Wind power plant real-time optimization scheduling method and device based on clustering network

Abstract

The invention provides a wind power plant real-time optimization scheduling method and device based on a clustering network, and relates to the field of wind power plant scheduling, and the method comprises the steps: obtaining a wake flow field of a wind power plant under different wind speeds and wind directions according to a wake flow model, and obtaining a wake flow diagram of the wind power plant according to the wake flow field; performing intelligent clustering processing on the wake flow graph to obtain distributed and distributed communication network structures; analyzing the control performance requirements of the whole wind power plant, and generating distributed and distributed control optimization strategies corresponding to the distributed and distributed communication network structures respectively; and respectively solving the distributed control optimization strategy and the distributed control optimization strategy to obtain a real-time optimization scheduling scheme of the wind power plant. According to the invention, different optimization algorithms are respectively used for solving the obtained optimization scheduling strategy aiming at the distributed network structure and the distributed network structure, so that the requirement of real-time scheduling can be met while the coordination optimization solution is ensured, and the coordination optimization control and scheduling precision of the wind power plant is further improved.

Description

Technical Field

[0001] The present application relates to the field of wind farm scheduling, and in particular to a wind farm real-time optimization scheduling method and device based on a clustering network. Background Art

[0002] At present, offshore wind power has developed rapidly with its advantages of high wind speed, low turbulence, and low wind shear, and has maintained a steady upward trend, becoming a key direction of new energy planning. The wind speed and direction of offshore wind farms are relatively stable, the wake effect is prolonged, and the coupling relationship between wind turbines is highly complex. The traditional control method is the greedy control of a single wind turbine, resulting in a small power generated by downstream wind turbines, which seriously affects the power generation efficiency of wind farms.

[0003] In recent years, offshore wind farms are gradually becoming larger, and wind farm wind turbines are turning to large-sized variable-speed types. In large offshore wind farms, as the number of wind turbines increases, the control variables of the wind farms also increase in a nearly exponential form. Based on this, distributed control architectures and optimization algorithms have received extensive attention from researchers. Summary of the invention

[0004] To address the above problems, a real-time optimization scheduling method and device for wind farms based on clustered networks are proposed. Different optimization algorithms are used for decentralized and distributed network structures respectively, and the optimized scheduling strategy obtained can meet the needs of real-time scheduling while ensuring coordinated optimization solution, thereby improving the collaborative optimization control and scheduling accuracy of wind farms.

[0005] In a first aspect, the present application proposes a real-time optimization scheduling method for a wind farm based on a clustering network, comprising:

[0006] Obtaining a wake field of a wind farm at different wind speeds and wind directions according to a wake model, and obtaining a wake map of the wind farm according to the wake field;

[0007] Performing intelligent clustering processing on the wake graph to obtain a decentralized and distributed communication network structure;

[0008] Analyze the overall control performance requirements of the wind farm and generate decentralized and distributed control optimization strategies corresponding to the decentralized and distributed communication network structures respectively;

[0009] The decentralized control optimization strategy and the distributed control optimization strategy are solved respectively to obtain a real-time optimization scheduling plan for the wind farm.

[0010] Optionally, obtaining the wake field of the wind farm at different wind speeds and wind directions according to the wake model, and obtaining the wake map of the wind farm according to the wake field, includes:

[0011] Inputting the position information and wind condition information of the wind turbines in the wind farm into the wake model to generate the wake field;

[0012] Obtaining a coupling relationship between the wind turbines according to the wake field;

[0013] A wake map of the wind farm is generated according to the coupling relationship between the wake field and the wind turbine generator set.

[0014] Optionally, solving the distributed control optimization strategy to obtain a real-time optimization scheduling solution for the wind farm includes:

[0015] The overall optimization control function of the wind farm is solved by the SQP algorithm to obtain a dispatching scheme of the distributed communication network structure, wherein the solving process is to obtain the maximum value of the power function for each cluster.

[0016] Optionally, solving the distributed control optimization strategy includes:

[0017] The overall optimization control function of the wind farm is solved according to the ADMM distributed algorithm and the E0 meta-heuristic algorithm, generating multiple solvable sub-problems;

[0018] Solve each subproblem in parallel to generate multiple subproblem solutions;

[0019] The multiple sub-problem solutions are coordinated to obtain a scheduling solution for the distributed communication network structure.

[0020] Optionally, the overall optimization control function of the wind farm is formulated as:

[0021] min x f(x)+.G(x);

[0022]

[0023] Where f(x) is the sum of the power of N wind turbines in the wind farm, g(x) is the sum of the fatigue loads of N wind turbines in the wind farm, and the control variable matrix x = [α, γ] T , -γ max and γ max are the minimum and maximum yaw angle ranges, α min and α max are the minimum and maximum axial factor ranges, γ j is the yaw angle of the j-th wind turbine, α j is the axial factor of the jth wind turbine, P j.low and P j.rate are the minimum power and rated power of the jth wind turbine, P j is the real-time power of the j-th wind turbine.

[0024] The second aspect of the present application proposes a wind farm real-time optimization scheduling device based on a clustering network, comprising:

[0025] An input module, used for obtaining a wake field of a wind farm at different wind speeds and wind directions according to a wake model, and obtaining a wake map of the wind farm according to the wake field;

[0026] A clustering module, used for performing intelligent clustering processing on the wake graph to obtain a decentralized and distributed communication network structure;

[0027] An analysis module, used for analyzing the overall control performance requirements of the wind farm, and generating decentralized and distributed control optimization strategies corresponding to the decentralized and distributed communication network structures respectively;

[0028] The solution module is used to solve the decentralized control optimization strategy and the distributed control optimization strategy respectively to obtain a real-time optimization scheduling plan for the wind farm.

[0029] A third aspect of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of the first aspects above is implemented.

[0030] In a fourth aspect, the present application proposes a non-temporary computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0031] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0032] Different optimization algorithms are used for decentralized and distributed network structures respectively, and the optimized scheduling strategies solved can meet the needs of real-time scheduling while ensuring coordinated optimization solutions, thereby improving the coordinated optimization control and scheduling accuracy of wind farms.

[0033] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0035] Figure 1 is a flow chart of a wind farm real-time optimization scheduling method based on a cluster network according to an embodiment of the present application;

[0036] Figure 2is a flow chart of a wind farm real-time optimization scheduling method based on a cluster network according to an embodiment of the present application;

[0037] Figure 3 is a flow chart of wind farm clustering according to an embodiment of the present application;

[0038] Figure 4 is a block diagram of a wind farm real-time optimization scheduling device based on a cluster network according to an embodiment of the present application;

[0039] Figure 5 It is a block diagram of an electronic device. DETAILED DESCRIPTION

[0040] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0041] Figure 1 The present invention is a flowchart of a method for real-time optimization and scheduling of a wind farm based on a cluster network according to an embodiment of the present application, including:

[0042] Step 101, obtaining a wake field of a wind farm at different wind speeds and wind directions according to a wake model, and obtaining a wake map of the wind farm according to the wake field.

[0043] In the embodiment of the present application, step 101 further includes:

[0044] Step 201: input the location information and wind condition information of the wind turbines in the wind farm into a wake model to generate a wake field.

[0045] Specifically, the generated wake field is as follows: Figure 3 shown.

[0046] Step 202: obtaining the coupling relationship between wind turbines according to the wake field.

[0047] In the embodiment of the present application, the coupling relationship includes distance information and direction information between wind turbines.

[0048] Step 203: generating a wake map of the wind farm according to the coupling relationship between the wake field and the wind turbines.

[0049] In the embodiment of the present application, the wake graph is essentially a directed network graph, such as Figure 3 shown.

[0050] Step 102, performing intelligent clustering processing on the wake graph to obtain a decentralized and distributed communication network structure.

[0051] In the embodiment of the present application, the wake graph is intelligently clustered to generate Figure 3 The decentralized and distributed communication network structure shown.

[0052] Among them, there is no communication between subsets of wind turbines in the distributed communication network structure, that is, there is no shared wind turbine between clusters, and the dispatching centers communicate with each other.

[0053] Among them, there are shared nodes between each subset of wind turbines in the distributed communication network structure, and coupling occurs between clusters.

[0054] Step 103, analyzing the overall control performance requirements of the wind farm, and generating decentralized and distributed control optimization strategies corresponding to the decentralized and distributed communication network structures, respectively.

[0055] In the embodiments of the present application, according to the overall control performance requirements, a wind farm overall control optimization strategy based on intelligent clustering is studied. Specifically, decentralized and distributed control optimization strategies corresponding to decentralized and distributed communication network structures are generated respectively.

[0056] Step 104 , respectively solving the decentralized control optimization strategy and the distributed control optimization strategy to obtain a real-time optimization scheduling solution for the wind farm.

[0057] First of all, it should be noted that, regardless of whether it is a decentralized control optimization strategy or a distributed control optimization strategy, corresponding to the characteristics of the coordinated optimization scheduling problem of large offshore wind farm units, the overall optimization control function of the wind farm can be expressed as:

[0058] min x f(x)+g(x);

[0059]

[0060] Where f(x) is the sum of the power of N wind turbines in the wind farm, g(x) is the sum of the fatigue loads of N wind turbines in the wind farm, and the control variable matrix x = [α, γ] T , -γ max and γ max are the minimum and maximum yaw angle ranges, α min and α max are the minimum and maximum axial factor ranges, γ j is the yaw angle of the j-th wind turbine, α j is the axial factor of the jth wind turbine, P j.low and P j.rate are the minimum power and rated power of the jth wind turbine, P j is the real-time power of the j-th wind turbine.

[0061] Normally, at time k, the optimal x[k] can be solved by an optimization algorithm, that is, the optimal yaw angle γ[k] and the optimal axial factor α[k] can be obtained, so that the wind farm power can be maximized by controlling each unit in the wind farm. However, for large wind farms, the large number of units greatly increases the cost of direct optimization, and the cost increases exponentially with the increase in the number of units. Therefore, different algorithms are used to solve the control optimization strategy.

[0062] Compared with the original centralized structure, the decentralized communication structure can greatly reduce the number of wind turbines in each cluster after clustering, and there is no shared wind turbine between clusters. Therefore, the optimization process will be greatly simplified, which is very suitable for online optimization.

[0063] In the embodiment of the present application, the overall optimization control function of the wind farm is solved by the SQP algorithm to obtain a scheduling solution for a distributed communication network structure, wherein the solution process is to obtain the maximum value of the power function for each cluster.

[0064] However, compared with the decentralized communication structure, the distributed scheduling strategy has coupling between clusters in the distributed communication structure due to the existence of shared nodes. Therefore, it is impossible to directly optimize and solve each cluster.

[0065] In the embodiment of the present application, the distributed control optimization strategy is solved according to the ADMM distributed algorithm and the EO meta-heuristic algorithm.

[0066] Specifically, the overall optimization control function of the wind farm is solved according to the ADMM distributed algorithm and the EO metaheuristic algorithm, multiple solvable subproblems are generated, each subproblem is solved in parallel, multiple subproblem solutions are generated, and multiple subproblem solutions are coordinated to obtain a scheduling scheme for a distributed communication network structure.

[0067] Example 1

[0068] For a wind farm consisting of 72 NREL5MW wind turbines, the wind turbines in the wind farm are arranged in 9 rows and 8 columns. Compared with the initial greedy operation, both the centralized and distributed DySC_IEO operation methods achieve significant power improvements.

[0069] Taking the scenario with an inlet wind direction of 0° as an example and the greedy method as a reference, the power of each wind turbine in the three methods is compared. After centralized operation optimization, the output power of upstream wind turbines 1-9 is reduced, and the overall output power of downstream wind turbines is partially improved. The power gain of a single wind turbine is concentrated between 0.5-0.8MW; after distributed operation optimization, a significant improvement is achieved in subsets.

[0070] In a possible embodiment, the centralized and distributed powers of subset 1 (the row where wind turbines numbered 5-8 are located) are 56.06MW and 58.41MW respectively, and the centralized and distributed powers of subset 2 (the row where wind turbine numbered 1 is located) are 14.05MW and 15.60MW respectively.

[0071] Figure 4 5 is a block diagram 500 of a wind farm real-time optimization scheduling device based on a cluster network according to an embodiment of the present application, including:

[0072] An input module 510 is used to obtain a wake field of a wind farm at different wind speeds and wind directions according to a wake model, and obtain a wake map of the wind farm according to the wake field;

[0073] A clustering module 520, for performing intelligent clustering processing on the wake graph to obtain a decentralized and distributed communication network structure;

[0074] An analysis module 530 is used to analyze the overall control performance requirements of the wind farm and generate decentralized and distributed control optimization strategies corresponding to decentralized and distributed communication network structures respectively;

[0075] The solution module 540 is used to solve the decentralized control optimization strategy and the distributed control optimization strategy respectively to obtain a real-time optimization scheduling solution for the wind farm.

[0076] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0077] Figure 5 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0078] like Figure 5As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0079] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0080] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the voice instruction response method. For example, in some embodiments, the voice instruction response method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the voice instruction response method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the voice instruction response method in any other appropriate manner (e.g., by means of firmware).

[0081] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0082] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0083] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0084] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0085] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0086] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0087] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.

[0088] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A real-time optimization scheduling method for wind farms based on clustering networks, characterized in that: include: Obtaining a wake field of a wind farm at different wind speeds and wind directions according to a wake model, and obtaining a wake map of the wind farm according to the wake field; Performing intelligent clustering processing on the wake graph to obtain a decentralized and distributed communication network structure; Analyze the overall control performance requirements of the wind farm and generate decentralized and distributed control optimization strategies corresponding to the decentralized and distributed communication network structures respectively; The decentralized control optimization strategy and the distributed control optimization strategy are solved respectively to obtain a real-time optimization scheduling plan for the wind farm.

2. The method according to claim 1, characterized in that The step of obtaining the wake field of a wind farm at different wind speeds and wind directions according to the wake model, and obtaining the wake map of the wind farm according to the wake field, comprises: Inputting the position information and wind condition information of the wind turbines in the wind farm into the wake model to generate the wake field; Obtaining a coupling relationship between the wind turbines according to the wake field; A wake map of the wind farm is generated according to the coupling relationship between the wake field and the wind turbine generator set.

3. The method according to claim 1, characterized in that The distributed control optimization strategy is solved to obtain a real-time optimization dispatching scheme for the wind farm, including: The overall optimization control function of the wind farm is solved by the SQP algorithm to obtain a dispatching scheme of the distributed communication network structure, wherein the solving process is to obtain the maximum value of the power function for each cluster.

4. The method according to claim 1, characterized in that: Solving the distributed control optimization strategy includes: Solve the overall optimization control function of the wind farm based on the ADMM distributed algorithm and the EO meta-heuristic algorithm, and generate multiple solvable sub-problems; Solve each subproblem in parallel to generate multiple subproblem solutions; The multiple sub-problem solutions are coordinated to obtain a scheduling solution for the distributed communication network structure.

5. The method according to claim 3 or 4, characterized in that: The overall optimization control function of the wind farm is formulated as: min x f(x)+.G(x); Where f(x) is the sum of the power of N wind turbines in the wind farm, g(x) is the sum of the fatigue loads of N wind turbines in the wind farm, and the control variable matrix x = [α, γ] T , -γ max and γ max are the minimum and maximum yaw angle ranges, α min and α max are the minimum and maximum axial factor ranges, γ j is the yaw angle of the j-th wind turbine, α j is the axial factor of the jth wind turbine, P j.low and P j.rate are the minimum power and rated power of the jth wind turbine, P j is the real-time power of the j-th wind turbine.

6. A wind farm real-time optimization dispatching device based on cluster network, characterized in that: include: An input module, used for obtaining a wake field of a wind farm at different wind speeds and wind directions according to a wake model, and obtaining a wake map of the wind farm according to the wake field; A clustering module, used for performing intelligent clustering processing on the wake graph to obtain a decentralized and distributed communication network structure; An analysis module, used for analyzing the overall control performance requirements of the wind farm, and generating decentralized and distributed control optimization strategies corresponding to the decentralized and distributed communication network structures respectively; The solution module is used to solve the decentralized control optimization strategy and the distributed control optimization strategy respectively to obtain a real-time optimization scheduling plan for the wind farm.

7. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A non-transitory 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 5 is implemented.

Images