Temperature prediction method, electronic equipment, storage medium and energy storage system
By combining convolutional neural networks and long-term memory network models, dynamically adjusting the operating strategies of energy storage equipment, the problem of inaccurate prediction of battery temperature changes in energy storage equipment in the existing technology is solved, and efficient temperature prediction is achieved after the anti-countercurrent and anti-overcurrent strategies are triggered and within ten minutes after the stop.
Patent Information
- Application Number
- CN202510264878.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-06
- Publication Date
- 2025-06-13
AI Technical Summary
The prior art cannot accurately predict the temperature changes of energy storage equipment battery under anti-countercurrent and anti-over-needing strategies, especially temperature changes within ten minutes after the strategy is triggered and stopped.
By obtaining ambient temperature and battery parameters, combining convolutional neural networks and long-term memory network models, the power changes of energy storage devices are calculated, and the battery temperature is predicted based on the predicted power and battery parameters, and the operating strategies of energy storage devices are dynamically adjusted to achieve accurate temperature prediction.
Efficient and accurate temperature prediction is achieved after the anti-countercurrent and anti-overcurrent strategies are triggered and within ten minutes after stopping, avoiding the delay in the prior art that needs to wait for the strategy to run for a period of time before predicting temperature changes.
Smart Images
Figure CN120142946A_ABST
Abstract
Description
[0001] This application is a divisional application. The application number of the original application is 202411577576.4, and the original application date is November 06, 2024. The entire content of the original application is incorporated herein by reference. Technical Field
[0002] This application relates to the field of energy storage technologies, and in particular, to a temperature prediction method, an electronic device, a storage medium, and an energy storage system. Background Art
[0003] In an energy storage system, it is necessary to ensure that the battery cells and supporting electrical equipment in the energy storage cabinet operate within a safe temperature range. In the prior art, the temperature change of the battery cells is predicted based on the changes in various data of the energy storage cabinet, and the battery is charged and discharged according to a long-term stable planned curve. However, under the strategies of preventing reverse current and preventing over-demand in specific scenarios, accurate temperature prediction cannot be achieved. Summary of the Invention
[0004] In view of this, this application provides a temperature prediction method, an electronic device, and a storage medium, which helps to solve the problem that the temperature change of the battery of the energy storage device cannot be accurately predicted under the strategies of preventing reverse current and preventing over-demand.
[0005] In a first aspect, this application provides a temperature prediction method, which is applied to an energy storage device and includes: Obtain the ambient temperature and the battery parameters of the energy storage device; Obtain the current first power, third power, and fourth power of the energy storage device, where the current first power is used to represent the current operating power of the energy storage device, the third power is used to represent the reverse current prevention threshold power of the energy storage device, and the fourth power is used to represent the over-demand prevention threshold power of the energy storage device; Calculate the second power of the energy storage device, where the second power is used to represent the load power of the energy storage device; if the difference between the second power and the current first power is not less than the fourth power, then determine the state of the energy storage device; If the energy storage device is in a charging state, taking the current first power as a standard, compensate the predicted first power, where the predicted first power is used to characterize the predicted operating power of the energy storage device; determine whether the difference between the second power and the compensated predicted first power is less than the fourth power; if the difference between the second power and the compensated predicted first power is less than the fourth power, output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power; If the energy storage device is in a discharging state, taking the current first power as a standard, compensate the predicted first power; determine whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power; If the energy storage device is in a static fully charged state, set the predicted first power to zero; determine whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power; Predict the battery temperature of the energy storage device based on the ambient temperature, the battery parameters, and the predicted first power.
[0006] In one possible implementation, the battery parameters include SOC parameters and SOH parameters.
[0007] In one possible implementation, calculating the second power of the energy storage device includes: calculating the second power of the energy storage device based on the historical power data, date data, weather conditions, and air quality of the energy storage device.
[0008] In one possible implementation, input the historical power data, date data, weather conditions, and air quality of the energy storage device into a preset model, output the power load demand of the energy storage device, and calculate the second power of the energy storage device.
[0009] In one possible implementation, if the difference between the second power and the current first power is not greater than the third power, then the predicted first power is adjusted based on the current first power and a preset second adjustment value.
[0010] In one possible implementation, determining the state of the energy storage device and adjusting the first power includes: if the energy storage device is in a charging state, increasing the predicted first power until the charging state stops; if the energy storage device is in a discharging state, increasing the predicted first power for discharging; if the energy storage device is in a static fully charged state, increasing the predicted first power for discharging.
[0011] In one possible implementation, adjusting the predicted first power based on the current first power and a preset second adjustment value includes: if the difference between the second power and the current first power is not greater than the third power, compensating the predicted first power with the current first power as a standard; determining whether the difference between the second power and the predicted first power is greater than the third power; if the difference between the second power and the predicted first power is greater than the third power, then outputting the predicted first power; if the difference between the second power and the predicted first power is not greater than the third power, subtracting the preset second adjustment value from the predicted first power until the difference between the second power and the current first power is greater than the third power, and outputting the adjusted predicted first power.
[0012] In one possible implementation, the energy storage device further includes a liquid chiller, and predicting the battery temperature of the energy storage device based on the ambient temperature, the battery parameters, and the predicted first power includes: training a temperature prediction model through the second power, the ambient temperature, the battery parameters, and the power of the liquid chiller; inputting the ambient temperature, the battery parameters, and the predicted first power into the temperature prediction model to predict the battery temperature of the energy storage device.
[0013] In a second aspect, the present application provides a temperature prediction device for an energy storage device, including: An acquisition module, where the acquisition module is used to acquire the ambient temperature and the battery parameters of the energy storage device; the acquisition module is further used to acquire the current first power, the third power, and the fourth power of the energy storage device, where the current first power is used to represent the current operating power of the energy storage device, the third power is used to represent the anti-backflow threshold power of the energy storage device, and the fourth power is used to represent the anti-over-demand threshold power of the energy storage device; A calculation module for calculating a second power of the energy storage device, where the second power is used to characterize the load power of the energy storage device; if the difference between the second power and the current first power is not less than the fourth power, then determine the state of the energy storage device. A compensation module, which is configured to, if the energy storage device is in a charging state, compensate a predicted first power based on the current first power, where the predicted first power is used to characterize the predicted operating power of the energy storage device; determine whether the difference between the second power and the compensated predicted first power is less than the fourth power; if the difference between the second power and the compensated predicted first power is less than the fourth power, then output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, then add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power. The compensation module is further configured to, if the energy storage device is in a discharging state, compensate the predicted first power based on the current first power; determine whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, then output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, then add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power. The compensation module is further configured to, if the energy storage device is in a static full charge state, set the predicted first power to zero; determine whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, then output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, then add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power. A prediction module, which is further configured to predict the battery temperature of the energy storage device based on the ambient temperature, the battery parameters, and the predicted first power.
[0014] In one possible implementation, the battery parameters include SOC parameters and SOH parameters.
[0015] In one possible implementation, the computing module is further configured to calculate a second power of the energy storage device based on historical power data, date data, weather conditions, and air quality of the energy storage device.
[0016] In one possible implementation, the computing module is further configured to input the historical power data, date data, weather conditions, and air quality of the energy storage device into a preset model, output the power load demand of the energy storage device, and calculate the second power of the energy storage device.
[0017] In one possible implementation, the temperature prediction device further includes an adjustment module, and the adjustment module is configured to, if the difference between the second power and the current first power is not greater than the third power, adjust the predicted first power based on the current first power and a preset second adjustment value.
[0018] In one possible implementation, the adjustment module is configured to, if the energy storage device is in a charging state, increase the predicted first power until the charging state stops; if the energy storage device is in a discharging state, increase the predicted first power for discharging; if the energy storage device is in a static full-charge state, increase the predicted first power for discharging.
[0019] In one possible implementation, the compensation module is configured to, if the difference between the second power and the current first power is not greater than the third power, compensate the predicted first power with the current first power as a standard; determine whether the difference between the second power and the predicted first power is greater than the third power; if the difference between the second power and the predicted first power is greater than the third power, output the predicted first power; if the difference between the second power and the predicted first power is not greater than the third power, subtract a preset second adjustment value from the predicted first power until the difference between the second power and the current first power is greater than the third power, and output the adjusted predicted first power.
[0020] In one possible implementation, the prediction module is further configured to train a temperature prediction model through the second power, the ambient temperature, the battery parameters, and the power of the liquid chiller; input the ambient temperature, the battery parameters, and the predicted first power into the temperature prediction model to predict the battery temperature of the energy storage device.
[0021] In a third aspect, the present application provides an electronic device, including: a processor and a memory, where the memory is used to store a computer program; the processor is used to run the computer program to implement the temperature prediction method as described in the first aspect.
[0022] Fourthly, the present application provides a computer-readable storage medium storing a computer program, which when running on a computer, enables the computer to implement the temperature prediction method as described in the first aspect. Description of the Drawings
[0023] Figure 1 It is a schematic flowchart of the operation strategy of the energy storage device provided by the embodiment of the present application; Figure 2 It is a schematic flowchart of the temperature prediction method provided by the embodiment of the present application; Figure 3 It is a schematic flowchart of the power prediction method provided by the embodiment of the present application; Figure 4 It is a schematic structural diagram of a temperature prediction device provided by the present application; Figure 5 It is a schematic structural diagram of an electronic device provided by the embodiment of the present application. Detailed Embodiments
[0024] In the embodiments of the present application, unless otherwise specified, the character " / " indicates that the related objects before and after are in an "or" relationship. For example, A / B may represent A or B. "And / or" describes the association relationship of the related objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone.
[0025] It should be noted that the terms "first", "second", etc. involved in the embodiments of the present application are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features, nor can they be understood as indicating or implying an order.
[0026] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. In addition, "at least one (item)" or its similar expression means any combination of these items, which can include any combination of single item (item) or plural items (items). For example, at least one (item) of A, B, or C can represent: A, B, C, A and B, A and C, B and C, or A, B, and C. Each of A, B, and C can itself be an element or a set containing one or more elements.
[0027] In the embodiments of the present application, terms such as "exemplary", "in some embodiments", "in another embodiment" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" in the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the term "exemplary" is intended to present concepts in a specific manner.
[0028] In the embodiments of the present application, "of", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the differences are not emphasized, the meanings to be expressed are the same. In the embodiments of the present application, communication and transmission can sometimes be used interchangeably. It should be noted that when the differences are not emphasized, the meanings they express are the same. For example, transmission can include sending and / or receiving, and can be a noun or a verb.
[0029] In the embodiments of the present application, the equality involved can be used in combination with greater than, applicable to the technical solutions adopted when greater than, and can also be used in combination with less than, applicable to the technical solutions adopted when less than. It should be noted that when equality is used in combination with greater than, it cannot be used in combination with less than; when equality is used in combination with less than, it is not used in combination with greater than.
[0030] In the prior art, the temperature prediction model cannot predict the temperature change within ten minutes after and after the anti-backflow and anti-over-demand strategies are triggered and stopped. Only after the anti-backflow and anti-over-demand strategies operate for a period of time and stop for a period of time, and after the power changes, can the next temperature change be predicted based on the current power.
[0031] Based on the above problems, the embodiments of the present application propose a temperature prediction method applied to energy storage devices.
[0032] Now in combination with Figure 1 - Figure 2 The temperature prediction method provided by the embodiments of the present application will be described.
[0033] Figure 1 It is a schematic flowchart of the operation strategy of the energy storage device provided by the embodiments of the present application. As Figure 1 shown, the above operation strategy includes the operation strategy of the energy storage device in the industrial and commercial scenarios. First, charge and discharge are performed according to the charge and discharge times set in the planned curve. Generally, charging is performed during the valley time of the electricity price; discharging is performed during the peak time of the electricity price. Then, the gateway meter is monitored in real time. When the gateway meter monitors the anti-backflow threshold power, the anti-backflow strategy is executed, and the energy storage device operates at a reduced power; when the gateway meter monitors the anti-over-demand threshold power, the anti-over-demand strategy is executed, and the power of the energy storage device is adjusted according to the current charging state of the energy storage device; if the energy storage device is in the charging state, the power is increased until the charging state stops; if the energy storage device is in the discharging state, the power is increased for discharging; if the energy storage device is in the static full charge state, the power is increased for discharging to control the power demand.
[0034] As Figure 2 shown is a schematic flowchart of an embodiment of the temperature prediction method provided by the present application, which specifically includes the following steps: Step 210, obtain the ambient temperature and the battery parameters of the energy storage device.
[0035] Specifically, an embodiment in the present application proposes to first obtain the ambient temperature of the energy storage device and the battery parameters of the energy storage device. Among them, the energy storage device may include multiple temperature sensors, which can be set inside or outside the energy storage device. The energy storage device obtains the ambient temperature through the temperature sensors. The specific acquisition method is not specifically limited in the embodiments of the present application. The battery parameters of the energy storage device proposed in the present application may include: SOC (State of Charge) parameter, SOH (State of Health) parameter, battery capacity, rated voltage, charge and discharge rate, charge and discharge depth, maximum charge and discharge power, and battery rated voltage, etc. Specifically, the SOC parameter is the percentage of the remaining battery power to the rated battery capacity, which is used to reflect the remaining capacity of the battery. The range of SOC is generally 0-100%; the SOH parameter is the ratio of the performance parameter to the nominal parameter after the battery has been used for a period of time. According to the IEEE standard, when the capacity of the battery when fully charged is less than 80% of the rated capacity, that is, when SOH is less than 80%, the battery should be replaced; the battery capacity is one of the important performance indicators to measure the battery performance, which represents the amount of electricity discharged by the battery under certain conditions; the rated voltage of the battery in the energy storage device refers to its designed or nominal working voltage, expressed in volts (V). The battery in the energy storage device is composed of single-cell battery cores connected in parallel and in series. Series connection increases the voltage, and parallel connection increases the capacity; the battery charge and discharge rate is a measure of the charging speed, which affects the continuous current and peak current during battery operation; the charge and discharge depth is used to measure the percentage between the battery discharge amount and the battery rated capacity. The deeper the discharge depth, the shorter the battery cycle life; the maximum charge and discharge power is the maximum current and power during battery charging and discharging; the rated voltage of the battery will change under different discharge currents and ambient temperatures. The greater the discharge current, the lower the voltage; the lower the temperature, the lower the voltage of the battery with the same capacity.
[0036] Step 220, obtain the current first power, third power, and fourth power of the energy storage device.
[0037] Specifically, an embodiment in the present application proposes to obtain the current first power, third power, and fourth power of the energy storage device. Among them, the current first power is used to characterize the current operating power of the energy storage device, the third power is used to characterize the anti-backflow threshold power of the energy storage device, and the fourth power is used to characterize the anti-over-demand threshold power of the energy storage device. The anti-backflow threshold power is a key parameter in the energy storage system. The anti-backflow threshold power defines the maximum amount of electric energy that the energy storage system can provide to the power grid or load during the discharge process. During the discharge process of the energy storage system, due to reasons such as power fluctuations and changes in load power consumption, electric energy may flow back to the power grid, which may affect the stability and safety of the power grid. Backflow may also cause damage to the energy storage device. An improper charge-discharge process may shorten the battery life. By setting the anti-backflow threshold power, it helps to protect the energy storage device and extend its service life. Further, it can ensure that the energy storage system does not inject too much energy into the power grid, thereby maintaining the stability of the power grid. The anti-over-demand threshold power refers to preventing the power provided by the energy storage system during the discharge process within a specific time period from exceeding the actual demand of the power grid or load. This time period can be 15 minutes, one hour, one day, etc., depending on the management and measurement requirements of the power system. During this period, the grid demand is usually the average maximum value of the electric power actually consumed by users. When the gateway meter calculates that the over-demand threshold is reached, the strategy of the energy storage device will be adjusted according to the current state of the energy storage device. The dynamic adjustment of the anti-backflow strategy and anti-over-demand strategy proposed in the present application is mainly based on whether the anti-backflow threshold power and anti-over-demand threshold power are triggered. Based on the current first power, third power, and fourth power, the load power can be effectively predicted, the power change of the energy storage device can be effectively predicted, and based on the charge-discharge power of the energy storage cabinet, the temperature change of the battery cells in the energy storage device can be effectively predicted.
[0038] Step 230, calculate the second power of the energy storage device. If the difference between the second power and the current first power is not less than the fourth power, then determine the state of the energy storage device.
[0039] Specifically, an embodiment in the present application proposes to calculate the second power of the energy storage device. If the difference between the second power and the current first power is not less than the fourth power, the state of the energy storage device is determined. Among them, the second power is used to characterize the load power of the energy storage device. Calculating the second power of the energy storage device includes calculating the second power of the energy storage device based on the historical power data, date data, weather conditions, and air quality of the energy storage device. Further, an embodiment in the present application proposes to input the historical power data, date data, weather conditions, and air quality of the energy storage device into a power load calculation model based on the historical power data, date data, weather conditions, and air quality of the energy storage device, output the power load demand of the energy storage device, and then calculate the second power. Among them, the power load calculation model proposed in the present application may include: a convolutional neural network and a long short-term memory network (Convolutional Neural Networks-Long Short-Term Memory, CNN-LSTM) model. It can be understood that a convolutional neural network usually includes an input layer, multiple convolutional layers, a pooling layer, a fully connected layer, etc.; local features of an image are automatically extracted through the convolutional layer, and local spatial structure information of the image can be captured. The long short-term memory network model unit contains three gates, namely an input gate, a forget gate, an output gate, and a cell state, and the flow of information is controlled through these gates. The long short-term memory network model is mainly used for tasks such as processing and predicting time series data, such as language modeling, text generation, speech recognition, etc. The convolutional neural network and the long short-term memory network proposed in the embodiment of the present application combine the convolutional neural network and the long short-term memory network. First, the convolutional neural network is used to extract features of the input object, and the features of each frame are extracted. Optionally, the spatial dimension of the features is further reduced to extract more abstract features. Then, the LSTM layer is used to take the feature sequence extracted by the CNN as input, and the LSTM is used to process the time series relationship of these features, capture the dynamic changes in time, and predict the power load. Finally, the fully connected layer is used for classification or regression tasks and for evaluating the prediction results.
[0040] Optionally, Figure 3 is a schematic flowchart of an embodiment of the power prediction method provided by the present application, as Figure 3As shown, W is the current first power, WY is the predicted first power predicted based on the above convolutional neural network and long short-term memory network model, W1 is the second power, W2 is the third power, W3 is the fourth power, n3 is the preset first adjustment value, and n2 is the preset second adjustment value. An embodiment in the present application proposes that if the difference between the second power and the current first power is not less than the fourth power, that is, the anti-overdemand threshold power is triggered, and the anti-overdemand strategy is executed. First, the state of the energy storage device is judged. If the energy storage device is in the charging state, the predicted first power is compensated with the current first power as the standard, and the predicted first power is used to represent the predicted operating power of the energy storage device; judge whether the difference between the second power and the compensated predicted first power is less than the fourth power; if the difference between the second power and the compensated predicted first power is less than the fourth power, output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power; Optionally, if the energy storage device is in the discharging state, the predicted first power is compensated with the current first power as the standard; judge whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power.
[0041] Optionally, if the energy storage device is in the static full charge state, set the predicted first power to zero; judge whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power. The preset first adjustment value can be different values in different application scenarios and can be set to vary with different anti-overdemand strategies. The present application does not make special limitations on the specific value of the preset first adjustment value.
[0042] Optionally, another embodiment in the present application proposes that if the difference between the second power and the current first power is not greater than the third power, the anti-counterflow threshold power is triggered, and the anti-counterflow strategy is executed. Based on the current first power and the preset second adjustment value, the predicted first power is adjusted. First, the working state of the energy storage device is judged. If the energy storage device is in the charging state, the predicted first power is increased until the charging state stops; if the energy storage device is in the discharging state, the predicted first power is increased for discharging; if the energy storage device is in the static full-charge state, the predicted first power is increased for discharging. It can be understood that in the present application, the predicted first power is adjusted according to the anti-counterflow strategy. Specifically, if the difference between the second power and the current first power is not greater than the third power, the predicted first power is compensated with the current first power as the standard; it is judged whether the difference between the second power and the predicted first power is greater than the third power; if the difference between the second power and the predicted first power is greater than the third power, the predicted first power is output; if the difference between the second power and the predicted first power is not greater than the third power, the predicted first power is subtracted by the preset second adjustment value until the difference between the second power and the current first power is greater than the third power, and the adjusted predicted first power is output. The preset second adjustment value can be different values in different application scenarios and can be set to vary with different anti-counterflow strategies. The present application does not make special limitations on the specific value of the preset second adjustment value.
[0043] Exemplarily, an embodiment in the present application proposes that the energy storage device has a negative power value during charging and a positive power value during discharging. Specifically, an embodiment in the present application proposes that W2 can be 20kW, W can be 100kW, and WY can be 100kW; W1 can be 100kW, that is, W1 - W is 0, triggering counterflow, and the anti-counterflow strategy is executed. WY is subtracted by the preset second adjustment value, where the preset second adjustment value can be 5kW, 10kW or any value not greater than W2 until W1 - WY > W2. When W1 is 200Kw and W is 100Kw, that is, W1 - W is 100kW which is greater than W2, no counterflow is triggered and no anti-counterflow strategy is executed.
[0044] Another embodiment in the present application proposes that if the energy storage device is in the charging state, W3 can be 300kW, W can be -100kW, and WY can be -100kW; W1 can be 240kW, that is, W1 - W is 340kW which is greater than W3, triggering over-demand, and the anti-over-demand strategy is executed. WY is added with the preset first adjustment value, where the preset first adjustment value can be 5kW, 10kW; until W1 - WY < W3. When W1 is 150kW and W is 100kW, that is, W1 - W is 100kW which is less than W3, no over-demand is triggered and no anti-over-demand strategy is executed.
[0045] Another embodiment in the present application proposes that if the energy storage device is in a discharging state, W3 can be 300 kW, W can be -100 kW, and WY can be -100 kW; W1 can be 240 kW, that is, W1 - W is 340 kW which is greater than W3, triggering over-demand, and implementing an over-demand prevention strategy by adding a preset first adjustment value to WY, where the preset first adjustment value can be 5 kW, 10 kW, until W1 - WY < W3. When W1 is 150 kW and W is 100 Kw, that is, W1 - W is 100 Kw which is less than W3, over-demand is not triggered and the over-demand prevention strategy is not implemented.
[0046] Another embodiment in the present application proposes that if the energy storage device is in a static fully charged state, W3 can be 300 kW, W can be -100 kW, and WY can be 0; W1 can be 240 kW, that is, W1 - W is 340 which is greater than W3, triggering over-demand, and implementing an over-demand prevention strategy by adding a preset first adjustment value to WY, where the preset first adjustment value can be 5 kW, 10 kW, until W1 - WY < W3. When W1 is 150kW and W is 100 kW, that is, W1 - W is 100 Kw which is less than W3, over-demand is not triggered and the over-demand prevention strategy is not implemented. The power prediction method proposed in the present application can predict the power change within ten minutes after and after the anti-counterflow strategy or over-demand prevention strategy is triggered and stopped. Without the anti-counterflow strategy or over-demand prevention strategy running for a period of time and stopping for a period of time, the power change of the next energy storage device can be directly predicted based on the predicted first power, which can predict the second power of the energy storage device more efficiently and accurately within ten minutes after and after the anti-counterflow strategy or over-demand prevention strategy is triggered compared with the prior art.
[0047] Step 240, predicting the battery temperature of the energy storage device based on the ambient temperature, battery parameters, and the predicted first power.
[0048] Specifically, an embodiment in the present application proposes to predict the battery temperature of an energy storage device based on the ambient temperature, battery parameters, and predicted first power. Among them, first, a temperature prediction model is trained through the second power, the ambient temperature, the battery parameters, and the power of the liquid chiller; the temperature prediction model proposed in the present application can be a Long Short-Term Memory (LSTM) model, or other temperature prediction models with the same prediction function. The present application does not make special limitations on this temperature prediction model. Before training the temperature prediction model, data processing is also required for data such as the second power, the ambient temperature, the battery parameters, and the power of the liquid chiller. Data processing includes missing value processing, charging segment extraction processing, and normalization processing. Among them, data missing can include continuous data missing and individual time point data missing. Continuous data missing cannot be filled by connecting the upper and lower time data, so this data can be directly removed; individual time point data missing can be processed by the mean interpolation method. When abnormal voltage or temperature data occurs due to abnormal acquisition by the battery system sensor, for example, the single-cell voltage of a lithium battery far exceeds the temperature range of the lithium battery, it is determined that the sensor data reading is abnormal. If the abnormal value appears continuously (number of times ≥ 3), it will be processed according to the method of data missing, and this segment of abnormal data will be removed. If the number of consecutive occurrences of the abnormal value is less than 3, the normal value of the previous moment is used to replace the abnormal value to ensure that there is no abnormal jump in the battery temperature value within 30 seconds. In order to more accurately predict the temperature change during the charging period, charging segment extraction processing is performed. The present application does not make special limitations on this charging segment extraction processing method. Then, the ambient temperature, battery parameters, and predicted first power are input into the temperature prediction model to predict the battery temperature of the energy storage device. The temperature prediction model in the present application can predict the temperature change within ten minutes after and after the anti-backflow strategy or anti-over-demand strategy is triggered and stopped. Without the anti-backflow strategy or anti-over-demand strategy running for a period of time and stopping for a period of time, the battery temperature change of the next energy storage device can be directly predicted based on the predicted first power.
[0049] The temperature prediction method provided by the embodiment of the present application can predict the temperature change within ten minutes after and after the anti-backflow strategy or anti-over-demand strategy is triggered and stopped. Without the anti-backflow strategy or anti-over-demand strategy running for a period of time and stopping for a period of time, the battery temperature change of the next energy storage device can be directly predicted based on the predicted first power. The temperature prediction method provided by the embodiment of the present application combines the specific charge and discharge strategies of industrial and commercial energy storage devices, uses the power load prediction algorithm to dynamically process the power adjustment of the energy storage device, and predicts the battery temperature of the energy storage device based on the predicted first power, so as to more efficiently and accurately predict the battery temperature change.
[0050] The temperature prediction device of the energy storage device provided by the embodiments of the present invention can execute the temperature prediction method of the energy storage device provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. The same parts can be referred to the description of the temperature prediction method of the energy storage device provided by the embodiments of the present invention above, and will not be repeated here.
[0051] Figure 4 It is a schematic structural diagram of an embodiment of the device of the present application. As Figure 4 shown, the above device 40 may include: An acquisition module 41, where the acquisition module 41 is used to acquire the ambient temperature and the battery parameters of the energy storage device; the acquisition module is further used to acquire the current first power, third power, and fourth power of the energy storage device, where the current first power is used to characterize the current operating power of the energy storage device, the third power is used to characterize the anti-backflow threshold power of the energy storage device, and the fourth power is used to characterize the anti-over-demand threshold power of the energy storage device; A calculation module 42, where the calculation module 42 is used to calculate the second power of the energy storage device, and the second power is used to characterize the load power of the energy storage device; if the difference between the second power and the current first power is not less than the fourth power, then judge the state of the energy storage device; A compensation module 43, where the compensation module 43 is used to, if the energy storage device is in a charging state, take the current first power as a standard to compensate the predicted first power, and the predicted first power is used to characterize the predicted operating power of the energy storage device; judge whether the difference between the second power and the compensated predicted first power is less than the fourth power; if the difference between the second power and the compensated predicted first power is less than the fourth power, then output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, then add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power; The compensation module 43 is further used to, if the energy storage device is in a discharging state, take the current first power as a standard to compensate the predicted first power; judge whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, then output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, then add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power; The compensation module 43 is further configured to set the predicted first power to zero if the energy storage device is in a static fully charged state; determine whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, add the preset first adjustment value to the predicted first power until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power. A prediction module 44, and the prediction module 44 is further configured to predict the battery temperature of the energy storage device based on the ambient temperature, the battery parameters, and the predicted first power.
[0052] In one possible implementation manner, the battery parameters include SOC parameters and SOH parameters.
[0053] In one possible implementation manner, the calculation module 42 is further configured to calculate the second power of the energy storage device based on the historical power data, date data, weather conditions, and air quality of the energy storage device.
[0054] In one possible implementation manner, the calculation module 42 is further configured to input the historical power data, date data, weather conditions, and air quality of the energy storage device into a preset model, output the power load demand of the energy storage device, and calculate the second power of the energy storage device.
[0055] In one possible implementation manner, the temperature prediction device further includes an adjustment module 45, and the adjustment module 45 is configured to adjust the predicted first power based on the current first power and a preset second adjustment value if the difference between the second power and the current first power is not greater than the third power.
[0056] In one possible implementation manner, the adjustment module 45 is configured to increase the predicted first power until the charging state stops if the energy storage device is in a charging state; increase the predicted first power for discharging if the energy storage device is in a discharging state; and increase the predicted first power for discharging if the energy storage device is in a static fully charged state.
[0057] In one possible implementation, the compensation module 43 is configured to: if the difference between the second power and the current first power is not greater than the third power, compensate the predicted first power based on the current first power; determine whether the difference between the second power and the predicted first power is greater than the third power; if the difference between the second power and the predicted first power is greater than the third power, output the predicted first power; if the difference between the second power and the predicted first power is not greater than the third power, subtract a preset second adjustment value from the predicted first power until the difference between the second power and the current first power is greater than the third power, and output the adjusted predicted first power.
[0058] In one possible implementation, the prediction module 44 is further configured to train a temperature prediction model through the second power, the ambient temperature, the battery parameters, and the power of the liquid chiller; and input the ambient temperature, the battery parameters, and the predicted first power into the temperature prediction model to predict the battery temperature of the energy storage device.
[0059] Next, in conjunction with Figure 5 the exemplary electronic device provided in the embodiments of the present application will be further introduced. Figure 5 FIG. shows a schematic structural diagram of an electronic device 500.
[0060] The above-mentioned electronic device 500 may include: at least one processor; and at least one memory communicatively connected to the above-mentioned processor, wherein: the above-mentioned memory stores program instructions executable by the above-mentioned processor, and the processor can execute the temperature prediction method of the energy storage device provided in the embodiments shown in the present application by invoking the above-mentioned program instructions.
[0061] Figure 5 FIG. shows a block diagram of an exemplary electronic device 500 suitable for implementing the embodiments of the present application. Figure 5 The shown electronic device 500 is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.
[0062] As Figure 5 shown, the electronic device 500 is presented in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: one or more processors 510, a memory 520, a communication bus 540 connecting different system components (including the memory 520 and the processor 510), and a communication interface 530.
[0063] The communication bus 540 represents one or more of several types of bus architectures, including a memory bus or memory controller, a peripheral bus, an Accelerated Graphics Port, a processor, or a local bus using any of the various bus architectures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnection (PCI) bus.
[0064] The electronic device 500 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device, including volatile and nonvolatile media, removable and non-removable media.
[0065] The memory 520 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device may further include other removable / non-removable, volatile / nonvolatile computer system storage media. Although Figure 3 not shown in the figure, a disk drive for reading and writing to a removable nonvolatile magnetic disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable nonvolatile optical disk (such as a Compact Disc Read Only Memory (CD-ROM), a Digital Video Disc Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to the communication bus 540 via one or more data media interfaces. The memory 520 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present application.
[0066] A program / util utility having a set (at least one) of program modules can be stored in the memory 520. Such program modules include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The program modules generally execute the functions and / or methods in the embodiments described in this application.
[0067] The electronic device 500 can also communicate with one or more external devices (such as a keyboard, a pointing device, a display, etc.), can also communicate with one or more devices that enable a user to interact with the electronic device, and / or can communicate with any device that enables the electronic device to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through the communication interface 530. And, the electronic device 500 can also communicate with one or more networks (such as a Local Area Network (LAN), a Wide Area Network (WAN), and / or a public network, such as the Internet) through a network adapter ( Figure 5 not shown in the figure). The above network adapter can communicate with other modules of the electronic device through the communication bus 540. It should be understood that although Figure 5 not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, Redundant Arrays of Independent Drives (RAID) systems, tape drives, and data backup storage systems, etc.
[0068] The processor 510 executes various functional applications and data processing by running the programs stored in the memory 520, such as implementing the method provided in the embodiments of this application.
[0069] It can be understood that the interface connection relationship between the modules illustrated in the embodiments of this application is only for illustrative purposes and does not constitute a structural limitation on the electronic device 500. In other embodiments of this application, the electronic device 500 can also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.
[0070] In the above embodiments, the involved processor may include, for example, a CPU, a DSP, a microcontroller or a digital signal processor, and may also include a GPU, an embedded neural-network processor (hereinafter referred to as: NPU) and an image signal processor (hereinafter referred to as: ISP). The processor may further include necessary hardware accelerators or logic processing hardware circuits, such as an ASIC, or one or more integrated circuits for controlling the execution of the program of the technical solution of the present application. In addition, the processor may have the function of operating one or more software programs, and the software programs may be stored in a storage medium.
[0071] The embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored. When it runs on a computer, it enables the computer to execute the temperature prediction method provided by the embodiment shown in the present application.
[0072] The embodiment of the present application also provides a computer program product, which includes a computer program. When it runs on a computer, it enables the computer to execute the temperature prediction method provided by the embodiment shown in the present application.
[0073] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.
[0074] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.
[0075] In several embodiments provided by the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may 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 various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (hereinafter referred to as ROM), random access memories (hereinafter referred to as RAM), magnetic disks, or optical discs that can store program codes.
[0076] The foregoing are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.
[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention.
Claims
1. A temperature prediction method, characterized in that: Applied to energy storage equipment, the method comprises: Acquiring ambient temperature and battery parameters of the energy storage device; Acquire a current first power, a third power, and a fourth power of the energy storage device, wherein the current first power is used to characterize the current operating power of the energy storage device, the third power is used to characterize the anti-backflow threshold power of the energy storage device, and the fourth power is used to characterize the anti-over-demand threshold power of the energy storage device; Calculating a second power of the energy storage device, where the second power is used to characterize the load power of the energy storage device; if a difference between the second power and the current first power is not less than the fourth power, determining the state of the energy storage device; If the energy storage device is in a charging state, the predicted first power is compensated based on the current first power, and the predicted first power is used to characterize the predicted operating power of the energy storage device; it is determined whether the difference between the second power and the predicted first power after compensation is less than the fourth power; if the difference between the second power and the predicted first power after compensation is less than the fourth power, the predicted first power is output; if the difference between the second power and the predicted first power is not less than the fourth power, the predicted first power is added with a preset first adjustment value until the difference between the second power and the current first power is less than the fourth power, and the adjusted predicted first power is output; If the energy storage device is in a discharging state, the predicted first power is compensated based on the current first power; it is determined whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, the predicted first power is output; if the difference between the second power and the predicted first power is not less than the fourth power, the predicted first power is added to the preset first adjustment value until the difference between the second power and the current first power is less than the fourth power, and the adjusted predicted first power is output; If the energy storage device is in a static fully charged state, the predicted first power is set to zero; determine whether the difference between the second power and the predicted first power is less than the fourth power; if the difference between the second power and the predicted first power is less than the fourth power, output the predicted first power; if the difference between the second power and the predicted first power is not less than the fourth power, add the predicted first power to the preset first adjustment value until the difference between the second power and the current first power is less than the fourth power, and output the adjusted predicted first power; Predicting a battery temperature of the energy storage device based on the ambient temperature, the battery parameter, and the predicted first power; The calculating the second power of the energy storage device comprises: Calculating a second power of the energy storage device based on historical power data, date data, weather conditions, and air quality of the energy storage device; The method further comprises: If the difference between the second power and the current first power is not greater than the third power, adjusting the predicted first power based on the current first power and a preset second adjustment value; The adjusting the predicted first power based on the current first power and the preset second adjustment value includes: If the difference between the second power and the current first power is not greater than the third power, compensating the predicted first power based on the current first power; Determine whether a difference between the second power and the predicted first power is greater than the third power; If the difference between the second power and the predicted first power is greater than the third power; outputting the predicted first power; If the difference between the second power and the predicted first power is not greater than the third power, the predicted first power is subtracted from the preset second adjustment value until the difference between the second power and the current first power is greater than the third power, and the adjusted predicted first power is output.
2. The temperature prediction method according to claim 1, characterized in that: The battery parameters include SOC parameters and SOH parameters.
3. The temperature prediction method according to claim 1, characterized in that: The calculating the second power of the energy storage device based on the historical power data, date data, weather conditions and air quality of the energy storage device comprises: The historical power data, date data, weather conditions and air quality of the energy storage device are input into a preset model, the power load demand of the energy storage device is output, and the second power of the energy storage device is calculated.
4. The temperature prediction method according to claim 3, characterized in that: The determining the state of the energy storage device and adjusting the first power includes: If the energy storage device is in a charging state, increasing the predicted first power until the charging state is stopped; If the energy storage device is in a discharging state, increasing the predicted first power for discharging; If the energy storage device is in a static fully charged state, the predicted first power is increased for discharge.
5. The temperature prediction method according to claim 1, characterized in that: The energy storage device further includes a liquid cooler, and predicting the battery temperature of the energy storage device based on the ambient temperature, the battery parameter, and the predicted first power includes: Training a temperature prediction model through the second power, the ambient temperature, the battery parameters, and the power of the liquid cooler; The ambient temperature, the battery parameters and the predicted first power are input into the temperature prediction model to predict the battery temperature of the energy storage device.
6. The temperature prediction method according to claim 1, characterized in that: The method further comprises: If the second power is greater than the third power and the second power is less than the fourth power, the predicted first power is the second power.
7. The temperature prediction method according to claim 5, characterized in that: Before training the temperature prediction model, the method further includes: Data processing is performed on the second power, the ambient temperature, the battery parameters, and the power of the liquid cooler, wherein the data processing includes missing value processing, charging segment extraction processing, and normalization processing.
8. The temperature prediction method according to claim 3, characterized in that: The preset models are convolutional neural network and long short-term memory network models.
9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store a computer program; the processor is used to run the computer program, and when the computer program is run on a computer, the temperature prediction method according to any one of claims 1 to 8 is implemented.
10. An energy storage system, characterized in that: include: A battery pack, a PCS and an EMS, wherein the EMS implements the temperature prediction method as described in any one of claims 1-8.