power generation, the photovoltaic predicted power, the charging pile charging power, the charging pile predicted power, and the state of charge of the energy storage system;

[0039] When the photovoltaic power generation power is greater than the charging power of the charging pile, and the state of charge of the energy storage system is less than the preset value A,

[0040] If it is during the peak electricity consumption period, photovoltaic power generation will charge the charging pile and the energy storage system. When the state of charge of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment will stop charging;

[0041] If it is in the high-use and low-use period, photovoltaic power generation will charge the charging pile, and at the same time, the excess photovoltaic power generation and the power grid will replenish the energy storage system. If the charge state of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment will stop charging.

[0042] According to one embodiment of the present invention, the data on photovoltaic power generation power, charging pile charging power and energy storage system capacity are obtained in real time through an energy controller, wherein the photovoltaic power generation power meter is the sum of the power generation efficiency of all photovoltaics in the substation area, the charging pile charging power meter is the sum of the charging efficiency of all charging piles in the substation area, and the energy storage system state of charge is the average value of the state of charge of each battery pack in the substation area.

[0043] According to one embodiment of the present invention, the process of outputting a heat pump prediction mode strategy based on the result of the second load prediction includes:

[0044] Obtain data on photovoltaic power generation power, photovoltaic predicted power, heat pump charging power, heat pump predicted power, and energy storage system capacity percentage, and perform charging and discharging management based on the relationship between the photovoltaic power generation power, photovoltaic predicted power, heat pump charging power, heat pump predicted power, and the energy storage system charge state.

[0045] According to one embodiment of the present invention, the process of outputting the economic priority forecasting strategy according to the result of the second load forecasting includes:

[0046] Calculate the peak-shaving cost of distributed photovoltaics with energy storage, including: the opportunity cost of distributed photovoltaics, the cost of purchasing electricity when charging energy storage, and the operation and maintenance costs of energy storage;

[0047] Calculate the peak-shaving benefits of distributed photovoltaics with energy storage, including peak-shaving compensation benefits and energy storage electricity benefits;

[0048] Establish and analyze the economic benefit model of distributed photovoltaics with energy storage providing peak load regulation. Based on the model constraints, maximize the model's objective function to calculate the economic benefits of distributed photovoltaics with energy storage participating in peak load regulation.

[0049] Based on the peak-shaving costs, peak-shaving benefits and the economic benefits of distributed photovoltaics with energy storage participating in peak-shaving, a distributed photovoltaic peak-shaving control strategy with energy storage is formulated.

[0050] In order to achieve the above objective, according to another aspect of the present application, a computer-readable storage medium is provided.

[0051] According to the computer-readable storage medium of the present application, a computer program is stored in the computer-readable storage medium, wherein the computer program is configured to execute the energy storage operation mode switching method when running.

[0052] In order to achieve the above objective, according to another aspect of the present application, an electronic device is provided.

[0053] The electronic device according to the present application includes: a memory and a processor, wherein the memory stores a computer program, wherein the processor is configured to run the computer program to execute the energy storage operation mode switching method.

[0054] Beneficial effect: In the embodiment of the present application, a method of generating an energy storage scheduling strategy through human-computer interaction is adopted, by presetting a first load forecasting model; obtaining first user input information; inputting the first user input information into the model for learning to generate a first user electricity consumption behavior model; inputting the prediction result of the first user electricity consumption behavior model and the result of the load forecast into the model for learning to generate a second load forecasting model; outputting the energy storage scheduling strategy based on the result of the second load forecast, thereby achieving the purpose of convenient information interaction and generation of energy storage scheduling strategy, thereby achieving the technical effect of setting different system performance maintenance strategies according to customer needs, and further solving the problem that the existing energy storage mode is single and cannot provide multiple application modes for users to choose from, and thus cannot be switched in time and effectively according to changes in application scenarios, resulting in a poor user experience; at the same time, there is a lack of convenient human-computer interaction methods, resulting in the technical problem of delayed information interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] FIG1 is a schematic flow chart of a method for switching an energy storage operation mode according to an embodiment of the present application;

[0056] FIG2 is a schematic structural diagram of an energy storage operation mode switching device according to an embodiment of the present application. DETAILED DESCRIPTION

[0057] To help those skilled in the art better understand the present invention, the following will provide a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. It should be understood that the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort should fall within the scope of protection of the present invention.

[0058] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0059] Furthermore, the terms "installed," "disposed," "provided with," "connected," "connected," and "socketed" should be interpreted broadly. For example, they can refer to fixed connections, removable connections, or integral structures; mechanical connections or electrical connections; direct connections or indirect connections through an intermediary; or internal communication between two devices, elements, or components. Those skilled in the art will understand the specific meanings of these terms in the present invention based on specific circumstances.

[0060] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0061] According to an embodiment of the present invention, a method for switching an energy storage operation mode is provided. As shown in FIG1 , the method includes the following steps S101 to S106:

[0062] S101, presetting a first load forecasting model;

[0063] By presetting the first load model, the load can be predicted, thereby obtaining basic prediction information.

[0064] According to an embodiment of the present invention, preferably, presetting the load forecast includes: receiving first data, wherein the first data includes:

[0065] Photovoltaic predicted power, load predicted power data, actual sampled power data, daily electricity consumption schedule, meteorological data, electricity price forecast data, energy storage system capacity percentage data, parameters of each aggregation unit of the power station and distribution network parameters.

[0066] By receiving the first data, real-time data collection can be achieved, thereby providing an accurate data foundation for subsequent model processing. Specifically, by using methods including but not limited to: sensors detecting device data, real-time device operating data, such as voltage, current, and temperature, can be obtained; the detected devices include but are not limited to: inverters, energy storage batteries, photovoltaic panels, and loads (refrigerators, washing machines, etc.).

[0067] By detecting and collecting relevant data such as photovoltaics, loads, and energy storage, accurate and real-time equipment parameter information can be obtained, and the above information can be fed back to the back end for data analysis and processing.

[0068] Step S102: obtaining first user input information;

[0069] The app collects the first user's actual energy storage needs or personal electricity usage habits through voice, text, etc. For example, "I am going out tomorrow, please adjust the optimal energy storage mode." The app collects the real-time natural voice and feeds it back to the processor for information input, thereby achieving good real-time information interaction effects and providing a data basis for subsequent accurate information correction.

[0070] Step S103: inputting the first user input information into a large language model for learning to generate a first user electricity usage behavior model;

[0071] By processing and analyzing the input information of the first user through the large language model and generating a first electricity usage behavior model, accurate user electricity usage behavior can be obtained, thereby providing a data basis for subsequent information correction.

[0072] Step S104: inputting the prediction result of the first user electricity consumption behavior model and the prediction result of the first load forecasting model into a large language model for learning to generate a second load forecasting model;

[0073] By sending the predicted results of the first load forecasting model and the predicted results of the first user electricity consumption behavior model to the large language model for deep learning, a second load forecasting model is generated. It has higher accuracy and can combine the load and the user's electricity consumption habits to give a high-precision second load forecasting model, so as to flexibly meet the actual electricity consumption needs and thus improve the user experience.

[0074] According to an embodiment of the present invention, preferably, the prediction result of the first user electricity consumption behavior model and the prediction result of the first load forecasting model are input into a model for learning to generate a second load forecasting model, including:

[0075] Inputting the prediction result of the first load forecasting model and the prediction result of the first user electricity consumption behavior model into the large language model for learning;

[0076] A random forest algorithm is used to further perform deep learning on the large language model based on the prediction results of the first load forecasting model and the prediction results of the first user electricity consumption behavior model to generate a second load forecasting model.

[0077] By adopting the random forest algorithm, good computer deep self-learning effects can be achieved, thereby generating the required charging strategy, and inferring a charging plan that is in line with the current or future period, which is more humane.

[0078] Step S105: Acquire the working data of the photovoltaic system and input it into the second load forecasting model to obtain the result of the second load forecast, and output the energy storage scheduling strategy according to the result of the second load forecast.

[0079] It can output accurate energy storage scheduling strategies, so that they can be more in line with actual usage scenarios.

[0080] According to an embodiment of the present invention, preferably, the output energy storage scheduling strategy includes:

[0081] Charging pile prediction strategy, heat pump prediction strategy, battery life priority prediction strategy, green electricity priority prediction strategy, economic priority prediction strategy and off-grid priority prediction strategy.

[0082] The output energy storage scheduling strategies include, but are not limited to, charging pile prediction strategies, heat pump prediction strategies, battery life priority prediction strategies, green power priority prediction strategies, economy priority prediction strategies, and off-grid priority prediction strategies. This enables flexible multi-mode usage, and additional modes can be added based on actual usage needs, greatly increasing the diversity of modes. Furthermore, mode switching can be performed based on different usage scenarios, enabling optimal adaptation to the current application scenario.

[0083] According to an embodiment of the present invention, preferably, the process of outputting a charging pile prediction strategy according to the result of the second load prediction includes:

[0084] Obtain data on photovoltaic power generation, photovoltaic predicted power, charging pile charging power, charging pile predicted power, and energy storage system capacity percentage;

[0085] Charging and discharging management is performed based on the relationship between the photovoltaic power generation power, the photovoltaic predicted power, the charging pile charging power, the charging pile predicted power, and the state of charge of the energy storage system.

[0086] By detecting the power of photovoltaic and charging piles, and managing the charging and discharging of the energy storage system's state of charge, it is possible to rationally allocate energy storage according to usage, thereby improving utilization.

[0087] According to an embodiment of the present invention, preferably, the data of photovoltaic power generation, charging pile charging power and energy storage system capacity are obtained in real time through an energy controller, wherein:

[0088] The photovoltaic power generation meter is the sum of the power generation efficiencies of all photovoltaics in the area;

[0089] The charging power of the charging pile is the sum of the charging efficiencies of all charging piles in the area;

[0090] The state of charge of the energy storage system is calculated as the average state of charge of each battery pack in the station area.

[0091] According to an embodiment of the present invention, preferably, when the photovoltaic power generation power is greater than the charging power of the charging pile, and at the same time, the state of charge of the energy storage system is less than a preset value A,

[0092] If it is during the peak electricity consumption period, photovoltaic power generation will charge the charging pile and the energy storage system. If the state of charge of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment will stop charging;

[0093] If it is in the high-use and low-use period, photovoltaic power generation will charge the charging pile, and at the same time, the excess photovoltaic power generation and the power grid will replenish the energy storage system. If the charge state of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment will stop charging.

[0094] Specifically, data on photovoltaic power generation power, charging pile charging power and energy storage system capacity are obtained in real time through the energy controller. Among them, the photovoltaic power generation power is measured as the sum of the power generation efficiency of all photovoltaics in the substation; the charging pile charging power is measured as the sum of the charging efficiency of all charging piles in the substation; and the energy storage system state of charge is measured as the average state of charge of each battery pack in the substation.

[0095] (1) When the photovoltaic power generation power is greater than the charging power of the charging pile, and at the same time, the state of charge of the energy storage system is less than 90%, if it is during the peak power consumption period, the photovoltaic power generation will charge the charging pile and the energy storage system. If the state of charge of the energy storage system is greater than or equal to 90%, the energy storage system equipment will stop charging; if it is during the level consumption period and the off-peak period, the photovoltaic power generation will charge the charging pile, and at the same time, the excess photovoltaic power generation and the power grid will simultaneously supplement the energy storage system. If the state of charge of the energy storage system is greater than or equal to 90%, the energy storage system equipment will stop charging.

[0096] (2) When the photovoltaic power generation power is greater than the charging power of the charging pile, and at the same time, the state of charge of the energy storage system is greater than or equal to 90%, the photovoltaic power will charge the charging pile, and the excess photovoltaic power generation will be integrated into the grid.

[0097] (3) When the photovoltaic power generation power is less than or equal to the charging power of the charging pile, and at the same time, the state of charge of the energy storage system is greater than or equal to 20%, if it is in the peak period, the working mode of the energy storage system equipment is set to the discharge mode. If the state of charge of the energy storage system is less than 20%, the energy storage system equipment stops discharging; if it is in the flat and off-peak period, the photovoltaic power generation and the power grid charge the charging pile, and the power grid replenishes the energy storage system. If the state of charge of the energy storage system battery is greater than or equal to 90%, the energy storage system equipment stops charging.

[0098] (4) When the photovoltaic power generation power is less than or equal to the charging power of the charging pile, and at the same time, the state of charge of the energy storage system is less than 20%, the photovoltaic power generation and the power grid jointly charge the charging pile and the energy storage system equipment; if it is in peak hours, the photovoltaic power generation and the power grid charge the charging pile; if it is in flat and off-peak hours, the photovoltaic power generation and the power grid charge the charging pile, and the power grid replenishes power for the energy storage system equipment. If the state of charge of the energy storage system is greater than or equal to 90%, the energy storage system equipment stops charging.

[0099] (5) When the photovoltaic power generation power is less than the charging power of the charging pile, and at the same time, the state of charge of the energy storage system is greater than or equal to 20%, if it is during peak hours, the energy storage system working equipment is set to the grid-connected discharge mode. If the photovoltaic power generation power is greater than the load of the substation or the state of charge of the energy storage system is greater than or equal to 20%, the energy storage system equipment stops discharging; if it is during flat and off-peak hours, the grid replenishes power to the energy storage system. If the state of charge of the energy storage system is greater than or equal to 90%, the energy storage system equipment stops charging.

[0100] (6) When the photovoltaic power generation power is less than the charging power of the charging pile, and at the same time, the energy storage system's state of charge is less than 20%, if it is during peak hours, the energy storage system equipment stops discharging; if it is during flat and off-peak hours, the power grid replenishes power to the energy storage system equipment. If the energy storage system's state of charge is greater than or equal to 90%, the energy storage system equipment stops charging.

[0101] (7) When the photovoltaic power generation power is greater than the charging power of the charging pile, and the energy storage system charge state is less than 90%,

[0102] If it is during peak hours, the energy storage system working equipment is set to grid-connected charging mode. If the energy storage system's state of charge is greater than or equal to 90%, the energy storage system equipment stops charging; if it is during flat and off-peak hours, the energy storage system working equipment is set to grid-connected charging mode. If the energy storage system's state of charge is greater than or equal to 90%, the energy storage system equipment stops charging.

[0103] (8) When the load rate of the transformer is greater than 70%, the charging power of the charging pile is read and a charging power limit instruction is sent to the charging pile, so that the charging pile reduces the load and charges; if the load rate of the transformer is less than or equal to 70%, if it is during peak hours, the energy storage system working equipment is set to the grid-connected discharge mode, and when the energy storage system charge state is less than or equal to 20%, the energy storage system equipment stops discharging; if it is during flat and off-peak hours, the energy storage system working equipment is set to the grid-connected charging mode, and when the energy storage system charge state is greater than or equal to 90%, the energy storage system equipment stops charging.

[0104] According to an embodiment of the present invention, preferably, the process of outputting a heat pump prediction mode strategy according to the result of the second load prediction includes:

[0105] Obtain data on photovoltaic power generation, photovoltaic predicted power, heat pump charging power, heat pump predicted power, and energy storage system capacity percentage;

[0106] Charging and discharging management is performed based on the relationship between the photovoltaic power generation power, the photovoltaic predicted power, the heat pump charging power, the heat pump predicted power, and the state of charge of the energy storage system.

[0107] By detecting the power of photovoltaics and heat pumps, and managing the charging and discharging of the energy storage system's state of charge, it is possible to rationally allocate energy storage based on usage, thereby improving utilization.

[0108] According to an embodiment of the present invention, preferably, the process of outputting a battery life priority prediction strategy according to the result of the second load prediction includes:

[0109] Obtaining battery operating condition information, wherein the operating condition information includes: current, battery cell and temperature;

[0110] The battery operating condition information is input into a machine self-learning model to generate a battery life priority model.

[0111] By adopting a battery life priority prediction strategy, the battery life priority effect can be ensured, thereby further increasing the battery life at the expense of a certain degree of economy.

[0112] According to an embodiment of the present invention, preferably, the process of outputting the green electricity priority prediction strategy according to the result of the second load forecast includes:

[0113] Obtain photovoltaic and energy storage related data;

[0114] The photovoltaic and energy storage related information is input into the model for learning to generate a green electricity priority model.

[0115] By adopting a green electricity priority forecasting strategy, only photovoltaic electricity can be used, thus achieving the effect of pure green electricity use.

[0116] According to an embodiment of the present invention, preferably, the process of outputting the economic priority forecasting strategy according to the result of the second load forecasting includes:

[0117] Calculate the peak-shaving cost of distributed photovoltaics with energy storage, including: the opportunity cost of distributed photovoltaics, the cost of purchasing electricity when charging energy storage, and the operation and maintenance costs of energy storage;

[0118] Calculate the peak-shaving benefits of distributed photovoltaics with energy storage, including peak-shaving compensation benefits and energy storage electricity benefits;

[0119] Establish and analyze the economic benefit model of distributed photovoltaics with energy storage providing peak load regulation. Based on the model constraints, maximize the model's objective function to calculate the economic benefits of distributed photovoltaics with energy storage participating in peak load regulation.

[0120] Based on the peak-shaving costs, peak-shaving benefits and the economic benefits of distributed photovoltaics with energy storage participating in peak-shaving, a distributed photovoltaic peak-shaving control strategy with energy storage is formulated.

[0121] By adopting an economic-first forecasting strategy, good economic results can be ensured.

[0122] According to an embodiment of the present invention, preferably, the process of outputting the off-grid priority prediction strategy according to the result of the second load prediction includes:

[0123] receiving second user input information;

[0124] The second user input information is sent to the model learning to generate an off-grid priority model.

[0125] By combining user usage habits, the backup power capacity is dynamically adjusted to ensure that there is no power outage.

[0126] According to an embodiment of the present invention, preferably, obtaining the first user input information includes:

[0127] Voice input, QR code scanning or text input.

[0128] It can provide a variety of input selection effects, thereby achieving flexible input effects.

[0129] According to an embodiment of the present invention, preferably, presetting a first load forecasting model includes:

[0130] The first data is input into a neural network model for training to generate a first load forecasting model.

[0131] By inputting the first data into an algorithm or model, and then processing and calculating the big data to generate a first load forecasting model, a pre-set load forecast can be achieved, thereby achieving the effect of predicting the load. The accuracy of the load forecasting model's predictions will affect the efficiency of photovoltaic and energy storage operations, so improving the accuracy of the load forecasting model is particularly important. For example, real-time photovoltaic and load data is collected to obtain their accurate status. When the first user needs electricity within a predetermined time in the future, the energy storage is pre-charged through the photovoltaic panel to ensure that the energy storage is sufficient, thereby meeting the device's power needs and reducing the use of external power grids, thereby reducing electricity costs and ensuring economic efficiency. The higher the load forecasting model's prediction accuracy, the more accurate the customer's electricity usage habits, and thus the more accurate the choice of charging time.

[0132] At the same time, the collected first data is input into the neural network model for learning and training to generate a load prediction model. Therefore, it is only necessary to input the load into the load prediction model through methods including but not limited to: voice input to obtain a result that matches the load.

[0133] According to an embodiment of the present invention, preferably, presetting a first load forecasting model includes:

[0134] A mapping relationship between the first data and the load is constructed to generate a first load prediction model.

[0135] According to an embodiment of the present invention, preferably, presetting a first load forecasting model includes:

[0136] Entities in the first data are extracted, and a knowledge graph is constructed with reference to the mapping relationship between the entities and the load to generate a first load prediction model.

[0137] According to an embodiment of the present invention, preferably, the solar energy storage prediction strategy includes:

[0138] Combining the photovoltaic predicted power, load predicted power data and actual sampled power data, and using a preset energy storage operation mode switching method, generate energy storage charging and discharging power or electricity plans for different electricity price time periods under various operation scenarios;

[0139] Active power of the energy storage system is regulated according to the charging and discharging plan.

[0140] By collecting and combining relevant data such as photovoltaic, load and energy storage power, and sending this data to the preset energy storage operation mode switching method, energy storage charging and energy storage discharge power or electricity plans for different electricity price time periods under various operating scenarios are generated. This can achieve reasonable allocation of energy storage according to usage, thereby improving utilization.

[0141] From the above description, it can be seen that this application achieves the following technical effects:

[0142] In an embodiment of the present application, a method of generating an energy storage scheduling strategy through human-computer interaction is adopted, by presetting a first load forecasting model; obtaining first user input information; inputting the first user input information into the model for learning to generate a first user electricity consumption behavior model; inputting the prediction result of the first user electricity consumption behavior model and the result of the load forecast into the model for learning to generate a second load forecasting model; outputting an energy storage scheduling strategy based on the result of the second load forecast, thereby achieving the purpose of convenient information interaction and generation of energy storage scheduling strategies, thereby achieving the technical effect of setting different system performance maintenance strategies according to customer needs, and further solving the problem that the existing energy storage mode is single and cannot provide multiple application modes for users to choose from, and thus cannot be switched in time and effectively according to changes in application scenarios, resulting in a poor user experience; at the same time, there is a lack of convenient human-computer interaction methods, resulting in a technical problem of delayed information interaction.

[0143] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for switching an energy storage operation mode is provided. As shown in FIG2 , the device for switching an energy storage operation mode comprises:

[0144] A preset module 10 is used to preset a first load forecasting model;

[0145] By presetting the first load model, the load can be predicted, thereby obtaining basic prediction information.

[0146] An input module 20 is configured to obtain first user input information;

[0147] The app collects the first user's actual energy storage needs or personal electricity usage habits through voice, text, etc. For example, "I am going out tomorrow, please adjust the optimal energy storage mode." The app collects the real-time natural voice and feeds it back to the processor for information input, thereby achieving good real-time information interaction effects and providing a data basis for subsequent accurate information correction.

[0148] A first learning module 30 is configured to input the first user input information into a learning model to generate a first user electricity usage behavior model;

[0149] By processing and analyzing the input information of the first user through the large language model and generating a first electricity usage behavior model, accurate user electricity usage behavior can be obtained, thereby providing a data basis for subsequent information correction.

[0150] A second learning module 40 is configured to input the prediction result of the first user electricity consumption behavior model and the prediction result of the first load forecasting model into a model for learning to generate a second load forecasting model;

[0151] By sending the predicted results of the first load forecasting model and the predicted results of the first user electricity consumption behavior model to the large language model for deep learning, a second load forecasting model is generated. It has higher accuracy and can combine the load and the user's electricity consumption habits to give a high-precision second load forecasting model, so as to flexibly meet the actual electricity consumption needs and thus improve the user experience.

[0152] Output module 50, used to output energy storage scheduling strategy based on the result of the second load forecast

[0153] It can output accurate energy storage scheduling strategies, so that they can be more in line with actual usage scenarios.

[0154] From the above description, it can be seen that this application achieves the following technical effects:

[0155] In an embodiment of the present application, a method of generating an energy storage scheduling strategy through human-computer interaction is adopted, by presetting a first load forecasting model; obtaining first user input information; inputting the first user input information into the model for learning to generate a first user electricity consumption behavior model; inputting the prediction result of the first user electricity consumption behavior model and the result of the load forecast into the model for learning to generate a second load forecasting model; outputting an energy storage scheduling strategy based on the result of the second load forecast, thereby achieving the purpose of convenient information interaction and generation of energy storage scheduling strategies, thereby achieving the technical effect of setting different system performance maintenance strategies according to customer needs, and further solving the problem that the existing energy storage mode is single and cannot provide multiple application modes for users to choose from, and thus cannot be switched in time and effectively according to changes in application scenarios, resulting in a poor user experience; at the same time, there is a lack of convenient human-computer interaction methods, resulting in a technical problem of delayed information interaction.

[0156] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the energy storage operation mode switching method when running.

[0157] Computer readable storage medium:

[0158] If the module integrated into the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the above-mentioned steps of displaying the above-mentioned memory power consumption optimization and processing the memory power consumption optimization.

[0159] The term "computer program" includes computer program code, which may be in source code, object code, executable file, or some intermediate form. Computer-readable media may include any entity or device capable of carrying computer program code, recording media, USB flash drives, removable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunications signals, and software distribution media. It should be noted that the content of computer-readable media may be appropriately expanded or reduced based on the requirements of legislation and patent practice within a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals or telecommunications signals.

[0160] One embodiment of the present application further provides an electronic device for storing the energy storage operation mode switching method. The electronic device includes: a memory and a processor, wherein the memory stores a computer program, wherein the processor is configured to execute the computer program to perform the energy storage operation mode switching method.

[0161] Obviously, those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computing device. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computing device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0162] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all fall within the scope of protection of the present invention.

Claims

1. A method for switching an energy storage operation mode, characterized in that: include: S101, presetting a first load forecasting model: receiving first data, wherein the first data includes photovoltaic forecast power, load forecast power data, actual sampled power data, daily electricity schedule, meteorological data, electricity price forecast data, data on energy storage system capacity percentage, parameters of each aggregation unit of the power station and distribution network parameters, or inputting the first data into a neural network model for training to generate a first load forecasting model, or extracting entities from the first data, and constructing a knowledge graph with reference to the mapping relationship between the entity and the load to generate a first load forecasting model; S102: Acquire first user input information, where the first user input information includes voice input, QR code scanning, or text input; S103, inputting the first user input information into a large language model for learning, to generate a first user electricity usage behavior model; S104: inputting the prediction result of the first user power consumption behavior model and the prediction result of the first load prediction model into a large language model for learning to generate a second load prediction model; S105, obtaining the working data of the photovoltaic system and inputting it into the second load prediction model to obtain the result of the second load prediction, and outputting the energy storage scheduling strategy according to the result of the second load prediction.

2. The energy storage operation mode switching method according to claim 1, characterized in that: The energy storage dispatching strategy includes: Charging pile prediction strategy, heat pump prediction strategy, economic priority prediction strategy and off-grid priority prediction strategy.

3. The energy storage operation mode switching method according to claim 2, characterized in that: The process of outputting the charging pile prediction strategy according to the result of the second load prediction includes: Obtain data on photovoltaic power generation, photovoltaic predicted power, charging pile charging power, charging pile predicted power and energy storage system capacity percentage; Perform charging and discharging management according to the photovoltaic power generation, the photovoltaic predicted power, the charging pile charging power, the charging pile predicted power, and the state of charge of the energy storage system; When the photovoltaic power generation power is greater than the charging power of the charging pile, and the state of charge of the energy storage system is less than the preset value A, If it is during the peak period of electricity consumption, photovoltaic power generation will charge the charging pile and the energy storage system. When the state of charge of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment will stop charging; If it is in the level usage period and the off-peak period, photovoltaic power generation charges the charging pile, and the excess photovoltaic power generation and the power grid simultaneously replenish the energy storage system. If the charge state of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment stops charging.

4. The energy storage operation mode switching method according to claim 3 is characterized in that: The data on photovoltaic power generation power, charging pile charging power and energy storage system capacity are obtained in real time through an energy controller, wherein the photovoltaic power generation power meter is the sum of the power generation efficiency of all photovoltaics in the area, the charging pile charging power meter is the sum of the charging efficiency of all charging piles in the area, and the energy storage system charge state meter is the average value of the charge state of each battery pack in the area.

5. The energy storage operation mode switching method according to claim 2, characterized in that: The process of outputting the heat pump prediction mode strategy according to the result of the second load prediction includes: Obtain data on photovoltaic power generation, photovoltaic predicted power, heat pump charging power, heat pump predicted power and energy storage system capacity percentage, and Charging and discharging are managed based on the pump charging power, heat pump predicted power, and the charge state of the energy storage system.

6. The energy storage operation mode switching method according to claim 2, characterized in that: The process of outputting the economic priority forecasting strategy according to the result of the second load forecasting includes: Calculate the peak-shaving cost of distributed photovoltaics with energy storage, including: the opportunity cost of distributed photovoltaics, the cost of purchasing electricity when charging energy storage, and the operation and maintenance cost of energy storage; Calculate the peak-shaving benefits of distributed photovoltaics with energy storage, including: peak-shaving compensation benefits and energy storage electricity benefits; Establish an economic benefit model for analyzing the peak-shaving provided by distributed photovoltaics with energy storage. According to the constraints of the model, maximize the objective function of the model to calculate the economic benefits of distributed photovoltaics with energy storage participating in peak-shaving. Based on the peak-shaving costs, peak-shaving benefits and the economic benefits of distributed photovoltaics with energy storage participating in peak-shaving, a distributed photovoltaic peak-shaving control strategy with energy storage is formulated.

7. The energy storage operation mode switching device is characterized in that: include: A preset module, used for presetting a first load forecasting model; An input module, used to obtain first user input information; A first learning module, configured to input the first user input information into a large language model for learning, and generate a first user power consumption behavior model; a second learning module, configured to input the prediction result of the first user power consumption behavior model and the prediction result of the first load prediction model into a large language model for learning, so as to generate a second load prediction model; The output module obtains the working data of the photovoltaic system and inputs it into the second load prediction model to obtain the result of the second load prediction, and is used to output the energy storage scheduling strategy according to the result of the second load prediction.

8. The energy storage operation mode switching device according to claim 7, characterized in that: The energy storage dispatching strategy includes: Charging pile prediction strategy, heat pump prediction strategy, economic priority prediction strategy and off-grid priority prediction strategy.

9. The energy storage operation mode switching method according to claim 8, characterized in that: The process of outputting the charging pile prediction strategy according to the result of the second load prediction includes: Obtain data on photovoltaic power generation, photovoltaic predicted power, charging pile charging power, charging pile predicted power and energy storage system capacity percentage; Perform charging and discharging management according to the photovoltaic power generation, the photovoltaic predicted power, the charging pile charging power, the charging pile predicted power, and the state of charge of the energy storage system; When the photovoltaic power generation power is greater than the charging power of the charging pile, and the state of charge of the energy storage system is less than the preset value A, If it is during the peak period of electricity consumption, photovoltaic power generation will charge the charging pile and the energy storage system. When the state of charge of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment will stop charging; If it is in the level usage period and the off-peak period, photovoltaic power generation charges the charging pile, and the excess photovoltaic power generation and the power grid simultaneously replenish the energy storage system. If the charge state of the energy storage system is greater than or equal to the preset value A, the energy storage system equipment stops charging.

10. The energy storage operation mode switching method according to claim 8, characterized in that: The data on photovoltaic power generation power, charging pile charging power and energy storage system capacity are obtained in real time through an energy controller, wherein the photovoltaic power generation power meter is the sum of the power generation efficiency of all photovoltaics in the area, the charging pile charging power meter is the sum of the charging efficiency of all charging piles in the area, and the energy storage system charge state meter is the average value of the charge state of each battery pack in the area.

11. The energy storage operation mode switching method according to claim 8, characterized in that: The process of outputting the heat pump prediction mode strategy according to the result of the second load prediction includes: Obtain data on photovoltaic power generation power, photovoltaic predicted power, heat pump charging power, heat pump predicted power and energy storage system capacity percentage, and perform charging and discharging management based on the relationship between photovoltaic power generation power, photovoltaic predicted power, heat pump charging power, heat pump predicted power and energy storage system charge state.

12. The energy storage operation mode switching method according to claim 8, characterized in that: The process of outputting the economic priority forecasting strategy according to the result of the second load forecasting includes: Calculate the peak-shaving cost of distributed photovoltaics with energy storage, including: the opportunity cost of distributed photovoltaics, the cost of purchasing electricity when charging energy storage, and the operation and maintenance cost of energy storage; Calculate the peak-shaving benefits of distributed photovoltaics with energy storage, including: peak-shaving compensation benefits and energy storage electricity benefits; Establish an economic benefit model for analyzing the peak-shaving provided by distributed photovoltaics with energy storage. According to the constraints of the model, maximize the objective function of the model to calculate the economic benefits of distributed photovoltaics with energy storage participating in peak-shaving. According to the peak-shaving cost, peak-shaving income and the economic benefits of distributed photovoltaics with energy storage participating in peak-shaving, To take advantage of the benefits, a distributed photovoltaic peak-shaving control strategy with energy storage is formulated.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the energy storage operation mode switching method according to any one of claims 1 to 6 when running.

14. Electronic equipment, including: A memory and a processor, characterized in that a computer program is stored in the memory, wherein the processor is configured to run the computer program to execute the energy storage operation mode switching method described in any one of claims 1 to 6.

Citation Information

Cited By

  • Urban distributed energy storage scheduling method and system based on charging stations

    CN119182133A

  • Power supply scheduling method, device and equipment based on photovoltaic energy storage and medium

    CN119182227A

  • Urban demand side novel load resource scheduling system and method

    CN119204586A

  • Battery energy storage management system based on photovoltaic power generation

    CN119315680A

  • Wind-light-electricity energy storage flexible coordination optimization method and system

    CN119448282A