Thermal energy storage control information determination method and device, computer equipment and readable storage medium

Abstract

The invention relates to a thermal energy storage control information determination method and device, computer equipment and a computer readable storage medium. The method comprises the following steps: acquiring meteorological information corresponding to a target area, building types of buildings in the target area, respective heat energy demand characteristics of the buildings, power grid load information corresponding to the target area and electricity price information; inputting the meteorological information, the building type and the heat energy demand characteristics into a pre-trained first model, and obtaining target heat energy storage load information corresponding to each building output by the first model; inputting the target heat energy storage load information, the power grid load information and the electricity price information into a pre-trained second model, and obtaining target heat energy storage control information which is output by the second model and aims at each building; the target thermal energy storage control information is used for performing thermal energy storage control on each building. By adopting the method, the accuracy of determining the thermal energy storage control information can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of energy, and particularly to a method, device, computer device, computer-readable storage medium and computer program product for determining thermal energy storage control information. Background Art

[0002] The heat storage device converts electric energy into heat energy for storage, so as to facilitate subsequent provision of heat energy, such as heating, for schools, factories, etc. At the same time, Renewable Energy Sources (RES) are gradually replacing traditional fossil fuel power generation units, and establishing a clean power system dominated by RES is an inevitable trend of the future energy system. However, due to the intermittency and uncertainty of RES, large-scale integration of RES makes power dispatching more complex, which requires flexible regulation of the power grid. Through thermal energy storage control, energy can be stored when the electricity price is low and used when the electricity price is high, thereby reducing the pressure of power demand during peak hours and improving the flexibility of power grid regulation. However, the accuracy of thermal energy storage control information in the prior art is poor, thus affecting the efficient utilization of energy. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, computer-readable storage medium and computer program product for determining thermal energy storage control information to improve the accuracy of determining thermal energy storage control information.

[0004] In a first aspect, the present application provides a method for determining thermal energy storage control information, including:

[0005] Obtain the meteorological information corresponding to the target area, the building types to which each building in the target area belongs, the thermal energy demand characteristics of each building, the grid load information corresponding to the target area, and the electricity price information;

[0006] Input the meteorological information, the building types and thermal energy demand characteristics corresponding to each building into a pre-trained first model for thermal energy storage demand prediction, and obtain the target thermal energy storage load information corresponding to each building output by the first model;

[0007] Input the target thermal energy storage load information, the grid load information, and the electricity price information into a pre-trained second model for thermal energy storage control prediction, and obtain the target thermal energy storage control information for each building output by the second model; the target thermal energy storage control information is used for thermal energy storage control for each building.

[0008] In one embodiment, the first model includes multiple thermal energy storage load prediction models, where one thermal energy storage load prediction model corresponds to one building type;

[0009] Input meteorological information, the building types corresponding to each building, and the thermal energy demand characteristics into a pre-trained first model for predicting the thermal energy storage demand, and obtain the target thermal energy storage load information corresponding to each building output by the first model, including:

[0010] Determine the thermal energy storage load prediction model corresponding to the building type in the first model as the target thermal energy storage load prediction model; and,

[0011] Input meteorological information and thermal energy demand characteristics into the target thermal energy storage load prediction model for predicting the thermal energy storage demand, and obtain the target thermal energy storage load information corresponding to the building output by the target thermal energy storage load prediction model.

[0012] In one embodiment, the building types include residential buildings, commercial buildings, public buildings, and industrial buildings;

[0013] Determining the thermal energy storage load prediction model corresponding to the building type in the first model as the target thermal energy storage load prediction model includes:

[0014] Input the building type into a third model, and obtain the target thermal energy storage load prediction model corresponding to the building type output by the third model.

[0015] In one embodiment, input the target thermal energy storage load information, grid load information, and electricity price information into a pre-trained second model for predicting thermal energy storage control, and obtain the target thermal energy storage control information for each building output by the second model, including:

[0016] Obtain the thermal energy storage control preference; the thermal energy storage control preference includes at least one of the economic benefit priority preference, comfort priority preference, or load priority preference;

[0017] Input the thermal energy storage control preference, the target thermal energy storage load information corresponding to each building, grid load information, and electricity price information into the second model for predicting thermal energy storage control, and obtain the target thermal energy storage control information for each building output by the second model.

[0018] In one embodiment, the above method further includes:

[0019] In the case where the thermal energy storage control preference includes at least two of the economic benefit priority preference, comfort priority preference, and load priority, obtain the preference weights corresponding to each preference in the thermal energy storage control preference;

[0020] Input the thermal energy storage control preference, the target thermal energy storage load information corresponding to each building, grid load information, and electricity price information into the second model for predicting thermal energy storage control, and obtain the target thermal energy storage control information for each building output by the second model, including:

[0021] Input the heat energy storage control preference, preference weight, target heat energy storage load information corresponding to each building, grid load information, and electricity price information into the second model to determine the preference heat energy storage control information corresponding to each preference in the heat energy storage control preference, and determine the target heat energy storage control information for each building based on the preference heat energy storage control information and preference weight.

[0022] In one embodiment, the above method further includes:

[0023] Update the meteorological information, building type, heat energy demand characteristics, grid load information, and electricity price information based on a preset period;

[0024] Update the target heat energy storage load information according to the updated meteorological information, building type, and heat energy demand characteristics;

[0025] Update the target heat energy storage control information according to the updated target heat energy storage load information, updated grid load information, and electricity price information.

[0026] In one embodiment, the above method further includes: controlling the release and replenishment of the heat energy storage corresponding to each building according to the target heat energy storage control information.

[0027] In a second aspect, the present application also provides a device for determining heat energy storage control information, including:

[0028] An acquisition module, configured to acquire meteorological information corresponding to a target area, building types to which each building in the target area belongs, heat energy demand characteristics of each building, grid load information corresponding to the target area, and electricity price information;

[0029] A demand prediction module, which inputs the meteorological information, building types corresponding to each building, and heat energy demand characteristics into a pre-trained first model for heat energy storage demand prediction, and obtains the target heat energy storage load information corresponding to each building output by the first model;

[0030] A storage control module, configured to input the target heat energy storage load information, grid load information, and electricity price information into a pre-trained second model for heat energy storage control prediction, and obtain the target heat energy storage control information for each building output by the second model; the target heat energy storage control information is used for heat energy storage control for each building.

[0031] In a third aspect, the present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in the first aspect are implemented.

[0032] Fourthly, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0033] Fifthly, the present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0034] For the above method, device, computer equipment, computer-readable storage medium and computer program product for determining thermal energy storage control information, by inputting meteorological information, building type and thermal energy demand characteristics into the first model to obtain target thermal energy storage load information. Since meteorological information, building type and thermal energy demand characteristics are taken as consideration factors and the first model is used for predicting thermal energy storage demand, this helps to improve the accuracy of the target thermal energy storage load information. By inputting the target thermal energy storage load information, grid load information and electricity price information into the second model to obtain target thermal energy storage control information for thermal energy storage control of each building. Since the accuracy of the target thermal energy storage load information is better, and combined with grid load information and electricity price information, and the second model is used for predicting thermal energy storage control, the target thermal energy storage control information is made more accurate. Description of the Drawings

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required to be used in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 It is a schematic flowchart of a method for determining thermal energy storage control information in an embodiment;

[0037] Figure 2 It is another schematic flowchart of a method for determining thermal energy storage control information in an embodiment;

[0038] Figure 3 It is a schematic diagram of thermal load demands corresponding to different building types in an embodiment;

[0039] Figure 4 It is a schematic diagram of the principle of a thermal energy storage dynamic load prediction and distribution decision-making system in an embodiment;

[0040] Figure 5 It is yet another schematic flowchart of a method for determining thermal energy storage control information in an embodiment;

[0041] Figure 6Schematic diagram of a possible BP algorithm model in an embodiment;

[0042] Figure 7 Schematic diagram of a possible heat load prediction curve in an embodiment;

[0043] Figure 8 Structural block diagram of a heat energy storage control information determination device in an embodiment;

[0044] Figure 9 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0045] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. As used herein, the term "a plurality" may include more than two, and may also include two, unless otherwise specified.

[0046] The heat energy storage load, that is, the heat energy storage demand, can be understood as specifically referring to the demand for electric energy in the heating direction. In the power system, the load corresponds to the normal power consumption on the user side. However, in the electrified heating system, during normal power consumption, the heat storage device converts electric energy into heat energy for advance storage. The heat energy storage load can be understood as specifically referring to the demand for electric energy in the heating direction.

[0047] The planning, construction and operation of the global energy system are undergoing a huge transformation, due to reasons such as increasing energy demand, energy shortage and environmental protection. The proportion of renewable energy sources (RES) in primary energy continues to rise, gradually replacing traditional fossil fuel power generation units. Establishing a RES-dominated clean power system is an inevitable trend for the future energy system. However, due to the intermittency and uncertainty of RES, large-scale integration of RES makes power dispatch more complex, and the demand for flexible regulation resources also increases accordingly. Urban energy consumption has risen due to rapid urbanization, resulting in an increasingly prominent contradiction between energy demand and fluctuating supply. Improving flexibility only on the supply side cannot meet the development needs of the energy system. It is necessary to enhance the flexibility of both the demand side and the supply side simultaneously. As an alternative, demand response (DR) improves the regulation flexibility of the system through supply-demand interaction. Buildings may play a key role in future DR mechanisms because they account for 40% of global energy consumption, especially higher in developed countries. With urbanization and the decarbonization of the heating sector, the proportion of energy consumption of electrified heating systems, such as heat pumps, has increased, making the coupling between electricity and heat in buildings closer.

[0048] Thermal energy storage is closely related to demand response. Thermal energy storage can store energy when electricity demand is low and release it during peak demand, thus balancing the grid load. By participating in demand response, the thermal energy storage system can store energy when electricity prices are low and use it when prices are high, thereby reducing the pressure on electricity demand during peak hours and enhancing the flexibility of grid regulation.

[0049] Currently, thermal energy storage load forecasting methods mainly rely on traditional statistical models and empirical algorithms. For example, the linear regression model based on historical data. With the improvement of computing power, more complex models have emerged, such as physical models and thermodynamics models, which consider the thermal characteristics of buildings, climate conditions, and usage patterns. However, these methods often prove insufficient in the face of complex load changes and seasonal factors and are difficult to accurately reflect the diverse needs of different building users. Although some studies have started to apply machine learning techniques, there is still a lack of dynamic forecasting capabilities tailored to specific seasonal and regional characteristics.

[0050] The Back-propagation algorithm is a multi-layer feedforward network trained according to the error backpropagation algorithm and is one of the most widely used neural network models. The BP neural network is a multi-level neural network whose structure includes an input layer, hidden layer, and output layer. Each neuron in each layer is independent, and neurons between layers are interconnected by neural lines that can be assigned different weights. Data propagates backward from the input layer and hidden layer. As the input signal changes continuously, the neural network will continuously update the weights and thresholds of the network model. Through self-learning, the error of the final result is continuously reduced. The BP neural network is mostly used in algorithm estimation, pattern recognition, function approximation, classification, etc. It can fit any non-linear function.

[0051] In terms of thermal load forecasting and decision control, since the relationship between input and output parameters is non-linear and difficult to calculate directly, using the self-learning ability of neural networks to extract complex features and trends from a large amount of historical data can effectively improve the accuracy and efficiency of load forecasting. However, the existing technology has not fully applied neural networks to the dynamic forecasting of thermal energy storage loads and the optimization of their energy distribution strategies.

[0052] Currently, the dynamic load forecasting of thermal energy storage faces the following deficiencies:

[0053] (1) The accuracy needs to be improved: Traditional statistical models and empirical algorithms are difficult to predict the thermal load changes of different buildings, especially in central areas with a large population. The building types vary greatly, and the demand differences of different buildings at the same time period are large, resulting in prediction errors.

[0054] (2) Poor flexibility: Existing technologies usually lack the ability to dynamically adjust according to the characteristics of different building users and cannot respond in real time to changes in user needs, thus affecting the efficient utilization of energy storage resources.

[0055] (3) Slow response speed: Traditional methods often require a long time for data processing and prediction and cannot quickly adapt to rapidly changing energy demands, resulting in untimely energy distribution.

[0056] Based on the above analysis, the technical solution of this application applies neural network-related technologies to the dynamic prediction of thermal energy storage load and the optimization of its energy distribution strategy. Specifically, in the aspect of thermal energy storage load prediction and decision control, considering that the relationship between input and output parameters is non-linear and difficult to directly calculate, the self-learning ability of the neural network is utilized to extract complex features and trends from a large amount of historical data, and dynamic prediction can be carried out according to specific seasonal and regional characteristics to improve the accuracy and efficiency of thermal energy storage load prediction. The technical solution provided by this application will be further described below by way of examples:

[0057] In one embodiment, as Figure 1 shown, a method for determining thermal energy storage control information is provided. In this embodiment, an example is given where this method is applied to a server. It can be understood that this method can also be applied to a system including a terminal and a server. Exemplarily, this method can also be applied to a thermal energy storage system, a thermal energy storage control system, an electrified heating system, etc. In this embodiment, this method includes steps S101 to S103:

[0058] Step S101: The server obtains the meteorological information corresponding to the target area, the building types to which the buildings in the target area belong, the thermal energy demand characteristics of each building, the grid load information corresponding to the target area, and the electricity price information.

[0059] Among them, the target area may include an area of one or more buildings. In some embodiments, the target area may be determined starting from at least one of geographical longitude and latitude, administrative division, building cluster, etc.

[0060] Among them, the meteorological information may include information characterizing the current meteorological situation of the target area. Of course, it may also include information characterizing the meteorological situation of the target area at a future time. In some embodiments, the meteorological information may also include information characterizing the meteorological situation of the target area at a historical time.

[0061] Among them, the building may be a building with a thermal energy demand.

[0062] In some embodiments, the building type can be determined based on the use of the building. For example, the building type can include medical buildings and non-medical buildings. Another example is that the building type can include residential buildings and non-residential buildings, etc.

[0063] Among them, the heat energy demand characteristic can characterize the characteristics related to the building's demand for heat energy supply.

[0064] In some embodiments, the heat energy demand characteristic can include a first heat energy demand characteristic and a second heat energy demand characteristic. Among them, the first heat energy demand characteristic is determined based on the building's own architectural structure. For example, for a building with a relatively thick wall thickness and good heat insulation effect, the first heat energy demand characteristic can be characterized as a relatively low corresponding heat energy demand; the second heat energy demand characteristic is determined based on the user information in the building. For example, for a building used for elderly care, the user information in the building indicates that the users are mainly the elderly, and such users have a relatively high demand for warmth. Therefore, the second heat energy demand characteristic can be characterized as a relatively high corresponding heat energy demand.

[0065] In some embodiments, the heat energy demand characteristic can be obtained by weighted summation of the first heat energy demand characteristic and the second heat energy demand characteristic.

[0066] Among them, the power grid load information can characterize the load situation of the power network in the target area. In some embodiments, since heat energy storage is achieved by converting electrical energy into heat energy for storage, this will affect the power grid load.

[0067] In some embodiments, for meteorological information, building type, heat energy demand characteristic, power grid load information, and electricity price information, the server can obtain them in real time or at a preset period, such as every hour, every day, etc.

[0068] Step S102: The server inputs the meteorological information, the building type and the heat energy demand characteristic corresponding to each building into a pre-trained first model for heat energy storage demand prediction, and obtains the target heat energy storage load information corresponding to each building output by the first model.

[0069] Among them, the first model can be an artificial intelligence model. Exemplarily, the first model can be a model obtained based on the backpropagation algorithm.

[0070] In some embodiments, step S102 may include: The server inputs meteorological information, the building type corresponding to each building, and the thermal energy demand characteristics into a pre-trained first model for predicting the thermal energy storage demand, and obtains the first thermal energy storage load information corresponding to each building output by the first model; and, the server inputs meteorological information, thermal energy demand characteristics, grid load information, and electricity price information into a pre-trained fourth model for predicting the thermal energy storage demand, and obtains the second thermal energy storage load information corresponding to each building output by the fourth model; The server determines the target thermal energy storage load information corresponding to each building according to the first thermal energy storage load information and the second thermal energy storage load information.

[0071] Exemplarily, based on the fourth model, the first model may add the input of "building type" to determine the thermal energy storage load information based on different building types.

[0072] Thus, the server can comprehensively determine the target thermal energy storage load information through the first thermal energy storage load information output by the first model and the second thermal energy storage load information output by the fourth model, thereby improving the accuracy of the target thermal energy storage load information.

[0073] Step S103: The server inputs the target thermal energy storage load information, grid load information, and electricity price information into a pre-trained second model for predicting thermal energy storage control, and obtains the target thermal energy storage control information for each building output by the second model; The target thermal energy storage control information is used to control the thermal energy storage for each building.

[0074] In some embodiments, the server may also input a constraint function or a limiting condition, etc. into the second model to constrain the thermal energy storage control prediction of the second model, so as to realize the limitation of the target thermal energy storage control information to meet diverse actual needs.

[0075] In some embodiments, the second model may generate initial thermal energy storage control information for each building according to the target thermal energy storage load information, grid load information, and electricity price information. Among them, the same building may correspond to multiple initial thermal energy storage control information, and the multiple initial thermal energy storage control information corresponding to the same building may be obtained based on different constraint functions or limiting conditions. The second model may determine the target thermal energy storage control information according to the multiple initial thermal energy storage control information.

[0076] In the above technical solution, by inputting meteorological information, building type, and thermal energy demand characteristics into the first model to obtain target thermal energy storage load information. Since meteorological information, building type, and thermal energy demand characteristics are taken as consideration factors and the first model is used for thermal energy storage demand prediction, this helps to improve the accuracy of the target thermal energy storage load information. By inputting the target thermal energy storage load information, grid load information, and electricity price information into the second model to obtain target thermal energy storage control information for thermal energy storage control of each building. Since the accuracy of the target thermal energy storage load information is better, and combined with grid load information and electricity price information, and the second model is used for thermal energy storage control prediction, the target thermal energy storage control information is made more accurate.

[0077] In one embodiment, the aforementioned first model may include multiple thermal energy storage load prediction models. Among them, one thermal energy storage load prediction model may correspond to one building type. The aforementioned "inputting meteorological information, the building type corresponding to each building, and thermal energy demand characteristics into the pre-trained first model for thermal energy storage demand prediction to obtain the target thermal energy storage load information corresponding to each building output by the first model" may include: The server determines the thermal energy storage load prediction model corresponding to the building type in the first model as the target thermal energy storage load prediction model. And inputting meteorological information and thermal energy demand characteristics into the target thermal energy storage load prediction model for thermal energy storage demand prediction to obtain the target thermal energy storage load information corresponding to the building output by the target thermal energy storage load prediction model.

[0078] Exemplarily, for each building type, a corresponding thermal energy storage load prediction model may be pre-trained. Based on this, the server can input meteorological information and thermal energy demand characteristics into the thermal energy storage load prediction model corresponding to the building type in the first model, so as to obtain the target thermal energy storage load information.

[0079] In some embodiments, the thermal energy storage load prediction model may be a model trained based on the backpropagation algorithm.

[0080] The above technical solution determines the target thermal energy storage load information by inputting meteorological information and thermal energy demand characteristics into the thermal energy storage load prediction model corresponding to the building type, which helps to improve the determination efficiency of the target thermal energy storage load information.

[0081] In one embodiment, the aforementioned "building type" may include residential buildings, commercial buildings, public buildings, and industrial buildings. The aforementioned "determining the thermal energy storage load prediction model corresponding to the building type in the first model as the target thermal energy storage load prediction model" may include: The server inputs the building type into the third model to obtain the target thermal energy storage load prediction model corresponding to the building type output by the third model.

[0082] Exemplarily, as described above, since different building types can correspond to different thermal energy storage load prediction models, it is necessary to find the corresponding thermal energy storage load prediction model according to the building type. For this purpose, a third model can be pre-trained to find the corresponding thermal energy storage load prediction model according to the building type.

[0083] In some embodiments, the first model may include a third model and multiple thermal energy storage load prediction models. Correspondingly, the server can input meteorological information, building type, and thermal energy demand characteristics into the first model, and automatically identify the target thermal energy storage load prediction model through the third model in the first model, so as to obtain the target thermal energy storage load information.

[0084] The above technical solution determines the thermal energy storage load prediction model corresponding to the building type in the first model through the third model, which helps to improve the efficiency and accuracy of determining the target thermal energy storage load information.

[0085] In one of the embodiments, the foregoing "inputting the target thermal energy storage load information, grid load information, and electricity price information into the pre-trained second model for thermal energy storage control prediction to obtain the target thermal energy storage control information for each building output by the second model", as Figure 2 shown, may include steps S201 to S202:

[0086] Step S201: The server obtains the thermal energy storage control preference; the thermal energy storage control preference includes at least one of economic benefit priority preference, comfort priority preference, or load priority preference.

[0087] In some embodiments, the thermal energy storage control preference may characterize the preference of relevant personnel, platforms, or institutional regulations responsible for thermal energy storage control for thermal energy storage control strategies. Exemplarily, the economic benefit priority preference may characterize that economic benefits are given priority in the process of controlling thermal energy storage. The same applies to the comfort priority preference and load priority, etc. Among them, comfort can characterize the comfort provided by the building to users achieved through thermal energy storage control for building heating; load can characterize the load of the power system in the process of converting electric energy into thermal energy storage.

[0088] Step S202: The server inputs the thermal energy storage control preference, the target thermal energy storage load information corresponding to each building, the grid load information, and the electricity price information into the second model for thermal energy storage control prediction to obtain the target thermal energy storage control information for each building output by the second model.

[0089] In some embodiments, the second model may use the thermal energy storage control preference as a constraint for determining the target thermal energy storage control information, and construct an objective function for determining the thermal energy storage control information based on the target thermal energy storage load information, grid load information, and electricity price information. Then, the target thermal energy storage control information is obtained by solving according to the constraint and the objective function. Exemplarily, the Lagrange multiplier method may be used for solving.

[0090] By taking the thermal energy storage control preference as one of the consideration factors, the above technical solution enables the determined target thermal energy storage control information to conform to the thermal energy storage control preference, such as achieving better economic benefits, etc., so that the target thermal energy storage control information better meets the actual thermal energy storage control requirements.

[0091] In one embodiment, the above method further includes: when the thermal energy storage control preference includes at least two of economic benefit priority preference, comfort priority preference, and load priority, obtaining the preference weights corresponding to each preference in the thermal energy storage control preference; the above-mentioned "inputting the thermal energy storage control preference, the target thermal energy storage load information corresponding to each building, grid load information, and electricity price information into the second model for thermal energy storage control prediction, and obtaining the target thermal energy storage control information for each building output by the second model" may further include: the server inputs the thermal energy storage control preference, preference weights, the target thermal energy storage load information corresponding to each building, grid load information, and electricity price information into the second model to determine the preference thermal energy storage control information corresponding to each preference in the thermal energy storage control preference, and determines the target thermal energy storage control information for each building based on the preference thermal energy storage control information and the preference weights.

[0092] In some embodiments, in practice, there may be more than one type of thermal energy storage control preference. For example, the actual demand for thermal energy storage control may be that both economic benefits and good comfort are required, and the thermal energy storage control preference includes both economic benefit priority preference and comfort priority preference. In this regard, the server can use the preference weights to synthesize different preferences and determine the target thermal energy storage control information by balancing each preference.

[0093] In some embodiments, the preference weights may be input into the server manually. For example, the server may send a preference weight acquisition request message to the management personnel through the thermal energy storage control platform or system and receive the preference weight information sent by the management personnel.

[0094] The above technical solution synthesizes different preferences through the preference weights and determines the target thermal energy storage control information by balancing each preference, so as to meet the requirements of multiple thermal energy storage control preferences and make the target thermal energy storage control information better meet the actual thermal energy storage control requirements.

[0095] In one embodiment, the above method further includes: updating meteorological information, building type, thermal energy demand characteristics, grid load information, and electricity price information based on a preset period; updating the target thermal energy storage load information according to the updated meteorological information, building type, and thermal energy demand characteristics; and updating the target thermal energy storage control information according to the updated target thermal energy storage load information, updated grid load information, and electricity price information.

[0096] In some embodiments, the preset period can be customized based on actual needs. For example, it can be one minute, one hour, one day, etc.

[0097] In some embodiments, the server can determine the respective change ranges of the meteorological information, building type, thermal energy demand characteristics, grid load information, and electricity price information before and after the update. In the case where the change range is greater than the preset change range, the target thermal energy storage load information is updated according to the updated meteorological information, building type, and thermal energy demand characteristics; and the target thermal energy storage control information is updated according to the updated target thermal energy storage load information, updated grid load information, and electricity price information. This can prevent the system from being overly sensitive to changes in information such as meteorological information, thereby avoiding the impact caused by incorrect changes in the above information, and at the same time reducing the computational amount and avoiding frequent updates.

[0098] Exemplarily, the meteorological information before the update includes that the current temperature is 13 degrees Celsius and the predicted temperature for tomorrow is 10 degrees Celsius, the preset period is 3 hours, the updated meteorological information includes that the current temperature is 12 degrees Celsius and the predicted temperature for tomorrow is 11 degrees Celsius, and the change range of the current temperature (1 degree Celsius) is less than the preset change range (5 degrees Celsius), and the same applies to the predicted temperature for tomorrow. If the change ranges of the building type, thermal energy demand characteristics, grid load information, and electricity price information before and after the update are not greater than the preset change range, the server may not update the target thermal energy storage load information and the target thermal energy storage control information.

[0099] The above technical solution updates information such as meteorological information, building type, thermal energy demand characteristics, grid load information, and electricity price information periodically, thereby realizing the update of the target thermal energy storage control information, which ensures the real-time accuracy of the target thermal energy storage control information.

[0100] In one embodiment, the above method further includes: the server controls the release and replenishment of the thermal energy storage corresponding to each building according to the target thermal energy storage control information.

[0101] Exemplarily, the server can issue instructions related to the release and replenishment of the thermal energy storage to the corresponding thermal energy storage device according to the target thermal energy storage control information, so as to replenish when the electricity price is low and release when the electricity price is high, thereby reducing the power demand pressure during peak hours.

[0102] By controlling the release and replenishment of the thermal energy storage corresponding to each building according to the target thermal energy storage control information, the grid load can be balanced and the regulation flexibility of the grid can be improved.

[0103] In an exemplary embodiment, a thermal energy storage dynamic load prediction and allocation decision-making system is provided. Through neural network learning, the thermal energy storage load in a specific season of a region (i.e., the target region) is dynamically predicted. In some embodiments, the system can execute the above-mentioned method for determining the thermal energy storage control information. As Figure 3 shown, the building types in the target region can be basically divided into 4 types: residential buildings; commercial buildings; public buildings and industrial buildings. Among them, due to different social divisions of labor participated by different building types, the thermal load demands are also different. According to the user behaviors of different buildings in the region, this application dynamically allocates and adjusts the energy storage allocation strategy. As Figure 4 shown, the corresponding schematic diagram of the principle is given. The specific implementation method is mainly divided into a training module and a decision module, aiming to realize the prediction of the thermal energy storage demands of different buildings in the region through the training and verification of the neural network model, and dynamically optimize the energy storage allocation strategy according to the user characteristics. Specifically as follows:

[0104] Regarding the training module: The training module is mainly responsible for learning and training the database through the neural network based on the collected historical data, and training and verifying two network models based on historical data such as weather and building usage information. The specific process is as follows:

[0105] 1. Data collection and preprocessing: Through channels such as the meteorological bureau website, building internal sensors, and data interfaces, collect weather data (such as temperature, humidity, sunshine conditions, etc.) in a specific season within 1 to 3 years, building internal personnel flow data, and building thermal load data. The input data is historical weather data, historical personnel flow data, and building structure data; the output data is the corresponding thermal load data. Standardize the collected data (such as normalization and denoising) to improve the accuracy of neural network training.

[0106] 2. Neural network model construction and training: Use deep neural network training to establish two independent neural networks, a prediction model (the first model) and a decision model (the second model). The prediction model is used to learn the non-linear relationship between the input of historical data and the thermal load output, while the decision model is used to optimize the control strategy according to the prediction results. During the training process, the backpropagation algorithm is used to continuously adjust the network parameters, and the goal is to minimize the loss function such as the mean square error MSE.

[0107] 3. Model Verification and Optimization: Verify the prediction model and decision model using 20% of the new historical data. By comparing the predicted results output by the model with the actual historical data, judge the accuracy of the model. If the output verification results are close to the 20% historical data, it is considered a successful verification and output to the next step. If the verification results are not satisfactory, readjust the model parameters or optimize the data features of the training set.

[0108] Regarding the decision module: The decision module receives the demand curve data and, through neural network learning, independently judges and adjusts the optimal control strategy suitable for each building. The specific process is as follows:

[0109] 1. Real-time Data Collection and Prediction: Based on the two black-box models (prediction model and decision model) verified by the training module, collect the real-time data of the day, such as weather and temperature (i.e., the corresponding meteorological information mentioned above), and personnel flow data (used to determine the thermal energy demand mentioned above), etc. The data collection frequency is at 30-minute intervals and input into the prediction model. The prediction model updates and predicts the heat load data of each building every 30 minutes (corresponding to the target thermal energy storage load information mentioned above). The prediction results in this step will be stored in the temporary database for further processing.

[0110] 2. Prediction Result Processing and Optimization: Input the predicted curves of each building (corresponding to the target thermal energy storage load information mentioned above) into the decision model. The decision model, through the adaptive learning function of the neural network, combines real-time electricity prices, building user characteristics, and other relevant data to independently generate an optimized control strategy to maximize the utilization rate of thermal energy storage and reduce energy costs. This process takes into account various complex factors such as seasonal fluctuations and user behavior patterns to achieve the best scheduling strategy.

[0111] Among them, the control strategies can be divided into the following types:

[0112] 1. Priority on Enterprise-side Economic Benefits: Under the strategy of giving priority to economic benefits, the control focus of the system is to help enterprises maximize economic returns and reduce operating costs. This strategy will give priority to optimizing the cost of energy use. For example, store energy during low electricity price periods (such as at night) and release energy during high electricity price periods (such as during the day or peak electricity consumption) to reduce the total cost using electricity price fluctuations. At the same time, the system will also dynamically adjust the energy release strategy of thermal energy storage according to the actual electricity demand and load prediction of the building to reduce the electricity procurement demand during peak periods. The control system in this mode can, through the analysis of the neural network on the changing trend of electricity prices, independently judge the priority of economic benefits and dynamically adjust the energy release and storage strategies, enabling enterprises to minimize energy consumption costs while meeting the thermal energy needs of users.

[0113] 2. User-side comfort priority: In the control strategy with user comfort as the top priority, the system formulates the distribution and release strategies of thermal energy storage based on the user's comfort requirements to ensure the stability of temperature and humidity in the building. The control system combines multi-dimensional data such as user activities, indoor-outdoor temperature difference, and human comfort index, and predicts the changing trend of user needs through a neural network model, so as to arrange the release and replenishment of energy storage in advance. This strategy is particularly suitable for applications in scenarios with dense user flow or temperature sensitivity (such as hospitals, residential buildings, etc.). The system can also automatically identify the differences in habits and needs of different users to adjust the distribution of thermal energy storage, enabling each building to reasonably allocate heat according to the demand characteristics of different groups of people. In addition, on the basis of energy conservation and without affecting user comfort, the system optimizes the time and intensity of thermal energy storage release to ensure the stability and comfort of the internal environment of the building.

[0114] 3. Grid-side load priority: Under the strategy of grid-side load priority, the core goal of the system is to cooperate with the load demand of the grid and help balance the supply and demand relationship of the grid. Especially during the peak period of grid load, the system will give priority to using the thermal energy storage equipment in the building to share the grid load, thus reducing the dependence on external power resources. The system will analyze and optimize the control strategy through a neural network based on the real-time load status of the grid, the predicted power load curve, and the energy usage requirements of each building. During the low-load period of electricity consumption, the thermal energy storage is replenished, and during the peak-load period, heat energy is released to relieve the pressure on the grid. While taking into account the stability of the grid, this strategy can also improve the utilization efficiency of energy storage, avoid power shortages during peak periods, and promote the reasonable distribution of energy and load balance. This mode can adapt to the fluctuations of regional energy demand and ensure the stability and efficient operation of the regional power system.

[0115] As shown in the following table, the advantages and disadvantages corresponding to the three strategy types of economic benefit priority, comfort priority, and load priority are given.

[0116]

[0117]

[0118] Reference Figure 5 As shown, the specific operation process corresponding to the above technical solution, that is, the process of the thermal energy storage control information determination method, may include steps S501 to S504:

[0119] Step S501: Collect basic historical data and input it into the neural network for learning. Specifically:

[0120] Collect weather data for fixed seasons within 1 to 3 years, building internal personnel flow data, and heat load data through channels such as calculations, meteorological bureau websites, and building internal sensors. The input data is historical weather data (including temperature, humidity, sunshine conditions, etc.), historical personnel flow data, and building structure data, and the output data is the corresponding heat load data. Use the BP neural network to learn the data in the training set. The BP neural network learning algorithm is mainly divided into two parts: forward propagation and backward propagation. Forward propagation corresponds to the input signal, and backward propagation corresponds to the expected value and error.

[0121] Regarding forward propagation, as Figure 6 shown, a schematic diagram of a possible BP algorithm model is provided. Assume that there are j inputs xj in the input layer, and the input net i (input1 i ) for the i-th node in the hidden layer is:

[0122] where

[0123] M represents the total number of j;

[0124] w ij is the network weight between the input layer of the network and the hidden layer of the network;

[0125] w ki is the network weight between the hidden layer of the network and the output layer of the network;

[0126] θ i and a k are the thresholds of the neurons in the hidden layer and the output layer;

[0127] The output oi of the i-th node in the hidden layer is: i as follows:

[0128] oi = f(input1i);

[0129] The input net k (input2 k ) for the k-th node in the output layer is:

[0130]

[0131] The output o k of the k-th node in the output layer is:

[0132]

[0133] Regarding backpropagation: By calculating the error between the outputs of all neurons in the output layer and the actual values, the weights and thresholds of the network parameters w are adjusted. By finding the reciprocals of the weights and thresholds of each layer of neurons with respect to the error, it is determined how to correct the parameters. Then, different data is used to repeat the training until the error meets the requirements, and the training is completed to obtain a black-box model for the input and output data.

[0134] Step S502: Verify the two trained network models.

[0135] Specifically, 20% of the new historical data can be used to verify the two network models. The prediction model is used to check the prediction accuracy of future heat loads, and the decision model is used to generate control strategies based on the predicted data. The input data of the test data is input into the trained neural network black-box model, and the corresponding result intervals output by the model are compared with the output results in the training set. According to different projects, an arbitrary error range D, such as 1%, is set. Calculate the total difference Dsum between the model output result and the output data of the historical data, and find the average value Dmean.

[0136] If Dmean > D, it means that the accuracy of the trained model is low, and the training data needs to be updated and the model continues to be trained.

[0137] If Dmean < D, it means that the model error is within the acceptable range, and the model is output to Step Three.

[0138] Step S503: Input the real-time data into the verified prediction model to obtain a prediction curve.

[0139] Specifically, based on the two black-box models verified in Step Two, real-time weather data, user data, and demand data are collected. The data collection frequency is 30 minutes. These data are input into the prediction model to obtain the heat load prediction curves of each building for a period of time in the future. Refer to Figure 7 , and this prediction result will be used as the basis for subsequent optimization of the control strategy.

[0140] Step S504: Input the prediction curve into the decision model to output the optimal control strategy.

[0141] Specifically, the prediction curves of each building can be input into the decision black-box model. The decision model dynamically adjusts among three decision-making schemes according to the heat load data set updated every 30 minutes and the real-time electricity price to maximize the utilization rate of the regional heat storage energy and optimize the energy economic benefits. The output of the strategy is displayed through a graphical user interface and is available for relevant decision-makers to refer to and execute.

[0142] Due to the following features of the above technical solution: 1. By adopting the neural network method, it can effectively cope with the non-linear characteristics of building thermal loads and improve the accuracy of prediction. 2. A method for real-time dynamic adjustment strategy is proposed, which helps to optimize the control efficiency and cost of the energy storage system. 3. Through continuous iterative update of deep learning, it realizes the adaptive adjustment of the demand characteristics of different buildings in the region and improves the energy utilization rate. 4. It has a flexible decision-making method considering multiple constraints. Therefore, it has the following effects: 1. Higher accuracy: By learning complex non-linear relationships through neural networks, the accuracy of load prediction is improved. 2. Stronger flexibility: It can dynamically adjust the energy storage allocation strategy according to the user characteristics and real-time demands of different buildings. 3. Faster response speed: Real-time data acquisition and prediction mechanism ensure that the system can quickly respond to changes in energy demand. 4. Better comprehensive benefits: It achieves dynamic balance among multiple objectives, reduces energy costs, and improves user comfort and grid stability.

[0143] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limitation, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0144] Based on the same inventive concept, the embodiments of the present application also provide a thermal energy storage control information determination device for implementing the above-mentioned thermal energy storage control information determination method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the thermal energy storage control information determination device provided below can refer to the limitations on the thermal energy storage control information determination method in the above text, and will not be repeated here.

[0145] In an exemplary embodiment, as Figure 8 shown, a thermal energy storage control information determination device 800 is provided, including:

[0146] An acquisition module 801, configured to acquire meteorological information corresponding to a target area, building types to which each building in the target area belongs, thermal energy demand characteristics of each building, grid load information corresponding to the target area, and electricity price information;

[0147] A demand prediction module 802 is configured to input meteorological information, the building types corresponding to each building, and the thermal energy demand characteristics into a pre-trained first model for predicting the thermal energy storage demand, and obtain the target thermal energy storage load information corresponding to each building output by the first model.

[0148] A energy storage control module 803 is configured to input the target thermal energy storage load information, grid load information, and electricity price information into a pre-trained second model for predicting the thermal energy storage control, and obtain the target thermal energy storage control information for each building output by the second model; the target thermal energy storage control information is used to control the thermal energy storage for each building.

[0149] In one embodiment, the first model includes multiple thermal energy storage load prediction models, where one thermal energy storage load prediction model corresponds to one building type; the demand prediction module 802 is further configured to input meteorological information, the building types corresponding to each building, and the thermal energy demand characteristics into the pre-trained first model for predicting the thermal energy storage demand, and obtain the target thermal energy storage load information corresponding to each building output by the first model, including: determining the thermal energy storage load prediction model corresponding to the building type in the first model as the target thermal energy storage load prediction model; and inputting the meteorological information and the thermal energy demand characteristics into the target thermal energy storage load prediction model for predicting the thermal energy storage demand, and obtaining the target thermal energy storage load information corresponding to the building output by the target thermal energy storage load prediction model.

[0150] In one embodiment, the building types include residential buildings, commercial buildings, public buildings, and industrial buildings; the demand prediction module 802 is further configured to determine the thermal energy storage load prediction model corresponding to the building type in the first model as the target thermal energy storage load prediction model, including: inputting the building type into a third model, and obtaining the target thermal energy storage load prediction model corresponding to the building type output by the third model.

[0151] In one embodiment, the energy storage control module 803 is further configured to input the target thermal energy storage load information, grid load information, and electricity price information into the pre-trained second model for predicting the thermal energy storage control, and obtain the target thermal energy storage control information for each building output by the second model, including: obtaining the thermal energy storage control preference; the thermal energy storage control preference includes at least one of an economic benefit priority preference, a comfort priority preference, or a load priority preference; inputting the thermal energy storage control preference, the target thermal energy storage load information corresponding to each building, grid load information, and electricity price information into the second model for predicting the thermal energy storage control, and obtaining the target thermal energy storage control information for each building output by the second model.

[0152] In one embodiment, the energy storage control module 803 is further configured to, when the thermal energy storage control preference includes at least two of the economic benefit priority preference, the comfort priority preference, and the load priority, obtain the preference weights corresponding to the respective preferences in the thermal energy storage control preference; input the thermal energy storage control preference, the target thermal energy storage load information corresponding to each building, the grid load information, and the electricity price information into a second model for thermal energy storage control prediction, and obtain the target thermal energy storage control information for each building output by the second model, including: inputting the thermal energy storage control preference, the preference weights, the target thermal energy storage load information corresponding to each building, the grid load information, and the electricity price information into the second model to determine the preference thermal energy storage control information corresponding to each preference in the thermal energy storage control preference, and determining the target thermal energy storage control information for each building based on the preference thermal energy storage control information and the preference weights.

[0153] In one embodiment, the energy storage control module 803 is further configured to update the meteorological information, the building type, the thermal energy demand characteristics, the grid load information, and the electricity price information based on a preset period; update the target thermal energy storage load information according to the updated meteorological information, the building type, and the thermal energy demand characteristics; and update the target thermal energy storage control information according to the updated target thermal energy storage load information, the updated grid load information, and the electricity price information.

[0154] In one embodiment, the energy storage control module 803 is further configured to control the release and replenishment of the thermal energy storage corresponding to each building according to the target thermal energy storage control information.

[0155] Each module in the above thermal energy storage control information determination device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form so that the processor can call and execute the operations corresponding to the above respective modules.

[0156] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 9As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data required for implementing the method for determining thermal energy storage control information, such as meteorological information, etc. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for determining thermal energy storage control information.

[0157] Those skilled in the art can understand that Figure 9 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0158] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0159] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0160] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0161] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, a database, or other media used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, Resistive RandomAccess Memory (ReRAM), MagnetoresistiveRandomAccess Memory (MRAM), Ferroelectric RandomAccess Memory (FRAM), Phase Change Memory (PCM), graphene memory, etc. Volatile memory can include Random Access Memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as Static RandomAccess Memory (SRAM) or Dynamic RandomAccess Memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, Artificial Intelligence (AI) processors, etc., without limitation.

[0162] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0163] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for determining thermal energy storage control information, characterized in that The method includes: Obtaining meteorological information corresponding to the target area, the building types to which each building in the target area belongs, the thermal energy demand characteristics of each building, the power grid load information corresponding to the target area, and electricity price information; Inputting the meteorological information, the building types corresponding to each building, and the thermal energy demand characteristics into a pre-trained first model for predicting the thermal energy storage demand, and obtaining the target thermal energy storage load information corresponding to each building output by the first model; Inputting the target thermal energy storage load information, the power grid load information, and the electricity price information into a pre-trained second model for predicting the thermal energy storage control, and obtaining the target thermal energy storage control information for each building output by the second model; the target thermal energy storage control information is used for controlling the thermal energy storage for each building.

2. The method according to claim 1, wherein The first model includes multiple thermal energy storage load prediction models, where one thermal energy storage load prediction model corresponds to one building type; The step of inputting the meteorological information, the building types corresponding to each building, and the thermal energy demand characteristics into a pre-trained first model for predicting the thermal energy storage demand, and obtaining the target thermal energy storage load information corresponding to each building output by the first model includes: Determining the thermal energy storage load prediction model corresponding to the building type in the first model as the target thermal energy storage load prediction model; and Inputting the meteorological information and the thermal energy demand characteristics into the target thermal energy storage load prediction model for predicting the thermal energy storage demand, and obtaining the target thermal energy storage load information corresponding to the building output by the target thermal energy storage load prediction model.

3. The method according to claim 2, wherein The building types include residential buildings, commercial buildings, public buildings, and industrial buildings; The step of determining the thermal energy storage load prediction model corresponding to the building type in the first model as the target thermal energy storage load prediction model includes: Inputting the building type into a third model, and obtaining the target thermal energy storage load prediction model corresponding to the building type output by the third model.

4. The method according to claim 1, characterized in that, The step of inputting the target thermal energy storage load information, the power grid load information, and the electricity price information into a pre-trained second model for predicting the thermal energy storage control, and obtaining the target thermal energy storage control information for each building output by the second model includes: Obtaining the thermal energy storage control preference; the thermal energy storage control preference includes at least one of the economic benefit priority preference, the comfort priority preference, or the load priority preference; Inputting the thermal energy storage control preference, the target thermal energy storage load information corresponding to each building, the power grid load information, and the electricity price information into the second model for predicting the thermal energy storage control, and obtaining the target thermal energy storage control information for each building output by the second model.

5. The method according to claim 4, wherein The method further includes: In the case where the thermal energy storage control preference includes at least two of the economic benefit priority preference, the comfort priority preference, and the load priority, obtaining the preference weights corresponding to each preference in the thermal energy storage control preference; Inputting the thermal energy storage control preference, the target thermal energy storage load information corresponding to each building, the power grid load information, and the electricity price information into a second model for thermal energy storage control prediction to obtain the target thermal energy storage control information for each building output by the second model, including: Inputting the thermal energy storage control preference, the preference weight, the target thermal energy storage load information corresponding to each building, the power grid load information, and the electricity price information into a second model to determine the preference thermal energy storage control information corresponding to each preference in the thermal energy storage control preference, and determining the target thermal energy storage control information for each building based on the preference thermal energy storage control information and the preference weight.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Updating the meteorological information, the building type, the thermal energy demand characteristics, the power grid load information, and the electricity price information based on a preset period; Updating the target thermal energy storage load information according to the updated meteorological information, the building type, and the thermal energy demand characteristics; Updating the target thermal energy storage control information according to the updated target thermal energy storage load information, the updated power grid load information, and the electricity price information.

7. The method according to any one of claims 1 to 5, characterized in that The method further includes: Controlling the release and replenishment of the thermal energy storage corresponding to each building according to the target thermal energy storage control information.

8. A device for determining thermal energy storage control information, characterized in that, The device includes: An acquisition module, configured to acquire the meteorological information corresponding to a target area, the building types to which the buildings in the target area belong, the respective thermal energy demand characteristics of the buildings, the power grid load information corresponding to the target area, and the electricity price information; A demand prediction module, configured to input the meteorological information, the building types corresponding to the buildings, and the thermal energy demand characteristics into a pre-trained first model for thermal energy storage demand prediction to obtain the target thermal energy storage load information corresponding to each building output by the first model; A storage control module, configured to input the target thermal energy storage load information, the power grid load information, and the electricity price information into a pre-trained second model for thermal energy storage control prediction to obtain the target thermal energy storage control information for each building output by the second model; the target thermal energy storage control information is used for thermal energy storage control for each building.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images