Auxiliary power generation method and device based on super-high temperature fluidization energy storage device

Abstract

The application provides an auxiliary power generation method and device based on an ultrahigh-temperature fluidized energy storage device, the method comprising the following steps: estimating the load power of a power grid in a future time period after a current time; obtaining the predicted power generation power of a power plant in the future time period; obtaining the current temperature of the ultrahigh-temperature fluidized energy storage device; obtaining the starting time of the future time period; in the case that the predicted power generation power is less than the load power, estimating the target heat release time and the target heat release rate of the ultrahigh-temperature fluidized energy storage device according to the predicted power generation power, the load power, the current temperature, the current time and the starting time; controlling the ultrahigh-temperature fluidized energy storage device to start continuously releasing heat energy at the target heat release rate at the target heat release time, and assisting the power plant to generate power, so that when the starting time is reached, the actual power generation power of the power plant is greater than or equal to the load power, and the power plant can generate power to meet the demand of the user end for power when it just enters the peak period of the power grid load.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computers, and particularly relates to an auxiliary power generation method and device based on an ultrahigh-temperature fluidized energy storage device, an electronic device and a storage medium. BACKGROUND

[0002] With the development of industry and technology, and with the continuous improvement of people's living standards, electric energy plays an increasingly important role in people's life and work.

[0003] At present, power plants usually generate electricity, transmit the electricity to a power grid, and the power grid transmits the electricity to a user end for use.

[0004] However, it is found through statistics that the load of the power grid has a peak period and a valley period. For example, during the valley period of the load of the power grid, the electricity consumption of the user end decreases, that is, the load of the power grid decreases, and during the peak period of the load of the power grid, the electricity consumption of the user end increases, that is, the load of the power grid increases. The amount of electricity generated by the power plant is usually maintained at a stable state. Therefore, during the peak period of the load of the power grid, the electricity may not be enough, and during the valley period of the load of the power grid, the electricity may be wasted.

[0005] Therefore, there is a demand for peak shaving and valley filling. The main purpose of peak shaving and valley filling is to increase the load of the power grid by fully utilizing electricity and other means during the valley period of the load of the power grid, or to assist the power plant in generating more electricity during the peak period of the load of the power grid to ensure that the amount of electricity can meet the use demand of the user end. SUMMARY

[0006] The present application shows an auxiliary power generation method and device based on an ultrahigh-temperature fluidized energy storage device, an electronic device and a storage medium.

[0007] In a first aspect, the present application shows an auxiliary power generation method based on an ultrahigh-temperature fluidized energy storage device. The heat output port of the ultrahigh-temperature fluidized energy storage device and the heat output port of the boiler of a power plant converge to a comprehensive heat output port, and the heat output by the comprehensive heat output port is used to heat the working medium of the power plant. The method comprises the following steps.

[0008] Estimating the load power of the power grid in a future time period after a current time; obtaining the predicted power generation power of the power plant in the future time period; obtaining the current temperature of the ultrahigh-temperature fluidized energy storage device; obtaining the starting time of the future time period; and the current time is earlier than the starting time.

[0009] In the case that the predicted power generation is less than the load power, a target heat release time and a target heat release rate of the super-high-temperature fluidized energy storage device are estimated according to the predicted power generation, the load power, the current temperature, the current time and the starting time; the target heat release time is earlier than the starting time; in the case that the super-high-temperature fluidized energy storage device releases heat at the target heat release rate at the target heat release time, the actual power generation of the power plant is greater than or equal to the load power when the starting time is reached.

[0010] The super-high-temperature fluidized energy storage device is controlled to start continuous heat release at the target heat release rate at the target heat release time to assist the power plant in power generation.

[0011] In an optional implementation, the estimating of the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage device according to the predicted power generation, the load power, the current temperature, the current time and the starting time comprises:

[0012] A power difference between the load power and the predicted power generation is obtained;

[0013] A time length between the starting time and the current time is calculated;

[0014] The predicted power generation, the load power, the current temperature, the current time, the starting time, the power difference and the time length are all input into a trained estimation model, so that the estimation model processes the predicted power generation, the load power, the current temperature, the current time, the starting time, the power difference and the time length to obtain the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage device.

[0015] In an optional implementation, the method further comprises:

[0016] A plurality of training data sets are obtained;

[0017] One training data set comprises sample data and labeled data;

[0018] The sample data comprises a real load power of a power grid in a sample time period, a real power generation of the power plant in the sample time period, a sample time length between a starting time and a sample time of the sample time period, a sample temperature of the super-high-temperature fluidized energy storage device at the sample time, and a sample difference between the real load power and the real power generation; the real load power is greater than the real power generation; the sample time is earlier than the starting time of the sample time period;

[0019] The labeled data comprises a labeled heat release time of the super-high-temperature fluidized energy storage and release device and a labeled heat release rate of the super-high-temperature fluidized energy storage and release device; the labeled heat release time is later than the sample time and earlier than a starting time of the sample time period;

[0020] obtaining a to-be-trained model;

[0021] training the to-be-trained model based on the plurality of training data sets until parameters in the to-be-trained model converge, thereby obtaining an estimation model.

[0022] In an optional implementation, the training of the to-be-trained model based on the plurality of training data sets comprises:

[0023] processing the sample data based on the to-be-trained model to obtain an estimated heat release rate and an estimated heat release time of the super-high-temperature fluidized energy storage and release device;

[0024] obtaining a heat release rate loss value according to the estimated heat release rate and the labeled heat release rate, and obtaining a heat release time loss value according to the estimated heat release time and the labeled heat release time;

[0025] obtaining a comprehensive loss value according to the heat release rate loss value and the heat release time loss value;

[0026] adjusting parameters in the to-be-trained model according to the comprehensive loss value.

[0027] In a second aspect, the present application shows an auxiliary power generation device based on a super-high-temperature fluidized energy storage and release device, a heat output port of the super-high-temperature fluidized energy storage and release device and a heat output port of a boiler of a power plant converge to a comprehensive heat output port, and heat output by the comprehensive heat output port is used to heat a working medium of the power plant; the device comprises:

[0028] an obtaining module, configured to obtain a load power of a power grid in a future time period after a current time; obtain a predicted power generation power of the power plant in the future time period; obtain a current temperature of the super-high-temperature fluidized energy storage and release device; obtain a starting time of the future time period; the current time is earlier than the starting time;

[0029] an estimation module, configured to, in a case where the predicted power generation power is less than the load power, estimate a target heat release time and a target heat release rate of the super-high-temperature fluidized energy storage and release device according to the predicted power generation power, the load power, the current temperature, the current time and the starting time; the target heat release time is earlier than the starting time; wherein, in a case where the super-high-temperature fluidized energy storage and release device releases heat at the target heat release rate at the target heat release time, the actual power generation power of the power plant is greater than or equal to the load power when the starting time is reached.

[0030] a control module configured to control the super-high-temperature fluidized energy storage device to start continuous heat release at the target heat release time and at the target heat release rate to assist the power plant in generating power.

[0031] In an optional implementation, the estimation module comprises:

[0032] a first obtaining unit configured to obtain a power difference between the load power and the predicted power generation power;

[0033] a calculation unit configured to calculate a time length between the start time and the current time;

[0034] a processing unit configured to input the predicted power generation power, the load power, the current temperature, the current time, the start time, the power difference, and the time length into a trained estimation model, so that the trained estimation model processes the predicted power generation power, the load power, the current temperature, the current time, the start time, the power difference, and the time length to obtain the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage device.

[0035] In an optional implementation, the estimation module further comprises:

[0036] a second obtaining unit configured to obtain a plurality of training data sets;

[0037] one training data set comprises sample data and labeled data;

[0038] the sample data comprises a real load power of a power grid in a sample time period, a real power generation power of the power plant in the sample time period, a sample time length between a start time and a sample time of the sample time period, a sample temperature of the super-high-temperature fluidized energy storage device at the sample time, and a sample difference between the real load power and the real power generation power; the real load power is greater than the real power generation power; and the sample time is earlier than the start time of the sample time period;

[0039] the labeled data comprises a labeled heat release time of the super-high-temperature fluidized energy storage device and a labeled heat release rate of the super-high-temperature fluidized energy storage device; the labeled heat release time is later than the sample time and earlier than the start time of the sample time period;

[0040] a third obtaining unit configured to obtain a to-be-trained model;

[0041] a training unit configured to train the to-be-trained model based on the plurality of training data sets until parameters in the to-be-trained model converge, thereby obtaining an estimation model.

[0042] In an optional implementation, the training unit comprises:

[0043] a processing subunit, configured to process the sample data based on the to-be-trained model, to obtain an estimated heat release rate and an estimated heat release time of the super-high-temperature fluidization energy storage device;

[0044] a first obtaining subunit, configured to obtain a heat release rate loss value according to the estimated heat release rate and a labeled heat release rate, and obtain a heat release time loss value according to the estimated heat release time and a labeled heat release time;

[0045] a second obtaining subunit, configured to obtain a comprehensive loss value according to the heat release rate loss value and the heat release time loss value;

[0046] an adjusting subunit, configured to adjust parameters in the to-be-trained model according to the comprehensive loss value.

[0047] In a third aspect, the present application shows an electronic device, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the method according to any one of the preceding aspects.

[0048] In a fourth aspect, the present application shows a non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the method according to any one of the preceding aspects.

[0049] In a fifth aspect, the present application shows a computer program product, when the instructions in the computer program product are executed by the processor of the electronic device, the electronic device can execute the method according to any one of the preceding aspects.

[0050] The technical scheme provided by the present application can include the following beneficial effects:

[0051] In the present application, the load power of the power grid in a future time period after a current time is estimated. The estimated power generation power of a power plant in the future time period is obtained. The current temperature of the super-high-temperature fluidized energy storage and release device is obtained. The starting time of the future time period is obtained. In the case where the estimated power generation power is less than the load power, the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage and release device are estimated according to the estimated power generation power, the load power, the current temperature, the current time, and the starting time. The target heat release time is earlier than the starting time. Wherein, in the case where the super-high-temperature fluidized energy storage and release device releases heat at the target heat release rate at the target heat release time, the actual power generation power of the power plant is greater than or equal to the load power when the starting time is reached. The super-high-temperature fluidized energy storage and release device is controlled to start continuous heat release at the target heat release rate at the target heat release time to assist the power plant in power generation.

[0052] By the present application, the actual power generation power of the power plant can be greater than or equal to the load power when the starting time is reached, so that the power generation of the power plant can meet the demand of the user end for power when the peak of the grid load is just reached. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 is a step flow chart of an auxiliary power generation method based on a super-high-temperature fluidized energy storage and release device of the present application.

[0054] Figure 2 is a structural block diagram of an auxiliary power generation device based on a super-high-temperature fluidized energy storage and release device of the present application.

[0055] Figure 3 is a block diagram of an electronic device of the present application.

[0056] Figure 4 is a block diagram of an electronic device of the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0058] In order to achieve the purpose of peak clipping and valley filling, during the valley period of the load of the power grid, the super-high-temperature fluidized energy storage and release device can store heat in the thermal energy storage tank by the unused electric energy in the power grid (for example, store the electric energy converted into heat energy), to achieve the purpose of increasing the load during the valley period of the load of the power grid and the purpose of storing energy (for example, storing the electric energy converted into heat energy).

[0059] After the peak of the grid load, the super-high-temperature fluidized energy storage device releases the heat stored in the heat storage tank, and the released heat is used to fuse with the heat generated by the boiler of the power plant. The fused heat heats the working substance (e.g., water or water vapor, or a mixture of water vapor, or other substances, etc.) of the power plant, and the heated mixture enters the steam turbine to assist in driving the steam turbine to rotate, thereby assisting in increasing the kinetic energy of the steam turbine, and further assisting in driving the generator to generate more electric energy, thereby increasing the power generation of the power plant, and further increasing the amount of electricity delivered to the grid to make up for the problem that the amount of electricity generated by the power plant cannot meet the demand of the user end for electricity.

[0060] After entering the peak of the grid load, the super-high-temperature fluidized energy storage device releases the heat stored in the heat storage tank to assist the power plant in generating electricity by the released heat, thereby increasing the amount of electricity generated by the power plant to meet the demand of the user end for electricity as much as possible.

[0061] However, the inventor found that the process of releasing heat to assist the power plant in generating more electric energy takes a period of time, which will result in a gap between the time when the super-high-temperature fluidized energy storage device releases the heat stored in the heat storage tank to assist the power plant in generating electricity by the released heat and the time when the amount of electricity generated by the power plant can meet the demand of the user end for electricity. If the super-high-temperature fluidized energy storage device releases the heat stored in the heat storage tank to assist the power plant in generating electricity by the released heat at the time when the peak of the grid load is just entered, there will be a gap after the time when the peak of the grid load is just entered, and the amount of electricity generated by the power plant cannot meet the demand of the user end for electricity in this gap.

[0062] Therefore, how to make the amount of electricity generated by the power plant meet the demand of the user end for electricity at the time when the peak of the grid load is just entered is a technical problem to be solved.

[0063] Therefore, in order to solve the above problems, the technical scheme of the present application is proposed.

[0064] Specifically, referring to Figure 1 , a step flow chart of an auxiliary power generation method based on a super-high-temperature fluidized energy storage device is shown, the heat output port of the super-high-temperature fluidized energy storage device and the heat output port of the boiler of the power plant converge to a comprehensive heat output port, the heat output by the comprehensive heat output port is used to heat the working substance of the power plant, and the heated mixture enters the steam turbine to assist in driving the steam turbine to rotate, thereby assisting in increasing the kinetic energy of the steam turbine, and further assisting in driving the generator to generate more electric energy.

[0065] The method is applied to an electronic device, which can include a control terminal of an ultra-high temperature fluidized energy storage device.

[0066] The method includes:

[0067] In step S101, the load power of the power grid in a future time period after the current time is estimated. The estimated power generation of the power plant in the future time period is obtained. The current temperature of the ultra-high temperature fluidized energy storage device is obtained. The starting time of the future time period is obtained.

[0068] The current time is earlier than the starting time.

[0069] The load power of the power grid in the future time period after the current time can be estimated using the currently existing estimation method, and the specific estimation method is not limited in the application.

[0070] In one embodiment, the historical load of the power grid in a historical time period before the current time can be obtained, and the current load of the power grid in a current time period in which the current time is located can be obtained. The historical additional electricity-related event in the historical time period in the power consumption area supplied by the power grid is obtained, and the current additional electricity-related event in the current time period in the power consumption area is obtained. The future additional electricity-related event in the future time period in the power consumption area is obtained. The historical weather data of the power consumption area in the historical time period is obtained, and the current weather data of the power consumption area in the current time period is obtained. The future weather data of the power consumption area in the future time period is obtained. The historical calendar data of the historical time period is obtained, and the current calendar data of the current time period is obtained. The future calendar data of the future time period is obtained. The historical electricity price in the historical time period in the power consumption area supplied by the power grid is obtained, and the current electricity price in the current time period in the power consumption area is obtained. The future electricity price in the future time period in the power consumption area is obtained. The historical load, the current load, the historical additional electricity-related event, the current additional electricity-related event, the future additional electricity-related event, the historical weather data, the current weather data, the future weather data, the historical calendar data, the current calendar data, the future calendar data, the historical electricity price, the current electricity price, and the future electricity price are all input into the power grid load power prediction model, so that the power grid load prediction model processes (such as cooperatively processes) the historical load, the current load, the historical additional electricity-related event, the current additional electricity-related event, the future additional electricity-related event, the historical weather data, the current weather data, the future weather data, the historical calendar data, the current calendar data, the future calendar data, the historical electricity price, the current electricity price, and the future electricity price, to obtain the load power of the power grid in the future time period after the current time.

[0071] The power plant can include a thermal power plant, etc.

[0072] The predicted power generation of the power plant in the future time period is directly provided by the power plant.

[0073] The predicted power generation of the power plant in the future time period can be understood as: the predicted power generation of the power plant in the future time period without the assistance of the super-high-temperature fluidized energy storage and release device, and the predicted power generation of the power plant in the future time period is irrelevant to the factors of the super-high-temperature fluidized energy storage and release device.

[0074] The predicted power generation of the power plant in the future time period can be directly obtained by the control system of the power plant.

[0075] The current temperature of the super-high-temperature fluidized energy storage and release device can be directly measured, and the current temperature of the super-high-temperature fluidized energy storage and release device can be understood as: the temperature of the energy storage medium in the thermal energy storage tank of the super-high-temperature fluidized energy storage and release device at the current time.

[0076] The load power of the power grid refers to the total of the electric power consumed by all power users (including industrial users, commercial users, and residential users, etc.) in the power grid. The size of the load power of the power grid directly reflects the power demand situation of the power grid.

[0077] The time is divided into time periods according to the time, and the time length of each time period can be the same, for example, the time length of a time period includes 1 hour, 2 hours, 3 hours, 6 hours, 12 hours, 24 hours, 36 hours, 48 hours, 72 hours, 7 days, 14 days, or one month, etc., and the ending time of the previous time period and the starting time of the next time period are adjacent.

[0078] The time period in which the current time is located is the current time period, and the time period adjacent to the current time period and located after the current time period is the future time period.

[0079] In step S102, in the case that the predicted power generation is less than the load power, the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage and release device are estimated according to the predicted power generation, the load power, the current temperature, the current time, and the starting time.

[0080] The target heat release time is earlier than the starting time. In the case that the super-high-temperature fluidized energy storage and release device releases heat at the target heat release rate at the target heat release time, the actual power generation of the power plant is greater than or equal to the load power when the starting time is reached.

[0081] In one embodiment, the case that the super-high-temperature fluidized energy storage and release device releases heat at the target heat release rate at the target heat release time can be understood as: during the heat release process, the heat release rate is continuously the target heat release rate, that is, uniform release.

[0082] In one embodiment of the present application, in the case that the predicted power generation is greater than or equal to the load power, it indicates that the predicted power generation of the power plant in the future time period can meet the load power of the power grid in the future time period, and can meet the demand of the user end for electricity in the future time period. Therefore, the super-high-temperature fluidized energy storage device does not need to assist the power plant to generate electricity, and the process can be ended.

[0083] Alternatively, in another embodiment of the present application, in the case that the predicted power generation is less than the load power, it indicates that the predicted power generation of the power plant in the future time period cannot meet the load power of the power grid in the future time period, and cannot meet the demand of the user end for electricity in the future time period. Therefore, the super-high-temperature fluidized energy storage device needs to assist the power plant to generate electricity, and steps S102 and S103 can be performed.

[0084] In one embodiment, in the present application, the prediction model is trained in advance, and the specific training process includes:

[0085] Obtain a plurality of training data sets.

[0086] One training data set includes sample data and labeled data.

[0087] The sample data includes the real load power of the power grid in the sample time period, the real power generation of the power plant in the sample time period, the sample time length between the start time of the sample time period and the sample time, the sample temperature of the super-high-temperature fluidized energy storage device at the sample time, the sample time being earlier than the start time of the sample time period, and the sample difference between the real load power and the real power generation. The real load power is greater than the real power generation. The sample time is earlier than the start time of the sample time period.

[0088] Among different training data sets, the sample data is different. The sample data being different can be specifically understood as: for any two sample data, at least one of the real load power, the real power generation, the sample time length, the sample temperature, and the sample difference is different.

[0089] The real power generation of the power plant in the sample time period is directly provided by the power plant.

[0090] The real power generation of the power plant in the sample time period can be understood as the real power generation of the power plant in the sample time period without the assistance of the super-high-temperature fluidized energy storage device. The real power generation of the power plant in the sample time period is independent of the factors of the super-high-temperature fluidized energy storage device.

[0091] The labeled data includes a labeled heat release time of the super-high-temperature fluidized energy storage and release device and a labeled heat release rate of the super-high-temperature fluidized energy storage and release device. The labeled heat release time is later than the sample time and earlier than the start time of the sample time period.

[0092] The labeled heat release time of the super-high-temperature fluidized energy storage and release device is an actual, real heat release time of the super-high-temperature fluidized energy storage and release device.

[0093] The labeled heat release rate of the super-high-temperature fluidized energy storage and release device is an actual, real heat release rate of the super-high-temperature fluidized energy storage and release device.

[0094] The to-be-trained model is obtained.

[0095] The to-be-trained model is trained based on the plurality of training data sets until the parameters in the to-be-trained model converge, thereby obtaining the estimation model.

[0096] When the to-be-trained model is trained based on the plurality of training data sets, the sample data can be processed based on the to-be-trained model to obtain an estimated heat release rate and an estimated heat release time of the super-high-temperature fluidized energy storage and release device.

[0097] Then, a heat release rate loss value is obtained according to the estimated heat release rate and the labeled heat release rate, and a heat release time loss value is obtained according to the estimated heat release time and the labeled heat release time.

[0098] A comprehensive loss value is obtained according to the heat release rate loss value and the heat release time loss value.

[0099] According to the comprehensive loss value, the parameters in the to-be-trained model are adjusted.

[0100] For example, a sum value of the heat release time loss value and the heat release rate loss value can be directly calculated, and the sum value is determined as the comprehensive loss value.

[0101] Alternatively, when the comprehensive loss value is calculated, the heat release time loss value and the heat release rate loss value can be weighted and summed to obtain the comprehensive loss value.

[0102] For example, the technician can set the weight corresponding to the heat release time loss value and the weight corresponding to the heat release rate loss value according to experience, and the specific values of the weight corresponding to the heat release time loss value and the weight corresponding to the heat release rate loss value are not limited in the present application. The sum of the weight corresponding to the heat release time loss value and the weight corresponding to the heat release rate loss value can be a specific value, which can include a value of 1 or a value of 2, etc.

[0103] For example, the weight corresponding to the heat release time loss value is 0.45, and the weight corresponding to the heat release rate loss value is 0.55.

[0104] For example, the weight corresponding to the exothermic time loss value is 0.4, and the weight corresponding to the exothermic rate loss value is 0.6.

[0105] The prediction model can include a random forest model, XGBoost (eXtreme Gradient Boosting), LSTM (Long Short Term Memory), or Transformer (a deep learning architecture based on self-attention mechanism, originally used for natural language processing tasks such as machine translation, etc.), etc.

[0106] In this way, in step S102, the power difference between the load power and the predicted power generation can be obtained, the time length between the starting time and the current time can be calculated, and the predicted power generation, the load power, the current temperature, the current time, the starting time, the power difference, and the time length can be input into the trained prediction model, so that the prediction model processes the predicted power generation, the load power, the current temperature, the current time, the starting time, the power difference, and the time length to obtain the target exothermic time and the target exothermic rate of the super-high-temperature fluidized energy storage device.

[0107] Specifically, the predicted power generation, the load power, the current temperature, the current time, the starting time, the power difference, and the time length can be input into the trained prediction model, and the feature extraction network in the prediction model can extract the feature vector corresponding to the predicted power generation, the feature vector corresponding to the load power, the feature vector corresponding to the current temperature, the feature vector corresponding to the current time, the feature vector corresponding to the starting time, the feature vector corresponding to the power difference, and the feature vector corresponding to the time length, respectively.

[0108] The feature extraction network can include an encoding layer and a multi-head self-attention layer. For the predicted power generation, the encoding layer can be used to encode the predicted power generation (e.g., one-hot encoding, etc.), to obtain a sparse vector corresponding to the predicted power generation, and then the multi-head self-attention layer can be used to perform multi-head self-attention weighting on the sparse vector corresponding to the predicted power generation, to obtain the feature vector corresponding to the predicted power generation.

[0109] For the load power, the current temperature, the current time, the starting time, the power difference, and the time length, the same applies, and will not be described in detail here.

[0110] The encoding layer can include one-hot, etc.

[0111] The multi-head self-attention layer can include a Multi-head Self-attention Layer, etc.

[0112] The feature vector corresponding to the predicted power generation, the feature vector corresponding to the load power, the feature vector corresponding to the current temperature, the feature vector corresponding to the current time, the feature vector corresponding to the starting time, the feature vector corresponding to the power difference, and the feature vector corresponding to the time length are input into an aggregation network in the prediction model, so that the aggregation network aggregates the feature vector corresponding to the predicted power generation, the feature vector corresponding to the load power, the feature vector corresponding to the current temperature, the feature vector corresponding to the current time, the feature vector corresponding to the starting time, the feature vector corresponding to the power difference, and the feature vector corresponding to the time length into an aggregated vector.

[0113] For example, the feature vector corresponding to the predicted power generation, the feature vector corresponding to the load power, the feature vector corresponding to the current temperature, the feature vector corresponding to the current time, the feature vector corresponding to the starting time, the feature vector corresponding to the power difference, and the feature vector corresponding to the time length can be sequentially spliced in order to obtain the aggregated vector.

[0114] Alternatively, the dimensions of each of the above-mentioned feature vectors are the same, and the feature vector corresponding to the predicted power generation, the feature vector corresponding to the load power, the feature vector corresponding to the current temperature, the feature vector corresponding to the current time, the feature vector corresponding to the starting time, the feature vector corresponding to the power difference, and the feature vector corresponding to the time length can be average-pooled or maximum-pooled to obtain the aggregated vector.

[0115] The aggregated vector is then processed using a prediction network in the prediction model to obtain the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage device.

[0116] The prediction network includes a logistic regression function, a normalized exponential function, a fully connected layer, or an activation function, for example, Sigmoid, Softmax, or ReLU.

[0117] The prediction network can first process the aggregated vector using an MLP (Multilayer Perceptron) to obtain an intermediate vector, then process the intermediate vector using an activation function tanh to obtain an activation vector, and then process the activation vector using Softmax, Sigmoid, or ReLU to obtain the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage device.

[0118] In step S103, the super-high-temperature fluidized energy storage device is controlled to start continuous heat release at the target heat release rate at the target heat release time to assist the power plant in power generation.

[0119] Or, after the end of the future time period, the super-high-temperature fluidized energy storage device can be controlled to stop heat release.

[0120] For example, the heat output port of the heat storage tank of the super-high-temperature fluidized energy storage device has a switch valve, the opening size of which can be adjusted, the larger the opening size, the faster the heat output rate, that is, the faster the heat release rate, or the smaller the opening size, the slower the heat output rate, that is, the slower the heat release rate.

[0121] Different heat release rates correspond to different opening sizes of the switch valve.

[0122] Therefore, the opening size of the switch valve corresponding to the target heat release rate can be determined, and then the switch valve is opened to the opening size of the switch valve corresponding to the target heat release rate at the target heat release time, so that continuous heat release is started at the target heat release rate at the target heat release time.

[0123] Different target heat release rates correspond to different opening sizes of the switch valve, which are set in advance, for example, by technicians according to actual conditions.

[0124] In the present application, the load power of the power grid in a future time period after the current time is estimated. The predicted power generation power of the power plant in the future time period is obtained. The current temperature of the super-high-temperature fluidized energy storage device is obtained. The starting time of the future time period is obtained. In the case where the predicted power generation power is less than the load power, the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage device are estimated according to the predicted power generation power, the load power, the current temperature, the current time and the starting time. The target heat release time is earlier than the starting time. Wherein, in the case where the super-high-temperature fluidized energy storage device releases heat at the target heat release rate at the target heat release time, the actual power generation power of the power plant is greater than or equal to the load power when the starting time is reached. The super-high-temperature fluidized energy storage device is controlled to start continuous heat release at the target heat release rate at the target heat release time to assist the power plant in power generation.

[0125] Through the present application, the actual power generation power of the power plant can be greater than or equal to the load power when the starting time is reached, so that the amount of electricity generated by the power plant can meet the demand of the user end for electricity when the power grid load enters the peak period.

[0126] In addition, the intelligent technology of peak-valley electric energy regulation can be realized through the application. In the valley period of the power grid load, the peak regulation time of the power grid is predicted by using the prediction model, the energy storage system predicts and purchases cheap valley electric energy from the power grid, the super-high temperature fluidized energy storage is heated and converted into heat energy for storage to realize real-time coupling, and the heat energy is released in the peak period of the power grid load to participate in electric energy production, so that the heat energy stored in the low valley period of the power grid load is increased, and the super-high temperature heat energy stored in the peak period of the power grid load is released.

[0127] The economic operation index of the unit machine group is realized, and the safety of the unit operation caused by shutdown or load reduction is reduced. The power grid unit has potential risks such as safety problems and life reduction in operation due to the load being lower than the design value. In order to make up for the actual problems caused by the change of the load of the peak-valley unit machine group, the scheme of the conversion and energy storage of the peak-valley electric energy is provided.

[0128] The valley electric energy is fully utilized to realize the maximum benefit of the enterprise. The electric energy peak-valley regulation can improve the power generation efficiency of the unit machine group and the best economic index of the plant power, and realize the economy and stability.

[0129] The high-temperature fluidized heat storage tank is a place for electric energy conversion and a place for power steam production. The stable and timely operation of the high-temperature fluidized heating storage tank is provided with technical support by coupling the power grid fluctuation. The real-time switching of the electric energy heating device is provided with technical support. The heating of the heat storage material is realized by the segmented heating mode to generate high-temperature heat energy. Data support is provided for the prediction and decision of actual demand.

[0130] The scheme of the application has good economic benefits, improves the equipment operation planning, increases the system safety, and prolongs the service life of the production system.

[0131] It should be noted that, for the method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the application is not limited to the action sequence described, because according to the application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions involved are not necessarily required by the application.

[0132] Referring to Figure 2 , a kind of auxiliary power generation device based on super-high temperature fluidized energy storage and release equipment of the application is shown, and the heat output port of super-high temperature fluidized energy storage and release equipment converges to the heat output port of the boiler of power plant to integrated heat output port, and the heat output by the integrated heat output port is used to heat the working medium of the power plant;The device comprises:

[0133] The acquisition module 11 is configured to acquire a load power of a power grid at a future time period after a current time point; acquire a predicted power generation of a power plant at the future time period; acquire a current temperature of the super-high-temperature fluidized energy storage and release device; and acquire a start time point of the future time period, the current time point being earlier than the start time point.

[0134] The estimation module 12 is configured to, in a case where the predicted power generation is less than the load power, estimate a target heat release time point and a target heat release rate of the super-high-temperature fluidized energy storage and release device according to the predicted power generation, the load power, the current temperature, the current time point and the start time point, the target heat release time point being earlier than the start time point, and in a case where the super-high-temperature fluidized energy storage and release device releases heat at the target heat release rate at the target heat release time point, an actual power generation of the power plant is greater than or equal to the load power when the start time point is reached.

[0135] The control module 13 is configured to control the super-high-temperature fluidized energy storage and release device to start continuous heat release at the target heat release rate at the target heat release time point, so as to assist the power plant in power generation.

[0136] In an optional implementation, the estimation module comprises:

[0137] A first acquisition unit is configured to acquire a power difference between the load power and the predicted power generation.

[0138] A calculation unit is configured to calculate a time length between the start time point and the current time point.

[0139] A processing unit is configured to input the predicted power generation, the load power, the current temperature, the current time point, the start time point, the power difference and the time length into a trained estimation model, so that the estimation model processes the predicted power generation, the load power, the current temperature, the current time point, the start time point, the power difference and the time length to obtain the target heat release time point and the target heat release rate of the super-high-temperature fluidized energy storage and release device.

[0140] In an optional implementation, the estimation module further comprises:

[0141] A second acquisition unit is configured to acquire a plurality of training data sets.

[0142] Each training data set comprises sample data and labeled data.

[0143] The sample data comprises: a real load power of the power grid in a sample time period, a real power generation power of the power plant in the sample time period, a sample time length between a starting time of the sample time period and a sample time, a sample temperature of the super-high-temperature fluidized energy storage device at the sample time, and a sample difference value between the real load power and the real power generation power; the real load power is greater than the real power generation power; and the sample time is earlier than the starting time of the sample time period.

[0144] The labeled data comprises: a labeled heat release time of the super-high-temperature fluidized energy storage device and a labeled heat release rate of the super-high-temperature fluidized energy storage device; the labeled heat release time is later than the sample time and earlier than the starting time of the sample time period.

[0145] The third obtaining unit is configured to obtain a to-be-trained model.

[0146] The training unit is configured to train the to-be-trained model based on the plurality of training data sets until parameters in the to-be-trained model converge, thereby obtaining a prediction model.

[0147] In an optional implementation, the training unit comprises:

[0148] The processing sub-unit is configured to process the sample data based on the to-be-trained model, thereby obtaining a predicted heat release rate and a predicted heat release time of the super-high-temperature fluidized energy storage device.

[0149] The first obtaining sub-unit is configured to obtain a heat release rate loss value based on the predicted heat release rate and the labeled heat release rate, and obtain a heat release time loss value based on the predicted heat release time and the labeled heat release time.

[0150] The second obtaining sub-unit is configured to obtain a comprehensive loss value based on the heat release rate loss value and the heat release time loss value.

[0151] The adjusting sub-unit is configured to adjust parameters in the to-be-trained model based on the comprehensive loss value.

[0152] In the present application, the load power of the power grid in a future time period after a current time is estimated. The predicted power generation power of a power plant in the future time period is obtained. The current temperature of the super-high-temperature fluidized energy storage and release device is obtained. The starting time of the future time period is obtained. In the case that the predicted power generation power is less than the load power, the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage and release device are estimated according to the predicted power generation power, the load power, the current temperature, the current time and the starting time. The target heat release time is earlier than the starting time. In the case that the super-high-temperature fluidized energy storage and release device releases heat at the target heat release rate at the target heat release time, the actual power generation power of the power plant is greater than or equal to the load power when the starting time is reached. The super-high-temperature fluidized energy storage and release device is controlled to start continuous heat release at the target heat release rate at the target heat release time to assist the power plant in power generation.

[0153] By the present application, the actual power generation power of the power plant can be greater than or equal to the load power when the starting time is reached, so that the power generation of the power plant can meet the demand of the user end for power when the power grid load is in the peak period.

[0154] Optionally, the present application also provides an electronic device, comprising: a processor, a memory, a computer program stored in the memory and executable on the processor, which realizes each process of the above-mentioned method embodiments and achieves the same technical effects. To avoid repetition, details are not repeated here.

[0155] The present application also provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to realize each process of the above-mentioned method embodiments and achieve the same technical effects. To avoid repetition, details are not repeated here. The computer readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0156] Figure 3 is a block diagram of an electronic device 800 shown in the present application. For example, the electronic device 800 can be a mobile phone, a computer, a digital broadcast terminal, a message transmission device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0157] Reference Figure 3The electronic device 800 can include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0158] The processing component 802 usually controls overall operations of the electronic device 800, such as operations associated with displaying, making phone calls, data communications, camera operations, and recording operations. The processing component 802 can include one or more processors 820 to execute instructions to complete all or part of steps of the above methods. In addition, the processing component 802 can include one or more modules to facilitate

[0159] The memory 804 is configured to store various types of data to support operations of the electronic device 800. Examples of these data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, images, videos, and the like. The memory 804 can be implemented by any type of volatile or non-volatile storage devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic or optical disk.

[0160] The power supply component 806 provides power for the various components of the electronic device 800. The power supply component 806 can include a power supply management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

[0161] The multimedia component 808 includes a screen to provide an output interface between the electronic device 800 and a user. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide, or a gesture on the touch panel. The touch sensor can not only sense a boundary of a touching or a sliding action, but also detect duration and intensity of the touching or sliding action. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. The front camera and / or the rear camera can receive external multimedia data when the electronic device 800 is in an operating mode, such as a shooting mode or a video mode. Each of the front and rear camera can be a fixed optical lens system or have a focal length and optical zooming capability.

[0162] The audio component 810 is configured to output and / or input an audio signal. For example, the audio component 810 includes a microphone (MIC) to receive an external audio signal when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker to output an audio signal.

[0163] The I / O interface 812 provides an interface for the processing component 802 and peripheral interface modules, such as a keypad, a click wheel, buttons, and the like. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0164] The sensor component 814 includes one or more sensors to provide various state assessments for the electronic device 800. For example, the sensor component 814 can monitor an open / closed state of the electronic device 800, relative positioning of components, such as a display and a keypad of the electronic device 800, a change in position of the electronic device 800 or a component of the electronic device 800, presence or absence of user contact with the electronic device 800, orientation or acceleration / deceleration of the electronic device 800, and a temperature change of the electronic device 800. The sensor component 814 can include a proximity sensor configured to detect presence of a nearby object without any physical touch. The sensor component 814 can further include a light sensor such as a CMOS or CCD image sensor for use in an imaging application. In some embodiments, the sensor component 814 can further include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0165] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, a cellular network standard (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an example embodiment, the communication component 816 receives broadcast signals or broadcast operation information from an external broadcast management system via a broadcast channel. In an example embodiment, the communication component 816 can further include a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) techniques, infrared data association (IrDA) techniques, ultra-wideband (UWB) techniques, Bluetooth (BT) techniques, and other techniques.

[0166] In an example embodiment, the electronic device 800 can be implemented with one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements, for performing the above-described methods.

[0167] In an example embodiment, a non-transitory computer-readable storage medium including instructions, such as the memory 804 including instructions, is also provided, which can be executed by the processor 820 of the electronic device 800 to complete the above-described methods. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disc, and an optical data storage device, etc.

[0168] Figure 4 is a block diagram of an electronic device 1900 shown in the present application. For example, the electronic device 1900 can be provided as a server.

[0169] Referring to Figure 4 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932, for storing instructions, such as an application program, executable by the processing component 1922. The application program stored in the memory 1932 can include one or more than one module each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above-described methods.

[0170] The electronic device 1900 can further include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 can operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0171] It should be noted that the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0172] Those skilled in the art can clearly understand the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for making a terminal (which can be a mobile phone, computer, server, air conditioner, or network device) execute the methods described in various embodiments of the present application.

[0173] The embodiments of the present application are described above in conjunction with the drawings, but the present application is not limited to the above-mentioned specific embodiments, which are only illustrative and not restrictive. Those skilled in the art can make many forms without departing from the purpose of the present application and the scope protected by the claims under the inspiration of the present application, which all belong to the protection of the present application.

[0174] Those skilled in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0175] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0176] In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiments described above are only schematic, for example, the division of the units is only a logical function division, and another division manner can be used in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0177] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0178] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0179] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, and various program code storage media.

[0180] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for generating power assisted by an ultra-high temperature fluidized energy storage device, characterized in that, The heat output port of the super-high-temperature fluidized energy storage device and the heat output port of the boiler of the power plant converge to a comprehensive heat output port, and heat output by the comprehensive heat output port is used to heat a working medium of the power plant, and the method comprises: estimating a load power of a power grid in a future time period after a current time; obtaining a predicted power generation power of the power plant in the future time period; obtaining a current temperature of the super-high-temperature fluidized energy storage device; obtaining a starting time of the future time period; the current time is earlier than the starting time; in the case that the predicted power generation power is less than the load power, estimating a target heat release time and a target heat release rate of the super-high-temperature fluidized energy storage device according to the predicted power generation power, the load power, the current temperature, the current time and the starting time; the target heat release time is earlier than the starting time; wherein in the case that the super-high-temperature fluidized energy storage device releases heat at the target heat release rate at the target heat release time, the actual power generation power of the power plant is greater than or equal to the load power when the starting time is reached; controlling the super-high-temperature fluidized energy storage device to start continuous heat release at the target heat release rate at the target heat release time to assist the power plant in power generation.

2. The method of claim 1, wherein, The method further comprises: obtaining a power difference between the load power and the predicted power generation power; calculating a time length between the starting time and the current time; inputting the predicted power generation power, the load power, the current temperature, the current time, the starting time, the power difference and the time length into a trained estimation model, so that the estimation model processes the predicted power generation power, the load power, the current temperature, the current time, the starting time, the power difference and the time length to obtain the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage device.

3. The method of claim 2, wherein, The method further comprises: obtaining a plurality of training data sets; one training data set comprises sample data and labeled data; the sample data comprises a real load power of a power grid in a sample time period, a real power generation power of the power plant in the sample time period, a sample time length between a starting time of the sample time period and a sample time, a sample temperature of the super-high-temperature fluidized energy storage device at the sample time, and a sample difference between the real load power and the real power generation power; the real load power is greater than the real power generation power; the sample time is earlier than the starting time of the sample time period; the labeled data comprises a labeled heat release time of the super-high-temperature fluidized energy storage device and a labeled heat release rate of the super-high-temperature fluidized energy storage device; the labeled heat release time is later than the sample time and earlier than the starting time of the sample time period; obtaining a model to be trained; training the to-be-trained model based on the plurality of training data sets until parameters in the to-be-trained model converge, thereby obtaining a prediction model.

4. The method of claim 3, wherein, The training the to-be-trained model based on the plurality of training data sets comprises: processing the sample data based on the to-be-trained model to obtain a predicted heat release rate and a predicted heat release time of the super-high-temperature fluidized energy storage and release device; obtaining a heat release rate loss value according to the predicted heat release rate and the labeled heat release rate, and obtaining a heat release time loss value according to the predicted heat release time and the labeled heat release time; obtaining a comprehensive loss value according to the heat release rate loss value and the heat release time loss value; adjusting parameters in the to-be-trained model according to the comprehensive loss value.

5. An auxiliary power generation device based on super-high-temperature fluidization energy storage equipment, characterized in that, A heat output port of the super-high-temperature fluidized energy storage and release device and a heat output port of a boiler of a power plant converge to a comprehensive heat output port, and heat output by the comprehensive heat output port is used to heat a working medium of the power plant; the device comprises: an obtaining module, configured to obtain a load power of a power grid in a future time period after a current time; obtain a predicted power generation power of the power plant in the future time period; obtain a current temperature of the super-high-temperature fluidized energy storage and release device; and obtain a start time of the future time period; the current time is earlier than the start time; a prediction module, configured to, in a case where the predicted power generation power is less than the load power, predict a target heat release time and a target heat release rate of the super-high-temperature fluidized energy storage and release device according to the predicted power generation power, the load power, the current temperature, the current time, and the start time; the target heat release time is earlier than the start time; wherein, in a case where the super-high-temperature fluidized energy storage and release device releases heat at the target heat release rate at the target heat release time, the actual power generation power of the power plant is greater than or equal to the load power when the start time is reached; a control module, configured to control the super-high-temperature fluidized energy storage and release device to start continuous heat release at the target heat release rate at the target heat release time to assist the power plant in power generation.

6. The apparatus of claim 5, wherein, The prediction module comprises: a first obtaining unit, configured to obtain a power difference value between the load power and the predicted power generation power; a calculation unit, configured to calculate a time length between the start time and the current time; a processing unit, configured to input the predicted power generation power, the load power, the current temperature, the current time, the start time, the power difference value, and the time length into a trained prediction model, so that the prediction model processes the predicted power generation power, the load power, the current temperature, the current time, the start time, the power difference value, and the time length to obtain the target heat release time and the target heat release rate of the super-high-temperature fluidized energy storage and release device.

7. The apparatus of claim 6, wherein, The prediction module further comprises: a second obtaining unit, configured to obtain a plurality of training data sets; one training data set comprises sample data and labeled data; The sample data comprises: real load power of the power grid in a sample time period, real power generation of the power plant in the sample time period, a sample time length between a starting time of the sample time period and a sample time, a sample temperature of the super-high-temperature fluidized energy storage device at the sample time, and a sample difference value between the real load power and the real power generation; the real load power is greater than the real power generation; and the sample time is earlier than the starting time of the sample time period. The labeled data comprises: a labeled heat release time of the super-high-temperature fluidized energy storage device and a labeled heat release rate of the super-high-temperature fluidized energy storage device; the labeled heat release time is later than the sample time and earlier than the starting time of the sample time period. The third obtaining unit is configured to obtain a to-be-trained model. The training unit is configured to train the to-be-trained model based on the plurality of training data sets until parameters in the to-be-trained model converge, thereby obtaining a prediction model.

8. The apparatus of claim 7, wherein, The training unit comprises: The processing sub-unit is configured to process the sample data based on the to-be-trained model, and obtain a predicted heat release rate and a predicted heat release time of the super-high-temperature fluidized energy storage device. The first obtaining sub-unit is configured to obtain a heat release rate loss value based on the predicted heat release rate and the labeled heat release rate, and obtain a heat release time loss value based on the predicted heat release time and the labeled heat release time. The second obtaining sub-unit is configured to obtain a comprehensive loss value based on the heat release rate loss value and the heat release time loss value. The adjusting sub-unit is configured to adjust parameters in the to-be-trained model based on the comprehensive loss value.

9. An electronic device, comprising: The computer program is stored in the memory and executable on the processor, and when executed by the processor, implements the method in any one of claims 1 to 4. The computer program is stored in the memory and executable on the processor, and when executed by the processor, implements the method in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, ​

Images