A new energy storage lithium battery control system and control method

Abstract

The present invention relates to the field of energy storage lithium batteries, and discloses a new energy storage lithium battery control system and control method, the method comprising: calculating the charge and discharge duration of each charge and discharge record in the historical charge and discharge records, and using the charge and discharge duration to divide the historical charge and discharge records; using the divided charge and discharge records to calculate the first remaining power of the energy storage lithium battery, and analyzing the second remaining power of the energy storage lithium battery when it arrives at the surrounding charging station; identifying the assembly scene of the energy storage lithium battery, analyzing the planned charge and discharge records corresponding to the divided charge and discharge records in the assembly scene, and testing the aging degree of the energy storage lithium battery; calculating the action value function of the energy storage lithium battery, calculating the state value function of the energy storage lithium battery, deciding the charge and discharge action of the energy storage lithium battery, and using the charge and discharge action to optimize the parameters of the action value function and the state value function respectively, to obtain the optimized action value function and the optimized state value function. The present invention can improve the adaptability of the charge and discharge control of the battery.

Description

Technical Field

[0001] The present invention relates to the field of energy storage lithium batteries, and in particular to a new energy storage lithium battery control system and a control method. Background Art

[0002] With the rapid growth of clean energy power generation and the rapid development of energy storage technology, lithium-ion battery energy storage systems will become a major key technology to promote the development of clean energy. When electricity prices are high, the discharge of energy storage lithium batteries is used to supplement the power grid. When electricity prices are low, the process of charging energy storage lithium batteries from the power grid can greatly save charging costs.

[0003] At present, there have been extensive studies on the control electrodes of new energy storage lithium batteries at home and abroad. Generally, the charge and discharge are controlled by voltage and current. For example, the patent publication number is CN102916456B, the publication date is November 18, 2015, and the invention is named: A lithium battery charge and discharge management system and method. The application discloses a lithium battery as a single-cell lithium battery. The system includes: a lithium battery charge and discharge management module, which is used to start the lithium battery to charge or discharge according to the voltage values ​​of the monitored lithium battery and the external charging power supply, specifically: monitoring the voltage of the external charging power supply, and judging whether the external charging power supply is normal, assuming that the normal voltage of the external charging power supply is 5V; when the judgment result is that the external charging power supply is When the power supply is abnormal, that is, when the external charging power supply voltage is monitored to be not 5V, the lithium battery is started to discharge; when the judgment result is that the power supply of the external charging power supply is normal, that is, when the external charging power supply voltage is monitored to be 5V, it is judged whether the lithium battery is in a fully charged state according to the monitored lithium battery voltage, that is, it is monitored to judge whether the voltage of the lithium battery is equal to its maximum voltage value. If not, the lithium battery is not fully charged, and if so, the lithium battery is fully charged; when the judgment result is that the lithium battery is not fully charged, the external charging power supply is started to charge the lithium battery according to the pre-set lithium battery charging curve: if the lithium battery voltage is monitored to be in a completely discharged state, the lithium battery is first pre-charged, then constant current charged, and when the battery voltage is high, the lithium battery is charged to a predetermined value. When the charging reaches 4.2V, constant voltage charging is performed, and finally trickle charging is performed until the charging current is about 0A. Charging is completed and the charging circuit is disconnected; when the judgment result is that the lithium battery is in a fully charged state, if the lithium battery voltage is monitored to be lower than the lithium battery charging voltage threshold, the lithium battery charging process is restarted; the lithium battery voltage over-discharge protection module is used to monitor the lithium battery discharge voltage. When the lithium battery discharge voltage is lower than the lithium battery's minimum discharge voltage threshold, the discharge circuit is disconnected until the lithium battery discharge voltage is higher than the lithium battery's minimum discharge voltage threshold; the lithium battery discharge over-current protection module is used to monitor the lithium battery discharge current. When the lithium battery discharge current exceeds the lithium battery's maximum discharge current threshold, the discharge circuit is disconnected. , until the lithium battery discharge current is lower than the maximum discharge current threshold of the lithium battery; a boost module is used to boost and stabilize the output voltage passing through the lithium battery charge and discharge management module after passing through the voltage over-discharge protection of the lithium battery voltage over-discharge protection module and the discharge over-current protection of the lithium battery discharge over-current protection module, so that the output voltage reaches the voltage value required by the application system; wherein the input end of the lithium battery charge and discharge management module is connected to an external charging power supply, the first output end is connected to a lithium battery, and the second output end of the lithium battery charge and discharge management module, the lithium battery voltage over-discharge protection module, and the lithium battery discharge over-current protection module are connected in sequence; the input end of the boost module is connected to the lithium battery discharge over-current protection module, and the output end is externally connected to the application system.

[0004] The above application needs to control the charging circuit and the discharging circuit by voltage and current, which requires the current threshold and voltage threshold to be set in advance. However, the current threshold and voltage threshold that need to be set need to be adaptively changed according to the charging and discharging status, battery capacity and battery aging degree of different batteries. Then, the process of controlling the charging and discharging only by setting the current threshold and voltage threshold does not take into account the characteristics of different batteries, which leads to the insufficient adaptability of the current threshold and voltage threshold to the charging and discharging control of batteries under different charging and discharging status, battery capacity and battery aging degree.

[0005] Therefore, a solution is urgently needed to improve the adaptability of battery charge and discharge control under different charge and discharge states, battery capacities and battery aging degrees. Summary of the invention

[0006] In order to solve the above problems, the present invention provides a new energy storage lithium battery control system and control method, which can improve the adaptability of battery charge and discharge control under different charge and discharge states, battery capacities and battery aging degrees.

[0007] In a first aspect, the present invention provides a new energy storage lithium battery control system, comprising:

[0008] A record segmentation module is used to collect historical charge and discharge records of the energy storage lithium battery, calculate the charge and discharge duration of each charge and discharge record in the historical charge and discharge records according to the time sequence in the historical charge and discharge records, and use the charge and discharge duration to segment the historical charge and discharge records to obtain segmented charge and discharge records;

[0009] A power analysis module, used to calculate a first remaining power of the energy storage lithium battery using the split charge and discharge records, locate a surrounding charging station of the energy storage lithium battery, and analyze a second remaining power of the energy storage lithium battery when it arrives at the surrounding charging station based on a travel distance between the energy storage lithium battery and the surrounding charging station;

[0010] An aging test module, used to identify the assembly scenario of the energy storage lithium battery, analyze the planned charging and discharging records corresponding to the split charging and discharging records under the assembly scenario based on the driving time of the energy storage lithium battery to reach the surrounding charging stations, and test the aging degree of the energy storage lithium battery;

[0011] an action construction module, configured to use the split charge and discharge record and the planned charge and discharge record as a charge and discharge state sequence of the energy storage lithium battery, use the first remaining power and the second remaining power as a remaining power sequence of the energy storage lithium battery, use the aging degree as an aging degree sequence of the energy storage lithium battery, construct a state space of the energy storage lithium battery using the charge and discharge state sequence, the remaining power sequence and the aging degree sequence, and construct an action space of the energy storage lithium battery;

[0012] A function optimization module, used to calculate the action value function of the energy storage lithium battery based on the state space and the action space, calculate the state value function of the energy storage lithium battery according to the state space, use the action value function and the state value function to decide the charging and discharging action of the energy storage lithium battery, and use the charging and discharging action to optimize the parameters of the action value function and the state value function respectively, to obtain an optimized action value function and an optimized state value function;

[0013] The charge and discharge control module is used to control the charge and discharge of the energy storage lithium battery according to the optimized action value function and the optimized state value function by using the state space and the action space to obtain the charge and discharge control result of the energy storage lithium battery.

[0014] In a possible implementation manner of the first aspect, the using the charge and discharge duration to segment the historical charge and discharge record to obtain the segmented charge and discharge record includes:

[0015] Query the record position corresponding to the shortest charge and discharge duration among the charge and discharge durations in the historical charge and discharge records;

[0016] Starting from the recording position, dividing the historical charge and discharge record according to the interval of the shortest charge and discharge time to obtain an initial divided charge and discharge record;

[0017] Determine whether there are two states in a single duration in the initial split charge and discharge record;

[0018] When there are two states in a single duration in the initial split charge and discharge record, the single duration is split according to the time boundary between the two states in the single duration to obtain a split charge duration and a split discharge duration;

[0019] According to the split charging time and the split discharging time, the split interval of the historical charge and discharge record is calculated using the following formula:

[0020]

[0021] Wherein, p represents the segmentation interval, k represents the sequence number of the single duration containing two states, K represents the total number of the single duration containing two states, represents the length of the split charging duration i in the kth single duration containing two states, represents the length of the split discharge duration j in the kth single duration containing two states, n represents the number of durations after the K split charge durations are split according to the split interval p, and m represents the number of durations after the K split discharge durations are split according to the split interval p;

[0022] The historical charge and discharge records are divided according to the division intervals to obtain divided charge and discharge records.

[0023] In a possible implementation of the first aspect, analyzing, based on the travel distance between the energy storage lithium battery and the surrounding charging station, a second remaining power of the energy storage lithium battery when it arrives at the surrounding charging station includes:

[0024] Query the remaining power sequence of the energy storage lithium battery during historical driving;

[0025] Calculating the power decrease value between the remaining power at adjacent moments in the remaining power sequence;

[0026] Calculating the mean of the power reduction values, and calculating the time difference between adjacent times in the remaining power sequence;

[0027] Calculating the driving time of the energy storage lithium battery using the driving distance and the driving speed of the energy storage lithium battery;

[0028] Calculating the number of the time differences within the driving duration to obtain the number of differences;

[0029] Calculate the mean-number product between the mean of the power reduction value and the number of differences;

[0030] The difference between the target remaining power corresponding to the energy storage lithium battery in the first remaining power and the product of the mean value and the number is used as the second remaining power.

[0031] In a possible implementation of the first aspect, the analyzing, based on the driving time of the energy storage lithium battery to reach the surrounding charging station, the planned charging and discharging record corresponding to the split charging and discharging record in the assembly scenario includes:

[0032] Obtain electrical appliances and charging power sources in the assembly scenario;

[0033] Querying the total power consumption of the electrical appliance from the split charge and discharge records;

[0034] Calculating the power demand of the electrical appliances using the total power consumption;

[0035] Taking the power demand as the discharge capacity of the energy storage lithium battery;

[0036] analyzing the charging capability of the charging power source;

[0037] Using the charging capacity as the charging amount of the energy storage lithium battery;

[0038] Acquiring the historical charge and discharge status in the split charge and discharge record;

[0039] According to the historical charge and discharge status, the planned charge and discharge status of the energy storage lithium battery within the driving time is calculated using the following formula:

[0040] f t =σ(w f [h t-1 ,x t ]+b f )

[0041] i t =σ(w i [h t-1 ,x t ]+b i )

[0042]

[0043] o t =σ(w o [h t-1 ,x t ]+b o )

[0044]

[0045] h t =o t *tanh(c t )

[0046] Among them, h t Indicates the planned charging and discharging state, f t represents the output of the forget gate, i t represents the output of the input gate, Represents the candidate memory cell of the memory gate output, o t represents the output of the output gate, w f represents the weight of the forget gate, h t-1 Indicates the charge and discharge status at the previous moment, x t Indicates the historical charge and discharge state, b f represents the bias of the forget gate, wi represents the weight of the input gate, b i represents the bias of the input gate, w c represents the weight of the memory gate, b c represents the bias of the memory gate, w o represents the weight of the output gate, b o represents the bias of the output gate, c t-1 Indicates the memory status of the previous moment;

[0047] The discharge amount and the charge amount are randomly added to the planned charge and discharge state to obtain the planned charge and discharge record.

[0048] In a possible implementation of the first aspect, the testing the aging degree of the energy storage lithium battery includes: collecting temperature data and voltage data of the energy storage lithium battery in the split charge and discharge record and the planned charge and discharge record; and calculating the aging degree of the energy storage lithium battery according to the temperature data and the voltage data using the following formula:

[0049]

[0050] Wherein, D represents the aging degree, T represents the temperature data, and V represents the voltage data.

[0051] In a possible implementation manner of the first aspect, calculating the action value function of the energy storage lithium battery based on the state space and the action space includes:

[0052] Based on the state space and the action space, the action value function after the energy storage lithium battery is updated is calculated using the following formula:

[0053]

[0054] Wherein, Q0(s,a,w) represents the action value function of the energy storage lithium battery corresponding to the updated s state and a action after the update, s represents the current state in the state space, a represents the action in the action space taken under the current state, α represents the state transition probability, Q(s,a,w) represents the action value function before the s state and a action are updated, r represents the difference between Q(s',a') and V(s') when the s state is converted to the s' state and the a action is converted to the a' action, γ represents a constant between 0 and 1, s' represents the next state of the s state, a' represents the next action of the a action taken under the s' state, Q(s',a',w)=Q(s',a'), Q9s',a',w) represents the updated action value function corresponding to the s' state and a' action, and w represents the weight parameter;

[0055] The action value function after the energy storage lithium battery is updated is used as the action value function of the energy storage lithium battery.

[0056] In a possible implementation of the first aspect, calculating the state value function of the energy storage lithium battery according to the state space includes:

[0057] According to the state space, the state value function of the energy storage lithium battery after updating is calculated using the following formula:

[0058] V0(s)=(1-α)*V(s)+α*(r+γ*V(s'))

[0059] Wherein, V0(s) represents the state value function of the energy storage lithium battery corresponding to the s state after the update, V(s) represents the state value function of the energy storage lithium battery corresponding to the s state before the update, r represents the difference between Q(s',a') and V(s') when the s state is converted to the s' state and the a action is converted to the a' action, γ represents a constant between 0 and 1, V(s') represents the state value function corresponding to the s' state, and α represents the state transition probability;

[0060] The updated state value function of the energy storage lithium battery is used as the state value function of the energy storage lithium battery.

[0061] In a possible implementation of the first aspect, the using the action value function and the state value function to determine the charging and discharging actions of the energy storage lithium battery includes:

[0062] Calculating a function difference between the action value function and the state value function;

[0063] When the function difference is the largest, the charging and discharging actions of the energy storage lithium battery are determined from the action value function and the state value function corresponding to the function difference.

[0064] In a possible implementation of the first aspect, the using the charging and discharging actions to respectively optimize the parameters of the action value function and the state value function to obtain an optimized action value function and an optimized state value function includes:

[0065] Determine the target state and target action in the action value function and the state value function according to the charging and discharging action;

[0066] According to the target state and the target action, the weight parameter in the action value function is updated using the following formula to obtain an updated weight parameter:

[0067]

[0068] Among them, w' represents the updated weight parameter, w represents the weight parameter, represents the action value function that meets the target action selected from the a action of Q0(s,a,w) and meets the target state selected from the s' state of Q(s',a',w), s represents the current state in the state space, a represents the action in the action space taken under the current state, α represents the state transition probability, express The corresponding actual action value function, r represents the difference between Q(s',a') and V(s') when converting the s state to the s' state and converting the a action to the a' action, γ represents a constant between 0 and 1, s' represents the next state of the s state, a' represents the next action of the a action taken in the s' state, Q(s',a',w)=Q(s',a'), Q(s',a',w) represents the updated action value function corresponding to the s' state and the a' action, and LOSS represents and Losses between

[0069] According to the target state, the constant parameters in the action value function and the state value function are updated using the following formula to obtain updated constant parameters:

[0070]

[0071]

[0072] Among them, γ' represents the update constant parameter, α represents the state transition probability, γ represents a constant between 0 and 1, and LOSS' represents and between, and The loss between represents the state value function selected from the s state of V0(s) that meets the target state, represents the actual state value function corresponding to V0(s), r represents the difference between Q(s',a') and V(s') when converting state s to state s' and action a to action a';

[0073] The update weight parameter and the update constant parameter are used to complete parameter optimization of the action value function and the state value function to obtain an optimized action value function and an optimized state value function.

[0074] In a second aspect, the present invention provides a new energy storage lithium battery control method, the method comprising:

[0075] Collect historical charge and discharge records of the energy storage lithium battery, calculate the charge and discharge duration of each charge and discharge record in the historical charge and discharge records according to the time sequence in the historical charge and discharge records, and divide the historical charge and discharge records by the charge and discharge duration to obtain divided charge and discharge records;

[0076] Calculating a first remaining power of the energy storage lithium battery using the split charge and discharge records, locating a peripheral charging station of the energy storage lithium battery, and analyzing a second remaining power of the energy storage lithium battery when it arrives at the peripheral charging station based on a travel distance between the energy storage lithium battery and the peripheral charging station;

[0077] Identify the assembly scenario of the energy storage lithium battery, analyze the planned charge and discharge records corresponding to the split charge and discharge records under the assembly scenario based on the driving time of the energy storage lithium battery to reach the surrounding charging stations, and test the aging degree of the energy storage lithium battery;

[0078] The split charge and discharge record and the planned charge and discharge record are used as the charge and discharge state sequence of the energy storage lithium battery, the first remaining power and the second remaining power are used as the remaining power sequence of the energy storage lithium battery, and the aging degree is used as the aging degree sequence of the energy storage lithium battery. The state space of the energy storage lithium battery is constructed by using the charge and discharge state sequence, the remaining power sequence and the aging degree sequence, and the action space of the energy storage lithium battery is constructed;

[0079] Based on the state space and the action space, the action value function of the energy storage lithium battery is calculated; according to the state space, the state value function of the energy storage lithium battery is calculated; the charging and discharging actions of the energy storage lithium battery are determined by using the action value function and the state value function; the charging and discharging actions are used to optimize the parameters of the action value function and the state value function, respectively, to obtain an optimized action value function and an optimized state value function;

[0080] According to the optimized action value function and the optimized state value function, the charge and discharge of the energy storage lithium battery is controlled by utilizing the state space and the action space to obtain the charge and discharge control result of the energy storage lithium battery.

[0081] Compared with the prior art, the technical principle and beneficial effects of this solution are:

[0082] The embodiment of the present invention divides the historical charge and discharge record by using the charge and discharge duration to ensure that there is only one charge and discharge state within each fixed interval, and uses the divided charge and discharge record as a basis for subsequent decision-making on the next charge and discharge action. The embodiment of the present invention calculates the first remaining power of the energy storage lithium battery by using the divided charge and discharge record to calculate the remaining power of the energy storage lithium battery in the historical time. Furthermore, the embodiment of the present invention analyzes the second remaining power of the energy storage lithium battery when it arrives at the surrounding charging station based on the driving distance between the energy storage lithium battery and the surrounding charging station, so as to calculate the remaining power of the energy storage lithium battery when it arrives at the surrounding charging station. Before charging and discharging can be performed, the change of the energy storage lithium battery compared to the first remaining power is analyzed, so as to prepare for the energy storage lithium battery to arrive at the surrounding charging station for charging and discharging. Furthermore, the embodiment of the present invention analyzes the planned charging and discharging records corresponding to the segmented charging and discharging records in the assembly scenario based on the driving time of the energy storage lithium battery to arrive at the surrounding charging station, so as to use the neural network model to analyze the change of the segmented charging and discharging records within the planned time. Furthermore, the embodiment of the present invention tests the aging degree of the energy storage lithium battery, so as to use the aging degree as the basis for subsequent decision-making on the next charging and discharging action. The embodiment of the present invention is based on the state The state space and the action space are used to calculate the action value function of the energy storage lithium battery, so as to calculate the expected value of the long-term reward of the energy storage lithium battery performing a certain action in the next step in a certain state. Further, the embodiment of the present invention calculates the state value function of the energy storage lithium battery according to the state space, so as to calculate the expected value of the long-term reward of the energy storage lithium battery performing any action in the next step in a certain state. Further, the embodiment of the present invention uses the action value function and the state value function to decide the charging and discharging action of the energy storage lithium battery, so as to use the difference between the action value function and the state value function to judge the long-term return of performing a certain action. The size of the long-term reward is used as the criterion for judging whether the next action is correct or not. Furthermore, the embodiment of the present invention optimizes the parameters of the action value function and the state value function respectively by utilizing the charging and discharging action, so as to improve the accuracy of action decision-making through the action value function and the state value function. The embodiment of the present invention controls the charging and discharging of the energy storage lithium battery by utilizing the state space and the action space according to the optimized action value function and the optimized state value function, so as to improve the adaptability of the charging and discharging control of the battery under different charging and discharging states, battery capacities and battery aging degrees. Therefore, a new energy energy storage lithium battery control system and control method proposed in the embodiment of the present invention can improve the adaptability of the charging and discharging control of the battery under different charging and discharging states, battery capacities and battery aging degrees. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0084] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0085] Figure 1 A schematic diagram of a module of a new energy storage lithium battery control system provided by an embodiment of the present invention;

[0086] Figure 2 A schematic flow chart of a new energy storage lithium battery control method provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0087] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0088] The embodiment of the present invention provides a new energy storage lithium battery control system, and the execution subject of the new energy storage lithium battery control system includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the system provided by the embodiment of the present invention. In other words, the new energy storage lithium battery control system can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0089] like Figure 1 The figure shows a functional module diagram of a new energy storage lithium battery control system of the present invention.

[0090] The new energy storage lithium battery control system 100 described in the present invention can be installed in an electronic device. According to the functions to be implemented, the new energy storage lithium battery control system can include a record segmentation module 101, a power analysis module 102, an aging test module 103, an action construction module 104, a function optimization module 105 and a charge and discharge control module 106. The module described in the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0091] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0092] The record segmentation module 101 is used to collect historical charge and discharge records of the energy storage lithium battery, calculate the charge and discharge duration of each charge and discharge record in the historical charge and discharge records according to the time sequence in the historical charge and discharge records, and use the charge and discharge duration to segment the historical charge and discharge records to obtain segmented charge and discharge records.

[0093] In the embodiment of the present invention, the energy storage lithium battery refers to a battery that uses chemical elements as energy storage media, and the charging and discharging process is accompanied by chemical reactions or changes in the energy storage medium, so that electrical energy is stored in the form of chemical energy and then released in the form of chemical energy. The historical charge and discharge record refers to charging data or discharging data at fixed intervals within a historical time period, such as the charge amount and discharge amount at fixed intervals within a historical time period.

[0094] Furthermore, in an embodiment of the present invention, the time sequence refers to the sequence from old time to new time, and the charging and discharging duration includes charging duration and discharging duration. The charging duration refers to the duration of the charging action, and the discharging duration refers to the duration of the discharging action.

[0095] Furthermore, the embodiment of the present invention divides the historical charge and discharge records by using the charge and discharge duration to ensure that there is only one charge and discharge state within each fixed interval, and uses the divided charge and discharge records as a basis for subsequent decision-making on the next charge and discharge action.

[0096] In one embodiment of the present invention, the use of the charge and discharge duration to divide the historical charge and discharge record to obtain the divided charge and discharge record includes: querying the record position corresponding to the shortest charge and discharge duration in the charge and discharge duration in the historical charge and discharge record; starting from the record position, dividing the historical charge and discharge record according to the interval of the shortest charge and discharge duration to obtain an initial divided charge and discharge record; judging whether there is a single duration containing two states in the initial divided charge and discharge record; when there is a single duration containing two states in the initial divided charge and discharge record, dividing the single duration according to the time boundary between the two states in the single duration to obtain a divided charge duration and a divided discharge duration; according to the divided charge duration and the divided discharge duration, calculating the division interval of the historical charge and discharge record using the following formula:

[0097]

[0098] Wherein, p represents the segmentation interval, k represents the sequence number of the single duration containing two states, K represents the total number of the single duration containing two states, represents the length of the split charging duration i in the kth single duration containing two states, represents the length of the split discharge duration j in the kth single duration containing two states, n represents the number of durations after the K split charge durations are split according to the split interval p, and m represents the number of durations after the K split discharge durations are split according to the split interval p;

[0099] The historical charge and discharge records are divided according to the division intervals to obtain divided charge and discharge records.

[0100] The single duration refers to the interval of the shortest single charge and discharge duration, and the two states include a charging state and a discharging state.

[0101] Exemplarily, the process of dividing the historical charge and discharge record according to the intervals of the shortest charge and discharge time starting from the record position to obtain the initial divided charge and discharge record means dividing the data before the record position into data with fixed intervals, and dividing the data after the record position into data with fixed intervals, starting from the record position.

[0102] It should be noted that in the formula There are three unknown numbers, namely p, n, and m. When calculating p, we randomly substitute rational numbers into n and m. When the result calculated by n and m meets the formula When , we can get p.

[0103] The power analysis module 102 is used to calculate the first remaining power of the energy storage lithium battery by using the split charge and discharge records, locate the surrounding charging stations of the energy storage lithium battery, and analyze the second remaining power of the energy storage lithium battery when it arrives at the surrounding charging stations based on the driving distance between the energy storage lithium battery and the surrounding charging stations.

[0104] The embodiment of the present invention calculates the first remaining power of the energy storage lithium battery by using the split charge and discharge records, so as to calculate the remaining power of the energy storage lithium battery in historical time.

[0105] The first remaining power refers to a sequence of remaining power in a historical period that is consistent with the historical charge and discharge record in time.

[0106] Optionally, the process of calculating the first remaining power of the energy storage lithium battery by using the divided charge and discharge record calculates the remaining power of the energy storage lithium battery by acquiring current and voltage data corresponding to the divided charge and discharge record.

[0107] Furthermore, the embodiment of the present invention analyzes the second remaining power of the energy storage lithium battery when it arrives at the surrounding charging station based on the driving distance between the energy storage lithium battery and the surrounding charging station, so as to analyze the changes in the energy storage lithium battery compared to the first remaining power before the energy storage lithium battery arrives at the surrounding charging station for charging and discharging, thereby preparing for the energy storage lithium battery to arrive at the surrounding charging station for charging and discharging.

[0108] In one embodiment of the present invention, the analyzing the second remaining power of the energy storage lithium battery when it arrives at the surrounding charging station based on the driving distance between the energy storage lithium battery and the surrounding charging station includes: querying the remaining power sequence of the energy storage lithium battery during historical driving; calculating the power drop value between the remaining power at adjacent moments in the remaining power sequence; calculating the mean of the power drop values, and calculating the time difference between adjacent moments in the remaining power sequence; calculating the driving time of the energy storage lithium battery using the driving distance and the driving speed of the energy storage lithium battery; calculating the number of time differences within the driving time to obtain the number of differences; calculating the mean-number product between the mean of the power drop values ​​and the number of differences; and taking the difference between the target remaining power corresponding to the energy storage lithium battery in the first remaining power and the mean-number product as the second remaining power.

[0109] Among them, the historical driving process refers to the process from positioning to the surrounding charging station to driving to the surrounding charging station, and the remaining power sequence refers to the remaining power data collected at fixed time intervals during the historical driving process. This fixed time interval is consistent with the time interval of the above-mentioned split charging and discharging records.

[0110] The aging test module 103 is used to identify the assembly scenario of the energy storage lithium battery, analyze the planned charging and discharging records corresponding to the split charging and discharging records under the assembly scenario based on the driving time of the energy storage lithium battery to reach the surrounding charging stations, and test the aging degree of the energy storage lithium battery.

[0111] In the embodiment of the present invention, the assembly scenario refers to the application scenario of the energy storage lithium battery, such as new energy vehicles, tricycles and battery vehicles, etc. The charging and discharging functions in different assembly scenarios are different. For example, in a new energy vehicle, the car discharges to charge a mobile phone, while a tricycle and a battery vehicle cannot charge a mobile phone.

[0112] Furthermore, the embodiment of the present invention analyzes the planned charging and discharging records corresponding to the split charging and discharging records in the assembly scenario based on the driving time of the energy storage lithium battery to reach the surrounding charging station, so as to use a neural network model to analyze the changes of the split charging and discharging records within the planned time.

[0113] The driving duration is consistent with the driving duration of the energy storage lithium battery calculated by using the driving distance and the driving speed of the energy storage lithium battery.

[0114] In one embodiment of the present invention, the planned charging and discharging records corresponding to the split charging and discharging records in the assembly scenario are analyzed based on the driving time of the energy storage lithium battery to reach the surrounding charging stations, including: obtaining the electrical appliances and charging power sources in the assembly scenario; querying the total power consumption of the electrical appliances from the split charging and discharging records; calculating the power demand of the electrical appliances using the total power consumption; using the power demand as the discharge amount of the energy storage lithium battery; analyzing the charging capacity of the charging power source; using the charging capacity as the charge amount of the energy storage lithium battery; obtaining the historical charging and discharging status in the split charging and discharging records; and calculating the planned charging and discharging status of the energy storage lithium battery within the driving time using the following formula according to the historical charging and discharging status:

[0115] f t =σ(w f [h t-1 ,x t ]+b f )

[0116] i t =σ(w i [h t-1 ,x t ]+b i )

[0117]

[0118] o t =σ(w o [h t-1 ,x t ]+b o )

[0119]

[0120] h t =o t *tanh(c t )

[0121] Among them, h t Indicates the planned charging and discharging state, f t represents the output of the forget gate, i t represents the output of the input gate, Represents the candidate memory cell of the memory gate output, o t represents the output of the output gate, w f represents the weight of the forget gate, h t-1 Indicates the charge and discharge status at the previous moment, x t Indicates the historical charge and discharge state, b f represents the bias of the forget gate, w i represents the weight of the input gate, b i represents the bias of the input gate, w c represents the weight of the memory gate, b c represents the bias of the memory gate, w o represents the weight of the output gate, b o represents the bias of the output gate, c t-1 Indicates the memory status of the previous moment;

[0122] The discharge amount and the charge amount are randomly added to the planned charge and discharge state to obtain the planned charge and discharge record.

[0123] Among them, the electrical appliance refers to the discharge object of the energy storage lithium battery, the charging power source refers to the charging object of the energy storage lithium battery, the power demand refers to the amount of power required by the electrical appliance after absorbing the total amount of power, the charging capacity refers to the amount of power remaining in the charging power source after the discharge action in the divided charge and discharge record, and the planned charge and discharge state refers to the charging state or discharge state at a fixed time interval within the planned period, and 0 can be used to represent the charging state and 1 can be used to represent the discharging state.

[0124] Optionally, randomly adding the discharge amount and the charge amount to the planned charge and discharge state to obtain the planned charge and discharge record includes: assigning a value to each planned charge and discharge state to ensure that the final discharge amount is the discharge amount and the charge amount is the charge amount.

[0125] Furthermore, the embodiment of the present invention tests the aging degree of the energy storage lithium battery, so as to use the aging degree as a basis for subsequent decision-making on the next charging and discharging action.

[0126] The aging degree refers to the ratio of the temperature change to the voltage change of the energy storage lithium battery at a fixed time interval.

[0127] In one embodiment of the present invention, the testing of the aging degree of the energy storage lithium battery includes: collecting the temperature data and the voltage data of the energy storage lithium battery in the split charge and discharge record and the planned charge and discharge record; and calculating the aging degree of the energy storage lithium battery according to the temperature data and the voltage data using the following formula:

[0128]

[0129] Wherein, D represents the aging degree, T represents the temperature data, and V represents the voltage data.

[0130] It should be noted that the more aged the energy storage lithium battery is, the smaller the peak value of D will be.

[0131] The action construction module 104 is used to use the divided charge and discharge records and the planned charge and discharge records as the charge and discharge state sequence of the energy storage lithium battery, use the first remaining power and the second remaining power as the remaining power sequence of the energy storage lithium battery, use the aging degree as the aging degree sequence of the energy storage lithium battery, use the charge and discharge state sequence, the remaining power sequence and the aging degree sequence to construct the state space of the energy storage lithium battery, and construct the action space of the energy storage lithium battery.

[0132] Optionally, the process of using the divided charge and discharge record and the planned charge and discharge record as the charge and discharge state sequence of the energy storage lithium battery is a process of merging the divided charge and discharge record and the planned charge and discharge record in chronological order.

[0133] Optionally, the process of using the first remaining power and the second remaining power as the remaining power sequence of the energy storage lithium battery is a process of merging the first remaining power and the second remaining power in chronological order.

[0134] Furthermore, in an embodiment of the present invention, the state space includes charging and discharging states, remaining power and aging degree, and the action space includes charging action, discharging action and no charging and discharging action.

[0135] The function optimization module 105 is used to calculate the action value function of the energy storage lithium battery based on the state space and the action space, calculate the state value function of the energy storage lithium battery according to the state space, use the action value function and the state value function to decide the charging and discharging actions of the energy storage lithium battery, and use the charging and discharging actions to optimize the parameters of the action value function and the state value function respectively to obtain an optimized action value function and an optimized state value function.

[0136] The embodiment of the present invention calculates the action value function of the energy storage lithium battery based on the state space and the action space, so as to calculate the expected value of the long-term reward of the energy storage lithium battery performing a certain action in the next step under a certain state.

[0137] In one embodiment of the present invention, the calculating the action value function of the energy storage lithium battery based on the state space and the action space includes: calculating the updated action value function of the energy storage lithium battery based on the state space and the action space using the following formula:

[0138]

[0139] Wherein, Q0(s,a,w) represents the action value function of the energy storage lithium battery corresponding to the updated s state and a action after the update, s represents the current state in the state space, a represents the action in the action space taken under the current state, α represents the state transition probability, Q(s,a,w) represents the action value function before the s state and a action are updated, r represents the difference between Q(s',a') and V(s') when the s state is converted to the s' state and the a action is converted to the a' action, γ represents a constant between 0 and 1, s' represents the next state of the s state, a' represents the next action of the a action taken under the s' state, Q(s',a',w)=Q(s',a'), Q(s',a',w) represents the updated action value function corresponding to the s' state and a' action, and w represents the weight parameter;

[0140] The action value function after the energy storage lithium battery is updated is used as the action value function of the energy storage lithium battery.

[0141] Furthermore, the embodiment of the present invention calculates the state value function of the energy storage lithium battery according to the state space, so as to calculate the expected value of the long-term reward of the energy storage lithium battery performing any next action in a certain state.

[0142] In one embodiment of the present invention, the calculating the state value function of the energy storage lithium battery according to the state space includes: calculating the updated state value function of the energy storage lithium battery according to the state space using the following formula:

[0143] V0(s)=(1-α)*V(s)+α*(r+γ*V(s'))

[0144] Wherein, V0(s) represents the state value function of the energy storage lithium battery corresponding to the s state after the update, V(s) represents the state value function of the energy storage lithium battery corresponding to the s state before the update, r represents the difference between Q(s',a') and V(s') when the s state is converted to the s' state and the a action is converted to the a' action, γ represents a constant between 0 and 1, V(s') represents the state value function corresponding to the s' state, and α represents the state transition probability;

[0145] The updated state value function of the energy storage lithium battery is used as the state value function of the energy storage lithium battery.

[0146] Furthermore, the embodiment of the present invention uses the action value function and the state value function to decide the charging and discharging actions of the energy storage lithium battery, so as to use the difference between the action value function and the state value function to determine the size of the long-term reward of performing a certain action, and use the size of the long-term reward as a criterion for determining whether the next action is performed correctly.

[0147] In one embodiment of the present invention, the use of the action value function and the state value function to determine the charging and discharging actions of the energy storage lithium battery includes: calculating the function difference between the action value function and the state value function; when the function difference is maximum, determining the charging and discharging actions of the energy storage lithium battery from the action value function and the state value function corresponding to the function difference.

[0148] Furthermore, the embodiment of the present invention optimizes the parameters of the action value function and the state value function respectively by utilizing the charging and discharging actions, so as to improve the accuracy of action decisions made by using the action value function and the state value function.

[0149] In one embodiment of the present invention, the use of the charging and discharging actions to optimize the parameters of the action value function and the state value function respectively to obtain an optimized action value function and an optimized state value function includes: determining the target state and the target action in the action value function and the state value function according to the charging and discharging actions; and updating the weight parameters in the action value function according to the target state and the target action using the following formula to obtain an updated weight parameter:

[0150]

[0151] Among them, w' represents the updated weight parameter, w represents the weight parameter, represents the action value function that meets the target action selected from the a action of Q0(s,a,w) and meets the target state selected from the s' state of Q9s',a',w), s represents the current state in the state space, a represents the action in the action space taken under the current state, α represents the state transition probability, express The corresponding actual action value function, r represents the difference between Q(s',a') and V(s') when converting the s state to the s' state and converting the a action to the a' action, γ represents a constant between 0 and 1, s' represents the next state of the s state, a' represents the next action of the a action taken in the s' state, Q(s',a',w)=Q(s',a'), Q(s',a',w) represents the updated action value function corresponding to the s' state and the a' action, and LOSS represents and Losses between

[0152] According to the target state, the constant parameters in the action value function and the state value function are updated using the following formula to obtain updated constant parameters:

[0153]

[0154] Among them, γ' represents the update constant parameter, α represents the state transition probability, γ represents a constant between 0 and 1, and LOSS' represents and between, and The loss between represents the state value function selected from the s state of V0(s) that meets the target state, represents the actual state value function corresponding to V0(s), r represents the difference between Q(s',a') and V(s') when converting state s to state s' and action a to action a';

[0155] The update weight parameter and the update constant parameter are used to complete parameter optimization of the action value function and the state value function to obtain an optimized action value function and an optimized state value function.

[0156] The target state refers to the state after the charging and discharging action is performed, and the target action refers to the charging and discharging action.

[0157] The charge and discharge control module 106 is used to control the charge and discharge of the energy storage lithium battery according to the optimized action value function and the optimized state value function by using the state space and the action space to obtain the charge and discharge control result of the energy storage lithium battery.

[0158] The embodiment of the present invention controls the charge and discharge of the energy storage lithium battery by using the state space and the action space according to the optimized action value function and the optimized state value function, so as to improve the adaptability of the charge and discharge control of the battery under different charge and discharge states, battery capacities and battery aging degrees.

[0159] Optionally, the process of controlling the charging and discharging of the energy storage lithium battery using the state space and the action space according to the optimized action value function and the optimized state value function is to calculate the long-term reward of performing a certain action under a certain state by using the optimized action value function and the optimized state value function, and decide which action to perform next based on the size of the long-term reward.

[0160] It can be seen that the embodiment of the present invention divides the historical charge and discharge record by using the charge and discharge time to ensure that there is only one charge and discharge state within each fixed interval, and uses the divided charge and discharge record as a basis for subsequent decision-making on the next charge and discharge action. The embodiment of the present invention calculates the first remaining power of the energy storage lithium battery by using the divided charge and discharge record to calculate the remaining power of the energy storage lithium battery in the historical time. Furthermore, the embodiment of the present invention analyzes the second remaining power of the energy storage lithium battery when it arrives at the surrounding charging station based on the driving distance between the energy storage lithium battery and the surrounding charging station, so as to calculate the remaining power of the energy storage lithium battery when the energy storage lithium battery arrives at the surrounding charging station. Before the charging station can charge and discharge, the change of the energy storage lithium battery compared to the first remaining power is analyzed, so as to prepare for the energy storage lithium battery to arrive at the surrounding charging station for charging and discharging. Furthermore, the embodiment of the present invention analyzes the planned charging and discharging records corresponding to the segmented charging and discharging records in the assembly scenario based on the driving time of the energy storage lithium battery to reach the surrounding charging station, so as to use the neural network model to analyze the changes of the segmented charging and discharging records within the planned time. Furthermore, the embodiment of the present invention tests the aging degree of the energy storage lithium battery, so as to use the aging degree as the basis for subsequent decision-making on the next charging and discharging action. The embodiment of the present invention is based on The state space and the action space are used to calculate the action value function of the energy storage lithium battery, which is used to calculate the expected value of the long-term reward of the energy storage lithium battery performing a certain action in the next step in a certain state. Further, the embodiment of the present invention calculates the state value function of the energy storage lithium battery according to the state space, which is used to calculate the expected value of the long-term reward of the energy storage lithium battery performing any action in the next step in a certain state. Further, the embodiment of the present invention uses the action value function and the state value function to decide the charging and discharging action of the energy storage lithium battery, so as to use the difference between the action value function and the state value function to determine whether to perform a certain action. The size of the long-term reward, and the size of the long-term reward is used as a criterion for judging whether the next action is correct or not. Furthermore, the embodiment of the present invention optimizes the parameters of the action value function and the state value function respectively by utilizing the charging and discharging actions, so as to improve the accuracy of action decisions made by the action value function and the state value function. The embodiment of the present invention controls the charging and discharging of the energy storage lithium battery by utilizing the state space and the action space according to the optimized action value function and the optimized state value function, so as to improve the adaptability of the charging and discharging control of the battery under different charging and discharging states, battery capacities and battery aging degrees. Therefore, a new energy energy storage lithium battery control system and control method proposed in the embodiment of the present invention can improve the adaptability of the charging and discharging control of the battery under different charging and discharging states, battery capacities and battery aging degrees.

[0161] See also Figure 2 FIG. 1 is a flow chart of a new energy storage lithium battery control method provided by an embodiment of the present invention. Figure 2 The new energy storage lithium battery control method described in the invention includes:

[0162] S1. Collect historical charge and discharge records of the energy storage lithium battery, calculate the charge and discharge duration of each charge and discharge record in the historical charge and discharge records according to the time sequence in the historical charge and discharge records, and divide the historical charge and discharge records by the charge and discharge duration to obtain divided charge and discharge records;

[0163] S2, calculating the first remaining power of the energy storage lithium battery using the split charge and discharge records, locating the surrounding charging stations of the energy storage lithium battery, and analyzing the second remaining power of the energy storage lithium battery when it arrives at the surrounding charging stations based on the driving distance between the energy storage lithium battery and the surrounding charging stations;

[0164] S3, identifying the assembly scenario of the energy storage lithium battery, analyzing the planned charge and discharge records corresponding to the split charge and discharge records under the assembly scenario based on the driving time of the energy storage lithium battery to reach the surrounding charging stations, and testing the aging degree of the energy storage lithium battery;

[0165] S4, using the split charge and discharge record and the planned charge and discharge record as the charge and discharge state sequence of the energy storage lithium battery, using the first remaining power and the second remaining power as the remaining power sequence of the energy storage lithium battery, using the aging degree as the aging degree sequence of the energy storage lithium battery, and constructing the state space of the energy storage lithium battery using the charge and discharge state sequence, the remaining power sequence and the aging degree sequence, and constructing the action space of the energy storage lithium battery;

[0166] S5. Based on the state space and the action space, the action value function of the energy storage lithium battery is calculated. According to the state space, the state value function of the energy storage lithium battery is calculated. The charging and discharging actions of the energy storage lithium battery are determined by using the action value function and the state value function. The charging and discharging actions are used to optimize the parameters of the action value function and the state value function, respectively, to obtain an optimized action value function and an optimized state value function.

[0167] S6. According to the optimized action value function and the optimized state value function, the state space and the action space are used to control the charge and discharge of the energy storage lithium battery to obtain the charge and discharge control result of the energy storage lithium battery.

[0168] In detail, the new energy storage lithium battery control method described in the embodiment of the present invention is as follows Figure 2The various processes described in the above are used in the same manner as above. Figure 1 The technical means are the same as the new energy storage lithium battery control system described in, and can produce the same technical effects, so I will not go into details here.

[0169] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0170] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0171] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0172] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0173] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A new energy storage lithium battery control system, characterized in that: The system comprises: A record segmentation module is used to collect historical charge and discharge records of the energy storage lithium battery, calculate the charge and discharge duration of each charge and discharge record in the historical charge and discharge records according to the time sequence in the historical charge and discharge records, and use the charge and discharge duration to segment the historical charge and discharge records to obtain segmented charge and discharge records; A power analysis module, used to calculate a first remaining power of the energy storage lithium battery using the split charge and discharge records, locate a surrounding charging station of the energy storage lithium battery, and analyze a second remaining power of the energy storage lithium battery when it arrives at the surrounding charging station based on a travel distance between the energy storage lithium battery and the surrounding charging station; An aging test module, used to identify the assembly scenario of the energy storage lithium battery, analyze the planned charging and discharging records corresponding to the split charging and discharging records under the assembly scenario based on the driving time of the energy storage lithium battery to reach the surrounding charging stations, and test the aging degree of the energy storage lithium battery; an action construction module, configured to use the split charge and discharge record and the planned charge and discharge record as a charge and discharge state sequence of the energy storage lithium battery, use the first remaining power and the second remaining power as a remaining power sequence of the energy storage lithium battery, use the aging degree as an aging degree sequence of the energy storage lithium battery, construct a state space of the energy storage lithium battery using the charge and discharge state sequence, the remaining power sequence and the aging degree sequence, and construct an action space of the energy storage lithium battery; A function optimization module, used to calculate the action value function of the energy storage lithium battery based on the state space and the action space, calculate the state value function of the energy storage lithium battery according to the state space, use the action value function and the state value function to decide the charging and discharging action of the energy storage lithium battery, and use the charging and discharging action to optimize the parameters of the action value function and the state value function respectively, to obtain an optimized action value function and an optimized state value function; A charge and discharge control module, used to control the charge and discharge of the energy storage lithium battery using the state space and the action space according to the optimized action value function and the optimized state value function, and obtain a charge and discharge control result of the energy storage lithium battery; The method of dividing the historical charge and discharge records by using the charge and discharge duration to obtain divided charge and discharge records includes: Query the record position corresponding to the shortest charge and discharge duration among the charge and discharge durations in the historical charge and discharge records; Starting from the recording position, dividing the historical charge and discharge record according to the interval of the shortest charge and discharge time to obtain an initial divided charge and discharge record; Determine whether there are two states in a single duration in the initial split charge and discharge record; When there are two states in a single duration in the initial split charge and discharge record, the single duration is split according to the time boundary between the two states in the single duration to obtain a split charge duration and a split discharge duration; According to the split charging time and the split discharging time, the split interval of the historical charge and discharge record is calculated using the following formula: Wherein, p represents the segmentation interval, k represents the sequence number of the single duration containing two states, K represents the total number of the single duration containing two states, represents the length of the split charging duration i in the kth single duration containing two states, represents the length of the split discharge duration j in the kth single duration containing two states, n represents the number of durations after the K split charge durations are split according to the split interval p, and m represents the number of durations after the K split discharge durations are split according to the split interval p; Splitting the historical charge and discharge records according to the split interval to obtain split charge and discharge records; The calculating the action value function of the energy storage lithium battery based on the state space and the action space includes: Based on the state space and the action space, the action value function after the energy storage lithium battery is updated is calculated using the following formula: Wherein, Q0(s,a,w) represents the action value function of the energy storage lithium battery corresponding to the updated s state and a action after the update, s represents the current state in the state space, a represents the action in the action space taken under the current state, α represents the state transition probability, Q(s,a,w) represents the action value function of the s state and a action before the update, r represents the difference between Q(s',a') and V(s') when the s state is converted to the s' state and the a action is converted to the a' action, γ represents a constant between 0 and 1, s' represents the next state of the s state, a' represents the next action of the a action taken under the s' state, Q(s',a',w)=Q(s',a'), Q(s',a',w) represents the updated action value function corresponding to the s' state and a' action, and w represents the weight parameter; The action value function after the energy storage lithium battery is updated is used as the action value function of the energy storage lithium battery; The step of calculating the state value function of the energy storage lithium battery according to the state space includes: According to the state space, the state value function of the energy storage lithium battery after updating is calculated using the following formula: V0(s)=(1-α)*V(s)+α*(r+γ*V(s′)) Wherein, V0(s) represents the state value function of the energy storage lithium battery corresponding to the s state after the update, V(s) represents the state value function of the energy storage lithium battery corresponding to the s state before the update, r represents the difference between Q(s′,a′) and V(s′) when the s state is converted to the s′ state and the a action is converted to the a′ action, γ represents a constant between 0 and 1, V(s′) represents the state value function corresponding to the s′ state, and α represents the state transition probability; The updated state value function of the energy storage lithium battery is used as the state value function of the energy storage lithium battery; The method of using the action value function and the state value function to determine the charging and discharging actions of the energy storage lithium battery includes: Calculating a function difference between the action value function and the state value function; When the function difference is the largest, the charging and discharging actions of the energy storage lithium battery are determined from the action value function and the state value function corresponding to the function difference; The method of optimizing the parameters of the action value function and the state value function by using the charging and discharging actions to obtain an optimized action value function and an optimized state value function includes: Determine the target state and target action in the action value function and the state value function according to the charging and discharging action; According to the target state and the target action, the weight parameter in the action value function is updated using the following formula to obtain an updated weight parameter: Among them, w′ represents the updated weight parameter, w represents the weight parameter, represents the action value function that meets the target action selected from the a action of Q0(s,a,w) and meets the target state selected from the s' state of Q(s′,a',w), s represents the current state in the state space, a represents the action in the action space taken under the current state, α represents the state transition probability, express The corresponding actual action value function, r represents the difference between Q(s',a') and V(s') when converting the s state to the s' state and the a action to the a' action, γ represents a constant between 0 and 1, s' represents the next state of the s state, a' represents the next action of the a action taken in the s' state, Q(s',a',w)=Q(s',a'), Q(s',a',w) represents the updated action value function corresponding to the s' state and the a' action, and LOSS represents and Losses between According to the target state, the constant parameters in the action value function and the state value function are updated using the following formula to obtain updated constant parameters: Among them, γ' represents the update constant parameter, α represents the state transition probability, γ represents a constant between 0 and 1, and LOSS' represents and between, and The loss between represents the state value function selected from the s state of V0(s) that meets the target state, represents the actual state value function corresponding to V0(s), r represents the difference between Q(s′,a′) and V(s′) when converting state s to state s′ and action a to action a′; The update weight parameter and the update constant parameter are used to complete parameter optimization of the action value function and the state value function to obtain an optimized action value function and an optimized state value function.

2. The system according to claim 1, characterized in that The analyzing, based on the travel distance between the energy storage lithium battery and the surrounding charging station, a second remaining power of the energy storage lithium battery when the energy storage lithium battery arrives at the surrounding charging station comprises: Query the remaining power sequence of the energy storage lithium battery during historical driving; Calculating the power decrease value between the remaining power at adjacent moments in the remaining power sequence; Calculating the mean of the power reduction values, and calculating the time difference between adjacent times in the remaining power sequence; Calculating the driving time of the energy storage lithium battery using the driving distance and the driving speed of the energy storage lithium battery; Calculating the number of the time differences within the driving duration to obtain the number of differences; Calculate the mean-number product between the mean of the power reduction value and the number of differences; The difference between the target remaining power corresponding to the energy storage lithium battery in the first remaining power and the product of the mean value and the number is used as the second remaining power.

3. The system according to claim 1, characterized in that The analyzing the planned charging and discharging records corresponding to the split charging and discharging records in the assembly scenario based on the driving time of the energy storage lithium battery to reach the surrounding charging station includes: Obtain electrical appliances and charging power sources in the assembly scenario; Querying the total power consumption of the electrical appliance from the split charge and discharge records; Calculating the power demand of the electrical appliances using the total power consumption; Taking the power demand as the discharge capacity of the energy storage lithium battery; analyzing the charging capability of the charging power source; Using the charging capacity as the charging amount of the energy storage lithium battery; Acquiring the historical charge and discharge status in the split charge and discharge record; According to the historical charge and discharge status, the planned charge and discharge status of the energy storage lithium battery within the driving time is calculated using the following formula: f t =σ(w f [h t-1 ,x t ]+b f ) i t =σ(w i [h t-1 ,x t ]+b i ) the t =σ(w o [h t-1 ,x t ]+b o h t =o t *tanh(c t ) Among them, h t Indicates the planned charging and discharging state, f t represents the output of the forget gate, i t represents the output of the input gate, Represents the candidate memory cell of the memory gate output, o t represents the output of the output gate, w f represents the weight of the forget gate, h t-1 Indicates the charge and discharge status at the previous moment, x t Indicates the historical charge and discharge state, b f represents the bias of the forget gate, w i represents the weight of the input gate, b i represents the bias of the input gate, w c represents the weight of the memory gate, b c represents the bias of the memory gate, w o represents the weight of the output gate, b o represents the bias of the output gate, c t-1 Indicates the memory status of the previous moment; The discharge amount and the charge amount are randomly added to the planned charge and discharge state to obtain the planned charge and discharge record.

4. The system according to claim 1, characterized in that The testing of the aging degree of the energy storage lithium battery includes: Collecting the temperature data and voltage data of the energy storage lithium battery in the split charge and discharge record and the planned charge and discharge record; According to the temperature data and the voltage data, the aging degree of the energy storage lithium battery is calculated using the following formula: Wherein, D represents the aging degree, T represents the temperature data, and V represents the voltage data.

5. A new energy storage lithium battery control method, the method is applied to the new energy storage lithium battery control system as claimed in claim 1, characterized in that: The method comprises: Collect historical charge and discharge records of the energy storage lithium battery, calculate the charge and discharge duration of each charge and discharge record in the historical charge and discharge records according to the time sequence in the historical charge and discharge records, and divide the historical charge and discharge records by the charge and discharge duration to obtain divided charge and discharge records; Calculating a first remaining power of the energy storage lithium battery using the split charge and discharge records, locating a peripheral charging station of the energy storage lithium battery, and analyzing a second remaining power of the energy storage lithium battery when it arrives at the peripheral charging station based on a travel distance between the energy storage lithium battery and the peripheral charging station; Identify the assembly scenario of the energy storage lithium battery, analyze the planned charge and discharge records corresponding to the split charge and discharge records under the assembly scenario based on the driving time of the energy storage lithium battery to reach the surrounding charging stations, and test the aging degree of the energy storage lithium battery; The split charge and discharge record and the planned charge and discharge record are used as the charge and discharge state sequence of the energy storage lithium battery, the first remaining power and the second remaining power are used as the remaining power sequence of the energy storage lithium battery, and the aging degree is used as the aging degree sequence of the energy storage lithium battery. The state space of the energy storage lithium battery is constructed by using the charge and discharge state sequence, the remaining power sequence and the aging degree sequence, and the action space of the energy storage lithium battery is constructed; Based on the state space and the action space, the action value function of the energy storage lithium battery is calculated; according to the state space, the state value function of the energy storage lithium battery is calculated; the charging and discharging actions of the energy storage lithium battery are determined by using the action value function and the state value function; the charging and discharging actions are used to optimize the parameters of the action value function and the state value function, respectively, to obtain an optimized action value function and an optimized state value function; According to the optimized action value function and the optimized state value function, the state space and the action space are used to control the charge and discharge of the energy storage lithium battery to obtain a charge and discharge control result of the energy storage lithium battery; The method of dividing the historical charge and discharge records by using the charge and discharge duration to obtain divided charge and discharge records includes: Query the record position corresponding to the shortest charge and discharge duration among the charge and discharge durations in the historical charge and discharge records; Starting from the recording position, dividing the historical charge and discharge record according to the interval of the shortest charge and discharge time to obtain an initial divided charge and discharge record; Determine whether there are two states in a single duration in the initial split charge and discharge record; When there are two states in a single duration in the initial split charge and discharge record, the single duration is split according to the time boundary between the two states in the single duration to obtain a split charge duration and a split discharge duration; According to the split charging time and the split discharging time, the split interval of the historical charge and discharge record is calculated using the following formula: Wherein, p represents the segmentation interval, k represents the sequence number of the single duration containing two states, K represents the total number of the single duration containing two states, represents the length of the split charging duration i in the kth single duration containing two states, represents the length of the split discharge duration j in the kth single duration containing two states, n represents the number of durations after the K split charge durations are split according to the split interval p, and m represents the number of durations after the K split discharge durations are split according to the split interval p; Splitting the historical charge and discharge records according to the split interval to obtain split charge and discharge records; The calculating the action value function of the energy storage lithium battery based on the state space and the action space includes: Based on the state space and the action space, the action value function after the energy storage lithium battery is updated is calculated using the following formula: Wherein, Q0(s,a,w) represents the action value function of the energy storage lithium battery corresponding to the updated s state and a action after the update, s represents the current state in the state space, a represents the action in the action space taken under the current state, α represents the state transition probability, Q(s,a,w) represents the action value function before the s state and a action are updated, r represents the difference between Q(s′,a′) and V(s′) when the s state is converted to the s′ state and the a action is converted to the a′ action, γ represents a constant between 0 and 1, s′ represents the next state of the s state, a′ represents the next action of the a action taken under the s′ state, Q(s′,a′,w)=Q(s',a′), Q(s′,a′,w) represents the updated action value function corresponding to the s′ state and a′ action, and w represents the weight parameter; The action value function after the energy storage lithium battery is updated is used as the action value function of the energy storage lithium battery; The step of calculating the state value function of the energy storage lithium battery according to the state space includes: According to the state space, the state value function of the energy storage lithium battery after updating is calculated using the following formula: V0(s)=(1-α)*V(s)+α*(r+γ*V(s′)) Wherein, V0(s) represents the state value function of the energy storage lithium battery corresponding to the s state after the update, V(s) represents the state value function of the energy storage lithium battery corresponding to the s state before the update, r represents the difference between Q(s′,a′) and V(s′) when the s state is converted to the s′ state and the a action is converted to the a′ action, γ represents a constant between 0 and 1, V(s′) represents the state value function corresponding to the s′ state, and α represents the state transition probability; The updated state value function of the energy storage lithium battery is used as the state value function of the energy storage lithium battery; The method of using the action value function and the state value function to determine the charging and discharging actions of the energy storage lithium battery includes: Calculating a function difference between the action value function and the state value function; When the function difference is the largest, the charging and discharging actions of the energy storage lithium battery are determined from the action value function and the state value function corresponding to the function difference; The method of optimizing the parameters of the action value function and the state value function by using the charging and discharging actions to obtain an optimized action value function and an optimized state value function includes: Determine the target state and target action in the action value function and the state value function according to the charging and discharging action; According to the target state and the target action, the weight parameter in the action value function is updated using the following formula to obtain an updated weight parameter: Among them, w′ represents the updated weight parameter, w represents the weight parameter, represents the action value function that meets the target action selected from the a action of Q0(s,a,w) and meets the target state selected from the s′ state of Q(s′,a′,w), s represents the current state in the state space, a represents the action in the action space taken under the current state, α represents the state transition probability, express The corresponding actual action value function, r represents the difference between Q(s′,a′) and V(s′) when converting the s state to the s′ state and the a action to the a′ action, γ represents a constant between 0 and 1, s′ represents the next state of the s state, a′ represents the next action of the a action taken in the s′ state, Q(s′,a′,w)=Q(s',a′), Q(s′,a′,w) represents the updated action value function corresponding to the s′ state and the a′ action, and LOSS represents and Losses between According to the target state, the constant parameters in the action value function and the state value function are updated using the following formula to obtain updated constant parameters: Among them, γ' represents the update constant parameter, α represents the state transition probability, γ represents a constant between 0 and 1, and LOSS' represents and between, and The loss between represents the state value function selected from the s state of V0(s) that meets the target state, represents the actual state value function corresponding to V0(s), r represents the difference between Q(s',a') and V(s') when converting state s to state s' and action a to action a'; The update weight parameter and the update constant parameter are used to complete parameter optimization of the action value function and the state value function to obtain an optimized action value function and an optimized state value function.

Images