Control method of flywheel lithium battery hybrid energy storage system for smoothing wind power fluctuation

Abstract

The disclosure provides a control method of a flywheel lithium battery hybrid energy storage system for stabilizing wind power fluctuation, and relates to the technical field of wind power generation. The method comprises the following steps: performing charge and discharge control on a flywheel energy storage unit and / or a lithium battery energy storage unit based on a wind speed value of a wind turbine generator, and preferentially controlling the flywheel energy storage unit to output power when the flywheel energy storage unit and the lithium battery energy storage unit do not need to jointly supply power to a power grid; wherein the speed of the flywheel in the flywheel energy storage unit is controlled by a fuzzy controller, and the fuzzy rule base and the membership function of the fuzzy controller are determined after optimization by a DBN neural network based on a stacked RBM and a BP. The disclosure can reduce the number of times that the lithium battery energy storage unit participates in adjusting the wind power fluctuation of the power grid, and improve the service life of the lithium battery. By optimizing the parameters of the fuzzy controller through the neural network, the nonlinear, time-varying and strong coupling characteristics of the PMSM can be better adapted, and the robustness, control accuracy and anti-interference ability of the hybrid energy storage system in stabilizing the wind power fluctuation can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of wind power generation technology, and in particular to a control method for a flywheel lithium battery hybrid energy storage system to mitigate wind power fluctuations. Background Technology

[0002] The large-scale application of clean energy, while bringing significant economic and environmental benefits to the power grid, has also become a major challenge in building new power systems. One key challenge is the instantaneous fluctuations in wind power output, which cause fluctuations in grid voltage and frequency, significantly impacting power quality and supply stability. Configuring energy storage systems on the power source side can effectively smooth these fluctuations. Hybrid energy storage systems combine the advantages and disadvantages of energy-type and power-type energy storage, achieving technological and economic complementarity, and have become the preferred choice for mitigating fluctuations in renewable energy output.

[0003] Due to the unstable actual environment in which wind turbines are connected to the grid, improving the grid connection safety of flywheel lithium battery hybrid energy storage systems while enhancing the performance of energy storage units in these systems has become one of the urgent problems to be solved in this field. Summary of the Invention

[0004] This disclosure aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the first aspect of this disclosure proposes a control method for a flywheel-lithium battery hybrid energy storage system to mitigate wind power fluctuations. The flywheel-lithium battery hybrid energy storage system is connected in parallel to the DC bus between the wind turbine and the power grid. The flywheel-lithium battery hybrid energy storage system includes a flywheel energy storage unit and a lithium battery energy storage unit. The method includes the following steps:

[0006] Obtain the wind speed value of the wind turbine;

[0007] In response to the wind speed value being less than or equal to a preset cut-in wind speed value, discharge control is performed on the flywheel energy storage unit and the lithium battery energy storage unit;

[0008] In response to the wind speed value being greater than the cut-in wind speed value, and the increase in the load of the power grid within a preset time period being greater than or equal to a preset threshold, discharge control is performed on the flywheel energy storage unit, and the state of charge (SOC) value of the flywheel energy storage unit is determined after the flywheel energy storage unit outputs power.

[0009] In response to the state of charge (SOC) of the flywheel energy storage unit being zero, discharge control is performed on the lithium battery energy storage unit;

[0010] In the flywheel energy storage unit, the rotational speed of the flywheel is controlled by a fuzzy controller. The fuzzy rule base and membership function of the fuzzy controller are determined after optimization by a DBN neural network based on stacked RBM and BP.

[0011] In some embodiments of this disclosure, the fuzzy rule base and the membership function are obtained through the following steps: determining the charging and discharging power of the flywheel energy storage unit; converting the charging and discharging power into a reference speed of the flywheel; determining the speed deviation value and speed deviation change rate of the flywheel based on the given reference; inputting the speed deviation value and speed deviation change rate as input data into the pre-trained DBN neural network to obtain the predicted values ​​of the PID parameters and the membership function parameters output by the DBN neural network; wherein the DBN neural network has learned to obtain the mapping relationship between the input data and the values ​​of the PID parameters and the membership function parameters; updating the membership function with the predicted values ​​of the membership function parameters, and updating the fuzzy rule base with the predicted values ​​of the PID parameters.

[0012] In some embodiments of this disclosure, the DBN neural network is pre-trained by: acquiring historical input data of the fuzzy controller and historical output data corresponding to the historical input data; wherein each historical input data includes historical speed deviation and historical speed deviation change rate, and the historical output data includes the true values ​​of PID parameters and the true values ​​of membership function parameters; training the DBN neural network using the historical input data and the historical output data, and adjusting the weights and biases of the DBN neural network.

[0013] In some embodiments of this disclosure, the method further includes: in response to the wind speed value being greater than the cut-in wind speed value and the increase in the load of the power grid within a preset time period being less than the preset threshold, after the output power of the wind turbine meets the load demand of the power grid, controlling the flywheel energy storage unit to enter a charging mode; and in response to the flywheel energy storage unit being fully charged, controlling the lithium battery energy storage unit to enter a charging mode.

[0014] In some embodiments of this disclosure, the discharge control of the flywheel energy storage unit and the lithium battery energy storage unit includes: obtaining the output power of the flywheel-lithium battery hybrid energy storage system based on the output power of the wind turbine and the load demand of the power grid; decomposing the output power into high-frequency components and low-frequency components; controlling the flywheel energy storage unit to output power based on the high-frequency components, and controlling the lithium battery energy storage unit to output power based on the low-frequency components.

[0015] A second aspect of this disclosure provides a control device for a flywheel-lithium battery hybrid energy storage system to mitigate wind power fluctuations. The flywheel-lithium battery hybrid energy storage system is connected in parallel to a DC bus between a wind turbine and the power grid. The flywheel-lithium battery hybrid energy storage system includes a flywheel energy storage unit and a lithium battery energy storage unit. The device includes:

[0016] The acquisition module is used to acquire the wind speed value of the wind turbine.

[0017] The first control module is used to control the discharge of the flywheel energy storage unit and the lithium battery energy storage unit in response to the wind speed value being less than or equal to a preset cut-in wind speed value.

[0018] The second control module is used to control the discharge of the flywheel energy storage unit in response to the wind speed value being greater than the cut-in wind speed value and the increase in the load of the power grid within a preset time period being greater than or equal to a preset threshold, and to determine the state of charge (SOC) value of the flywheel energy storage unit after the flywheel energy storage unit outputs power.

[0019] The third control module is used to control the discharge of the lithium battery energy storage unit in response to the state of charge (SOC) of the flywheel energy storage unit being zero.

[0020] The fuzzy control unit is used to optimize the fuzzy rule base and membership function of the fuzzy controller through a DBN neural network based on stacked RBM and BP, and to control the rotational speed of the flywheel in the flywheel energy storage unit using the fuzzy controller.

[0021] In some embodiments of this disclosure, the fuzzy control unit is specifically used for: determining the charging and discharging power of the flywheel energy storage unit; converting the charging and discharging power into a reference rotational speed of the flywheel; determining the rotational speed deviation value and the rate of change of the rotational speed deviation of the flywheel based on the given reference; inputting the rotational speed deviation value and the rate of change of the rotational speed deviation as input data into the pre-trained DBN neural network to obtain the predicted values ​​of the PID parameters and the membership function parameters output by the DBN neural network; wherein the DBN neural network has learned to obtain the mapping relationship between the input data and the values ​​of the PID parameters and the membership function parameters; updating the membership function using the predicted values ​​of the membership function parameters, and updating the fuzzy rule base using the predicted values ​​of the PID parameters.

[0022] In some embodiments of this disclosure, a fourth control module is also included; the fourth control module is configured to: in response to the wind speed value being greater than the cut-in wind speed value, and the increase in the load of the power grid within a preset time period being less than the preset threshold, after the output power of the wind turbine meets the load demand of the power grid, control the flywheel energy storage unit to enter a charging mode; and in response to the flywheel energy storage unit being fully charged, control the lithium battery energy storage unit to enter a charging mode.

[0023] In response to the flywheel energy storage unit

[0024] In some embodiments of this disclosure, the first control module is specifically used to: obtain the output power of the flywheel lithium battery hybrid energy storage system based on the output power of the wind turbine and the load demand of the power grid; decompose the output power into high-frequency components and low-frequency components; control the flywheel energy storage unit to output power based on the high-frequency components, and control the lithium battery energy storage unit to output power based on the low-frequency components.

[0025] A third aspect of this disclosure provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0026] The memory stores computer-executed instructions;

[0027] The processor executes computer execution instructions stored in the memory to implement the method described in the first aspect above.

[0028] The control method for a flywheel-lithium battery hybrid energy storage system for mitigating wind power fluctuations disclosed herein reduces the number of times the lithium battery energy storage unit participates in regulating wind power fluctuations by prioritizing the flywheel energy storage unit's output, thus reducing lithium battery losses and extending the lifespan of the lithium battery during the process of the hybrid energy storage system participating in mitigating wind power fluctuations. Furthermore, this disclosure optimizes the fuzzy rule base and membership function of the fuzzy controller using a neural network, enabling the PID parameters output by the fuzzy controller to better adapt to the nonlinear, time-varying, and strongly coupled characteristics of the permanent magnet synchronous motor (PMSM), thereby improving the robustness, control accuracy, and anti-interference capability of the hybrid energy storage system in mitigating wind power fluctuations.

[0029] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0030] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0031] Figure 1A flowchart illustrating a control method for a flywheel-lithium battery hybrid energy storage system for mitigating wind power fluctuations, provided in an embodiment of this disclosure.

[0032] Figure 2 This is a schematic diagram of a flywheel lithium battery hybrid energy storage system provided in an embodiment of this disclosure;

[0033] Figure 3 A schematic diagram of a fuzzy controller provided in an embodiment of this disclosure;

[0034] Figure 4 A schematic diagram of a DBN neural network based on stacked RBM and BP provided in an embodiment of this disclosure;

[0035] Figure 5 A topology diagram of a flywheel energy storage unit provided in an embodiment of this disclosure;

[0036] Figure 6 This is a schematic diagram of a control device for a flywheel-lithium battery hybrid energy storage system that mitigates wind power fluctuations, as provided in an embodiment of this disclosure. Detailed Implementation

[0037] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0038] Specifically, the control method of a flywheel lithium battery hybrid energy storage system for mitigating wind power fluctuations according to embodiments of the present disclosure is described below with reference to the accompanying drawings.

[0039] Figure 1 This is a flowchart illustrating a control method for a flywheel-lithium battery hybrid energy storage system to mitigate wind power fluctuations, as provided in an embodiment of this disclosure. The flywheel-lithium battery hybrid energy storage system is connected in parallel to the DC bus between the wind turbine and the power grid, and includes a flywheel energy storage unit and a lithium battery energy storage unit. Figure 2 This is a schematic diagram of a flywheel lithium battery hybrid energy storage system provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, the flywheel energy storage unit and the lithium battery energy storage unit are connected to the DC bus after being connected in parallel through a DC / DC converter.

[0040] This flywheel lithium battery hybrid energy storage system uses a DC / DC converter to regulate the direction and magnitude of energy flow, ensuring that the voltage and current values ​​of each device reach the desired levels. Connecting the DC / DC converter to auxiliary energy devices within the flywheel lithium battery hybrid energy storage system expands the motor speed range, smoothly adjusts motor speed, clamps the maximum operating current, and enables regenerative braking. Based on these features, DC / DC converters are widely used in hybrid energy storage systems.

[0041] In flywheel lithium-ion battery hybrid energy storage systems, energy storage units can be connected to the DC bus in various ways. Parallel connection of energy storage units increases system capacity, making it suitable for megawatt-level and larger capacity energy storage systems, and enabling regulation of DC bus voltage and system power. Energy storage units, through DC / DC converters, can achieve centralized control and regulation of microgrid output power, ensuring stable DC bus voltage and fast, accurate reference power tracking. DC / DC converters can be configured independently to meet the power requirements of their respective connected energy storage units. Figure 2 In the topology shown, both the lithium battery voltage and the flywheel voltage are controllable, which can effectively achieve energy distribution among different energy storage units.

[0042] like Figure 1 As shown, the control method for this flywheel-lithium battery hybrid energy storage system for mitigating wind power fluctuations may include the following steps:

[0043] Step 101: Obtain the wind speed value of the wind turbine.

[0044] Step 102: In response to the wind speed value being less than or equal to the preset cut-in wind speed value, discharge control is performed on the flywheel energy storage unit and the lithium battery energy storage unit.

[0045] The cut-in wind speed value indicates whether the current wind speed of the wind turbine can meet the load demand of the power grid. If the wind speed value is less than or equal to the preset cut-in wind speed value, it means that the flywheel-lithium battery hybrid energy storage system needs to be put into operation to supply power to the grid in order to smooth out wind power fluctuations, that is, to control the discharge of the flywheel energy storage unit and the lithium battery energy storage unit.

[0046] In some embodiments of this disclosure, the output power of the flywheel-lithium battery hybrid energy storage system can be obtained according to the output power of the wind turbine and the load demand of the power grid; the output power is decomposed into high-frequency components and low-frequency components; the flywheel energy storage unit is controlled to output power according to the high-frequency components, and the lithium battery energy storage unit is controlled to output power according to the low-frequency components.

[0047] As an example, the difference between the output power of the wind turbine and the load demand of the power grid is used as the output power P of the flywheel lithium battery hybrid energy storage system. win dFiltering techniques (such as low-pass filters, high-pass filters, or wavelet transforms) can be used to reduce the output power P. win d Decomposed into high-frequency components P hig h and low-frequency component P low It controls the flywheel energy storage unit to output power based on the high-frequency component and controls the lithium battery energy storage unit to output power based on the low-frequency component.

[0048] P wind =P low +P high

[0049] In one implementation, the flywheel energy storage unit's output power P flywheel As shown below, the minimum value between the maximum charging and discharging power of the flywheel energy storage unit and the high-frequency component can be taken as the output power of the flywheel energy storage unit:

[0050]

[0051] The output power of a lithium battery energy storage unit can be shown below:

[0052] P battery =P low +(P high -P flywheel )

[0053] in, This represents the maximum charging and discharging power of the flywheel energy storage unit.

[0054] Step 103: In response to the wind speed value being greater than the cut-in wind speed value and the increase in the load of the power grid within a preset time period being greater than or equal to a preset threshold, discharge control is performed on the flywheel energy storage unit, and the state of charge (SOC) value of the flywheel energy storage unit is determined after the flywheel energy storage unit outputs power.

[0055] The determination of whether there is a sudden increase in grid load is based on whether the increase in grid load within a preset time period is greater than or equal to a preset threshold. If the increase is greater than or equal to the preset threshold, it indicates a sudden increase in grid load. Even if the wind speed is greater than the cut-in wind speed, the output power of the wind turbine cannot cope with the sudden increase in load, and the hybrid energy storage system still needs to be put into operation. When the wind speed is greater than the cut-in wind speed and the increase in grid load within a preset time period is greater than or equal to the preset threshold, the flywheel energy storage unit is preferentially discharged until the state of charge (SOC) of the flywheel energy storage unit is zero.

[0056] As an example, the discharge of the flywheel energy storage unit can be controlled based on its maximum discharge power.

[0057] Step 104: In response to the state of charge (SOC) of the flywheel energy storage unit being zero, discharge control is performed on the lithium battery energy storage unit.

[0058] When the flywheel energy storage unit is supplying power independently, if its state of charge (SOC) is zero, it indicates that the flywheel generator cannot meet the grid load, and the lithium battery energy storage unit needs to be activated. As an example, the discharge of the lithium battery energy storage unit can be controlled based on the maximum discharge power of the lithium battery.

[0059] In some embodiments of this disclosure, in response to a wind speed greater than the cut-in wind speed and a grid load increase within a preset time period less than a preset threshold, the flywheel energy storage unit is controlled to enter charging mode after the wind turbine's output power meets the grid's load demand; in response to the flywheel energy storage unit being fully charged, the lithium battery energy storage unit is controlled to enter charging mode. A grid load increase within a preset time period less than the preset threshold indicates that the grid load does not surge but fluctuates slightly, in which case the wind turbine's output power can meet the grid's load demand. Therefore, after the wind turbine's output power meets the grid's load demand, the flywheel energy storage unit is prioritized to store excess wind turbine energy until it is fully charged, and then the excess wind power is stored in the lithium battery energy storage unit.

[0060] Optionally, when the flywheel energy storage unit and the lithium battery energy storage unit are being charged, they can be charged based on the maximum charging power of their respective energy storage units.

[0061] This disclosure prioritizes flywheel energy storage for output or storage under load disturbances or power supply disturbances and short-term frequency regulation, which can reduce the number of times the lithium battery participates in regulation, reduce battery damage, and improve the service life of the lithium battery.

[0062] It should be noted that in this embodiment, a fuzzy controller is used to control the speed of the flywheel in the flywheel energy storage unit through a closed-loop control of the flywheel speed. The fuzzy rule base and membership function of the fuzzy controller are determined after optimization using a DBN neural network based on stacked RBM and BP. The inputs of the fuzzy controller (speed deviation e(t) and speed deviation change rate ec(t)) need to be fuzzified using the membership function. The DBN neural network can optimize the shape, range, and overlapping area of ​​the membership function to better suit the nonlinear characteristics of PMSM and adapt to the high speed regulation accuracy in wind farms. After optimizing the fuzzy rule base and membership function of the fuzzy controller through the DBN neural network, the output voltage waveform can be further improved, reducing wind power fluctuations and making them smoother.

[0063] In some embodiments of this disclosure, the charging and discharging power of the flywheel energy storage unit can be determined, and the charging and discharging power can be converted into a reference rotational speed of the flywheel; the rotational speed deviation value and the rate of change of the rotational speed deviation of the flywheel can be determined based on a given reference; the rotational speed deviation value and the rate of change of the rotational speed deviation are input as input data into a pre-trained DBN neural network to obtain the predicted values ​​of the PID parameters and the membership function parameters output by the DBN neural network; wherein, the DBN neural network has learned to obtain the mapping relationship between the input data and the values ​​of the PID parameters and the membership function parameters; the membership function is updated by the predicted values ​​of the membership function parameters, and the fuzzy rule base is updated by the predicted values ​​of the PID parameters.

[0064] Optionally, the membership function can be a Gaussian membership function, a triangular membership function, etc. Taking Gaussian as an example, the parameters include the mean μ and the standard deviation σ:

[0065]

[0066] Figure 3 This is a schematic diagram of a fuzzy controller provided in an embodiment of this disclosure. Figure 4 This is a schematic diagram of a DBN neural network based on stacked RBM and BP, provided in an embodiment of this disclosure. Figure 5 A topology diagram of a flywheel energy storage unit provided in this disclosure embodiment ( Figure 5 (The DBN neural network in the middle is not shown). Figure 4 As shown, two RBMs are a probabilistic generation model and also an energy model. An RBM module includes a hidden layer and a visible layer. The hidden layer and the visible layer are connected bidirectionally, while there are no interconnections between units in the same layer.

[0067] This can be expressed as:

[0068]

[0069] Among them, v i It is the state of the i-th node in the visible layer, h i It is the state of the j-th node in the hidden layer, a i It is the bias of the i-th node in the visible layer, b j It is the bias of the j-th node in the hidden layer, w ij It is the connection weight matrix between the hidden layer and the visible layer units.

[0070] The network assigns a probability value to each pair of visible and hidden vectors using the following energy function:

[0071]

[0072] DBN neural networks are generative models composed of multiple layers of RBM stacks. Typically, the network weights are initialized by training the RBMs layer by layer, and then fine-tuned using the backpropagation (BP) algorithm.

[0073] Backpropagation is used to fine-tune the parameters of a DBN neural network by updating the weights and biases by minimizing a loss function such as mean squared error.

[0074] The loss function can be expressed as follows:

[0075]

[0076] The weight update of a DBN neural network can be represented as follows:

[0077]

[0078] Where η is the learning rate.

[0079] The gradient of the loss function with respect to the weights and biases is calculated using the chain rule:

[0080]

[0081] In a fuzzy controller, the inputs to the DBN are the speed deviation e(t) and the rate of change of speed deviation ec(t), and the outputs are the PID parameters (Kp, Ki, Kd).

[0082] Input layer

[0083] v = [e(t), ec(t)]

[0084] Output layer

[0085] y = [K p ,K i ,K d ]

[0086] By learning the nonlinear mapping relationship between input and output through a DBN neural network, the output of the fuzzy controller can optimize the performance of the PID controller.

[0087] By implementing the embodiments of this disclosure, when neither the flywheel energy storage unit nor the lithium battery energy storage unit is needed to jointly supply power to the grid, the principle of prioritizing the output of the flywheel energy storage unit reduces the number of times the lithium battery energy storage unit participates in regulating wind power fluctuations in the grid, thereby reducing lithium battery losses and improving the lifespan of the lithium battery during the process of the hybrid energy storage system participating in the smoothing of wind power fluctuations. Furthermore, this disclosure optimizes the fuzzy rule base and membership function of the fuzzy controller through a neural network, enabling the PID parameters output by the fuzzy controller to better adapt to the nonlinear, time-varying, and strongly coupled characteristics of the permanent magnet synchronous motor (PMSM), thus improving the robustness, control accuracy, and anti-interference capability of the hybrid energy storage system in participating in the smoothing of wind power fluctuations.

[0088] Figure 6 This is a schematic diagram of a control device for a flywheel-lithium battery hybrid energy storage system that mitigates wind power fluctuations, as provided in an embodiment of this disclosure. Figure 6 As shown, the control device of the flywheel lithium battery hybrid energy storage system includes: an acquisition module 601, a first control module 602, a second control module 603, a third control module 604, and a fuzzy control unit 605.

[0089] The acquisition module 601 is used to acquire the wind speed value of the wind turbine.

[0090] The first control module 602 is used to control the discharge of the flywheel energy storage unit and the lithium battery energy storage unit in response to the wind speed value being less than or equal to the preset cut-in wind speed value.

[0091] The second control module 603 is used to control the discharge of the flywheel energy storage unit in response to the wind speed value being greater than the cut-in wind speed value and the increase in the load of the power grid within a preset time period being greater than or equal to a preset threshold, and to determine the state of charge (SOC) value of the flywheel energy storage unit after the flywheel energy storage unit outputs power.

[0092] The third control module 604 is used to control the discharge of the lithium battery energy storage unit in response to the state of charge (SOC) of the flywheel energy storage unit being zero.

[0093] The fuzzy control unit 605 is used to optimize the fuzzy rule base and membership function of the fuzzy controller through a DBN neural network based on stacked RBM and BP, and to control the speed of the flywheel in the flywheel energy storage unit using the fuzzy controller.

[0094] In some embodiments of this disclosure, the fuzzy control unit 605 is specifically used for: determining the charging and discharging power of the flywheel energy storage unit; converting the charging and discharging power into a reference speed of the flywheel; determining the speed deviation value and speed deviation change rate of the flywheel based on a given reference; inputting the speed deviation value and speed deviation change rate as input data into a pre-trained DBN neural network to obtain the predicted values ​​of the PID parameters and membership function parameters output by the DBN neural network; wherein the DBN neural network has learned to obtain the mapping relationship between the input data and the values ​​of the PID parameters and membership function parameters; updating the membership function through the predicted values ​​of the membership function parameters, and updating the fuzzy rule base using the predicted values ​​of the PID parameters.

[0095] In some embodiments of this disclosure, the control device of the flywheel lithium battery hybrid energy storage system is as follows: Figure 6Based on the illustrated embodiment, a training module may also be included. The training module is used to: acquire historical input data and corresponding historical output data of the fuzzy controller; wherein each historical input data includes historical speed deviation and historical speed deviation change rate, and the historical output data includes the true values ​​of the PID parameters and the true values ​​of the membership function parameters; train the DBN neural network using the historical input data and historical output data, and adjust the weights and biases of the DBN neural network.

[0096] In some embodiments of this disclosure, the control device of the flywheel lithium battery hybrid energy storage system is as follows: Figure 6 Based on the illustrated embodiment, a fourth control module may also be included. The fourth control module is configured to: control the flywheel energy storage unit to enter charging mode in response to a wind speed value greater than the cut-in wind speed value and a grid load increase within a preset time period less than a preset threshold, after the wind turbine's output power meets the grid's load demand; and control the lithium battery energy storage unit to enter charging mode in response to the flywheel energy storage unit being fully charged.

[0097] In some embodiments of this disclosure, the first control module is specifically used to: obtain the output power of the flywheel lithium battery hybrid energy storage system based on the output power of the wind turbine and the load demand of the power grid; decompose the output power into high-frequency components and low-frequency components; control the flywheel energy storage unit to output power based on the high-frequency components, and control the lithium battery energy storage unit to output power based on the low-frequency components.

[0098] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0099] To implement the above embodiments, this disclosure also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0100] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0101] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0102] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0103] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0104] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0105] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0106] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0107] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0108] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0109] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A control method for a flywheel-lithium battery hybrid energy storage system to mitigate wind power fluctuations, characterized in that, The flywheel-lithium battery hybrid energy storage system is connected in parallel to the DC bus between the wind turbine and the power grid. The flywheel-lithium battery hybrid energy storage system includes a flywheel energy storage unit and a lithium battery energy storage unit. The method includes the following steps: Obtain the wind speed value of the wind turbine; In response to the wind speed value being less than or equal to a preset cut-in wind speed value, discharge control is performed on the flywheel energy storage unit and the lithium battery energy storage unit; In response to the wind speed value being greater than the cut-in wind speed value, and the increase in the load of the power grid within a preset time period being greater than or equal to a preset threshold, discharge control is performed on the flywheel energy storage unit, and the state of charge (SOC) value of the flywheel energy storage unit is determined after the flywheel energy storage unit outputs power. In response to the state of charge (SOC) of the flywheel energy storage unit being zero, discharge control is performed on the lithium battery energy storage unit; In the flywheel energy storage unit, the rotational speed of the flywheel is controlled by a fuzzy controller. The fuzzy rule base and membership function of the fuzzy controller are determined after optimization by a DBN neural network based on stacked RBM and BP.

2. The method according to claim 1, characterized in that, The fuzzy rule base and the membership function are obtained through the following steps: Determine the charging and discharging power of the flywheel energy storage unit; The charging and discharging power is converted into a reference rotational speed of the flywheel; The speed deviation value and the rate of change of speed deviation of the flywheel are determined based on the given reference. The speed deviation value and the speed deviation change rate are input as input data into the pre-trained DBN neural network to obtain the predicted values ​​of the PID parameters and the membership function parameters output by the DBN neural network; wherein, the DBN neural network has learned to obtain the mapping relationship between the input data and the PID parameters and the membership function parameter values; The membership function is updated using the predicted value of the membership function parameter, and the fuzzy rule base is updated using the predicted value of the PID parameter.

3. The method according to claim 2, characterized in that, The DBN neural network is pre-trained in the following manner: The historical input data of the fuzzy controller and the historical output data corresponding to the historical input data are obtained; wherein, each historical input data includes historical speed deviation and historical speed deviation change rate, and the historical output data includes the true value of the PID parameter and the true value of the membership function parameter; The DBN neural network is trained using the historical input data and the historical output data, and the weights and biases of the DBN neural network are adjusted.

4. The method according to claim 1, characterized in that, Also includes: In response to the wind speed value being greater than the cut-in wind speed value, and the increase in the load of the power grid within a preset time period being less than the preset threshold, after the output power of the wind turbine meets the load demand of the power grid, the flywheel energy storage unit is controlled to enter the charging mode. In response to the flywheel energy storage unit being fully charged, the lithium battery energy storage unit is controlled to enter the charging mode.

5. The method according to any one of claims 1-4, characterized in that, The discharge control of the flywheel energy storage unit and the lithium battery energy storage unit includes: The output power of the flywheel lithium battery hybrid energy storage system is obtained based on the output power of the wind turbine and the load demand of the power grid. The power to be output is decomposed into high-frequency components and low-frequency components; The flywheel energy storage unit is controlled to output power according to the high-frequency component, and the lithium battery energy storage unit is controlled to output power according to the low-frequency component.

6. A control device for a flywheel-lithium battery hybrid energy storage system for mitigating wind power fluctuations, characterized in that, The flywheel-lithium battery hybrid energy storage system is connected in parallel to the DC bus between the wind turbine and the power grid. The flywheel-lithium battery hybrid energy storage system includes a flywheel energy storage unit and a lithium battery energy storage unit. The device includes: The acquisition module is used to acquire the wind speed value of the wind turbine. The first control module is used to control the discharge of the flywheel energy storage unit and the lithium battery energy storage unit in response to the wind speed value being less than or equal to a preset cut-in wind speed value. The second control module is used to control the discharge of the flywheel energy storage unit in response to the wind speed value being greater than the cut-in wind speed value and the increase in the load of the power grid within a preset time period being greater than or equal to a preset threshold, and to determine the state of charge (SOC) value of the flywheel energy storage unit after the flywheel energy storage unit outputs power. The third control module is used to control the discharge of the lithium battery energy storage unit in response to the state of charge (SOC) of the flywheel energy storage unit being zero. The fuzzy control unit is used to optimize the fuzzy rule base and membership function of the fuzzy controller through a DBN neural network based on stacked RBM and BP, and to control the rotational speed of the flywheel in the flywheel energy storage unit using the fuzzy controller.

7. The apparatus according to claim 6, characterized in that, The fuzzy control unit is specifically used for: Determine the charging and discharging power of the flywheel energy storage unit; The charging and discharging power is converted into a reference rotational speed of the flywheel; The speed deviation value and the rate of change of speed deviation of the flywheel are determined based on the given reference. The speed deviation value and the speed deviation change rate are input as input data into the pre-trained DBN neural network to obtain the predicted values ​​of the PID parameters and the membership function parameters output by the DBN neural network; wherein, the DBN neural network has learned to obtain the mapping relationship between the input data and the PID parameters and the membership function parameter values; The membership function is updated using the predicted value of the membership function parameter, and the fuzzy rule base is updated using the predicted value of the PID parameter.

8. The apparatus according to claim 6, characterized in that, It also includes a fourth control module; the fourth control module is used for: In response to the wind speed value being greater than the cut-in wind speed value, and the increase in the load of the power grid within a preset time period being less than the preset threshold, after the output power of the wind turbine meets the load demand of the power grid, the flywheel energy storage unit is controlled to enter the charging mode. In response to the flywheel energy storage unit being fully charged, the lithium battery energy storage unit is controlled to enter the charging mode.

9. The apparatus according to claim 6, characterized in that, The first control module is specifically used for: The output power of the flywheel lithium battery hybrid energy storage system is obtained based on the output power of the wind turbine and the load demand of the power grid. The power to be output is decomposed into high-frequency components and low-frequency components; The flywheel energy storage unit is controlled to output power according to the high-frequency component, and the lithium battery energy storage unit is controlled to output power according to the low-frequency component.

10. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-5.

Images