CN116864871A - Thermal management method of energy storage system and training method of thermal management regulation model - Google Patents
Thermal management method of energy storage system and training method of thermal management regulation model Download PDFInfo
- Publication number
- CN116864871A CN116864871A CN202310761174.9A CN202310761174A CN116864871A CN 116864871 A CN116864871 A CN 116864871A CN 202310761174 A CN202310761174 A CN 202310761174A CN 116864871 A CN116864871 A CN 116864871A
- Authority
- CN
- China
- Prior art keywords
- energy storage
- storage system
- temperature
- thermal management
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 297
- 230000033228 biological regulation Effects 0.000 title claims abstract description 154
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012549 training Methods 0.000 title claims abstract description 52
- 238000007726 management method Methods 0.000 title abstract description 191
- 230000001105 regulatory effect Effects 0.000 claims abstract description 114
- 230000009471 action Effects 0.000 claims abstract description 72
- 230000001276 controlling effect Effects 0.000 claims abstract description 32
- 230000006870 function Effects 0.000 claims description 134
- 238000004088 simulation Methods 0.000 claims description 43
- 230000007613 environmental effect Effects 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 12
- 238000009499 grossing Methods 0.000 abstract description 8
- 238000001816 cooling Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010438 heat treatment Methods 0.000 description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 9
- 230000002787 reinforcement Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 239000003795 chemical substances by application Substances 0.000 description 4
- 239000000110 cooling liquid Substances 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 238000012983 electrochemical energy storage Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000005057 refrigeration Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/092—Reinforcement learning
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/61—Types of temperature control
- H01M10/613—Cooling or keeping cold
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/61—Types of temperature control
- H01M10/615—Heating or keeping warm
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/62—Heating or cooling; Temperature control specially adapted for specific applications
- H01M10/627—Stationary installations, e.g. power plant buffering or backup power supplies
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/60—Heating or cooling; Temperature control
- H01M10/63—Control systems
- H01M10/633—Control systems characterised by algorithms, flow charts, software details or the like
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Chemical & Material Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Automation & Control Theory (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The specification relates to a thermal management method of an energy storage system and a training method of a thermal management regulation model. The thermal management method comprises the following steps: acquiring charge and discharge power data and temperature data of an energy storage system; inputting the charge and discharge power data and the temperature data into a target thermal management regulation model to obtain regulation action parameters for carrying out thermal management on the energy storage system; the regulation and control action parameters are used for regulating and controlling a temperature regulating device of the energy storage system, so that the power consumption of the temperature regulating device meets preset conditions and the temperature of the energy storage system reaches a target temperature. According to the embodiment of the specification, the temperature state and the charge and discharge state of the energy storage system can be considered at the same time, the target thermal management regulation model is utilized for predicting regulation parameters, and the purposes of reducing the power consumption of the temperature regulation device and smoothing and accurately controlling the temperature of the energy storage system are achieved.
Description
Technical Field
The present disclosure relates to the field of thermal management technologies, and in particular, to a thermal management method of an energy storage system and a training method of a thermal management regulation model.
Background
The large-scale and commercial development of electrochemical energy storage is not possible. While safe and efficient operation of electrochemical energy storage relies on temperature control of the thermal management system.
The temperature control strategy of the related art thermal management system generally determines whether cooling or heating should be performed according to the highest temperature and the lowest temperature of the battery pack of the energy storage system. However, this strategy can have problems with regulatory hysteresis, overshoot, and the like.
Disclosure of Invention
The present specification aims to solve at least one of the technical problems in the related art to some extent. Therefore, an object of the present disclosure is to provide a thermal management method for an energy storage system, which considers the working state and the temperature state of the energy storage system, and performs thermal management on the energy storage system, so as to ensure the temperature stability of the energy storage system and reduce the power consumption of a temperature adjusting device.
A second object of the present disclosure is to provide a training method for a thermal management control model.
A third object of the present disclosure is to provide a thermal management device of an energy storage system.
A fourth object of the present disclosure is to provide a training device for a thermal management control model.
A fifth object of the present disclosure is to provide an energy storage system.
A sixth object of the present specification is to propose a computer readable storage medium.
To achieve the above object, an embodiment of a first aspect of the present disclosure provides a method for thermal management of an energy storage system. The method comprises the following steps: acquiring charge and discharge power data and temperature data of an energy storage system; inputting the charge and discharge power data and the temperature data into a target thermal management regulation model to obtain regulation action parameters for carrying out thermal management on the energy storage system; the regulation and control action parameters are used for regulating and controlling a temperature regulating device of the energy storage system, so that the power consumption of the temperature regulating device meets preset conditions and the temperature of the energy storage system reaches a target temperature.
In some embodiments of the present description, the target thermal management regulation model is trained by:
acquiring environment state variables and action variables of the energy storage system at different moments in a history preset period; the environment state variables comprise charge and discharge power variables of the energy storage system and temperature variables of the energy storage system; the action variables comprise regulatory action variables for performing thermal management on the energy storage system; constructing a reward function of the thermal management regulation model by taking the power consumption of the temperature regulating device in the historical preset period as a target that the preset condition is met and the temperature of the energy storage system reaches the target temperature; and taking the environmental state variable and the action variable as the input of the thermal management regulation model, and updating the parameters of the thermal management regulation model based on the value of the reward function to obtain a target thermal management regulation model.
In some embodiments of the present disclosure, the constructing a reward function of the thermal management control model with the objective that the power consumption of the temperature adjustment device in the historical preset period satisfies the preset condition and the temperature of the energy storage system reaches the target temperature includes: constructing a first main line rewarding function according to the difference value between the maximum historical power consumption of the temperature regulating device and the total power consumption of the temperature regulating device in the historical preset period; constructing a second main line rewarding function according to absolute differences between temperature data of the temperature variable of the energy storage system at different moments in the historical preset period and target temperatures corresponding to different moments; and constructing the reward function according to the first mainline reward function and the second mainline reward function.
In some embodiments of the present description, the reward function includes a mainline reward function and a spur penalty term; constructing the bonus function from the first and second dominant bonus functions, comprising: according to a first weight coefficient corresponding to the first main line rewarding function and a second weight coefficient corresponding to the second main line rewarding function, carrying out weighted summation on the first main line rewarding function and the second main line rewarding function to obtain the main line rewarding function; determining the branch line punishment term according to the product of the times that the temperature of the energy storage system exceeds a preset temperature range in the history preset period and a third weight coefficient; and carrying out difference solving on the main line reward function and the branch line penalty term to obtain the reward function.
In some embodiments of the present disclosure, constructing a second main line bonus function according to absolute differences between temperature data of the temperature variable of the energy storage system at different times within the history preset period and target temperatures corresponding to different times includes: determining a first branch item of the second main line rewarding function according to the sum of squares of absolute differences of temperature data of the temperature variable of the energy storage system at different moments in the history preset period and target temperatures corresponding to different moments; determining a sum of squares of the target temperatures at different moments as a second branch term of the second main line bonus function; and carrying out difference solving on the second branch item and the first branch item to obtain the second main line reward function.
In some embodiments of the present description, the method further comprises: acquiring historical operation data of the energy storage system and historical working parameters of the temperature regulating device; training the constructed physical field simulation model based on the historical operation data and the historical working parameters to obtain a target physical field simulation model; the target physical field simulation model is used for solving temperature data of the energy storage system at the next moment according to the operation data of the energy storage system at the current moment and the working parameters of the temperature regulating device.
In some embodiments of the present description, the method further comprises: and acquiring environmental state variables and action variables of the energy storage system at different moments in a preset period through the target physical field simulation model.
To achieve the above objective, an embodiment of a second aspect of the present disclosure provides a method for training a thermal management control model. The training method of the thermal management regulation model comprises the following steps: acquiring environment state variables and action variables of the energy storage system at different moments in a preset period; the environment state variables comprise charge and discharge power variables of the energy storage system and temperature variables of the energy storage system; the action variables comprise regulatory action variables for performing thermal management on the energy storage system; constructing an objective function of the thermal management regulation model by taking the power consumption of the temperature regulating device for thermal management in the preset period of time as a target, wherein the power consumption of the temperature regulating device for thermal management meets a preset condition, and the temperature of the energy storage system reaches a target temperature; and taking the environmental state variable and the action variable as the input of the thermal management control model, and updating the parameters of the thermal management control model based on the value of the objective function to obtain the objective thermal management control model.
To achieve the above object, embodiments of a third aspect of the present disclosure provide a thermal management device of an energy storage system. The thermal management device of the energy storage system includes: the acquisition module is used for acquiring charge and discharge power data and temperature data of the energy storage system; the regulation and control action determining module is used for inputting the charge and discharge power data and the temperature data into a target thermal management regulation and control model to obtain regulation and control action parameters for carrying out thermal management on the energy storage system; the regulation and control action parameters are used for regulating and controlling a temperature regulating device of the energy storage system, so that the power consumption of the temperature regulating device meets preset conditions and the temperature of the energy storage system reaches a target temperature.
To achieve the above object, a fourth aspect of the present disclosure provides a training device for a thermal management control model. The training device of the thermal management regulation model comprises: the sample acquisition module is used for acquiring environment state variables and action variables of the energy storage system at different moments in a preset period; the environment state variables comprise charge and discharge power variables of the energy storage system and temperature variables of the energy storage system; the action variables comprise regulatory action variables for performing thermal management on the energy storage system; the target function determining module is used for constructing a target function of the thermal management regulation model by taking the power consumption of the temperature regulating device for thermal management in the preset period of time as a target, wherein the power consumption of the temperature regulating device for thermal management meets a preset condition, and the temperature of the energy storage system reaches a target temperature; and the training module is used for updating parameters of the thermal management control model based on the value of the objective function by taking the environmental state variable and the action variable as the input of the thermal management control model to obtain the objective thermal management control model.
To achieve the above object, an embodiment of a fifth aspect of the present specification proposes an energy storage system. The energy storage system comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the method according to any one of the embodiments of the first aspect.
To achieve the above object, an embodiment of a sixth aspect of the present specification proposes a computer-readable storage medium. The computer readable storage medium comprises a stored computer program, wherein the computer program when run controls a device in which the computer readable storage medium is located to perform the method according to any one of the embodiments of the first aspect.
Through the embodiment, when the energy storage system is thermally managed, the temperature data and the charge and discharge power data are utilized, and the regulation and control action parameters for thermally managing the energy storage system are predicted through the target thermal management regulation and control model. And then, regulating and controlling the temperature regulating device by utilizing the regulating and controlling action parameters, so that the power consumption of the temperature regulating device meets the preset condition and the temperature of the energy storage system reaches the target temperature. According to the embodiment of the specification, the temperature state and the charge and discharge state of the energy storage system are considered at the same time, the target thermal management regulation model is utilized for predicting regulation parameters, and the purposes of reducing the power consumption of the temperature regulation device and smoothing and accurately controlling the temperature of the energy storage system are achieved.
Additional aspects and advantages of the present description will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the present description.
Drawings
Fig. 1a is a schematic diagram of an energy storage system thermal management system provided in an embodiment of the present disclosure.
Fig. 1b is a schematic diagram of an energy storage system according to an embodiment of the present disclosure.
Fig. 2 is a flow chart of a method of thermal management of an energy storage system of an embodiment of the present disclosure.
FIG. 3a is a line drawing of a thermal management simulation of an energy storage system according to one embodiment of the present disclosure.
Fig. 3b is a line drawing of thermal management of an energy storage system according to one embodiment of the present disclosure.
FIG. 4 is a flow chart of a method of training a thermal management regulation model provided in an embodiment of the present disclosure.
Fig. 5 is a block diagram of a thermal management device of an energy storage system according to an embodiment of the present disclosure.
FIG. 6 is a block diagram of a thermal management regulation model training apparatus according to an embodiment of the present disclosure.
Fig. 7 is a functional block diagram of an energy storage system of an embodiment of the present description.
Detailed Description
Embodiments of the present specification are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of illustrating the present description and are not to be construed as limiting the present description.
Clean replacement of global energy is urgent, and large-scale and commercial development of electrochemical energy storage is also impossible. Along with the change of the supply and demand relationship of raw materials, the energy storage participation electric power market mechanism steps into the deepwater area, and the energy storage economy and the demand are also changed in an important way. Safe and efficient operation of electrochemical energy storage relies on temperature control of the thermal management system.
The temperature control strategy of the heat management in the related art is simpler, and the temperature control device is judged to be heating, circulating (the compressor is turned off) or refrigerating according to the highest temperature and/or the lowest temperature of the battery PACK. The battery PACK generally refers to a combined battery, mainly refers to processing and assembling of a lithium battery PACK, and mainly comprises a battery core, a battery protection plate, a battery connecting sheet, label paper and the like which are combined and processed into products required by customers through a battery PACK process. Multiple battery PACKs may be included in the energy storage system.
In the related art, after energy storage is started, the working state of the water chilling unit is adjusted according to the change of the temperature of the battery PACK, and the following problems generally exist:
first, hysteresis and overshoot are regulated. After the energy storage system stops charging and discharging and enters a standby state, the temperature of the battery cell is higher at the moment. After the temperature detection, the compressor of the temperature regulating device is still judged to be started for refrigeration, so that unnecessary waste is caused. Likewise, the same start and stop temperatures used under different charge and discharge rates of the energy storage system can cause unnecessary overshoot and cause temperature fluctuations.
Secondly, the overshoot causes rapid temperature fluctuation of the battery cells, so that the maximum temperature difference between the battery cells can be increased, the inconsistency is aggravated, and the service life of the battery cells is reduced.
Thirdly, because of inaccuracy of temperature control, a larger margin is reserved for the temperature control target in order to prevent temperature out-of-limit alarm. For example, the battery PACK temperature control target could be set to an upper limit of 35 c and to reduce the temperature overrun could be set to only 32 c.
Aiming at the problems in the related art, the specification provides a thermal management method of an energy storage system and a training method of a thermal management regulation model. According to the energy storage system, the heat management can be carried out on the energy storage system by considering the charge and discharge working state of the energy storage system and the temperature state of the energy storage battery, so that the power consumption of the temperature regulation and control device can be reduced under the condition that the temperature of the energy storage system is kept stable.
The embodiments of the present disclosure provide an example of a scenario of a thermal management method of an energy storage system, where the thermal management method of an energy storage system is applied to the thermal management system of an energy storage system shown in fig. 1 a. The energy storage system thermal management system includes an energy storage system 102, a client 104, and a server 106. The server 106 is used to train the thermal management regulation model.
The specific composition of the energy storage system 102 may be referred to in fig. 1b. The energy storage system 102 includes a plurality of battery modules, each of which is comprised of a plurality of battery PACKs 110. A temperature measuring point is provided on each battery PACK110 to measure the temperature of the battery PACK 110. The energy storage system 102 also includes a temperature regulation device 120, such as a water chiller. As shown in fig. 1b, the temperature control device 120 may be disposed on the left side of the container of the energy storage system, and the air inlet and outlet mode is front inlet top outlet. The system flow channel is designed to be lower in and upper out, the cooling liquid flows to 6 branches through a water inlet pipeline, and each branch is divided into 8 small branches to flow to the liquid cooling PACK to cool or heat the battery cell. And after the cooling liquid flows out of the PACK, the cooling liquid is collected to a water return pipeline through a branch pipeline and returns to the water cooling unit, so that circulation is formed.
The energy storage system 102 is also typically configured with a local controller that is capable of collecting charge and discharge power data of the energy storage system 102.
In this scenario example, the energy storage system 102 is communicatively coupled to a client 104 and a server 106, respectively. The energy storage system 102 may provide training sample data for the thermal management regulation model to the server 106. The target thermal management regulation model trained by the server 106 may be configured at the client 104, where the thermal management regulation is performed on the energy storage system at the client 104. The trained target thermal management regulation model may also be configured directly in the energy storage system 102, such that the energy storage system 102 is capable of automatically performing thermal management regulation.
The thermal management regulation model can be built by using a near-end strategy optimization algorithm in deep reinforcement learning. The training process of the server 106 on the thermal management regulation model includes: environmental state variables and action variables of the energy storage system 102 at different moments in a history preset period are acquired. The environmental state variables include charge and discharge power variables of the energy storage system 102, temperature variables of the energy storage system. The action variables include regulatory action variables that thermally manage the energy storage system. And constructing a reward function of the thermal management regulation model by taking the power consumption of the temperature regulating device in the historical preset period as a target that the power consumption meets the preset condition and the temperature of the energy storage system reaches the target temperature. And taking the environmental state variable and the action variable as the input of the thermal management regulation model, and updating the parameters of the thermal management regulation model based on the value of the reward function to obtain the target thermal management regulation model.
Take the example of a target thermal management regulation model configuration at client 104. First, the client 104 obtains the charge-discharge power data and the temperature data of the energy storage system 102. And inputting the charge and discharge power data and the temperature data into a target thermal management regulation model, and obtaining regulation action parameters for carrying out thermal management on the energy storage system through the processing of the target thermal management regulation model. The client 104 regulates and controls the temperature regulating device of the energy storage system 104 based on the regulating action parameters, so that the temperature regulating device refrigerates or heats the battery module of the energy storage system, and the power consumption of the temperature regulating device meets the preset condition and the temperature of the energy storage system reaches the target temperature. Through the regulation and control process, the charge and discharge working states and the temperature states of the energy storage system are considered in the thermal management process of the energy storage system 102, and the working states of the temperature regulating device can be timely regulated according to the charge and discharge power of the energy storage system, so that the whole temperature of the energy storage system is kept in a stable state, and the power consumption of the temperature regulating device is correspondingly reduced due to the reduction of the regulation and control lag or overshoot.
FIG. 2 is a flow chart of a method of thermal management of an energy storage system according to an embodiment of the present disclosure. Referring to fig. 2, the thermal management method of the energy storage system includes:
s210, acquiring charge and discharge power data and temperature data of an energy storage system.
S220, the charge and discharge power data and the temperature data are input into a target thermal management regulation model, and regulation action parameters for carrying out thermal management on the energy storage system are obtained.
The regulation and control action parameters are used for regulating and controlling a temperature regulating device of the energy storage system, so that the power consumption of the temperature regulating device meets preset conditions and the temperature of the energy storage system reaches the target temperature.
In the embodiment of the present disclosure, the target thermal management regulation model is configured to calculate, based on charge and discharge power data and temperature data of the energy storage system, a regulation and control action parameter for performing thermal management on the energy storage system, with power consumption of the thermal management temperature regulation device meeting a preset condition and temperature of the energy storage system reaching a target temperature as a target.
The temperature data comprise temperature data of different battery PACKs in the energy storage system. In general, the thermal management regulation and control period of the energy storage system can be unified with the power dispatching period of the energy storage system, and the step length can be set independently, for example, 1min and 5min. One step length is a regulation and control period, and one regulation and control period can be recorded as one moment.
When the target thermal management regulation model is utilized to predict regulation action parameters, the charge and discharge power data and the temperature data of the energy storage system at the moment can be obtained. And the charge and discharge power data and the temperature data at the moment are input into a target thermal management regulation model to obtain regulation action parameters for thermally managing the energy storage system at the next moment. And regulating and controlling the temperature regulating device of the energy storage system at the next moment based on the obtained regulating and controlling action parameters. The temperature regulating device is regulated and controlled according to the predicted regulating action parameters at continuous moments, so that the power consumption of the temperature regulating device can meet preset conditions and the temperature of the energy storage system reaches the target temperature. The temperature of the energy storage system can be the temperature of a specified battery PACK, the highest temperature in all battery PACKs, or the average temperature of the battery PACK, and is specifically determined according to the temperature control requirement of the energy storage system.
In order to reduce the waste of power consumption, the preset condition of the temperature adjusting device may be that the total power consumption of the temperature adjusting device is minimum in a preset period. That is, the temperature regulation and control device regulates and controls at each moment in the preset time period based on the regulating and controlling action parameters predicted by the target thermal management regulating and controlling model, so that the total power consumption of the temperature regulation and control device in the preset time period can be minimized.
In a preset period, the temperature of the energy storage system at each moment can be close to the target temperature by regulating and controlling the temperature regulating and controlling device at the next moment based on the regulating and controlling action parameters predicted by the target thermal management regulating and controlling model. Therefore, the overall temperature of the energy storage system in a preset period tends to be smooth and accurate, the temperature difference caused by overshoot is reduced, and the service life of the battery cell is reduced. And moreover, the more accurate temperature control capability can enable the energy storage system to have a more flexible temperature control range. Under the condition that the temperature of the battery PACK does not generate out-of-limit alarm, the battery PACK works at the upper temperature limit as much as possible, so that the power consumption of the temperature regulating device is reduced, the efficiency of the energy storage system is effectively improved, and the return on investment of the energy storage system is improved.
Through the embodiment, when the energy storage system is thermally managed, the temperature data and the charge and discharge power data are utilized, and the regulation and control action parameters for thermally managing the energy storage system are predicted through the target thermal management regulation and control model. And then, regulating and controlling the temperature regulating device by utilizing the regulating and controlling action parameters, so that the power consumption of the temperature regulating device meets the preset condition and the temperature of the energy storage system reaches the target temperature. According to the embodiment of the specification, the temperature state and the charge and discharge state of the energy storage system are considered at the same time, the target thermal management regulation model is utilized for predicting regulation parameters, and the purposes of reducing the power consumption of the temperature regulation device and smoothing and accurately controlling the temperature of the energy storage system are achieved.
In some embodiments of the present description, the target thermal management regulation model is trained by:
and acquiring environment state variables and action variables of the energy storage system at different moments in a history preset period. The environment state variables comprise charge and discharge power variables of the energy storage system and temperature variables of the energy storage system; the action variables include regulatory action variables that thermally manage the energy storage system. And constructing a reward function of the thermal management regulation model by taking the power consumption of the temperature regulating device in the historical preset period as a target that the power consumption meets the preset condition and the temperature of the energy storage system reaches the target temperature. And taking the environmental state variable and the action variable as input of the thermal management regulation model, and updating parameters of the thermal management regulation model based on the value of the reward function to obtain the target thermal management regulation model.
By way of example, an initial thermal management regulation model is constructed according to a near-end policy optimization algorithm with the actual power environment in which the thermal management energy storage system is located as a theoretical basis. And meanwhile, determining the regulation and control period of the temperature regulating device according to the actual regulation and control requirements. For example, the regulation period of the temperature regulating device may be consistent with the scheduling period of the charge-discharge scheduling of the energy storage system, or the step size may be set independently. For example, if the step length is set to 5min, one regulation cycle is 5min, and one day includes 288 regulation cycles. One time corresponds to one regulation cycle.
Based on the established initial thermal management regulation model, establishing a minimum energy consumption objective function of a temperature regulating device for thermal management, and establishing constraint conditions of the thermal management regulation model. And simultaneously, establishing a state observation space, an action space and a reward function required by the thermal management regulation model. Wherein the bonus function is designed according to the objective function and the constraint condition. And (3) taking the state variable and the action variable at the time t as the input of a strategy network and an action network of the model, and performing iterative training on the thermal management regulation model by utilizing a strategy gradient and time sequence difference method to obtain an optimal real-time regulation model for performing thermal management on the energy storage system, namely a target thermal management regulation model.
In the embodiment of the present disclosure, the power consumption of the temperature adjustment device meeting the preset condition may be that the total power consumption of the temperature adjustment device is the lowest. The temperature of the energy storage system reaching the target temperature may be understood as having a minimum difference between the temperature of the energy storage system and the target temperature. And the target function is established by taking the minimum total power consumption of the temperature regulating device for heat management within a certain period and the minimum difference between the temperature of the energy storage system and the target temperature as targets. Based on the objective function, the upper limit temperature and the lower limit temperature preset for the battery PACK of the energy storage system are taken into consideration as constraint conditions, and a reward function of the thermal management regulation model is constructed.
Acquiring environment state variables s of an energy storage system at different moments in a history preset period t And action variable a t . Wherein the environmental state variable s t Charge-discharge power variable p including energy storage system t Temperature variable T of energy storage system t The method comprises the steps of carrying out a first treatment on the surface of the Action variable a t Including regulatory action variables that thermally manage the energy storage system. The regulating action variable represents the power of the temperature regulating device at the moment t, and the value of the regulating action variable can be positive or negative. The positive direction representing refrigerationThe negative direction indicates heating, 0 indicates that the compressor of the thermostat is stopped and only the circulation pump is turned on. The environment state variable is the state variable corresponding to the state observation space. The motion variable is the motion variable corresponding to the motion space. In the embodiments of the present specification, the charge-discharge power variable represents the charge-discharge power data corresponding at different times; the temperature variables represent corresponding temperature data at different times.
Specifically, the energy storage system may be used as an agent in a deep reinforcement learning environment when training the thermal management regulation model. The intelligent agent executes the optimal action to interact with the intelligent agent environment, so that the instant rewards and the next environment state variables can be obtained. The current environmental state variable, the optimal action variable, the instant prize, and the next environmental state variable constitute a transfer experience, which is stored in a buffer.
For example, the history preset period may generally select a day of history to train the thermal management regulation model in a training round of one day. If the step length is set to be 5min, the history preset period comprises 288 regulation and control periods, namely 288 corresponding moments. The battery PACK temperature is too high to cause safety problems, while the temperature is too low to affect the performance of the energy storage system. Therefore, to reduce the occurrence of safety problems, the highest temperature in the plurality of battery PACKs of the energy storage system may be used as temperature data of the energy storage system.
Acquiring environmental state variables s of energy storage system at 288 moments in certain day of history t {p t ,T t Sum of action variables a t . Wherein p is t Representing the charge and discharge power of the energy storage system at the time t; t (T) t Representing the maximum temperature T of the battery PACK in the energy storage system at the time T max . And constructing a reward function by taking the aim that the total power consumption of the temperature regulating device is the lowest and the difference between the temperature of the energy storage system and the target temperature is the smallest in a certain day. The environment state variables s corresponding to 288 moments t {p t ,T t Sum of action variables a t As the input of a strategy network and an action network of a thermal management regulation model, the { s } obtained by multiple interactions of an agent with the environment is based on the value of a reward function t ,a t, s t+1 ,r t And updating model parameters in the strategy neural network by utilizing a near-end strategy optimization algorithm, and continuously updating iteration until the model converges to obtain a target thermal management regulation model. Wherein r is t A value representing a bonus function corresponding to time t; s is(s) t+1 The environmental state variable at time t+1 is represented.
In some embodiments of the present disclosure, constructing a reward function of a thermal management regulation model with a goal that power consumption of a temperature regulation device in a historical preset period satisfies a preset condition and a temperature of an energy storage system reaches a target temperature includes: and constructing a first main line rewarding function according to the difference value between the historical maximum total power consumption of the temperature regulating device and the total power consumption of the temperature regulating device in the historical preset period. And constructing a second main line rewarding function according to absolute difference values of temperature data of the temperature variable of the energy storage system at different moments in a historical preset period and target temperatures corresponding to different moments. And constructing the bonus function according to the first dominant line bonus function and the second dominant line bonus function.
In the embodiments of the present description, the objective function is established according to two objectives, one of which is that the power consumption of the temperature adjustment device is the lowest; the two targets are that the temperature of the energy storage system reaches the target temperature. Corresponding dominant line reward functions may thus be built separately for the two targets.
For one of the targets, if the model is trained by taking the day as one round, determining that the historical maximum total power consumption of the temperature regulating device is the historical maximum daily power consumption of the temperature regulating device as the maximum total power consumption W max . The total power consumption of the temperature regulating device in the history preset period is the power consumption W of each moment in the history preset period i And (3) summing. Determining a first main line rewarding function W according to the difference value of the first main line rewarding function W and the second main line rewarding function W k . It can be seen that the first mainline reward functionWherein k represents the number of times within a history preset period; i represents the i-th time (i-th control period).
For the two purposes, according to the temperature change of the energy storage systemAnd constructing a second main line rewarding function by measuring absolute difference values of temperature data of different moments in a history preset period and target temperatures corresponding to different moments. Since the temperature is continuously variable, a target curve can be constructed from which the target temperatures corresponding to different times can be determined. If the true temperature of the energy storage system is closer to the target temperature, the absolute difference between the two is smaller. Therefore, the absolute difference between the temperature data of the energy storage system at different moments in time in the historical preset period and the target temperature corresponding to the moment can be determined. And constructing a second main line rewarding function based on the absolute difference value corresponding to each moment in the history preset period. For example, since the temperature data of the energy storage system may be greater or less than the target temperature, the magnitude of the absolute difference between the two may be represented by the square of the difference. Second principal line reward function Wherein k represents the number of times within a history preset period; TR (TR) i Temperature data of the energy storage system at the ith moment is represented; t (T) i Indicating the target temperature corresponding to the i-th time. Δt is the sum of squares of the difference between the temperature data and the target temperature over the historical preset period, with smaller values indicating that the temperature data is closer to the target temperature.
In some embodiments of the present disclosure, constructing a second main line bonus function according to absolute differences between temperature data of a temperature variable of the energy storage system at different times in a historical preset period and a target temperature corresponding to the different times includes: and determining a first branch item of the second main line rewarding function according to the sum of squares of absolute differences between temperature data of the temperature variable of the energy storage system at different moments in a historical preset period and target temperatures corresponding to different moments. The sum of squares of the target temperatures at different times is determined as the second branch term of the second main line bonus function. And carrying out difference solving on the second branch item and the first branch item to obtain a second main line rewarding function.
Because of the near-end policy optimization algorithm, the design habit of the Reward function, reward, is generally that the larger the value of the Reward function, the better. However, Δt constructed as described above is smaller in value and closer to the target. Thus, the sum of squares of the target temperatures can be introduced as the second branch term. The second main line bonus function is constructed by the difference of the second branch term and the first branch term deltat such that a larger value of the second main line bonus function indicates that the temperature data of the energy storage system is closer to the target temperature.
Specifically, the first branch term delta T of the second main line reward function is determined according to the sum of squares of absolute differences between temperature data of different moments of the temperature variable of the energy storage system in a historical preset period and target temperatures corresponding to different moments. The construction process of the first branch term Δt may refer to the above-mentioned construction process of Δt, and will not be described again. The sum of squares of the target temperatures at different times is determined as the second branch term of the second main line bonus function. The second branch term may be represented asThe second branch term and the first branch term are differenced to obtain a second main line reward function +.>
In some embodiments of the present description, the reward function includes a mainline reward function and a spur penalty term. Constructing a bonus function from the first dominant bonus function and the second dominant bonus function, comprising: and carrying out weighted summation on the first main line rewarding function and the second main line rewarding function according to the first weight coefficient corresponding to the first main line rewarding function and the second weight coefficient corresponding to the second main line rewarding function to obtain the main line rewarding function. And determining a branch penalty term according to the product of the times that the temperature of the energy storage system exceeds the preset temperature range in the history preset period and the third weight coefficient. And differencing the main line reward function and the branch line penalty term to obtain the reward function.
In the embodiment of the present disclosure, in order to make the convergence speed of the thermal management and control model faster and the accuracy higher, the reward function needs to consider the unexpected situation of the energy storage system in the historical preset period in addition to the two targets represented by the objective function. Thus, a spur penalty term is added to reflect the incident. During thermal management of an energy storage system, the most common incident includes the temperature of the energy storage system exceeding a preset upper and lower limit temperature. Exceeding the upper temperature may create safety issues and exceeding the lower temperature may reduce the performance of the energy storage system.
For example, the branch penalty term may be constructed using the number of times the temperature of the energy storage system exceeds the preset temperature range within the historical preset period as the penalty term.
The bonus function includes a mainline bonus function and a spur penalty term. The dominant line bonus function is constructed by a first dominant line bonus function and a second dominant line bonus function. Because the main targets of the thermal management of the energy storage system in different environments are different, corresponding weight coefficients can be allocated to the first main line rewarding function, the second main line rewarding function and the punishment items.
Specifically, according to a first weight coefficient corresponding to the first main line rewarding function and a second weight coefficient corresponding to the second main line rewarding function, the first main line rewarding function and the second main line rewarding function are weighted and summed to obtain the main line rewarding function. The dominant line bonus function may be expressed as r master ＝α 1 ×W k +α 2 ×T k . Wherein alpha is 1 Representing a first weight coefficient;representing a first dominant line reward function; alpha 2 Representing a second weight coefficient; />Representing a second dominant line reward function.
Determining a branch penalty term r according to the product of the times that the temperature of the energy storage system exceeds a preset temperature range in a history preset period and a third weight coefficient branch ＝α 3 X K. Wherein alpha is 3 Representing a third weight coefficient; k represents the times that the temperature of the energy storage system exceeds the upper limit and the lower limit in the historical preset period.
Thus, the reward function r t ＝r master -r branch ＝α 1 ×W k +α 2 ×T k -α 3 X K. It will be appreciated thatIn the process of training the thermal management regulation model, three weight coefficients can be correspondingly adjusted according to the model training result.
In some embodiments of the present description, the method further comprises: historical operation data of the energy storage system and historical working parameters of the temperature adjusting device are obtained. Training the constructed physical field simulation model based on the historical operation data and the historical working parameters to obtain a target physical field simulation model. The target physical field simulation model is used for solving the temperature data of the energy storage system at the next moment according to the operation data of the energy storage system at the current moment and the working parameters of the temperature regulating device.
Because a large amount of sample data is required for training the thermal management control model, the actual historical operation data of the energy storage system is difficult to reach the sample data magnitude required for model training, and therefore, a simulation environment of the energy storage system is usually established. And simulating the real thermal management process of the energy storage system through a simulation environment to obtain a large number of data sets.
The electrochemical-thermal coupling model of the battery cell level in the related art actually calculates the reaction and heat generation of the battery by the electrochemical model, and then calculates the temperature of the battery according to the heat transfer and heat dissipation principles. And transmitting the calculated temperature to the electrochemical model as a temperature dependent kinetic transport parameter of the lithium ion battery. The container-level thermal simulation system generally uses finite element analysis software such as ANSYS Fluent and the like, and can accurately give out the temperature change result of the battery cell. However, the simulation environment requirements for reinforcement learning are different from those of the general model, and extremely high operation speed is required, and each round should be within seconds, preferably milliseconds. The thermal simulation system in the related art has low calculation speed, and is difficult to meet the performance requirement.
Therefore, in order to solve the problem of slow operation speed of the thermal simulation system in the related art, the embodiment of the specification uses a deep learning algorithm to construct a deep learning neural network numerical simulation model, namely a physical field simulation model. The model is trained by using limited data, and environmental state parameters at the next moment can be rapidly solved.
Specifically, historical operation data of the energy storage system and historical working parameters of the temperature adjusting device are obtained as training sample data. The historical operation data and the historical working parameter data are measured data. When the actually measured data cannot meet the training requirement, the simulation history data obtained by the thermal simulation system in the related technology can be combined to train the physical field simulation model.
The historical operation data of the energy storage system comprises historical charge and discharge power data of the energy storage system and historical temperature data of the energy storage system. Meanwhile, more simulation operation data and simulation working parameters in different states can be obtained based on a thermal simulation system in the related technology. The two are combined to form a basic training sample data set.
The basic training sample dataset is divided into a training set and a test set. Based on various deep learning algorithms, training the constructed physical field simulation model according to the training set part until the physical field simulation model converges, and obtaining regression models between different system states and temperature change estimated data, namely a target physical field simulation model. The deep learning algorithm may include, but is not limited to, a recurrent neural network (Recurrent Neural Network, RNN), a convolutional neural network (convnet, CNN), a neural network transducer based on an attention mechanism, and the like, among others.
The target physical field simulation model is used for solving the temperature data of the energy storage system at the next moment according to the operation data of the energy storage system at the current moment and the working parameters of the temperature regulating device.
In some embodiments of the present description, the method of thermal management of an energy storage system further comprises: and acquiring environmental state variables and action variables of the energy storage system at different moments in a preset period through a target physical field simulation model.
Since the calculation speed of the target physical field simulation model can reach the millisecond level, the thermal management regulation model requires extremely high operation speed and the sample magnitude for training is very large. Therefore, training sample data for training the thermal management control model can be obtained through the target physical field simulation model, namely environmental state variables and action variables of the energy storage system at different moments in a preset period.
And the law between the charge and discharge power, the temperature and the working state of the temperature regulating device of the energy storage system learned by the physical field simulation model is solidified in the training of the thermal management regulating model, so that hysteresis and overshoot phenomena can be reduced. The temperature of the energy storage system is controlled more accurately and stably.
It should be understood that the thermal management method in the embodiments of the present disclosure is not limited to a liquid-cooled energy storage system, and the method is also applicable to energy storage systems with other cooling modes, such as air cooling. Correspondingly, the temperature adjusting device can be a water cooling unit in the liquid cooling energy storage system, and also can be an air cooling unit in the air cooling energy storage system.
In one particular embodiment of the present description, a method of thermal management of an energy storage system may include the following process:
And constructing a physical field simulation model of the energy storage system, wherein the physical field simulation model can support single-step simulation. The step size can be arbitrarily set, for example, 1min, 5min, etc. And simulating the thermal management process of the energy storage system through the trained target physical field simulation model to obtain the thermal management simulation effect line diagram of the energy storage system shown in fig. 3 a. The abscissa of fig. 3a represents time, and the first line represents the maximum temperature of the battery PACK in the energy storage system; the second straight line represents the lowest temperature of the battery PACK in the energy storage system; the third straight line represents the power consumption of the temperature adjustment device (cooling system power consumption); the fourth line represents the power (active power) of the energy storage system.
And constructing a deep reinforcement learning environment of the thermal management regulation model, wherein the deep reinforcement learning environment is embedded with a method for quickly realizing the single-step calling target physical field simulation model.
An initial thermal management regulation model is built, including but not limited to a strategy gradient deep reinforcement learning neural network model framework such as a deep reinforcement learning (Proximal Policy Optimization, PPO) algorithm, a reinforcement learning (Asynchronous Advantage Actor-Critic, A3C) algorithm, a dual delay depth deterministic strategy gradient (Twin Delayed Deep Deterministic PolicyGradient, TD 3) and the like.
Based on the established initial thermal management regulation model, establishing a minimum energy consumption objective function of a temperature regulating device for thermal management, and establishing constraint conditions of the thermal management regulation model. And simultaneously, establishing a state observation space, an action space and a reward function required by the thermal management regulation model. Wherein the bonus function is designed according to the objective function and the constraint condition.
Based on historical data of energy storage system test operation or simulation data obtained by simulation of a target physical field simulation model, data preprocessing and normalization are carried out, and a multithreading method is utilized to train a thermal management regulation model.
And stopping training when the training of the thermal management regulation model meets the termination condition, and storing the optimal model file. And meanwhile, the optimal model file is subjected to model conversion by using a model conversion tool, so that the converted model file is suitable for various platform environments, such as a central linux, ARM and the like.
And immediately acquiring charge and discharge power data and temperature data of the energy storage system. And inputting the charge and discharge power data and the temperature data into a trained target thermal management regulation model to obtain regulation action parameters for carrying out thermal management on the energy storage system. The regulatory action parameters may be expressed in the form of instructions, for example, instruction 1 representing heating; instruction 2 represents a pump cycle (compressor off); instruction 3 indicates refrigeration.
And regulating and controlling the temperature regulating device of the energy storage system based on the regulating and controlling action parameters. The temperature regulating device comprises a water pump, a valve, a compressor and other actuating mechanisms. Illustratively, the actual control of the compressor controller's actions based on the commands represented by the regulatory action parameters can be divided into three categories: 1. cooling point 40 ℃ and heating point 40 ℃;2. circulating a water pump; 3. cooling point 18 deg.c and heating point 10 deg.c. The temperature of the cooling liquid is higher than the refrigerating point to start refrigerating and lower than the heating point to start heating, so the equivalent logic of the above 3 actions is as follows: 1. heating; 2. circulating a water pump; 3. and (5) refrigerating. The heat management system only outputs refrigeration targets to the compressor controller, the specific compressor power consumption, the frequency converter is used for automatically controlling and executing closed loop, and the heat management system does not interfere.
Through the embodiment, the energy storage system can realize efficient and stable thermal management of the energy storage system by executing the thermal management scheduling instruction expressed by the regulation and control action parameters. Hysteresis and overshoot can be reduced. The temperature of the energy storage system is controlled more accurately and stably. FIG. 3b is a graph illustrating a thermal management effect of the energy storage system after implementing the thermal management method described above. The abscissa of fig. 3b represents time, and the fifth straight line represents the power consumption of the thermostat (cooling system power consumption); the sixth line represents the temperature of the battery PACK (battery temperature) of the energy storage system; the seventh line represents the power (active power) of the energy storage system. The temperature of the energy storage system in fig. 3b is the highest temperature of the battery PACK of the energy storage system. As can be seen by comparing the first straight line of fig. 3a with the sixth straight line of fig. 3b, the maximum temperature of the battery PACK of the energy storage system becomes smoother and approaches the preset upper temperature limit after the above-mentioned thermal management method is implemented. The power consumption of the temperature regulating device is reduced while the temperature of the energy storage system is stably controlled, and the efficiency of the energy storage system is effectively improved.
Corresponding to the above embodiment, the embodiment of the present specification further provides a training method of the thermal management control model. Referring to fig. 4, the training method of the thermal management control model includes:
s410, acquiring environment state variables and action variables of the energy storage system at different moments in a preset period.
The environment state variables comprise charge and discharge power variables of the energy storage system and temperature variables of the energy storage system; the action variables include regulatory action variables that thermally manage the energy storage system.
S420, constructing an objective function of a thermal management regulation model by taking the power consumption of a temperature regulating device for thermal management in a preset period of time to meet a preset condition and the temperature of an energy storage system to reach a target temperature as targets.
S430, taking the environmental state variable and the action variable as input of the thermal management regulation model, and updating parameters of the thermal management regulation model based on the value of the objective function to obtain the objective thermal management regulation model.
For specific limitations regarding the training method of the thermal management control model, reference may be made to the above limitation of the training process of the thermal management control model, and no further description is given here.
Through the embodiment, the target thermal management control model is obtained by training the thermal management control model based on the environmental state variable and the action variable. And the target thermal management regulation model is utilized to predict regulation parameters, so that the purposes of reducing the power consumption of the temperature regulation device and smoothing and accurately controlling the temperature of the energy storage system are achieved. The whole temperature of the energy storage system in the preset period tends to be smooth and accurate, the temperature difference caused by overshoot is reduced, and the service life of the battery cell is reduced. And moreover, the more accurate temperature control capability can enable the energy storage system to have a more flexible temperature control range. Under the condition that the temperature of the battery PACK does not generate out-of-limit alarm, the battery PACK works at the upper temperature limit as much as possible, so that the power consumption of the temperature regulating device is reduced, the efficiency of the energy storage system is effectively improved, and the return on investment of the energy storage system is improved.
Corresponding to the above embodiment, the embodiment of the present disclosure further provides a thermal management device of an energy storage system. Referring to fig. 5, a thermal management device of an energy storage system includes:
the acquiring module 510 is configured to acquire charging and discharging power data and temperature data of the energy storage system.
The regulation and control action determining module 520 is configured to input the charge and discharge power data and the temperature data to the target thermal management regulation and control model, and obtain a regulation and control action parameter for performing thermal management on the energy storage system.
The regulation and control action parameters are used for regulating and controlling a temperature regulating device of the energy storage system, so that the power consumption of the temperature regulating device meets preset conditions and the temperature of the energy storage system reaches the target temperature.
Through the embodiment, when the energy storage system is thermally managed, the temperature data and the charge and discharge power data are utilized, and the regulation and control action parameters for thermally managing the energy storage system are predicted through the target thermal management regulation and control model. And then, regulating and controlling the temperature regulating device by utilizing the regulating and controlling action parameters, so that the power consumption of the temperature regulating device meets the preset condition and the temperature of the energy storage system reaches the target temperature. According to the embodiment of the specification, the temperature state and the charge and discharge state of the energy storage system are considered at the same time, the target thermal management regulation model is utilized for predicting regulation parameters, and the purposes of reducing the power consumption of the temperature regulation device and smoothing and accurately controlling the temperature of the energy storage system are achieved.
Specific limitations regarding the thermal management device of the energy storage system may be found in the above limitations regarding the thermal management method of the energy storage system, and will not be described in detail herein. The various modules in the thermal management device of the energy storage system described above may be implemented in whole or in part in software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
Corresponding to the above embodiment, the embodiment of the present specification further provides a training device for a thermal management control model. Referring to fig. 6, the training apparatus for thermal management control model includes:
the sample obtaining module 610 is configured to obtain environmental state variables and action variables of the energy storage system at different moments in a preset period.
The environment state variables comprise charge and discharge power variables of the energy storage system and temperature variables of the energy storage system; the action variables include regulatory action variables that thermally manage the energy storage system.
The objective function determining module 620 is configured to construct an objective function of the thermal management regulation model with the power consumption of the temperature regulating device for thermal management in a preset period meeting a preset condition and the temperature of the energy storage system reaching a target temperature as targets.
The training module 630 is configured to update parameters of the thermal management control model based on a value of the objective function by taking the environmental state variable and the action variable as input of the thermal management control model, so as to obtain the objective thermal management control model.
Through the embodiment, the target thermal management control model is obtained by training the thermal management control model based on the environmental state variable and the action variable. And the target thermal management regulation model is utilized to predict regulation parameters, so that the purposes of reducing the power consumption of the temperature regulation device and smoothing and accurately controlling the temperature of the energy storage system are achieved. The whole temperature of the energy storage system in the preset period tends to be smooth and accurate, the temperature difference caused by overshoot is reduced, and the service life of the battery cell is reduced. And moreover, the more accurate temperature control capability can enable the energy storage system to have a more flexible temperature control range. Under the condition that the temperature of the battery PACK does not generate out-of-limit alarm, the battery PACK works at the upper temperature limit as much as possible, so that the power consumption of the temperature regulating device is reduced, the efficiency of the energy storage system is effectively improved, and the return on investment of the energy storage system is improved.
For specific limitations on the training apparatus of the thermal management control model, reference may be made to the above limitation on the training method of the thermal management control model, and no further description is given here. The modules in the training device of the thermal management and control model can be all or partially implemented by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
Corresponding to the above embodiment, the embodiment of the present disclosure further provides an energy storage system.
Fig. 7 is a block diagram of an energy storage system according to one embodiment of the present description. As shown in fig. 7, the energy storage system 700 includes a memory 704, a processor 702, and a computer program 706 stored on the memory 704 and executable on the processor 702, wherein the processor 702 implements the thermal management method of the energy storage system of any of the above embodiments when executing the computer program 706.
According to the electronic device of the embodiment of the present disclosure, when the processor 702 executes the computer program 706, the temperature state and the charge-discharge state of the energy storage system can be considered at the same time, and the target thermal management regulation model is utilized to predict the regulation parameters, so as to achieve the purposes of reducing the power consumption of the temperature regulation device and smoothing and accurately controlling the temperature of the energy storage system.
Corresponding to the above embodiments, the present description further proposes a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of thermal management of an energy storage system of any of the above embodiments.
According to the computer readable storage medium of the embodiment of the specification, when the computer program is executed by the processor, the temperature state and the charge and discharge state of the energy storage system can be simultaneously considered, and the target thermal management regulation model is utilized for predicting the regulation parameters, so that the purposes of reducing the power consumption of the temperature regulation device and smoothing and accurately controlling the temperature of the energy storage system are achieved.
It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, for example, may be considered as a ordered listing of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It should be understood that portions of this specification may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present specification. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
In the description of the present specification, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present specification and simplifying the description, and do not indicate or imply that the device or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present specification.
Furthermore, the terms "first," "second," and the like, as used in the embodiments of the present specification, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or as implicitly indicating the number of technical features indicated in the embodiments. Thus, the definition of a term "first," "second," or the like in an embodiment of this specification can expressly or implicitly indicate that at least one such feature is included in the embodiment. In the description of the present specification, the word "plurality" means at least two or more, for example, two, three, four, etc., unless explicitly defined otherwise in the embodiments.
In this specification, unless clearly indicated or limited otherwise in the examples, the terms "mounted," "connected," and "fixed" as used in the examples are to be construed broadly, and for example, the connection may be a fixed connection, a removable connection, or an integral unit, and it is to be appreciated that the connection may also be a mechanical connection, an electrical connection, or the like; of course, it may be directly connected, or indirectly connected through an intermediate medium, or may be in communication with each other, or in interaction with each other. The specific meaning of the terms in this specification can be understood by those skilled in the art according to specific embodiments.
In this specification, unless expressly stated or limited otherwise, a first feature "up" or "down" a second feature may be the first and second features in direct contact, or the first and second features in indirect contact via an intervening medium. Moreover, a first feature being "above," "over" and "on" a second feature may be a first feature being directly above or obliquely above the second feature, or simply indicating that the first feature is level higher than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is less level than the second feature.
Although embodiments of the present disclosure have been shown and described above, it should be understood that the above embodiments are illustrative and not to be construed as limiting the present disclosure, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the present disclosure.
Claims (11)
1. A method of thermal management of an energy storage system, the method comprising:
acquiring charge and discharge power data and temperature data of an energy storage system;
inputting the charge and discharge power data and the temperature data into a target thermal management regulation model to obtain regulation action parameters for carrying out thermal management on the energy storage system; the regulation and control action parameters are used for regulating and controlling a temperature regulating device of the energy storage system, so that the power consumption of the temperature regulating device meets preset conditions and the temperature of the energy storage system reaches a target temperature.
2. The method of claim 1, wherein the target thermal management regulation model is trained by:
acquiring environment state variables and action variables of the energy storage system at different moments in a history preset period; the environment state variables comprise charge and discharge power variables of the energy storage system and temperature variables of the energy storage system; the action variables comprise regulatory action variables for performing thermal management on the energy storage system;
Constructing a reward function of the thermal management regulation model by taking the power consumption of the temperature regulating device in the historical preset period as a target that the preset condition is met and the temperature of the energy storage system reaches the target temperature;
and taking the environmental state variable and the action variable as the input of the thermal management regulation model, and updating the parameters of the thermal management regulation model based on the value of the reward function to obtain a target thermal management regulation model.
3. The method of claim 2, wherein constructing the reward function of the thermal management regulation model with the goal that the power consumption of the temperature regulation device satisfies the preset condition and the temperature of the energy storage system reaches the target temperature within the historical preset period of time includes:
constructing a first main line rewarding function according to the difference value between the maximum historical power consumption of the temperature regulating device and the total power consumption of the temperature regulating device in the historical preset period;
constructing a second main line rewarding function according to absolute differences between temperature data of the temperature variable of the energy storage system at different moments in the historical preset period and target temperatures corresponding to different moments;
And constructing the reward function according to the first mainline reward function and the second mainline reward function.
4. A method according to claim 3, wherein the reward function comprises a mainline reward function and a spur penalty term; constructing the bonus function from the first and second dominant bonus functions, comprising:
according to a first weight coefficient corresponding to the first main line rewarding function and a second weight coefficient corresponding to the second main line rewarding function, carrying out weighted summation on the first main line rewarding function and the second main line rewarding function to obtain the main line rewarding function;
determining the branch line punishment term according to the product of the times that the temperature of the energy storage system exceeds a preset temperature range in the history preset period and a third weight coefficient;
and carrying out difference solving on the main line reward function and the branch line penalty term to obtain the reward function.
5. A method according to claim 3, wherein constructing a second mainline reward function based on absolute differences between temperature data of the energy storage system at different times within the historical preset period and the target temperatures corresponding to the different times, comprises:
Determining a first branch item of the second main line rewarding function according to the sum of squares of absolute differences of temperature data of the temperature variable of the energy storage system at different moments in the history preset period and target temperatures corresponding to different moments;
determining a sum of squares of the target temperatures at different moments as a second branch term of the second main line bonus function;
and carrying out difference solving on the second branch item and the first branch item to obtain the second main line reward function.
6. The method according to claim 1, wherein the method further comprises:
acquiring historical operation data of the energy storage system and historical working parameters of the temperature regulating device;
training the constructed physical field simulation model based on the historical operation data and the historical working parameters to obtain a target physical field simulation model; the target physical field simulation model is used for solving temperature data of the energy storage system at the next moment according to the operation data of the energy storage system at the current moment and the working parameters of the temperature regulating device.
7. The method of claim 6, wherein the method further comprises: and acquiring environmental state variables and action variables of the energy storage system at different moments in a preset period through the target physical field simulation model.
8. A method of training a thermal management regulation model, the method comprising:
acquiring environment state variables and action variables of the energy storage system at different moments in a preset period; the environment state variables comprise charge and discharge power variables of the energy storage system and temperature variables of the energy storage system; the action variables comprise regulatory action variables for performing thermal management on the energy storage system;
constructing an objective function of the thermal management regulation model by taking the power consumption of the temperature regulating device for thermal management in the preset period of time as a target, wherein the power consumption of the temperature regulating device for thermal management meets a preset condition, and the temperature of the energy storage system reaches a target temperature;
and taking the environmental state variable and the action variable as the input of the thermal management control model, and updating the parameters of the thermal management control model based on the value of the objective function to obtain the objective thermal management control model.
9. A thermal management device for an energy storage system, the device comprising:
the acquisition module is used for acquiring charge and discharge power data and temperature data of the energy storage system;
the regulation and control action determining module is used for inputting the charge and discharge power data and the temperature data into a target thermal management regulation and control model to obtain regulation and control action parameters for carrying out thermal management on the energy storage system; the regulation and control action parameters are used for regulating and controlling a temperature regulating device of the energy storage system, so that the power consumption of the temperature regulating device meets preset conditions and the temperature of the energy storage system reaches a target temperature.
10. An energy storage system comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the method of any one of claims 1 to 7 when the computer program is executed.
11. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310761174.9A CN116864871A (en) | 2023-06-26 | 2023-06-26 | Thermal management method of energy storage system and training method of thermal management regulation model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310761174.9A CN116864871A (en) | 2023-06-26 | 2023-06-26 | Thermal management method of energy storage system and training method of thermal management regulation model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116864871A true CN116864871A (en) | 2023-10-10 |
Family
ID=88233252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310761174.9A Pending CN116864871A (en) | 2023-06-26 | 2023-06-26 | Thermal management method of energy storage system and training method of thermal management regulation model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116864871A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408170A (en) * | 2023-12-15 | 2024-01-16 | 南京群顶科技股份有限公司 | Energy-saving predictive control method suitable for water cooling system of data center |
-
2023
- 2023-06-26 CN CN202310761174.9A patent/CN116864871A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408170A (en) * | 2023-12-15 | 2024-01-16 | 南京群顶科技股份有限公司 | Energy-saving predictive control method suitable for water cooling system of data center |
| CN117408170B (en) * | 2023-12-15 | 2024-03-08 | 南京群顶科技股份有限公司 | Energy-saving predictive control method suitable for water cooling system of data center |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109708258A (en) | A kind of temperature of ice house feedforward-Fuzzy control system and control method based on load dynamic change | |
| CN100446310C (en) | Fuel-cell power generation system and control method therefor | |
| CN109890176B (en) | Device for optimizing energy consumption efficiency of machine room based on artificial intelligence | |
| CN205980188U (en) | Ice cold -storage optimal control system based on load forecast | |
| CN116864871A (en) | Thermal management method of energy storage system and training method of thermal management regulation model | |
| CN106842914B (en) | Temperature control energy-saving processing method, device and system | |
| CN109282499A (en) | A kind of method and water heater of water heater prediction user's water behavior | |
| CN109844654B (en) | Random packet-based power management system and method for conditional control loads and bi-directional distributed energy storage systems | |
| CN112490540A (en) | Power battery system, temperature control method and device thereof, medium and processor | |
| CN113739365A (en) | Central air-conditioning cold station group control energy-saving control method, device, equipment and storage medium | |
| CN113825356B (en) | Energy-saving control method and device for cold source system, electronic equipment and storage medium | |
| CN113283156A (en) | Subway station air conditioning system energy-saving control method based on deep reinforcement learning | |
| CN115832532B (en) | Control method, device and system of liquid cooling energy storage system | |
| CN108089440A (en) | Energy-saving control method and device | |
| Moura et al. | Modeling heterogeneous populations of thermostatically controlled loads using diffusion-advection PDEs | |
| CN113224412B (en) | Temperature control method of power battery, AMPC controller, thermal management system and medium | |
| CN116776746B (en) | Energy storage liquid cooling temperature control optimizing system based on fluid dynamics | |
| CN114330852B (en) | Energy-saving optimization method and device for tail end air conditioning system of integrated data center cabinet | |
| KR20180138371A (en) | Method for evaluating data based models and conducting predictive control of capsule type ice thermal storage system using the same | |
| US10209729B2 (en) | Energy control system, energy control device, energy control method, and storage medium | |
| CN114185374B (en) | Target feed liquid temperature control method and system, temperature control method and related equipment | |
| CN114909945A (en) | Energy-saving intelligent control method and device for cooling tower, electronic device and medium | |
| Zhang et al. | DRL-S: Toward safe real-world learning of dynamic thermal management in data center | |
| Idowu et al. | Machine learning in district heating system energy optimization | |
| US20220198584A1 (en) | Computer-Assisted Energy Management Method And Energy Management System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |