DeePC-based energy scheduling method and micro-grid off-grid operation system

Abstract

The embodiment of the invention discloses an energy scheduling method based on DeePC and a micro-grid off-grid operation system. Comprising the following steps: acquiring output power of a plurality of power generation subsystems and an energy storage value of a storage battery energy storage subsystem in different time periods; generating a control input sequence of the micro-grid off-grid operation system according to the obtained output power, and generating an energy storage output sequence of the micro-grid off-grid operation system according to the obtained energy storage value; determining power reference trajectories of the plurality of power generation subsystems and the storage battery energy storage subsystem in corresponding time periods, and inputting the control input sequence, the energy storage output sequence and the power reference trajectories into a micro-grid system energy management optimization model established based on a DeePC algorithm, the optimal control input sequence of the micro-grid off-grid operation system in the corresponding time period is calculated; and performing power adjustment on the plurality of power generation subsystems according to the optimal control input sequence in the corresponding time period.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to the field of microgrid technology, and specifically to a DeePC-based energy scheduling method and a microgrid off-grid operation system. Background Art

[0002] For new energy microgrids, in order to improve the consumption of renewable energy, ensure load power supply capacity, and coordinate the production and utilization of green electricity and green hydrogen, the key lies in the optimized operation and energy management during the real-time operation stage of the microgrid.

[0003] In related technologies, accurate models are established based on operating data, and multi-step decision optimization control is performed through model states and outputs, such as MPC (Model Predictive Control) and its improved solutions. However, when faced with changes in system parameters (such as degradation or update of energy storage systems), such methods cannot provide accurate energy control, and system modeling and parameter identification must be re-performed. Summary of the invention

[0004] The embodiments of this specification provide an energy scheduling method and a microgrid off-grid operation system based on DeePC, and the technical solutions are as follows: In a first aspect, an embodiment of this specification provides an energy scheduling method based on DeePC, which is applied to a microgrid off-grid operation system, wherein the microgrid off-grid operation system includes multiple power generation subsystems and a battery energy storage subsystem, including: Obtaining the output power of the multiple power generation subsystems and the energy storage value of the battery energy storage subsystem in different time periods; Generate a control input sequence of the microgrid off-grid operation system according to the acquired output power, and generate an energy storage output sequence of the microgrid off-grid operation system according to the acquired energy storage value; Determine the power reference trajectories of the multiple power generation subsystems and the battery energy storage subsystem in the corresponding time period, and input the control input sequence, the energy storage output sequence and the power reference trajectory into the microgrid system energy management optimization model established based on the DeePC algorithm to calculate the optimal control input sequence of the microgrid off-grid operation system in the corresponding time period; The power of the plurality of power generation subsystems is adjusted according to the optimal control input sequence during corresponding time periods.

[0005] In a second aspect, an embodiment of this specification provides a microgrid off-grid operation system, wherein the microgrid off-grid operation system includes multiple power generation subsystems and a battery energy storage subsystem, including: An acquisition unit, used for acquiring the output power of the plurality of power generation subsystems and the energy storage value of the battery energy storage subsystem in different time periods; A generating unit, configured to generate a control input sequence of the microgrid off-grid operation system according to the acquired power difference value, and to generate an energy storage output sequence of the microgrid off-grid operation system according to the acquired energy storage value; A calculation unit, used to determine the power reference trajectory of the multiple power generation subsystems and the battery energy storage subsystem in the corresponding time period, and input the control input sequence, the energy storage output sequence and the power reference trajectory into the microgrid system energy management optimization model established based on the DeePC algorithm to calculate the optimal control input sequence of the microgrid off-grid operation system in the corresponding time period; An adjustment unit is used to adjust the power of the multiple power generation subsystems according to the optimal control input sequence during corresponding time periods.

[0006] In the third aspect, an embodiment of this specification provides an electronic device, comprising a processor and a memory; the processor is connected to the memory; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the DeePC-based energy scheduling method described in the first aspect of the above embodiment.

[0007] In a fourth aspect, an embodiment of this specification provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the steps of the energy scheduling method based on DeePC described in the first aspect of the above embodiment.

[0008] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least: DeePC is used to replace MPC, and an optimization method is adopted to implicitly include the state estimation and prediction process in the optimization constraints, so as to realize data-driven predictive control and thus realize the energy dispatch of the microgrid. On the one hand, the energy dispatch of the microgrid can be realized without establishing an accurate prediction model, which not only reduces the cost but also improves the efficiency; on the other hand, the influence of the system parameter change on the energy dispatch is avoided, which improves the accuracy of the energy dispatch. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0010] Figure 1It is a flowchart of a DeePC-based energy scheduling method provided in an embodiment of this specification.

[0011] Figure 2 It is a block diagram of a microgrid off-grid operation system provided in an embodiment of this specification.

[0012] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0013] The technical solutions in the embodiments of this specification will be described clearly and completely below in conjunction with the drawings in the embodiments of this specification.

[0014] The terms "first", "second", etc. in the description and claims of this specification and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any variation thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0015] The energy scheduling method based on DeePC is described in detail below in combination with one or more embodiments.

[0016] For new energy microgrids, in order to improve the consumption of renewable energy, ensure load power supply capacity, and coordinate the production and utilization of green electricity and green hydrogen, the key lies in the optimized operation and energy management during the real-time operation stage of the microgrid.

[0017] In related technologies, accurate models are established based on operating data, and multi-step decision optimization control is performed through model states and outputs, such as MPC (Model Predictive Control) and its improved solutions. However, when faced with changes in system parameters (such as degradation or update of energy storage systems), such methods cannot provide accurate energy control, and system modeling and parameter identification must be re-performed.

[0018] In order to solve the deficiencies in the related art, this specification proposes a DeePC energy scheduling method and a microgrid off-grid operation system.

[0019] The Deep Predictive Control (DeePC) algorithm is an advanced control strategy that combines deep learning and model predictive control (MPC). The algorithm uses deep learning technology to learn the dynamic model of the system and uses this model for prediction and control. The core idea of ​​the DeePC algorithm is data-driven model learning and predictive control. Among them, data-driven model learning: Unlike traditional physical model-based control methods, the DeePC algorithm learns the dynamic behavior of the system from data without the need for an explicit mathematical model; predictive control: The algorithm uses the learned model for multi-step predictions and optimizes the control input to drive the system to the desired trajectory or state.

[0020] The main steps include: data collection: collecting input-output data from the actual system or simulation; model learning: using deep learning networks (such as convolutional neural networks, recurrent neural networks, etc.) to learn the dynamic model of the system; state estimation: during the control process, the learned model is used to estimate the state of the system; optimization problem construction: construct an optimization problem to minimize the prediction error and meet the control objectives and constraints; solving the optimization problem: obtaining a series of control inputs by solving the optimization problem; executing control: applying the first calculated control input to the system and repeating the process in the next control cycle.

[0021] See also Figure 1 , Figure 1 A schematic diagram of a process flow of a DeePC-based energy scheduling method provided in an embodiment of this specification is shown, such as Figure 1 As shown, the energy scheduling method based on DeePC is applied to a microgrid off-grid operation system, wherein the microgrid off-grid operation system includes multiple power generation subsystems and a battery energy storage subsystem, and may at least include the following steps: Step 102: Obtain the output power of the multiple power generation subsystems and the energy storage value of the battery energy storage subsystem in different time periods.

[0022] A microgrid is a small power system that is able to operate independently or in parallel with the main grid. A microgrid combines distributed generation resources (such as solar photovoltaic, wind power, fuel cells, micro hydropower and energy storage systems) with loads and power electronics to optimize the use and management of energy. A microgrid contains a variety of distributed energy resources, which are usually located near the load. Microgrids are usually equipped with energy storage systems, such as batteries, to store excess power and release it when needed. Microgrids use power electronics such as inverters, converters and switches to control the flow and conversion of energy. Microgrids are able to operate independently when disconnected from the main grid, which is called island mode. Microgrids can easily increase or decrease generation and storage resources as needed.

[0023] In one embodiment, the plurality of power generation subsystems include at least one of the following: a photovoltaic power generation subsystem, a wind power generation subsystem, a fuel cell power generation subsystem, a micro gas turbine power generation subsystem, a battery energy storage subsystem, and an electrolysis hydrogen production subsystem.

[0024] The energy storage value of the battery energy storage subsystem is the state of charge of the battery in the subsystem.

[0025] Step 104: Generate a control input sequence of the microgrid off-grid operation system according to the acquired output power, and generate an energy storage output sequence of the microgrid off-grid operation system according to the acquired energy storage value.

[0026] In one embodiment, the generating of the control input sequence of the microgrid off-grid operation system according to the acquired output power, and the generating of the energy storage output sequence of the microgrid off-grid operation system according to the acquired energy storage value, include: inputting the acquired output power and the acquired energy storage value into a pre-built linear discrete model, and generating the control input sequence and the energy storage output sequence according to the output of the linear discrete model; wherein the linear discrete model includes a first output power in a current period, a second output power in a previous period compared to the current period, and a power regulation amount in the current period, and the control input sequence is generated based on the power regulation amounts in different time periods.

[0027] The embodiment is introduced below in combination with the formula: The microgrid offline operation systems involved include photovoltaic power generation subsystem (PV), wind power generation subsystem (WTG), fuel cell power generation subsystem (FC), micro gas turbine power generation system (MT), battery energy storage subsystem (Bat), electrolysis hydrogen production subsystem (EL), power conversion power electronic equipment and power load (Load).

[0028] The linear discrete model of the microgrid off-grid system is as follows: ; ; ; Among them, usually the parameter matrices A and B are 1, because S0C Bat (k+1) and P Bat (k) SOC Bat (k), so A must have one dimension that is not 1, and the matrix C is [0 0 0 0 1]. MT (k) is the output power of the micro gas turbine (micro gas turbine generator system), P FC (k) is the output power of the fuel cell (fuel cell power generation subsystem), PEL (k) is the input power of the alkaline electrolyzer (electrolysis hydrogen production subsystem), P MT (k) Output power of the battery (battery energy storage subsystem), SOC Bat (k) is the state of charge of the battery (battery energy storage subsystem), which is used to reflect the remaining capacity of the battery. P MT (k) is the power regulation of the micro-turbine at time k, P FC (k) Power regulation of the fuel cell, P EL (k) Power regulation of the electrolytic cell, P Bat (k) is the power regulation value of the battery.

[0029] The control input sequence is , the energy storage output sequence is , the historical data sequence obtained by combining the two is .

[0030] In one embodiment, the method further includes: performing data processing on the control input sequence and the energy storage output sequence according to a Hankel matrix to facilitate calculation of the optimal control input sequence.

[0031] Assume that the length of the historical data sequence is T and the initial sample size is , the total time range is H, the operation step is s, and the prediction step is N.

[0032] Generate input / output trajectories based on historical data sequences , the formula is as follows: ; Next, divide the past data into future data.

[0033] Assume that the past data divided is U p and Y p , used to estimate the state of the initial conditions; the future data U divided f and Y f , used to predict future trajectories. p is the generator matrix Before OK, U f is the generator matrix The last N rows; Y p is the generator matrix Before OK, Y f is the generator matrix The next N rows. The formula is as follows: .

[0034] is a Hankel matrix, which is generated as follows: ; Among them, T needs to be greater than , the "5" here corresponds to the 4 power adjustment values ​​in u(k) above. If there are 3 power adjustment values ​​in u(k), the value here is "4", which is the number of power adjustment values ​​plus 1. is the rank of the system observability matrix. In actual use, historical data sequences of sufficient time periods are collected.

[0035] Step 106: determine the power reference trajectories of the multiple power generation subsystems and the battery energy storage subsystem in the corresponding time period, and input the control input sequence, the energy storage output sequence and the power reference trajectory into the microgrid system energy management optimization model established based on the DeePC algorithm to calculate the optimal control input sequence of the microgrid off-grid operation system in the corresponding time period.

[0036] The power reference trajectory is the trajectory of the output power of each power generation subsystem and the energy storage value of the battery energy storage subsystem in each time period as expected by the manager of the microgrid offline operation system.

[0037] In one embodiment, a constraint set of the control input sequence and the energy storage output sequence is pre-set in the microgrid system energy management optimization model, and the calculation process of the optimal control input sequence includes: solving the DeePC optimization problem when the control input sequence and the energy storage output sequence satisfy the constraint set, and the result of the solution is the optimal control input sequence.

[0038] Furthermore, the optimization constraints in the DeePC optimization problem include: the square of the difference between the energy storage output sequence and the power reference trajectory in the same time period, and the square of the control input sequence.

[0039] Initialization of relevant parameters of the DeePC optimization problem: Assume that the power reference trajectory is , the output weight matrix is ​​Q, the input weight matrix is ​​R, and the initial trajectory is .

[0040] According to the above parameters and related data, the energy management model of the microgrid system is established as shown in the following formula: Among them, the first formula in the model is the optimization constraint, They are the input and output constraint sets, as follows: Among them, the adjustment power of each power generation subsystem and the upper and lower limits of the energy storage value are pre-set by the managers of the microgrid offline operation system.

[0041] Establish the DeePC optimization problem and iteratively solve it to obtain the control microgrid management method. The steps are as follows: Step 1061: solve the optimization problem for each operation step s within the total time range H; Step 1062: solve the optimization problem in formula (6) to obtain ; Step 1063, calculate the optimal control input sequence ; Step 1064, in the time period from t to t+s, the control input sequence Apply to the system; Step 1065, the initial time step t moves to t+s, and the most recent The input and output observation values ​​of the step are assigned to ; Step 1066, repeat the process of step 1061-step 1065 within the time step of t+s.

[0042] Step 108: Perform power adjustment on the plurality of power generation subsystems according to the optimal control input sequence during corresponding time periods.

[0043] In one embodiment, the control input sequence is generated based on power adjustment amounts in different time periods; and power adjustment of the multiple power generation subsystems in the corresponding time period according to the optimal control input sequence includes: calculating the output power of the corresponding time period based on the power adjustment amount of the corresponding time period and the output power of the previous time period.

[0044] In this embodiment, DeePC is used to replace MPC, and an optimization method is adopted to implicitly include the state estimation and prediction process in the optimization constraints, so as to realize data-driven predictive control and thus realize the energy dispatch of the microgrid. On the one hand, the energy dispatch of the microgrid can be realized without establishing an accurate prediction model, which not only reduces the cost but also improves the efficiency; on the other hand, the influence of the system parameter change on the energy dispatch is avoided, which improves the accuracy of the energy dispatch.

[0045] See also Figure 2 , Figure 2 A block diagram of a microgrid off-grid operation system provided in an embodiment of this specification. The microgrid off-grid operation system includes multiple power generation subsystems and battery energy storage subsystems, including: An acquisition unit 202 is used to acquire the output power of the multiple power generation subsystems and the energy storage value of the battery energy storage subsystem in different time periods; A generating unit 204, configured to generate a control input sequence of the microgrid off-grid operation system according to the acquired power difference value, and to generate an energy storage output sequence of the microgrid off-grid operation system according to the acquired energy storage value; The calculation unit 206 is used to determine the power reference trajectory of the multiple power generation subsystems and the battery energy storage subsystem in the corresponding time period, and input the control input sequence, the energy storage output sequence and the power reference trajectory into the microgrid system energy management optimization model established based on the DeePC algorithm to calculate the optimal control input sequence of the microgrid off-grid operation system in the corresponding time period; The adjustment unit 208 is used to adjust the power of the plurality of power generation subsystems according to the optimal control input sequence during a corresponding period.

[0046] Optionally, the generating unit 204 is specifically configured to: The obtained output power and the obtained energy storage value are input into a pre-built linear discrete model, and the control input sequence and the energy storage output sequence are generated according to the output of the linear discrete model; wherein the linear discrete model includes a first output power of a current time period, a second output power of a previous time period compared to the current time period, and a power adjustment amount of the current time period, and the control input sequence is generated based on the power adjustment amounts of different time periods.

[0047] Optionally, also include: The processing unit 210 is used to perform data processing on the control input sequence and the energy storage output sequence according to the Hankel matrix to facilitate the calculation of the optimal control input sequence.

[0048] Optionally, a constraint set of the control input sequence and the energy storage output sequence is pre-set in the microgrid system energy management optimization model, and the calculation process of the optimal control input sequence includes: When the control input sequence and the energy storage output sequence satisfy the constraint set, the DeePC optimization problem is solved, and the solution result is the optimal control input sequence.

[0049] Optionally, the optimization constraints in the DeePC optimization problem include: the square of the difference between the energy storage output sequence and the power reference trajectory in the same time period, and the square of the control input sequence.

[0050] Optionally, the control input sequence is generated based on the power adjustment amount in different time periods; the adjustment unit 208 is specifically used for: The output power of the corresponding period is calculated according to the power adjustment amount of the corresponding period and the output power of the previous period.

[0051] Optionally, the multiple power generation subsystems include at least one of the following: a photovoltaic power generation subsystem, a wind power generation subsystem, a fuel cell power generation subsystem, a micro gas turbine power generation subsystem, a battery energy storage subsystem, and an electrolysis hydrogen production subsystem.

[0052] In this embodiment, DeePC is used to replace MPC, and an optimization method is adopted to implicitly include the state estimation and prediction process in the optimization constraints, so as to realize data-driven predictive control and thus realize the energy dispatch of the microgrid. On the one hand, the energy dispatch of the microgrid can be realized without establishing an accurate prediction model, which not only reduces the cost but also improves the efficiency; on the other hand, the influence of the system parameter change on the energy dispatch is avoided, which improves the accuracy of the energy dispatch.

[0053] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the energy scheduling device embodiment based on DeePC, since it is basically similar to the energy scheduling method embodiment based on DeePC, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0054] See also Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification is shown.

[0055] like Figure 3 As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0056] The communication bus 302 may be used to realize the connection and communication among the above-mentioned components.

[0057] The user interface 303 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0058] The network interface 304 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0059] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts within the entire electronic device 300, and executes various functions and processes data of the electronic device 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor 301 can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to handle wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0060] Among them, the memory 305 may include RAM or ROM. Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be at least one storage device located away from the aforementioned processor 301. The memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an energy scheduling application based on DeePC. The processor 301 can be used to call the energy scheduling application based on DeePC stored in the memory 305, and execute the steps of energy scheduling based on DeePC mentioned in the above-mentioned embodiments.

[0061] The embodiment of the present specification also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a computer or a processor, the computer or the processor executes the above Figure 1 One or more steps in the illustrated embodiment. If the components of the electronic device described above are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0062] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of this specification is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0063] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0064] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Without departing from the design spirit of this specification, various modifications and improvements made to the technical solutions of this specification by ordinary technicians in this field should fall within the scope of protection determined by the claims of this specification.

Claims

1. A DeePC-based energy dispatching method, applied to a microgrid off-grid operation system, wherein the microgrid off-grid operation system includes a plurality of power generation subsystems and a battery energy storage subsystem, including: Obtaining the output power of the multiple power generation subsystems and the energy storage value of the battery energy storage subsystem in different time periods; Generate a control input sequence of the microgrid off-grid operation system according to the acquired output power, and generate an energy storage output sequence of the microgrid off-grid operation system according to the acquired energy storage value; Determine the power reference trajectories of the multiple power generation subsystems and the battery energy storage subsystem in the corresponding time period, and input the control input sequence, the energy storage output sequence and the power reference trajectory into the microgrid system energy management optimization model established based on the DeePC algorithm to calculate the optimal control input sequence of the microgrid off-grid operation system in the corresponding time period; The power of the plurality of power generation subsystems is adjusted according to the optimal control input sequence during corresponding time periods.

2. According to the energy scheduling method based on DeePC in claim 1, the control input sequence of the microgrid off-grid operation system is generated according to the acquired output power, and the energy storage output sequence of the microgrid off-grid operation system is generated according to the acquired energy storage value, including: The obtained output power and the obtained energy storage value are input into a pre-built linear discrete model, and the control input sequence and the energy storage output sequence are generated according to the output of the linear discrete model; wherein the linear discrete model includes a first output power of a current time period, a second output power of a previous time period compared to the current time period, and a power adjustment amount of the current time period, and the control input sequence is generated based on the power adjustment amounts of different time periods.

3. The energy scheduling method based on DeePC according to claim 1, further comprising: Data processing is performed on the control input sequence and the energy storage output sequence according to the Hankel matrix to facilitate calculation of the optimal control input sequence.

4. According to the energy scheduling method based on DeePC in claim 1, the constraint set of the control input sequence and the energy storage output sequence is pre-set in the microgrid system energy management optimization model, and the calculation process of the optimal control input sequence includes: When the control input sequence and the energy storage output sequence satisfy the constraint set, the DeePC optimization problem is solved, and the solution result is the optimal control input sequence.

5. According to the energy scheduling method based on DeePC in claim 4, the optimization constraints in the DeePC optimization problem include: The square of the difference between the energy storage output sequence and the power reference trajectory, and the square of the control input sequence in the same time period.

6. According to the energy scheduling method based on DeePC in claim 1, the control input sequence is generated based on the power adjustment amount in different time periods; the power adjustment of the plurality of power generation subsystems according to the optimal control input sequence in the corresponding time period comprises: The output power of the corresponding period is calculated according to the power adjustment amount of the corresponding period and the output power of the previous period.

7. According to the DeePC-based energy scheduling method described in claim 1, the multiple power generation subsystems include at least one of the following: a photovoltaic power generation subsystem, a wind power generation subsystem, a fuel cell power generation subsystem, a micro gas turbine power generation subsystem, a battery energy storage subsystem, and an electrolysis hydrogen production subsystem.

8. A microgrid off-grid operation system, the microgrid off-grid operation system comprising a plurality of power generation subsystems and a battery energy storage subsystem, including: An acquisition unit, used for acquiring the output power of the plurality of power generation subsystems and the energy storage value of the battery energy storage subsystem in different time periods; A generating unit, configured to generate a control input sequence of the microgrid off-grid operation system according to the acquired power difference value, and to generate an energy storage output sequence of the microgrid off-grid operation system according to the acquired energy storage value; A calculation unit, used to determine the power reference trajectory of the multiple power generation subsystems and the battery energy storage subsystem in the corresponding time period, and input the control input sequence, the energy storage output sequence and the power reference trajectory into the microgrid system energy management optimization model established based on the DeePC algorithm to calculate the optimal control input sequence of the microgrid off-grid operation system in the corresponding time period; An adjustment unit is used to adjust the power of the multiple power generation subsystems according to the optimal control input sequence during corresponding time periods.

9. An electronic device comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute 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, the method according to any one of claims 1 to 7 is implemented.

Images