Hybrid energy storage energy-saving control method and device, computer device and storage medium

Abstract

The application relates to a hybrid energy storage energy-saving control method and device, computer equipment and a storage medium. The method comprises the following steps: predicting a total power demand mapping relationship of a load on a DC bus in a future period based on historical operation data of the load; predicting a chargeable and dischargeable rate mapping relationship of a lithium battery pack in the future period based on historical operation data of the lithium battery pack; predicting a chargeable and dischargeable rate mapping relationship of a super capacitor pack in the future period based on historical operation data of the super capacitor pack; and generating an instruction sequence for controlling the coordinated charging and discharging of the super capacitor pack and the lithium battery pack based on the predicted total power demand mapping relationship, the chargeable and dischargeable rate mapping relationship of the lithium battery pack and the chargeable and dischargeable rate mapping relationship of the super capacitor pack. The method can realize intelligent collaborative control of the super capacitor and the lithium battery, thereby improving system response speed, optimizing energy distribution efficiency and prolonging the service life of the energy storage equipment.

Description

Technical Field

[0001] This application relates to the field of energy storage and energy conservation technology, and in particular to a hybrid energy storage and energy conservation control method, device, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] In the fields of power electronics and energy-saving control technology, energy feedback and energy storage technologies have been widely used to improve the energy efficiency of equipment such as elevators and cranes. When these devices brake or lower heavy objects, their drive motors generate electricity, producing a considerable amount of regenerative energy for recycling.

[0003] Current approaches tend to employ hybrid energy storage systems composed of supercapacitors and lithium batteries to balance power response and energy storage. However, traditional hybrid energy storage coordination control methods are mostly based on fixed voltage thresholds or simple power allocation logic, representing a passive response mode. Because lithium battery charging and discharging management has an inherent delay of hundreds of milliseconds, while power peaks in situations like elevator start-stop often occur within seconds or even sub-seconds, the system's rapid response capability heavily relies on supercapacitors, while the regulatory effect of lithium batteries lags, making it difficult to achieve smooth and efficient coordination. Furthermore, the lack of prediction of the energy storage components' own state (such as health and temperature) and load change trends prevents the system from proactively optimizing energy allocation strategies, hindering further improvements in overall energy efficiency, equipment lifespan, and system economy.

[0004] Therefore, there is an urgent need for a hybrid energy storage energy-saving control method, device, computer equipment, computer-readable storage medium, and computer program product that can realize intelligent collaborative control of supercapacitors and lithium batteries, thereby improving system response speed, optimizing energy distribution efficiency, and extending the life of energy storage equipment. Summary of the Invention

[0005] Based on this, it is necessary to provide a hybrid energy storage energy-saving control method, device, computer equipment, computer-readable storage medium, and computer program product that can achieve intelligent collaborative control of supercapacitors and lithium batteries, thereby improving system response speed, optimizing energy distribution efficiency, and extending the life of energy storage equipment, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a hybrid energy storage energy-saving control method, including:

[0007] Obtain an operational dataset of lithium battery pack, supercapacitor pack and at least one load, wherein the operational dataset includes real-time operational data and historical operational data;

[0008] Based on the historical operating data of the load, predict the total power demand mapping relationship of the load on the DC bus in the future period;

[0009] Based on the historical operating data of the lithium battery pack, predict the charge / discharge rate mapping relationship of the lithium battery pack in the future period.

[0010] Based on the historical operating data of the supercapacitor bank, predict the charge / discharge rate mapping relationship of the supercapacitor bank in the future period.

[0011] Based on the predicted total power demand mapping relationship, the charge / discharge rate mapping relationship of the lithium battery pack, and the charge / discharge rate mapping relationship of the supercapacitor pack, a command sequence is generated to control the coordinated charging and discharging of the supercapacitor pack and the lithium battery pack.

[0012] In one embodiment, the historical operating data includes historical current data, historical voltage data, and duration data; the step of predicting the total power demand mapping relationship of the load on the DC bus in the future period based on the historical operating data of the load includes:

[0013] The historical current data, historical voltage data, and duration data of the load are normalized to obtain the overall characteristic curve of the load on the DC bus.

[0014] With the goal of minimizing the loss index between the predicted and actual values, the total characteristic curve is subjected to autoregressive optimization to obtain the total energy demand mapping relationship that includes future demand current, voltage and duration.

[0015] In one embodiment, predicting the charge / discharge rate mapping relationship of the lithium battery pack in the future based on the historical operating data of the lithium battery pack includes:

[0016] Construct a cross-dimensional feature set for lithium battery packs, which includes at least: voltage-state of charge correlation, voltage-temperature correlation, health state-temperature correlation, and historical charge-discharge coupling features obtained based on historical data;

[0017] With the comprehensive optimization of charge-discharge efficiency, safe operation and life decay indicators as the training objective, the model is trained and parameters are optimized on the cross-dimensional feature set of the lithium battery pack. The prediction results for the future period are corrected by using the historical charge-discharge coupling features to obtain the charge-discharge rate mapping relationship of the lithium battery pack.

[0018] In one embodiment, the safe operation index is calculated based on the deviation of the temperature rise rate from the safe threshold voltage; the lifespan degradation index is calculated based on the correlation function of the predicted charge / discharge rate, temperature change rate, and health status degradation coefficient.

[0019] In one embodiment, predicting the charge / discharge rate mapping relationship of the supercapacitor bank in the future period based on the historical operating data of the supercapacitor bank includes:

[0020] Construct a cross-dimensional feature set for the supercapacitor bank, which includes at least: voltage-capacitance variation correlation and internal resistance-temperature correlation obtained based on historical data;

[0021] Initial rate prediction is performed based on the circuit physical model and the feature set, and autoregressive optimization is performed with the goal of minimizing prediction loss. At the same time, the maximum / minimum charge / discharge rate and voltage limit are used as physical constraints to adjust the prediction results of the initial rate, so as to obtain the charge / discharge rate mapping relationship of the supercapacitor group.

[0022] In one embodiment, generating the instruction sequence for coordinating the charging and discharging of the supercapacitor bank and the lithium battery bank includes:

[0023] When the total demand current determined based on the total power demand mapping relationship is greater than the operating current threshold and the direction is from the load end to the DC bus end, the total demand current is compared with the predicted maximum allowable charging current of the supercapacitor group and the predicted maximum allowable charging current of the lithium battery group.

[0024] If the total demand current is not greater than the predicted maximum allowable charging current of the supercapacitor bank, then a command sequence is generated that prioritizes charging by the supercapacitor bank.

[0025] If the total required current is greater than the predicted maximum allowable charging current of the supercapacitor bank but not greater than the predicted maximum allowable charging current of the lithium battery bank, then a sequence of instructions for coordinated charging by the supercapacitor bank and the lithium battery bank is generated.

[0026] If the total required current is greater than the predicted maximum allowable charging current of the lithium battery pack, then a sequence of instructions is generated to initiate current limiting and charge the battery in conjunction with the lithium battery pack.

[0027] In one embodiment, generating the instruction sequence for coordinating the charging and discharging of the supercapacitor bank and the lithium battery bank includes:

[0028] When the total demand current is greater than the operating current threshold and the direction is from the DC bus end to the load end, the supercapacitor bank is controlled to discharge first, and the command sequence for synchronous discharge of the lithium battery bank is controlled according to the relationship between the total demand current and the predicted maximum allowable discharge current of the lithium battery bank.

[0029] When the total required current is not greater than the operating current threshold, a sequence of instructions is generated to control the transfer of energy from the supercapacitor bank to the lithium battery bank.

[0030] Secondly, this application also provides a hybrid energy storage and energy-saving control device, comprising:

[0031] The acquisition module is used to acquire the operating dataset of the lithium battery pack, the supercapacitor pack and at least one load, wherein the operating dataset includes real-time operating data and historical operating data;

[0032] The prediction module is used to predict the total power demand mapping relationship of the load on the DC bus in the future period based on the historical operating data of the load.

[0033] The prediction module is also used to predict the charge / discharge rate mapping relationship of the lithium battery pack in the future period based on the historical operating data of the lithium battery pack.

[0034] The prediction module is also used to predict the charge / discharge rate mapping relationship of the supercapacitor bank in the future period based on the historical operating data of the supercapacitor bank.

[0035] The control module is used to generate a sequence of instructions for coordinating the charging and discharging of the supercapacitor group and the lithium battery group based on the predicted total power demand mapping relationship, the charge / discharge rate mapping relationship of the lithium battery group and the charge / discharge rate mapping relationship of the supercapacitor group.

[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0037] Obtain an operational dataset of lithium battery pack, supercapacitor pack and at least one load, wherein the operational dataset includes real-time operational data and historical operational data;

[0038] Based on the historical operating data of the load, predict the total power demand mapping relationship of the load on the DC bus in the future period;

[0039] Based on the historical operating data of the lithium battery pack, predict the charge / discharge rate mapping relationship of the lithium battery pack in the future period.

[0040] Based on the historical operating data of the supercapacitor bank, predict the charge / discharge rate mapping relationship of the supercapacitor bank in the future period.

[0041] Based on the predicted total power demand mapping relationship, the charge / discharge rate mapping relationship of the lithium battery pack, and the charge / discharge rate mapping relationship of the supercapacitor pack, a command sequence is generated to control the coordinated charging and discharging of the supercapacitor pack and the lithium battery pack.

[0042] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0043] Obtain an operational dataset of lithium battery pack, supercapacitor pack and at least one load, wherein the operational dataset includes real-time operational data and historical operational data;

[0044] Based on the historical operating data of the load, predict the total power demand mapping relationship of the load on the DC bus in the future period;

[0045] Based on the historical operating data of the lithium battery pack, predict the charge / discharge rate mapping relationship of the lithium battery pack in the future period.

[0046] Based on the historical operating data of the supercapacitor bank, predict the charge / discharge rate mapping relationship of the supercapacitor bank in the future period.

[0047] Based on the predicted total power demand mapping relationship, the charge / discharge rate mapping relationship of the lithium battery pack, and the charge / discharge rate mapping relationship of the supercapacitor pack, a command sequence is generated to control the coordinated charging and discharging of the supercapacitor pack and the lithium battery pack.

[0048] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0049] Obtain an operational dataset of lithium battery pack, supercapacitor pack and at least one load, wherein the operational dataset includes real-time operational data and historical operational data;

[0050] Based on the historical operating data of the load, predict the total power demand mapping relationship of the load on the DC bus in the future period;

[0051] Based on the historical operating data of the lithium battery pack, predict the charge / discharge rate mapping relationship of the lithium battery pack in the future period.

[0052] Based on the historical operating data of the supercapacitor bank, predict the charge / discharge rate mapping relationship of the supercapacitor bank in the future period.

[0053] Based on the predicted total power demand mapping relationship, the charge / discharge rate mapping relationship of the lithium battery pack, and the charge / discharge rate mapping relationship of the supercapacitor pack, a command sequence is generated to control the coordinated charging and discharging of the supercapacitor pack and the lithium battery pack.

[0054] The aforementioned hybrid energy storage energy-saving control methods, devices, computer equipment, computer-readable storage media, and computer program products acquire real-time and historical operating data of energy storage components and loads to construct a multi-dimensional dataset, providing a comprehensive and dynamic data foundation for intelligent decision-making. By analyzing historical load data to predict future power demand, they achieve advanced perception of system power changes, providing a forward-looking basis for energy dispatch. Through parallel prediction of the charge / discharge capabilities of lithium batteries and supercapacitors in future periods, they accurately grasp the real-time state boundaries and dynamic performance of each energy storage component. Finally, by comprehensively utilizing the above three types of predictive mapping relationships to generate coordinated control commands, the energy allocation between the supercapacitor bank and the lithium battery bank is no longer a passive response based on instantaneous states, but rather a collaborative optimization based on future system states. This solves the power coordination lag problem caused by lithium battery response delay in traditional hybrid energy storage systems, significantly improving the system's adaptability to instantaneous power fluctuations, overall energy recovery efficiency, and the lifespan of energy storage equipment. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a flowchart illustrating a hybrid energy storage energy-saving control method in one embodiment;

[0057] Figure 2 This is a flowchart illustrating the hybrid energy storage energy-saving control method in another embodiment;

[0058] Figure 3 Here is a trend chart of the characteristic curve of a load characteristic prediction model in one embodiment;

[0059] Figure 4 This is a structural block diagram of a hybrid energy storage and energy-saving control device in one embodiment;

[0060] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0063] In one exemplary embodiment, such as Figure 1 As shown, a hybrid energy storage energy-saving control method is provided, and the method is applied to a server for illustration, including the following steps S102 to S110. Wherein:

[0064] Step S102: Obtain the operating dataset of the lithium battery pack, supercapacitor pack and at least one load. The operating dataset includes real-time operating data and historical operating data.

[0065] Specifically, the operating data of the lithium battery pack, supercapacitor pack and at least one load are collected simultaneously and integrated into a complete dataset containing real-time operating data and historical operating data.

[0066] For lithium battery packs, the acquired real-time operating data includes, but is not limited to: the total voltage and total current of the battery pack, the individual voltages of multiple cells read through the battery management system (BMS), the real-time state of charge (SOC) reflecting the amount of charge remaining, the state of health (SOH) characterizing the degree of battery aging, and the temperature of the battery pack and each cell. These parameters are continuously recorded at a preset sampling period (e.g., once per second) to form historical operating sequence data, which is used to analyze the evolution of battery characteristics with the number of cycles and time.

[0067] For supercapacitor banks, the acquired real-time operating data includes, but is not limited to: the total voltage and current of the supercapacitor bank, the voltage of each capacitor cell, the real-time available capacity calculated from the voltage and rated capacity, the equivalent internal resistance characterizing performance, and the temperature. Similarly, these data are continuously recorded to form a historical sequence, specifically used to analyze its unique voltage-capacity relationship and the trend of internal resistance changes due to temperature and aging.

[0068] For loads (such as elevators, cranes, and other multiple devices), the acquired operating data is used to characterize their power demand features, including the motor operating frequency (or speed) of each load, the duration of a single operation, the time markers of start-stop events, and the corresponding bus current and voltage on the DC side of the frequency converter. Real-time data captures transient demands, while historical data accumulates typical power curves and operating cycle patterns under different operating conditions (such as different load weights and different operating distances).

[0069] All the aforementioned real-time data are aggregated to the central processing unit in real time via a system communication network (such as a CAN bus). Historical data is stored in a structured manner on storage media, forming a data warehouse that grows over time. Real-time data provides an instantaneous snapshot of the system's current state and serves as direct input for triggering immediate control decisions; historical operational data provides training samples and learning patterns for machine learning models.

[0070] Step S104: Based on the historical operating data of the load, predict the total power demand mapping relationship of the load on the DC bus in the future period.

[0071] Specifically, the total load power demand prediction step is based on the historical operating data of the loads and uses data modeling methods to proactively infer their overall power demand on the DC bus system in a specific future period. Specifically, the system calls upon the stored historical operating dataset, which contains time-series records of multiple loads (such as multiple elevators or cranes) over past periods. Key dimensions include: the operating frequency of each load, the duration of a single operation, and the corresponding DC-side current and voltage values ​​of the inverter.

[0072] Step S106: Based on the historical operating data of the lithium battery pack, predict the charge / discharge rate mapping relationship of the lithium battery pack in the future period.

[0073] Specifically, predicting the future charge / discharge rate mapping relationship based on the historical operating data of lithium battery packs refers to using the state and performance data recorded during the past operation of lithium batteries, through data analysis and model deduction, to pre-calculate the range of rates (i.e., rates) at which it can safely and effectively charge and discharge in the coming period, and to characterize this capability range in the form of a clear correspondence.

[0074] This involves analyzing historical operational data, such as records of battery voltage, current, temperature, and state of charge, over time to summarize the evolution patterns, operating limits, and degradation trends of battery performance. Based on these summarized patterns, the maximum charging and discharging currents that the battery can withstand at a specific future time period under a certain expected state are extrapolated or calculated. The final output, a charge / discharge rate mapping relationship, can be understood as a lookup table or function that indicates the safe operating current range allowed for the lithium battery under different future conditions (e.g., corresponding to different voltages or remaining states of charge).

[0075] Step S108: Based on the historical operating data of the supercapacitor bank, predict the charge / discharge rate mapping relationship of the supercapacitor bank in the future period.

[0076] Specifically, predicting the future charge / discharge rate mapping relationship based on the historical operating data of supercapacitor banks refers to using the performance records accumulated by supercapacitors in past operations, through analysis and modeling, to predict in advance how fast they can safely store (charge) or release (discharge) electrical energy in the upcoming period, and describing this rate capability in a clear and structured form.

[0077] Specifically, the charge / discharge rate directly reflects its power handling capability; a higher rate means a stronger ability to process current in a short time. The historical operating data relied upon for prediction is primarily the characteristic parameters of the supercapacitor that are closely related to the rate in its past operation, mainly its terminal voltage variation history, temperature records, and capacity changes reflecting its energy storage state.

[0078] Analyzing this historical data allows us to identify patterns and dynamics in the performance changes of supercapacitors. For example, voltage levels directly affect the current potential for continued charging or discharging, while temperature variations are related to internal resistance and efficiency, thus influencing the actual operating rate range. The prediction process utilizes these patterns, combined with the supercapacitor's current real-time state, to extrapolate its performance boundaries for specific future moments or time periods. The final output, the charge / discharge rate mapping, is a clear description linking possible future conditions (such as voltage levels) to their corresponding maximum allowable charge / discharge current (i.e., the specific manifestation of the rate).

[0079] Step S110: Based on the predicted total power demand mapping relationship, the charge / discharge rate mapping relationship of the lithium battery pack, and the charge / discharge rate mapping relationship of the supercapacitor pack, generate a command sequence for controlling the coordinated charging and discharging of the supercapacitor pack and the lithium battery pack.

[0080] Specifically, the three mapping relationships will be received and parsed synchronously. The core of the decision-making logic lies in comparison and matching: the predicted total load demand (current magnitude and direction) will be compared in real time with the predicted charging and discharging capabilities of the two energy storage elements. By analyzing whether the demand exceeds the capability range of one party or falls within the capability range of both, the basic operating mode to be adopted in the future can be determined (such as pure supercapacitor operation, both working together, or a working together requiring protection current limiting), and the power share that each should bear can be determined.

[0081] Based on this judgment, a sequence of instructions is generated. This sequence of instructions is a set of pre-programmed logical commands for controlling relevant power electronic switching devices (such as a bidirectional gating module connected to a supercapacitor and a current-limiting module connected to a lithium battery). It is not a single instruction, but an operation plan that takes into account time sequence or condition triggering, and its content directly corresponds to the specific circuit state switching required to achieve the aforementioned operating mode. For example, it may contain low-level operation commands such as turning certain switches on or off at specific times, or adjusting the current-limiting resistor level.

[0082] In the aforementioned hybrid energy storage energy-saving control method, a multi-dimensional dataset is constructed by acquiring real-time and historical operating data of energy storage components and loads, providing a comprehensive and dynamic data foundation for intelligent decision-making. By analyzing historical load data to predict future power demand, advanced perception of system power changes is achieved, providing a forward-looking basis for energy dispatch. By predicting the charge / discharge capabilities of lithium batteries and supercapacitors in future periods in parallel, the real-time state boundaries and dynamic performance of each energy storage component are accurately grasped. Finally, by comprehensively utilizing the above three types of predictive mapping relationships to generate coordinated control commands, the energy allocation between the supercapacitor bank and the lithium battery bank is no longer a passive response based on instantaneous states, but rather a collaborative optimization based on future system states. This method fundamentally solves the power coordination lag problem caused by lithium battery response delay in traditional hybrid energy storage systems, significantly improving the system's adaptability to instantaneous power fluctuations, overall energy recovery efficiency, and the lifespan of energy storage equipment, achieving a leap from "passive response" to "active optimization" in intelligent control.

[0083] In one exemplary embodiment, historical operating data includes historical current data, historical voltage data, and duration data; such as Figure 2 As shown, based on historical load operating data, the total power demand mapping relationship of the load on the DC bus is predicted for future periods, including:

[0084] Step S202: Normalize the historical current data, historical voltage data and duration data of the load to obtain the overall characteristic curve of the load on the DC bus.

[0085] Step S204: With minimizing the loss index between the predicted value and the actual value as the optimization objective, the total characteristic curve is subjected to autoregressive optimization to obtain the total energy demand mapping relationship that includes future demand current value, voltage value and duration.

[0086] Specifically, the mapping relationship of the overall operating characteristics of N loads in the next working stage of the load measurement. Where i is one of the N loads, I is the operating current of load i, and V is the DC bus voltage of load i. This is the operating time of the i-th load; thus, the mapping relationship of the load's response to the electrical energy demand in the battery's DC circuit is obtained. , yes The minimum value in Within the time limit , It is the maximum voltage among all loads. .

[0087] 1) Input: Real-time data of the above load. and historical data ;

[0088] 2) Load characteristic prediction model:

[0089] right The overall characteristics exhibited by the N loads in the DC circuit, obtained after normalization, are as follows: ,in yes at the same time The duration of all existence yes at the same time The initial time of all occurrences, and the constructed curve trend as follows Figure 3 As shown:

[0090] The optimal prediction result is obtained by performing an autoregressive optimization based on minimizing the load loss index. And output it. The load loss metric is the mean square error between the predicted and actual values, such as... .

[0091] In this embodiment, by normalizing and fusing the historical current, voltage, and duration data of the load, a total characteristic curve that reflects its macroscopic characteristics is constructed. With the goal of minimizing the prediction error, autoregressive optimization is performed to achieve high-precision and structured prediction of future power demand. The inherent operating rules of the load are effectively extracted, and the output demand mapping relationship clearly includes three-dimensional information of current, voltage, and duration.

[0092] In one exemplary embodiment, based on historical operating data of the lithium battery pack, the prediction of the charge / discharge rate mapping relationship of the lithium battery pack in a future period includes:

[0093] Construct a cross-dimensional feature set for lithium battery packs. The cross-dimensional feature set for lithium battery packs includes at least: voltage-state of charge correlation, voltage-temperature correlation, health state-temperature correlation, and historical charge-discharge coupling characteristics obtained based on historical data.

[0094] With the comprehensive optimization of charge-discharge efficiency, safe operation and life decay indicators as the training objective, the model is trained and the parameters are optimized on the cross-dimensional feature set of lithium battery packs. The prediction results for future periods are corrected by using historical charge-discharge coupling characteristics, so as to obtain the charge-discharge rate mapping relationship of lithium battery packs.

[0095] Specifically, based on the predicted next nearest period Total workload demand, synchronous forecasting Internal lithium battery capacity Mapping relationship.

[0096] Input: Real-time data from the lithium battery rate dataset described above. and historical data ; For voltage, For temperature;

[0097] Constructing a multidimensional prediction model:

[0098] S1: Construct a cross-dimensional feature set, including voltage and state of charge. - Relationship , The slope coefficient and the characteristic set of M lithium batteries. Where i is the number of cells connected in series in the lithium battery;

[0099] Lithium battery voltage and temperature - Relationship ,in Polarization coefficient; SOH temperature of lithium battery - Relationship ,in, Here, s is the degradation factor, s is the SOH degradation index, and s is the characteristic set of M lithium-ion cells. Where i is the number of cells connected in parallel in the lithium battery. These are the minimum and maximum temperatures in cell M;

[0100] The average charge / discharge rate of the first k charge / discharge cycles in the historical data of lithium battery (including M cells) charge / discharge coupling characteristics. Peak temperature and recovery time and voltage fluctuations during the period ( .

[0101] Model training: For the feature set of M battery cells, according to... After maximum / minimum denoising and normalization, the optimization is performed according to maximizing efficiency, minimizing safety, and minimizing lifetime, and the charge-discharge coupling characteristics are used for the next... The time-period forecast is adjusted and corrected to obtain the optimal forecast result. And output it.

[0102] In one exemplary embodiment, the safe operation index is calculated based on the deviation of the temperature rise rate from the safe threshold voltage; the lifespan degradation index is calculated based on the correlation function of the predicted charge / discharge rate, temperature change rate, and health status degradation coefficient.

[0103] Specifically, the efficiency indicator, namely the charge / discharge rate. Energy conversion efficiency ; The safety operation index is the product of the temperature rise rate and the battery overcharge / over-discharge deviation value, i.e. ( The lifetime degradation index is calculated as charge / discharge rate * temperature acceleration * SOH degradation coefficient, i.e. ( .

[0104] In this embodiment, a cross-dimensional feature set integrating voltage, temperature, health status, and historical charge / discharge behavior is constructed. A comprehensive objective integrating efficiency, safety, and lifespan metrics is used for model training and optimization, enabling multi-constraint, high-precision dynamic prediction of the future charge / discharge capability of lithium batteries. This effectively overcomes the limitations of traditional models that only consider a single state parameter, ensuring that the prediction results not only maximize energy throughput efficiency but also strictly guarantee that the battery operates within a safe range and delays lifespan degradation.

[0105] In one exemplary embodiment, based on historical operating data of the supercapacitor bank, the prediction of the charge / discharge rate mapping relationship of the supercapacitor bank in a future period includes:

[0106] Construct a cross-dimensional feature set for supercapacitor banks. The cross-dimensional feature set for supercapacitor banks shall include at least: voltage-capacity change correlation and internal resistance-temperature correlation obtained based on historical data.

[0107] Initial rate prediction is performed based on the circuit physical model and feature set, and autoregressive optimization is carried out with the goal of minimizing prediction loss. At the same time, the maximum / minimum charge / discharge rate and voltage limit are used as physical constraints to adjust the prediction results of the initial rate, so as to obtain the charge / discharge rate mapping relationship of the supercapacitor group.

[0108] Specifically, based on the predicted next nearest period Total workload demand, synchronous forecasting Internal supercapacitor charge / discharge rate Mapping relationship.

[0109] Input: Real-time data from the supercapacitor rate dataset mentioned above. and historical data ;in, For voltage, Here, T represents the rated capacity, K represents the temperature, K represents the number of supercapacitor cells, and t represents the time period.

[0110] S1: Construct a cross-dimensional feature set, including voltage-capacity correlation. , The slope coefficient and the characteristic set of K supercapacitor cells. Where i is the number of cells connected in series in the supercapacitor;

[0111] Temperature compensation correlation: First, the relationship between internal resistance and temperature at different times t for each cell. K corresponding to the time period Series and parallel connections yield the overall set of supercapacitor characteristics. ;

[0112] S2: Model Training: Using this model on the dataset from S1. Autoregressive optimization is performed based on minimizing the loss metric, and physical constraint features are incorporated for the next iteration. The time-period forecast is adjusted and corrected to obtain the optimal forecast result. And output. The loss metric is the mean square error between the predicted and actual ratios, such as... The physical limiting characteristics are maximum discharge rate and / or minimum discharge rate and / or maximum temperature and / or maximum / minimum voltage.

[0113] In this embodiment, a data-driven approach combining the circuit physical model and incorporating the physical limits of charge / discharge rate and voltage as constraints for prediction and calibration is used to achieve a rapid, accurate, and safe assessment of the dynamic power boundary of the supercapacitor. This approach leverages the theoretical reliability of the physical model while using data autoregressive optimization to capture the complex nonlinear characteristics of actual operation, ensuring that the prediction results are not only highly accurate but also strictly conform to the device's safe operating area.

[0114] In one exemplary embodiment, a sequence of instructions for controlling the coordinated charging and discharging of the supercapacitor bank and the lithium battery bank is generated, including:

[0115] When the total demand current determined based on the total power demand mapping relationship is greater than the operating current threshold and the direction is from the load end to the DC bus end, the total demand current is compared with the predicted maximum allowable charging current of the supercapacitor group and the predicted maximum allowable charging current of the lithium battery group.

[0116] If the total demand current is not greater than the predicted maximum allowable charging current of the supercapacitor bank, then a sequence of instructions is generated to prioritize charging by the supercapacitor bank.

[0117] If the total demand current is greater than the predicted maximum allowable charging current of the supercapacitor bank but not greater than the predicted maximum allowable charging current of the lithium battery bank, then a sequence of instructions for coordinated charging by the supercapacitor bank and the lithium battery bank is generated.

[0118] If the total demand current exceeds the predicted maximum allowable charging current of the lithium battery pack, a sequence of instructions is generated to start current limiting and charge the battery in conjunction with the lithium battery pack.

[0119] Specifically, if in Within the time limit, ,in, The operating current threshold is set, and the current direction is from the load end to the battery end (i.e., the bus end), requiring charging;

[0120] 1) Non-current-limited lithium battery charging:

[0121] Judgment condition 1: During the time period, if the current in the DC circuit... Within the maximum allowable charging current of lithium batteries, i.e. And lithium battery voltage Less than or equal to the full charge limit of lithium batteries During this period, the lithium battery can be charged according to the allowable current.

[0122] Control command 1: Control the lithium battery according to the charging current. Entering the charging state means recovering the regenerative energy generated on the load side into the lithium battery until... When the time is up or the lithium battery voltage is greater than or equal to the full charge limit. .

[0123] 2) Non-current-limited supercapacitor charging:

[0124] Judgment condition 2: During the time period, if Greater than the maximum allowable charging current of the lithium battery, i.e. ,and Less than the maximum allowable charging current of the supercapacitor, i.e. And at the supercapacitor voltage Less than or equal to the full charge limit of a supercapacitor During this period, lithium batteries cannot be charged at the permissible current, but supercapacitors can be charged at the permissible current.

[0125] Control command 2: Control the lithium battery to be in a non-charging / discharging state, and the supercapacitor to charge according to the charging current. Upon entering the charging state, the regenerative energy generated on the load side is recovered into the supercapacitor until... When the time is up or the supercapacitor voltage is greater than or equal to the full charge limit. .

[0126] 3) Current-limited charging:

[0127] Judgment condition 3: During the time period, conditions 1) and 2) are not satisfied, that is, if Greater than the maximum allowable charging current of the supercapacitor, i.e. And lithium battery voltage Less than or equal to the full charge limit of lithium batteries During this period, lithium batteries and supercapacitors must not be charged at the permissible current.

[0128] Control command 3: Current limiting control is in the current limiting state, and the lithium battery operates according to the charging current. When in charging state, the supercapacitor operates according to the charging current. When in charging mode, it recovers the regenerative energy generated on the load side into the supercapacitor and lithium battery.

[0129] In this embodiment, intelligent hierarchical allocation and dynamic path planning of regenerative energy are achieved by comparing and deciding on the predicted total current demand with the predicted charging capabilities of the supercapacitor and lithium battery in three levels. This ensures that the system always prioritizes the use of the supercapacitor's fast response characteristics to absorb energy peaks, only calls upon the lithium battery when necessary and operates strictly within its safe capacity, and activates a current-limiting protection mechanism in extreme cases. This hierarchical decision-making logic fundamentally overcomes the coordination bottleneck caused by the lithium battery's response delay.

[0130] In one exemplary embodiment, a sequence of instructions for controlling the coordinated charging and discharging of the supercapacitor bank and the lithium battery bank is generated, including:

[0131] When the total demand current is greater than the operating current threshold and the direction is from the DC bus end to the load end, the supercapacitor bank is controlled to discharge first, and the command sequence for synchronous discharge of the lithium battery bank is controlled according to the relationship between the total demand current and the predicted maximum allowable discharge current of the lithium battery bank.

[0132] When the total demand current is not greater than the operating current threshold, a sequence of instructions is generated to control the transfer of energy from the supercapacitor bank to the lithium battery bank.

[0133] Specifically, if in Within the time limit, ,in The operating current threshold is set, and the current direction is from the battery terminal (i.e., the bus terminal) to the load terminal (which needs to be discharged).

[0134] 1) Prioritize supercapacitor discharge. Control command: Control the supercapacitor to be in a discharge state until the supercapacitor voltage is greater than or equal to the full discharge limit. Then, the supercapacitor is put into standby mode.

[0135] 2) Non-current-limited discharge:

[0136] Judgment Condition 1: During the time period, at the same time as 1), if the current in the DC circuit... Within the maximum allowable discharge current of the lithium battery, i.e. And lithium battery voltage Less than or equal to the full discharge limit of lithium batteries During this period, the lithium battery can discharge according to the allowable current.

[0137] Control command 1: Control the lithium battery according to the discharge current. When entering the discharge state, the current limiting unit is in an unlimited state until... When the time is up or the lithium battery voltage is less than or equal to the full discharge limit. .

[0138] 3) Current-limited lithium battery discharge:

[0139] Judgment condition 2: During the time period, if condition 2) is not met, if Greater than the maximum allowable discharge current of the lithium battery, i.e. During this period, lithium batteries must not be discharged at the permissible current.

[0140] Control command 2: The current limiting control is in the current limiting state, controlling the lithium battery to... It is in a discharging state.

[0141] In this embodiment, by establishing a multi-mode decision-making framework guided by load power demand and prioritizing supercapacitor response, intelligent switching and dynamic optimization of the hybrid energy storage system's operating modes under different conditions are achieved. This method ensures rapid fulfillment of instantaneous power demands when the load is consuming electricity, and actively optimizes the transfer of energy forms when the system is idle. This allows both types of energy storage components to perform at their optimal levels in different scenarios, thereby improving the overall dynamic response quality, energy management efficiency, and equipment lifespan of the system.

[0142] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0143] Based on the same inventive concept, this application also provides a hybrid energy storage energy-saving control device for implementing the hybrid energy storage energy-saving control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the hybrid energy storage energy-saving control device provided below can be found in the limitations of the hybrid energy storage energy-saving control method described above, and will not be repeated here.

[0144] In one exemplary embodiment, such as Figure 4 As shown, a hybrid energy storage and energy-saving control device is provided, comprising:

[0145] The acquisition module 402 is used to acquire the operating dataset of the lithium battery pack, the supercapacitor pack and at least one load, wherein the operating dataset includes real-time operating data and historical operating data.

[0146] Prediction module 404 is used to predict the total power demand mapping relationship of the load on the DC bus in the future period based on the historical operating data of the load.

[0147] The prediction module 404 is also used to predict the charge / discharge rate mapping relationship of the lithium battery pack in the future period based on the historical operating data of the lithium battery pack.

[0148] The prediction module 404 is also used to predict the charge-discharge rate mapping relationship of the supercapacitor bank in the future period based on the historical operating data of the supercapacitor bank.

[0149] The control module 408 is used to generate a sequence of instructions for coordinating the charging and discharging of the supercapacitor and the lithium battery based on the predicted total power demand mapping relationship, the chargeable discharge rate mapping relationship of the lithium battery pack and the chargeable discharge rate mapping relationship of the supercapacitor.

[0150] In an exemplary embodiment, the historical operating data includes historical current data, historical voltage data, and duration data; the prediction module 404 is further used to normalize the historical current data, historical voltage data, and duration data of the load to obtain the total characteristic curve of the load on the DC bus; with the goal of minimizing the loss index between the predicted value and the actual value, the total characteristic curve is subjected to autoregressive optimization to obtain the total energy demand mapping relationship that includes the future demand current value, voltage value, and duration.

[0151] In an exemplary embodiment, the prediction module 404 is further configured to construct a cross-dimensional feature set of the lithium battery pack. The cross-dimensional feature set of the lithium battery pack includes at least: voltage-state of charge correlation, voltage-temperature correlation, health state-temperature correlation, and historical charge-discharge coupling features obtained based on historical data. With the comprehensive optimization of charge-discharge efficiency indicators, safe operation indicators, and life decay indicators as the training objective, the cross-dimensional feature set of the lithium battery pack is used for model training and parameter optimization. The prediction results for future periods are corrected using historical charge-discharge coupling features to obtain the charge-discharge rate mapping relationship of the lithium battery pack.

[0152] In one exemplary embodiment, the safe operation index is calculated based on the deviation of the temperature rise rate from the safe threshold voltage; the lifespan degradation index is calculated based on the correlation function of the predicted charge / discharge rate, temperature change rate, and health status degradation coefficient.

[0153] In an exemplary embodiment, the prediction module 404 is further configured to construct a cross-dimensional feature set of the supercapacitor bank. The cross-dimensional feature set of the supercapacitor bank includes at least: voltage-capacity change correlation and internal resistance-temperature correlation obtained based on historical data; perform initial rate prediction based on the circuit physical model and feature set, and perform autoregressive optimization with the goal of minimizing prediction loss. At the same time, the maximum / minimum charge / discharge rate and voltage limit are used as physical constraints to adjust the prediction result of the initial rate, thereby obtaining the charge / discharge rate mapping relationship of the supercapacitor bank.

[0154] In an exemplary embodiment, the control module 406 is further configured to, when the total demand current determined based on the total power demand mapping relationship is greater than the operating current threshold and the direction is from the load end to the DC bus end, compare the total demand current with the predicted maximum allowable charging current of the supercapacitor group and the predicted maximum allowable charging current of the lithium battery group; if the total demand current is not greater than the predicted maximum allowable charging current of the supercapacitor group, then generate an instruction sequence that prioritizes charging by the supercapacitor group; if the total demand current is greater than the predicted maximum allowable charging current of the supercapacitor group but not greater than the predicted maximum allowable charging current of the lithium battery group, then generate an instruction sequence that coordinates charging by the supercapacitor group and the lithium battery group; if the total demand current is greater than the predicted maximum allowable charging current of the lithium battery group, then generate an instruction sequence that initiates current limiting and coordinates charging by both.

[0155] In an exemplary embodiment, the control module 406 is further configured to: prioritize the discharge of the supercapacitor bank when the total demand current is greater than the operating current threshold and the direction is from the DC bus end to the load end; and control the synchronous discharge instruction sequence of the lithium battery bank according to the relationship between the total demand current and the predicted maximum allowable discharge current of the lithium battery bank; and generate an instruction sequence to control the transfer of energy from the supercapacitor bank to the lithium battery bank when the total demand current is not greater than the operating current threshold.

[0156] Each module in the aforementioned hybrid energy storage and energy-saving control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0157] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores a runtime dataset for at least one load, including real-time and historical runtime data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a hybrid energy storage and energy-saving control method.

[0158] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0159] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0160] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0161] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described above.

[0162] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0163] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0164] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0165] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A hybrid energy storage and energy-saving control method, characterized in that, The method includes: Obtain an operational dataset of lithium battery pack, supercapacitor pack and at least one load, wherein the operational dataset includes real-time operational data and historical operational data; Based on the historical operating data of the load, predict the total power demand mapping relationship of the load on the DC bus in the future period; Based on the historical operating data of the lithium battery pack, predict the charge / discharge rate mapping relationship of the lithium battery pack in the future period. Based on the historical operating data of the supercapacitor bank, predict the charge / discharge rate mapping relationship of the supercapacitor bank in the future period. Based on the predicted total power demand mapping relationship, the charge / discharge rate mapping relationship of the lithium battery pack, and the charge / discharge rate mapping relationship of the supercapacitor pack, a command sequence is generated to control the coordinated charging and discharging of the supercapacitor pack and the lithium battery pack.

2. The method according to claim 1, characterized in that, The historical operating data includes historical current data, historical voltage data, and duration data; the prediction of the total power demand mapping relationship of the load on the DC bus in the future period based on the historical operating data of the load includes: The historical current data, historical voltage data, and duration data of the load are normalized to obtain the overall characteristic curve of the load on the DC bus. With the goal of minimizing the loss index between the predicted and actual values, the total characteristic curve is subjected to autoregressive optimization to obtain the total energy demand mapping relationship that includes future demand current, voltage and duration.

3. The method according to claim 1, characterized in that, The prediction of the charge / discharge rate mapping relationship of the lithium battery pack in the future period based on the historical operating data of the lithium battery pack includes: Construct a cross-dimensional feature set for lithium battery packs, which includes at least: voltage-state of charge correlation, voltage-temperature correlation, health state-temperature correlation, and historical charge-discharge coupling features obtained based on historical data; With the comprehensive optimization of charge-discharge efficiency, safe operation and life decay indicators as the training objective, the model is trained and parameters are optimized on the cross-dimensional feature set of the lithium battery pack. The prediction results for the future period are corrected by using the historical charge-discharge coupling features to obtain the charge-discharge rate mapping relationship of the lithium battery pack.

4. The method according to claim 3, characterized in that, The safe operation index is calculated based on the deviation of the temperature rise rate from the safe threshold voltage; the lifespan degradation index is calculated based on the correlation function of the predicted charge / discharge rate, temperature change rate, and health status degradation coefficient.

5. The method according to claim 1, characterized in that, The prediction of the charge / discharge rate mapping relationship of the supercapacitor bank in the future period based on the historical operating data of the supercapacitor bank includes: Construct a cross-dimensional feature set for the supercapacitor bank, which includes at least: voltage-capacitance variation correlation and internal resistance-temperature correlation obtained based on historical data; Initial rate prediction is performed based on the circuit physical model and the feature set, and autoregressive optimization is performed with the goal of minimizing prediction loss. At the same time, the maximum / minimum charge / discharge rate and voltage limit are used as physical constraints to adjust the prediction results of the initial rate, so as to obtain the charge / discharge rate mapping relationship of the supercapacitor group.

6. The method according to claim 1, characterized in that, The generation of the instruction sequence for controlling the coordinated charging and discharging of the supercapacitor bank and the lithium battery bank includes: When the total demand current determined based on the total power demand mapping relationship is greater than the operating current threshold and the direction is from the load end to the DC bus end, the total demand current is compared with the predicted maximum allowable charging current of the supercapacitor group and the predicted maximum allowable charging current of the lithium battery group. If the total demand current is not greater than the predicted maximum allowable charging current of the supercapacitor bank, then a command sequence is generated that prioritizes charging by the supercapacitor bank. If the total required current is greater than the predicted maximum allowable charging current of the supercapacitor bank but not greater than the predicted maximum allowable charging current of the lithium battery bank, then a sequence of instructions for coordinated charging by the supercapacitor bank and the lithium battery bank is generated. If the total required current is greater than the predicted maximum allowable charging current of the lithium battery pack, then a sequence of instructions is generated to initiate current limiting and charge the battery in conjunction with the lithium battery pack.

7. The method according to claim 6, characterized in that, The generation of the instruction sequence for controlling the coordinated charging and discharging of the supercapacitor bank and the lithium battery bank includes: When the total demand current is greater than the operating current threshold and the direction is from the DC bus end to the load end, the supercapacitor bank is controlled to discharge first, and the command sequence for synchronous discharge of the lithium battery bank is controlled according to the relationship between the total demand current and the predicted maximum allowable discharge current of the lithium battery bank. When the total required current is not greater than the operating current threshold, a sequence of instructions is generated to control the transfer of energy from the supercapacitor bank to the lithium battery bank.

8. A hybrid energy storage and energy-saving control device, characterized in that, The device includes: The acquisition module is used to acquire the operating dataset of the lithium battery pack, the supercapacitor pack and at least one load, wherein the operating dataset includes real-time operating data and historical operating data; The prediction module is used to predict the total power demand mapping relationship of the load on the DC bus in the future period based on the historical operating data of the load. The prediction module is also used to predict the charge / discharge rate mapping relationship of the lithium battery pack in the future period based on the historical operating data of the lithium battery pack. The prediction module is also used to predict the charge / discharge rate mapping relationship of the supercapacitor bank in the future period based on the historical operating data of the supercapacitor bank. The control module is used to generate a sequence of instructions for coordinating the charging and discharging of the supercapacitor group and the lithium battery group based on the predicted total power demand mapping relationship, the charge / discharge rate mapping relationship of the lithium battery group and the charge / discharge rate mapping relationship of the supercapacitor group.

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

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

Images