[go: up one dir, main page]

CN115936924B - Wind energy forecasting method and system for a wind farm - Google Patents

Wind energy forecasting method and system for a wind farm Download PDF

Info

Publication number
CN115936924B
CN115936924B CN202211607577.XA CN202211607577A CN115936924B CN 115936924 B CN115936924 B CN 115936924B CN 202211607577 A CN202211607577 A CN 202211607577A CN 115936924 B CN115936924 B CN 115936924B
Authority
CN
China
Prior art keywords
wind energy
wind
power equipment
electric power
energy data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202211607577.XA
Other languages
Chinese (zh)
Other versions
CN115936924A (en
Inventor
祁乐
唐健
江平
李润
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing East Environment Energy Technology Co ltd
Guangxi Power Grid Co Ltd
Original Assignee
Beijing East Environment Energy Technology Co ltd
Guangxi Power Grid Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing East Environment Energy Technology Co ltd, Guangxi Power Grid Co Ltd filed Critical Beijing East Environment Energy Technology Co ltd
Priority to CN202211607577.XA priority Critical patent/CN115936924B/en
Publication of CN115936924A publication Critical patent/CN115936924A/en
Application granted granted Critical
Publication of CN115936924B publication Critical patent/CN115936924B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention provides a wind energy prediction method and a system for a wind power plant, and relates to the technical field of wind power generation. The method comprises the following steps: firstly, historical capacity data of fan equipment and estimated weather data of the next period of an area of a wind power plant are obtained, a first input feature is built according to the historical capacity data of the fan equipment and the estimated weather data of the next period of the area of the wind power plant, then a synchronous stable value of the current period of the electric power equipment is obtained, a second input feature is built according to the synchronous stable value of the current period of the electric power equipment, finally the first input feature and the second input feature are input into a pre-trained wind energy data prediction model, and actual output wind energy prediction data of the next period of the wind power plant is obtained. In the invention, the influence of the power equipment on the actual output electric energy of the wind power plant in the running process is also used as a reference condition for predicting the wind energy data actually output by the wind power plant, so that the prediction result is more accurate.

Description

一种风力发电场风能预测方法以及系统Wind energy forecasting method and system for a wind farm

技术领域technical field

本发明涉及风力发电技术领域,尤其涉及一种风力发电场风能预测方法以及系统。The present invention relates to the technical field of wind power generation, in particular to a wind energy prediction method and system for a wind power plant.

背景技术Background technique

在现代生活中,随着能源局势的不断紧张,新能源得到了空前的重视。新能源成为我国乃至全球资源匮乏的国家高度重视的产业,而由于其优势诸多,风力发电得到快速发展,随着中国风电装机的国产化与规模化,风电成本有望更进一步降低。因此风电将成为未来电力的支柱产业。In modern life, with the continuous tension of the energy situation, new energy has received unprecedented attention. New energy has become a highly valued industry in our country and even in resource-poor countries around the world. Due to its many advantages, wind power has developed rapidly. With the localization and scale of China's wind power installed capacity, the cost of wind power is expected to be further reduced. Therefore, wind power will become the pillar industry of electric power in the future.

相关技术中,对风力发电场进行风能预测时,只对风电机组的实际发电量进行预测,并且并未风力发电场中各类电力装备在运行过程中对风力发电场的实际输出电能的影响。In related technologies, when predicting wind energy for a wind farm, only the actual power generation of the wind turbine is predicted, and the influence of various power equipment in the wind farm on the actual output power of the wind farm during operation is not considered.

发明内容Contents of the invention

本发明实施例提供一种风力发电场风能预测方法以及系统,旨在解决或者部分解决上述背景技术中存在的问题。Embodiments of the present invention provide a wind energy prediction method and system for a wind farm, aiming to solve or partially solve the problems existing in the above-mentioned background technology.

为了解决上述技术问题,本发明是这样实现的:In order to solve the problems of the technologies described above, the present invention is achieved in that:

第一方面,本发明实施例提供了一种风力发电场风能预测方法,方法包括:In a first aspect, an embodiment of the present invention provides a method for predicting wind energy in a wind farm, the method comprising:

获得风机设备的历史产能数据,以及风电场所处区域下一周期的预估天气数据;Obtain the historical production capacity data of wind turbine equipment, as well as the forecast weather data of the area where the wind farm is located in the next cycle;

根据风机设备的历史产能数据和风电场所处区域下一周期的预估天气数据,构建第一输入特征;Construct the first input feature according to the historical production capacity data of the wind turbine equipment and the forecast weather data of the area where the wind farm is located in the next cycle;

获取电力装备当前周期的同步稳定值,并根据电力装备当前周期的同步稳定值,构建第二输入特征,其中,同步稳定值用于表征电力装备与风电场的连接稳定状态;Obtaining the synchronous stable value of the current period of the electric equipment, and constructing the second input feature according to the synchronous stable value of the current period of the electric equipment, wherein the synchronous stable value is used to represent the stable state of the connection between the electric equipment and the wind farm;

将第一输入特征和第二输入特征,输入预先训练得到的风能数据预测模型,输出得到风电场下一周期的实际输出风能预测数据。The first input feature and the second input feature are input into the pre-trained wind energy data prediction model, and the actual output wind energy forecast data of the next cycle of the wind farm is output.

可选地,获取电力装备当前周期的同步稳定值的步骤包括:Optionally, the step of obtaining the synchronous stable value of the current period of the electric equipment includes:

根据电力装备当前周期的电力运行参数,计算电力装备当前周期的阻抗压降参数;According to the power operation parameters of the current cycle of the power equipment, calculate the impedance voltage drop parameter of the current cycle of the power equipment;

根据电力装备在执行无功补偿时,对风机设备的影响能力,计算电力装备当前周期的无功补偿特性参数;According to the power equipment's ability to influence the fan equipment when performing reactive power compensation, calculate the reactive power compensation characteristic parameters of the current cycle of the power equipment;

根据电力装备当前周期的阻抗压降参数和电力装备当前周期的无功补偿特性参数,计算电力装备当前周期的同步稳定值。According to the impedance voltage drop parameters of the current period of the electric equipment and the reactive power compensation characteristic parameters of the current period of the electric equipment, the synchronous stable value of the current period of the electric equipment is calculated.

可选地,电力运行参数包括电网电压幅值和电力装备的机端电压额定值,根据电力装备当前周期的电力运行参数,计算电力装备当前周期的阻抗压降参数的步骤包括:Optionally, the power operation parameters include the grid voltage amplitude and the terminal voltage rating of the power equipment. According to the power operation parameters of the power equipment in the current cycle, the step of calculating the impedance drop parameter of the power equipment in the current cycle includes:

根据电网电压幅值和电力装备的机端电压额定值,计算电力装备的机端电压向量;Calculate the terminal voltage vector of the power equipment according to the grid voltage amplitude and the terminal voltage rating of the power equipment;

将电力装备的机端电压向量分解为交轴方向的分量;Decompose the terminal voltage vector of the power equipment into components in the direction of the quadrature axis;

根据电力装备的交轴分量,计算电力装备当前周期的阻抗压降参数。According to the quadrature axis component of the power equipment, the impedance voltage drop parameter of the current period of the power equipment is calculated.

可选地,风能数据预测模型是通过以下步骤获得的:Optionally, the wind energy data prediction model is obtained through the following steps:

获取风机设备的样本历史产能数据以及风电场所处区域的样本历史天气数据,并进行规整处理,获得第一输入特征样本;Obtain the sample historical production capacity data of the wind turbine equipment and the sample historical weather data of the area where the wind farm is located, and perform regular processing to obtain the first input feature sample;

获取电力装备的样本历史同步稳定值,并进行规整处理,获得第二输入特征样本;Obtain the historical synchronous stable value of the sample of the electric equipment, and perform regularization processing to obtain the second input feature sample;

根据第一输入特征样本和第二输入特征样本,对预设的随机森林模型进行训练和交叉验证,获得初始风能数据预测模型和风能数据预测模型的历史风能数据预测序列;According to the first input feature sample and the second input feature sample, the preset random forest model is trained and cross-validated to obtain the initial wind energy data prediction model and the historical wind energy data prediction sequence of the wind energy data prediction model;

根据风能数据预测模型的历史风能数据预测序列,对初始风能数据预测模型进行修正,获得目标风能数据预测模型。According to the historical wind energy data prediction sequence of the wind energy data prediction model, the initial wind energy data prediction model is corrected to obtain the target wind energy data prediction model.

可选地,根据风能数据预测模型的历史风能数据预测序列,对初始风能数据预测模型进行修正的步骤包括:Optionally, according to the historical wind energy data prediction sequence of the wind energy data prediction model, the step of correcting the initial wind energy data prediction model includes:

获取风力发电场的历史实际输出风能数据;Obtain the historical actual output wind energy data of the wind farm;

根据历史风能数据预测序列与历史实际输出风能数据,计算风力发电场的历史实际输出风能预测误差;According to the historical wind energy data prediction sequence and the historical actual output wind energy data, calculate the historical actual output wind energy prediction error of the wind farm;

根据风力发电场的历史实际输出风能预测误差,对初始风能数据预测模型的修正。According to the historical actual output wind energy prediction error of the wind farm, the correction of the initial wind energy data prediction model.

基于多元高斯分布对风力发电场的历史实际输出风能预测误差进行建模,以实现对初始风能数据预测模型的修正。Based on the multivariate Gaussian distribution, the historical actual output wind energy prediction error of the wind farm is modeled to realize the correction of the initial wind energy data prediction model.

可选地,根据风力发电场的历史实际输出风能预测误差,对初始风能数据预测模型的修正的步骤,包括:Optionally, the step of correcting the initial wind energy data prediction model according to the historical actual output wind energy prediction error of the wind farm includes:

基于多元高斯分布对风力发电场的历史实际输出风能预测误差进行建模,以实现对初始风能数据预测模型的修正。Based on the multivariate Gaussian distribution, the historical actual output wind energy prediction error of the wind farm is modeled to realize the correction of the initial wind energy data prediction model.

可选地,在根据所述风能数据预测模型的历史风能数据预测序列,对所述初始风能数据预测模型进行修正,获得目标风能数据预测模型的步骤之后,所述方法还包括:Optionally, after the step of correcting the initial wind energy data prediction model and obtaining a target wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model, the method further includes:

将目标风能数据预测模型的预测错误率最低确定为第一优化函数的优化方向;The lowest prediction error rate of the target wind energy data prediction model is determined as the optimization direction of the first optimization function;

将目标风能数据预测模型的多样性指标值最高确定为所述第二优化函数的优化方向;determining the highest diversity index value of the target wind energy data prediction model as the optimization direction of the second optimization function;

根据及所述第一优化函数的优化方向和所述第二优化函数的优化方向,对所述目标风能数据预测模型进行优化。The target wind energy data prediction model is optimized according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.

本发明实施例第二方面提出一种风力发电场风能预测系统,系统包括:The second aspect of the embodiment of the present invention proposes a wind energy forecasting system for a wind farm, the system includes:

风机参数获取模块,用于获得风机设备的历史产能数据,以及风电场所处区域下一周期的预估天气数据;The wind turbine parameter acquisition module is used to obtain the historical production capacity data of the wind turbine equipment, and the forecast weather data of the area where the wind farm is located in the next cycle;

第一特征构建模块,用于根据风机设备的历史产能数据和风电场所处区域下一周期的预估天气数据,构建第一输入特征;The first feature construction module is used to construct the first input feature according to the historical production capacity data of the wind turbine equipment and the forecast weather data of the next cycle in the area where the wind farm site is located;

电力装备参数获取模块,用于获取电力装备当前周期的同步稳定值;The power equipment parameter acquisition module is used to acquire the synchronous stable value of the current period of the power equipment;

第二特征构建模块,用于根据电力装备当前周期的同步稳定值,构建第二输入特征,其中,同步稳定值用于表征电力装备与风电场的连接稳定状态;The second feature construction module is used to construct a second input feature according to the synchronization stability value of the current cycle of the electric equipment, wherein the synchronization stability value is used to represent the connection stability state of the electric equipment and the wind farm;

预测模块,用于将第一输入特征和第二输入特征,输入预先训练得到的风能数据预测模型,输出得到风电场下一周期的实际输出风能预测数据。The forecasting module is used to input the first input feature and the second input feature into the pre-trained wind energy data forecasting model, and output the actual output wind energy forecasting data of the next cycle of the wind farm.

可选地,电力装备参数获取模块包括:Optionally, the power equipment parameter acquisition module includes:

阻抗压降计算子模块,用于根据电力装备当前周期的电力运行参数,计算电力装备当前周期的阻抗压降参数;The impedance voltage drop calculation sub-module is used to calculate the impedance voltage drop parameter of the current cycle of the power equipment according to the power operation parameters of the current cycle of the power equipment;

无功补偿特性参数计算子模块,用于根据电力装备在执行无功补偿时,对风机设备的影响能力,计算电力装备当前周期的无功补偿特性参数;The reactive power compensation characteristic parameter calculation sub-module is used to calculate the reactive power compensation characteristic parameters of the current period of the electric power equipment according to the ability of the electric power equipment to influence the fan equipment when performing reactive power compensation;

同步稳定值计算子模块,用于根据电力装备当前周期的阻抗压降参数和电力装备当前周期的无功补偿特性参数,计算电力装备当前周期的同步稳定值。The synchronous stable value calculation sub-module is used to calculate the synchronous stable value of the current period of the electric equipment according to the impedance voltage drop parameter of the current period of the electric equipment and the reactive power compensation characteristic parameter of the current period of the electric equipment.

可选地,阻抗压降计算子模块包括:Optionally, the impedance drop calculation submodule includes:

机端电压计算单元,用于向量根据电网电压幅值和电力装备的机端电压额定值,计算电力装备的机端电压向量;The machine terminal voltage calculation unit is used to calculate the machine terminal voltage vector of the power equipment according to the grid voltage amplitude and the machine terminal voltage rating of the power equipment;

划分单元,用于将电力装备的机端电压向量分解为交轴方向的分量;The division unit is used to decompose the machine terminal voltage vector of the power equipment into components in the direction of the quadrature axis;

阻抗压降参数计算单元,用于根据电力装备的交轴分量,计算电力装备当前周期的阻抗压降参数。The impedance voltage drop parameter calculation unit is used to calculate the impedance voltage drop parameter of the current period of the electric equipment according to the quadrature axis component of the electric equipment.

可选地,系统还包括模型训练单元,模型训练模块包括:Optionally, the system also includes a model training unit, and the model training module includes:

第一特征获取子模块,用于获取风机设备的样本历史产能数据以及风电场所处区域的样本历史天气数据,并进行规整处理,获得第一输入特征样本;The first feature acquisition sub-module is used to acquire the sample historical production capacity data of the wind turbine equipment and the sample historical weather data of the area where the wind farm is located, and perform normalization processing to obtain the first input feature sample;

第二特征获取子模块,用于获取电力装备的样本历史同步稳定值,并进行规整处理,获得第二输入特征样本;The second feature acquisition sub-module is used to acquire the sample history synchronous stable value of the electric equipment, and perform normalization processing to obtain the second input feature sample;

训练子模块,用于根据第一输入特征样本和第二输入特征样本,对预设的随机森林模型进行训练和交叉验证,获得初始风能数据预测模型和风能数据预测模型的历史风能数据预测序列;The training sub-module is used to train and cross-validate the preset random forest model according to the first input feature sample and the second input feature sample, and obtain the initial wind energy data prediction model and the historical wind energy data prediction sequence of the wind energy data prediction model;

修正子模块,用于根据风能数据预测模型的历史风能数据预测序列,对初始风能数据预测模型进行修正,获得目标风能数据预测模型。The correction sub-module is used to correct the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model, and obtain the target wind energy data prediction model.

可选地,修正子模块包括:Optionally, the correction submodule includes:

获取单元,用于获取风力发电场的历史实际输出风能数据;The obtaining unit is used to obtain the historical actual output wind energy data of the wind farm;

误差确定单元,用于根据历史风能数据预测序列与历史实际输出风能数据,计算风力发电场的历史实际输出风能预测误差;The error determination unit is used to calculate the historical actual output wind energy prediction error of the wind farm according to the historical wind energy data prediction sequence and the historical actual output wind energy data;

模型修正单元,用于根据风力发电场的历史实际输出风能预测误差,对初始风能数据预测模型的修正。The model correction unit is used for correcting the initial wind energy data prediction model according to the historical actual output wind energy prediction error of the wind farm.

可选地,修正子模块还包括:Optionally, the correction submodule also includes:

第一优化单元,用于将目标风能数据预测模型的预测错误率最低确定为第一优化函数的优化方向;The first optimization unit is used to determine the lowest prediction error rate of the target wind energy data prediction model as the optimization direction of the first optimization function;

第二优化单元,用于将目标风能数据预测模型的多样性指标值最高确定为所述第二优化函数的优化方向;The second optimization unit is configured to determine the highest diversity index value of the target wind energy data prediction model as the optimization direction of the second optimization function;

模型优化单元,用于根据及所述第一优化函数的优化方向和所述第二优化函数的优化方向,对所述目标风能数据预测模型进行优化。A model optimization unit, configured to optimize the target wind energy data prediction model according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.

本发明实施例第三方面提出一种电子设备,包括处理器、通信接口、存储器和通信总线,其中,处理器,通信接口,存储器通过通信总线完成相互间的通信;The third aspect of the embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus;

存储器,用于存放计算机程序;memory for storing computer programs;

处理器,用于执行存储器上所存放的程序时,实现本发明实施例第一方面提出方法步骤。The processor is configured to implement the method steps provided in the first aspect of the embodiments of the present invention when executing the program stored in the memory.

本发明实施例第四方面提出一种计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现如本发明实施例第一方面提出方法。The fourth aspect of the embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method as proposed in the first aspect of the embodiment of the present invention is implemented.

本发明实施例包括以下优点:首先,获得风机设备的历史产能数据,以及风电场所处区域下一周期的预估天气数据,并根据风机设备的历史产能数据和风电场所处区域下一周期的预估天气数据,构建第一输入特征,然后,获取电力装备当前周期的同步稳定值,并根据电力装备当前周期的同步稳定值,构建第二输入特征,最后,将第一输入特征和第二输入特征,输入预先训练得到的风能数据预测模型,输出得到风电场下一周期的实际输出风能预测数据。在本发明中,将电力设备在运行过程中对风力发电场的实际输出电能的影响,也作为预测风电场实际输出的风能数据的参考条件,使得预测的结果更加准确,并且能够为风电场中各类设备的正常运行提供足够的电能预留空间。The embodiment of the present invention has the following advantages: First, the historical production capacity data of the wind turbine equipment and the forecast weather data of the next period of the area where the wind farm is located are obtained, and the weather data of the next period of the area where the wind farm is located is Estimating the weather data, constructing the first input feature, then obtaining the synchronous stable value of the current period of the electric equipment, and constructing the second input feature according to the synchronous stable value of the current period of the electric equipment, finally, combining the first input feature and the second input Features, input the pre-trained wind energy data prediction model, and output the actual output wind energy prediction data of the next cycle of the wind farm. In the present invention, the influence of power equipment on the actual output electric energy of the wind farm during operation is also used as a reference condition for predicting the wind energy data actually output by the wind farm, so that the predicted results are more accurate and can be used in wind farms. The normal operation of all kinds of equipment provides enough power reserve space.

附图说明Description of drawings

为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

图1是本发明实施例中一种风力发电场风能预测方法的步骤流程图;Fig. 1 is a flow chart of the steps of a wind energy forecasting method for a wind farm in an embodiment of the present invention;

图2是本发明实施例中一种风力发电场风能预测系统的模块示意图。Fig. 2 is a block diagram of a wind energy forecasting system for a wind farm in an embodiment of the present invention.

具体实施方式Detailed ways

下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

相关技术中,现有的风力发电场风能预测方法大多只是对风力发电场中风机部分的产生的电能进行预测,但是实际输送到电网上时,发生了损耗,而这部分损耗是用于风力发电场中各类电力装备维持系统的稳态运行的,而这部分损耗是随风机部分产生的电能进行动态变化的,因此现有的风力发电场风能预测方法并未考虑电力装备部分的影响,导致预测发送到电网部分的电能数据够准确。基于此,本申请提出了一种全新的风力发电场风能预测方法。In related technologies, most of the existing wind energy prediction methods for wind farms only predict the electric energy generated by the wind turbines in the wind farm, but when it is actually delivered to the grid, losses occur, and this part of the loss is used for wind power generation All kinds of power equipment in the field maintain the steady-state operation of the system, and this part of the loss is dynamically changed with the power generated by the fan part. Therefore, the existing wind energy prediction methods for wind farms do not consider the influence of the power equipment part. This results in accurate predictions of the electrical energy data sent to the part of the grid. Based on this, the present application proposes a brand-new wind energy prediction method for wind farms.

基于此,发明人提出了本申请的核心技术构思:通过将电力装备维持系统的稳态运行所消耗的电能也作为发电场风能预测的参考条件,从而得到以电力装备稳定值的风能数据预测模型,并且从模型识别准确率和模型多样性两方面对风能数据预测模型进行多目标优化,从而能够使得实际输出风能预测数据能够更加准确。Based on this, the inventor proposed the core technical idea of this application: by taking the power consumed by the power equipment to maintain the steady-state operation of the system as a reference condition for the wind energy prediction of the power plant, a wind energy data prediction model based on the stable value of the power equipment can be obtained , and carry out multi-objective optimization on the wind energy data prediction model from two aspects of model recognition accuracy and model diversity, so that the actual output wind energy prediction data can be more accurate.

下面对本申请的风力发电场风能预测方法进行说明,如图1所示,图1示出了本申请的一种风力发电场风能预测方法的流程示意图。The following describes the wind energy forecasting method for a wind farm of the present application, as shown in FIG. 1 , which shows a schematic flowchart of a wind energy forecasting method for a wind farm of the present application.

首先,本发明的风能数据预测模型是通过以下步骤获得的:First, the wind energy data prediction model of the present invention is obtained through the following steps:

S100-1:获取风机设备的样本历史产能数据以及风电场所处区域的样本历史天气数据,并进行规整处理,获得第一输入特征样本;S100-1: Obtain the sample historical production capacity data of the wind turbine equipment and the sample historical weather data of the area where the wind farm is located, and perform regular processing to obtain the first input feature sample;

S100-2:获取电力装备的样本历史同步稳定值,并进行规整处理,获得第二输入特征样本;S100-2: Obtain the historical synchronous stable value of the sample of the electric equipment, and perform regularization processing to obtain the second input feature sample;

S100-3:根据第一输入特征样本和第二输入特征样本,对预设的随机森林模型进行训练和交叉验证,获得初始风能数据预测模型和风能数据预测模型的历史风能数据预测序列;S100-3: According to the first input feature sample and the second input feature sample, train and cross-validate the preset random forest model to obtain the initial wind energy data prediction model and the historical wind energy data prediction sequence of the wind energy data prediction model;

S100-4:根据风能数据预测模型的历史风能数据预测序列,对初始风能数据预测模型进行修正,获得目标风能数据预测模型。S100-4: Correct the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model to obtain a target wind energy data prediction model.

在步骤S100-1至S100-4的实施方式中,若要创建风电场的风能数据预测模型,需要获取风电场的风机设备的样本历史产能数据以及风电场所处区域的样本历史天气数据,电力装备的样本历史同步稳定值。In the implementation of steps S100-1 to S100-4, to create a wind energy data prediction model for a wind farm, it is necessary to obtain sample historical production capacity data of the wind turbine equipment in the wind farm and sample historical weather data of the area where the wind farm is located. The sample history syncs stable value of .

作为示例的,设风机设备的样本历史产能数据的是从1月至5月,样本持有时长为四个月,则应获取风电场对应的输入的样本历史产能数据以及风电场所处区域的样本历史天气数据,经过规整平均处理形成训练数据集,用于构建6月的风电场的风能数据预测模型。该训练数据集包括多个历史时段单位的产能数据和天气数据,即1月至5月,一共5个时段的样本历史产能数据以及风电场所处区域的样本历史天气数据,在本发明中,不对选取的样本历史产能数据以及风电场所处区域的样本历史天气数据的数量进行限制,但是选取的样本历史产能数据以及风电场所处区域的样本历史天气数据的数量越多,在训练的时候作为样本的数据就会越多,通常会使得模型的精度更高。As an example, if the sample historical production capacity data of wind turbine equipment is from January to May, and the sample holding period is four months, then the input sample historical production capacity data corresponding to the wind farm and the sample of the area where the wind farm is located should be obtained The historical weather data, after regular average processing, forms a training data set, which is used to build the wind energy data prediction model of the wind farm in June. The training data set includes production capacity data and weather data of multiple historical period units, that is, from January to May, a total of 5 period sample historical production capacity data and sample historical weather data of the area where the wind farm is located. In the present invention, no The selected sample historical production capacity data and the number of sample historical weather data in the area where the wind farm is located are limited. More data will usually lead to higher accuracy of the model.

使用规整后的风机设备的样本历史产能数据和风电场所处区域的样本历史天气数据构成的第一输入特征样本以及电力装备的样本历史同步稳定值构成的第二输入特征样本,对随机森林模型进行训练和交叉验证,得到初始风能数据预测模型以及基于初始风能数据预测模型预测的初始风能数据预测模型的历史风能数据预测序列。然后据风能数据预测模型的历史风能数据预测序列,对初始风能数据预测模型进行修正,从而获得最终的目标风能数据预测模型。Using the first input feature sample composed of the sample historical production capacity data of the wind turbine equipment and the sample historical weather data of the area where the wind farm is located, and the second input feature sample composed of the sample historical synchronous stable value of the power equipment, the random forest model is training and cross-validation to obtain the initial wind energy data prediction model and the historical wind energy data prediction sequence based on the initial wind energy data prediction model predicted by the initial wind energy data prediction model. Then, according to the historical wind energy data prediction sequence of the wind energy data prediction model, the initial wind energy data prediction model is corrected to obtain the final target wind energy data prediction model.

在一种可行的实施方式中,对初始风能数据预测模型进行修正的步骤包括:In a feasible implementation manner, the step of correcting the initial wind energy data prediction model includes:

获取风力发电场的历史实际输出风能数据;Obtain the historical actual output wind energy data of the wind farm;

根据历史风能数据预测序列与历史实际输出风能数据,计算风力发电场的历史实际输出风能预测误差;According to the historical wind energy data prediction sequence and the historical actual output wind energy data, calculate the historical actual output wind energy prediction error of the wind farm;

根据风力发电场的历史实际输出风能预测误差,对初始风能数据预测模型的修正。According to the historical actual output wind energy prediction error of the wind farm, the correction of the initial wind energy data prediction model.

基于多元高斯分布对风力发电场的历史实际输出风能预测误差进行建模,以实现对初始风能数据预测模型的修正。Based on the multivariate Gaussian distribution, the historical actual output wind energy prediction error of the wind farm is modeled to realize the correction of the initial wind energy data prediction model.

在本实施方式中,风力发电场的历史实际输出风能数据是指风力发电场历史记录的向外部电网输出的风能数据,过将风力发电场的历史实际输出风能数据的真实序列与历史风能数据预测序列作差,从而获得风力发电场的历史实际输出风能预测误,并使用多元高斯分布对误差进行建模,获得节点对电价预测误差的联合概率分布。使用多元高斯分布对误差序列的概率分布进行建模,使用极大似然法估计多元高斯分布的位置参数和协方差矩阵,即可以多元高斯分布表征误差的联合概率分布,并基于联合概率分布实现对初始风能数据预测模型的修正。In this embodiment, the historical actual output wind energy data of the wind farm refers to the wind energy data exported to the external power grid in the history of the wind farm. The sequence difference is used to obtain the historical actual output wind energy prediction error of the wind farm, and the multivariate Gaussian distribution is used to model the error to obtain the joint probability distribution of the node-to-electricity price prediction error. Use the multivariate Gaussian distribution to model the probability distribution of the error sequence, and use the maximum likelihood method to estimate the position parameters and covariance matrix of the multivariate Gaussian distribution, that is, the joint probability distribution of the error can be represented by the multivariate Gaussian distribution, and realized based on the joint probability distribution Modifications to the prediction model for initial wind energy data.

在一种可行的实施方式中,根据风力发电场的历史实际输出风能预测误差,对初始风能数据预测模型的修正的步骤,包括:In a feasible implementation manner, according to the historical actual output wind energy prediction error of the wind farm, the step of correcting the initial wind energy data prediction model includes:

基于多元高斯分布对风力发电场的历史实际输出风能预测误差进行建模,以实现对初始风能数据预测模型的修正。Based on the multivariate Gaussian distribution, the historical actual output wind energy prediction error of the wind farm is modeled to realize the correction of the initial wind energy data prediction model.

在一种可行的实施方式中,在根据所述风能数据预测模型的历史风能数据预测序列,对所述初始风能数据预测模型进行修正,获得目标风能数据预测模型的步骤之后,所述方法还包括:In a feasible implementation manner, after correcting the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model to obtain a target wind energy data prediction model, the method further includes :

将目标风能数据预测模型的预测错误率最低确定为第一优化函数的优化方向;The lowest prediction error rate of the target wind energy data prediction model is determined as the optimization direction of the first optimization function;

将目标风能数据预测模型的多样性指标值最高确定为所述第二优化函数的优化方向;determining the highest diversity index value of the target wind energy data prediction model as the optimization direction of the second optimization function;

根据及所述第一优化函数的优化方向和所述第二优化函数的优化方向,对所述目标风能数据预测模型进行优化。The target wind energy data prediction model is optimized according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.

在本实施方式中,在获得目标风能数据预测模型之后,为了进一步对模型进行优化,可以从风能数据预测模型的预测错误率和目标风能数据预测模型的多样性指标值两个方面进行多目标优化。首先,确定本次优化的优化算法,优化算法可以选择第二代非劣排序遗传进化算法,第二代非劣排序遗传进化算法优点在于探索性能较好,在非支配排序中,接近帕累托前沿的个体被选择,使帕累托前进能力增强。为了保证目标风能数据预测模型的预测错误率最小化,将目标风能数据预测模型的预测错误率作为第一优化函数,优化方向为最小化,比例因子为0.2,权重为1.0;为了保证目标风能数据预测模型的多样性指标值能够最优,将目标风能数据预测模型的多样性指标值作为第二优化函数,优化方向为最大化,比例因子为0.0002,权重r为2.0。在确定第一优化函数和第二优化函数的参数之后,根据第一优化函数和第二优化函数二对目标风能数据预测模型进行优化,获得满足多目标优化需求的风能数据预测模型,在风能数据预测模型之后,可以根据帕累托支配关系确定出风能数据预测模型的参数解集。而获得风能数据预测模型的参数解集是通过剔除具有被支配关系的帕累托解来实现的。In this embodiment, after obtaining the target wind energy data prediction model, in order to further optimize the model, multi-objective optimization can be carried out from two aspects: the prediction error rate of the wind energy data prediction model and the diversity index value of the target wind energy data prediction model . First, determine the optimization algorithm for this optimization. The optimization algorithm can choose the second-generation non-inferior sorting genetic evolution algorithm. The advantage of the second-generation non-inferior sorting genetic evolution algorithm is that it has better exploration performance. In non-dominated sorting, it is close to Pareto Frontier individuals are selected to enhance Pareto forward capability. In order to ensure that the prediction error rate of the target wind energy data prediction model is minimized, the prediction error rate of the target wind energy data prediction model is used as the first optimization function, the optimization direction is minimized, the scale factor is 0.2, and the weight is 1.0; in order to ensure the target wind energy data The diversity index value of the prediction model can be optimal, and the diversity index value of the target wind energy data prediction model is used as the second optimization function, the optimization direction is maximization, the scale factor is 0.0002, and the weight r is 2.0. After determining the parameters of the first optimization function and the second optimization function, optimize the target wind energy data prediction model according to the first optimization function and the second optimization function two, and obtain a wind energy data prediction model that meets the requirements of multi-objective optimization. After the data prediction model, the parameter solution set of the wind energy data prediction model can be determined according to the Pareto dominance relationship. Obtaining the parameter solution set of the wind energy data prediction model is achieved by eliminating the Pareto solution with the dominated relationship.

作为示例的,若对于编号为A、B、C、和D的风能数据预测模型的参数解,根据适应度计算结果,发现A支配B,D支配C,且A和D之间不存在支配关系,则可以将B和C剔除,将A和D作为风能数据预测模型的参数解。As an example, if for the parameter solutions of the wind energy data prediction models numbered A, B, C, and D, according to the fitness calculation results, it is found that A dominates B, D dominates C, and there is no dominance relationship between A and D , then B and C can be eliminated, and A and D can be used as the parameter solution of the wind energy data prediction model.

而在获得风能数据预测模型的参数解集之后,需要选择分布性最好的解作为风能数据预测模型最终的模型参数进行固化,而判断每个风能预测模型的参数解的稀疏度,是通过判断风能预测模型的参数解相邻区域内其他风能预测模型的参数解的数量,来进行确定的,相邻区域内其他风能预测模型的参数解的数量越少,则该风能预测模型的参数解的分布性越好,相邻区域内其他风能预测模型的参数解的数量越多,则该风能预测模型的参数解的分布性越差。以风能数据预测模型的预测错误率为横轴,以风能数据预测模型的多样性指标值为纵轴,建立坐标系。在该坐标系下,预测模型的参数解对应的圆的范围则表征该风能预测模型的参数解的小生境范围预测模型的参数解在坐标系中的相邻预测模型的参数解越多,则该预测模型的参数解的稀疏度越低,分布性越差。而在确定分布性最好的风能预测模型的参数之后,将其参数进行固化,并将固化后的目标风能数据预测模型用于对风力发电场下一周期的实际输出风能数据的预测。After obtaining the parameter solution set of the wind energy data prediction model, it is necessary to select the solution with the best distribution as the final model parameter of the wind energy data prediction model for solidification, and to judge the sparsity of the parameter solution of each wind energy prediction model is to judge The parameter solution of the wind energy prediction model is determined by the number of parameter solutions of other wind energy prediction models in the adjacent area. The smaller the number of parameter solutions of other wind energy prediction models in the adjacent area, the distribution of the parameter solutions of the wind energy prediction model The better, the more the number of parameter solutions of other wind energy prediction models in the adjacent area, the worse the distribution of the parameter solutions of this wind energy prediction model. The horizontal axis is the prediction error rate of the wind energy data prediction model, and the vertical axis is the diversity index value of the wind energy data prediction model to establish a coordinate system. In this coordinate system, the range of the circle corresponding to the parameter solution of the prediction model represents the niche range of the parameter solution of the wind energy prediction model. The lower the sparsity of the parameter solution of the predictive model, the worse the distribution. After determining the parameters of the wind energy prediction model with the best distribution, its parameters are solidified, and the solidified target wind energy data prediction model is used to predict the actual output wind energy data of the wind farm in the next period.

在获得目标风能数据预测模型之后,基于目标风能数据预测模型对风力发电场下一周期的实际输出风能数据进行预测,其具体的步骤包括:After the target wind energy data prediction model is obtained, the actual output wind energy data of the wind farm in the next cycle is predicted based on the target wind energy data prediction model, and the specific steps include:

S101:获得风机设备的历史产能数据,以及风电场所处区域下一周期的预估天气数据。S101: Obtain historical production capacity data of the wind turbine equipment, and forecast weather data of the area where the wind farm site is located in the next cycle.

在本实施方式中,对于一个风力发电场,可以将其的设备主要分为两种类型,一种类型是风机设备,即风力发电机组,用于将风能转换为电能,另一种类型是电力装备,如无功补偿装置等。而在风电场中,根据电网的要求,故障期间风电场需向电网提供一定量的动态无功支撑。无功补偿装置对风电场并网点的无功补偿速度比风电机组更快,所以风电机组通过风电转换后得到的电能还需要用于风电场内的电力装备的协调与工作。因此,风电场实际输出的电能不等于风机设备实际产生的电能。In this embodiment, for a wind farm, its equipment can be mainly divided into two types, one type is fan equipment, that is, wind power generators, which are used to convert wind energy into electrical energy, and the other type is electrical Equipment, such as reactive power compensation device, etc. In the wind farm, according to the requirements of the grid, the wind farm needs to provide a certain amount of dynamic reactive power support to the grid during the fault period. The reactive power compensation device can compensate the reactive power of the grid-connected point of the wind farm faster than the wind turbine, so the electric energy obtained by the wind turbine through wind power conversion also needs to be used for the coordination and work of the power equipment in the wind farm. Therefore, the actual output power of the wind farm is not equal to the power actually generated by the wind turbine equipment.

风机设备的历史产能数据可以为风机设备之前时间段的实际电能生产数据,时间段可以采用月为单位,也可以采用季度为单位,通过生产部门发布的报表即可获取。预估天气数据可以为气象部分发布的风电场所处区域的天气预报。The historical production capacity data of the fan equipment can be the actual power production data of the fan equipment in the previous time period. The time period can be taken as a month or a quarter, and can be obtained through the report issued by the production department. The predicted weather data may be the weather forecast of the area where the wind farm is located issued by the meteorological department.

作为示例的,风机设备的历史产能数据可以为某某风电场第一季度的生产报表,风电场所处区域下一周期的预估天气数据可以为电视台发布的某某地区未来几日的天气预报。As an example, the historical production capacity data of wind turbine equipment can be the production report of a certain wind farm in the first quarter, and the forecast weather data of the area where the wind farm is located in the next cycle can be the weather forecast for the next few days in a certain area released by a TV station.

在一种可行的实施方式中,预估天气数据至少包括风向参数、风速参数、气温参数、气压参数、以及湿度参数中的一个。In a feasible implementation manner, the predicted weather data includes at least one of a wind direction parameter, a wind speed parameter, a temperature parameter, a pressure parameter, and a humidity parameter.

在本实施方式中,对于风能发电,直接对其产生影响的因素为风速,而风速可以根据预估天气数据中的任意一项参数,与预设天气数据与风速数据之间的映射关系来进行确定。天气数据与风速数据之间的映射关系可以通过天气数据与风速数据全国的平均数据的映射关系来进行确定,也可以根据该地区实际的天气数据与风速数据的映射关系来进行确定。In this embodiment, for wind power generation, the factor that directly affects it is the wind speed, and the wind speed can be determined according to any parameter in the forecast weather data and the mapping relationship between the preset weather data and the wind speed data. Sure. The mapping relationship between weather data and wind speed data can be determined through the mapping relationship between weather data and the national average data of wind speed data, or can be determined according to the mapping relationship between the actual weather data and wind speed data in the region.

S102:根据风机设备的历史产能数据和风电场所处区域下一周期的预估天气数据,构建第一输入特征。S102: Construct a first input feature according to the historical production capacity data of the wind turbine equipment and the forecast weather data of the region where the wind farm is located in the next cycle.

在本实施方式中,在获得风机设备的历史产能数据和风电场所处区域下一周期的预估天气数据之后,由于其各自采用的时间单位并不相同,因此需要对其进行以时间为单位,对其进行规整处理,并基于处理后的数据构建第一输入特征。In this embodiment, after obtaining the historical production capacity data of the wind turbine equipment and the forecast weather data of the next period in the area where the wind farm is located, since the time units used are different, it is necessary to take time as the unit, It is normalized and the first input features are constructed based on the processed data.

S103:获取电力装备当前周期的同步稳定值,并根据电力装备当前周期的同步稳定值,构建第二输入特征。S103: Obtain the synchronization stable value of the current period of the electric equipment, and construct the second input feature according to the synchronization stability value of the current period of the electric equipment.

在本实施方式中,同步稳定值,同步稳定值用于表征电力装备与风电场的连接稳定状态,同步稳定裕度的判别如下:若同步稳定值等于100%,表明电力装备与风电场的连接稳定状态为最稳定的状态;若电力装备与风电场的连接稳定状态等于0,电力装备与风电场的连接稳定状态为最不稳定的状态,因此风电场的电力系统不具有任何抗扰能力。在实际生产中,同步稳定值位于0到1之间,同步稳定值越大稳定性越高。In this embodiment, the synchronous stability value is used to represent the stable state of the connection between the power equipment and the wind farm, and the discrimination of the synchronous stability margin is as follows: if the synchronous stability value is equal to 100%, it indicates that the connection between the power equipment and the wind farm is The stable state is the most stable state; if the stable state of the connection between the power equipment and the wind farm is equal to 0, the stable state of the connection between the power equipment and the wind farm is the most unstable state, so the power system of the wind farm does not have any anti-interference ability. In actual production, the synchronous stable value is between 0 and 1, and the greater the synchronous stable value, the higher the stability.

在获得电力装备的当前周期的同步稳定值,对其进行规整处理,并基于处理后的数据构建第二输入特征。After obtaining the synchronous stable value of the current period of the electric equipment, regularize it, and construct the second input feature based on the processed data.

而获取力装备当前周期的同步稳定值的步骤包括:The steps to obtain the synchronous stable value of the current cycle of the force equipment include:

S103-1:根据电力装备当前周期的电力运行参数,计算电力装备当前周期的阻抗压降参数。S103-1: Calculate the impedance voltage drop parameter of the current period of the electric equipment according to the electric power operation parameters of the current period of the electric equipment.

在本实施方式中,电力运行参数可以为电网电压幅值和电力装备的机端电压额定值,而确定阻抗压降参数的步骤可以为:In this embodiment, the power operation parameters may be the grid voltage amplitude and the rated value of the machine terminal voltage of the power equipment, and the step of determining the impedance voltage drop parameter may be:

S103-1-1:根据电网电压幅值和电力装备的机端电压额定值,计算电力装备的机端电压向量;S103-1-1: Calculate the terminal voltage vector of the electric equipment according to the grid voltage amplitude and the terminal voltage rating of the electric equipment;

S103-1-2:将电力装备的机端电压向量分解为交轴方向的分量;S103-1-2: Decompose the terminal voltage vector of the electric equipment into components in the quadrature direction;

S103-1-3:根据电力装备的交轴分量,计算电力装备当前周期的阻抗压降参数。S103-1-3: Calculate the impedance voltage drop parameter of the current period of the electric equipment according to the quadrature axis component of the electric equipment.

在S103-1-1至S103-1-3的实施方式中,电网电压幅值可通过离线等值计算或在线辨识得到,电力装备的机端电压额定值可由场站业主提供的数据查询获得,根据电网电压幅值和电力装备的机端电压额定值,计算电力装备的机端电压向量,然后将电力装备机端电压向量在锁相环坐标系中分解为直轴和交轴分量,最后根据电力装备的交轴分量,计算电力装备当前周期的阻抗压降参数。电力装备与电网的同步要求阻抗压降越小越好,由于阻抗压降的存在,机端电压受到一定程度的影响,进而对电力装备的同步稳定性产生影响。In the implementations of S103-1-1 to S103-1-3, the voltage amplitude of the power grid can be obtained through offline equivalent calculation or online identification, and the rated value of the terminal voltage of the power equipment can be obtained from the data query provided by the station owner. According to the voltage amplitude of the grid and the rated value of the terminal voltage of the power equipment, the terminal voltage vector of the power equipment is calculated, and then the terminal voltage vector of the power equipment is decomposed into direct-axis and quadrature-axis components in the phase-locked loop coordinate system, and finally according to The quadrature axis component of the power equipment is used to calculate the impedance voltage drop parameter of the current period of the power equipment. The synchronization between power equipment and the power grid requires that the impedance voltage drop be as small as possible. Due to the existence of impedance voltage drop, the machine terminal voltage is affected to a certain extent, which in turn affects the synchronization stability of power equipment.

S103-2:根据电力装备在执行无功补偿时,对风机设备的影响能力,计算电力装备当前周期的无功补偿特性参数;S103-2: Calculate the reactive power compensation characteristic parameters of the current period of the power equipment according to the influence ability of the power equipment on the fan equipment when performing reactive power compensation;

S103-3:根据电力装备当前周期的阻抗压降参数和电力装备当前周期的无功补偿特性参数,计算电力装备当前周期的同步稳定值。S103-3: Calculate the synchronous stable value of the current period of the electric equipment according to the impedance voltage drop parameter of the current period of the electric equipment and the reactive power compensation characteristic parameter of the current period of the electric equipment.

在S103-2至S103-3的实施方式中,无功补偿特性参数用于表征风电场的暂态故障穿越能力,本申请中构造风电场无功优化函数,通过在线求解该风电场无功优化函数,获得集中式无功补偿装置无功容量使用最少的工作点In the implementation of S103-2 to S103-3, the reactive power compensation characteristic parameters are used to characterize the transient fault ride-through capability of the wind farm. In this application, the reactive power optimization function of the wind farm is constructed, and the reactive power optimization function of the wind farm is solved online function to obtain the operating point where the reactive power capacity of the centralized reactive power compensation device is used the least

无功补偿装置最少的工作点对应的参数即为无功补偿特性参数,在获取到电力述电力装备当前周期的阻抗压降参数和电力装备当前周期的无功补偿特性参数之后,按照同步稳定值的计算公式,即可获得电力装备当前周期的同步稳定值。The parameter corresponding to the least working point of the reactive power compensation device is the reactive power compensation characteristic parameter. The calculation formula can be used to obtain the synchronous stable value of the current period of the power equipment.

S104:将第一输入特征和第二输入特征,输入预先训练得到的风能数据预测模型,输出得到风电场下一周期的实际输出风能预测数据。S104: Input the first input feature and the second input feature into the pre-trained wind energy data prediction model, and output the actual output wind energy forecast data of the next cycle of the wind farm.

在本实施方式中,在构建风电场的第一输入特征和第二输入特征之后,需要根据第一输入特征和第二输入特征对风电场下一周期的实际输出风能预测数据,即将生产电能减去用于电力系统维护系统稳态的电能,In this embodiment, after constructing the first input feature and the second input feature of the wind farm, it is necessary to predict the actual output wind energy data of the wind farm in the next cycle according to the first input feature and the second input feature, that is, to reduce the production power The electric energy used to maintain the steady state of the power system,

因此将第一输入特征和第二输入特征到预先训练好的风能数据预测模型中,从而获得风电场对在下一周期的预测的实际输出风能数据,该预测电价是一种短期的预测数据。Therefore, the first input feature and the second input feature are put into the pre-trained wind energy data forecasting model, so as to obtain the actual output wind energy data of the wind farm for the forecast in the next period, and the forecast electricity price is a short-term forecast data.

本发明通过获得风机设备的历史产能数据,以及风电场所处区域下一周期的预估天气数据,并根据风机设备的历史产能数据和风电场所处区域下一周期的预估天气数据,构建第一输入特征,然后,获取电力装备当前周期的同步稳定值,并根据电力装备当前周期的同步稳定值,构建第二输入特征,最后,将第一输入特征和第二输入特征,输入预先训练得到的风能数据预测模型,输出得到风电场下一周期的实际输出风能预测数据。在本发明中,将电力设备在运行过程中对风力发电场的实际输出电能的影响,也作为预测风电场实际输出的风能数据的参考条件,使得预测的结果更加准确,并且能够为风电场中各类设备的正常运行提供足够的电能预留空间。并且能够提升风电场故障阶段的动态无功支撑能力,还能够维持风电机组机端电压在合理的运行区间,保证风电机组的运行安全。The present invention obtains the historical production capacity data of the wind turbine equipment and the forecast weather data of the next period of the area where the wind farm is located, and constructs the first Input features, then, obtain the synchronous stable value of the current period of the electric equipment, and construct the second input feature according to the synchronous stable value of the current period of the electric equipment, finally, input the first input feature and the second input feature into the pre-trained Wind energy data prediction model, the output is the actual output wind energy forecast data of the next cycle of the wind farm. In the present invention, the influence of power equipment on the actual output electric energy of the wind farm during operation is also used as a reference condition for predicting the wind energy data actually output by the wind farm, so that the predicted results are more accurate and can be used in wind farms. The normal operation of all kinds of equipment provides enough power reserve space. And it can improve the dynamic reactive power support capability of the wind farm in the fault stage, and can also maintain the terminal voltage of the wind turbine in a reasonable operating range to ensure the safe operation of the wind turbine.

本发明实施例还提供了一种风力发电场风能预测系统,参照图2,示出了本发明一种风力发电场风能预测系统实施例第一方面的功能模块图,系统包括:The embodiment of the present invention also provides a wind energy forecasting system for a wind farm. Referring to FIG. 2 , it shows a functional block diagram of the first aspect of an embodiment of a wind energy forecasting system for a wind farm according to the present invention. The system includes:

风机参数获取模块201,用于获得风机设备的历史产能数据,以及风电场所处区域下一周期的预估天气数据;The wind turbine parameter acquisition module 201 is used to obtain the historical production capacity data of the wind turbine equipment, and the forecast weather data of the area where the wind farm is located in the next period;

第一特征构建模块202,用于根据风机设备的历史产能数据和风电场所处区域下一周期的预估天气数据,构建第一输入特征;The first feature construction module 202 is used to construct the first input feature according to the historical production capacity data of the wind turbine equipment and the forecast weather data of the area where the wind farm is located in the next cycle;

电力装备参数获取模块203,用于获取电力装备当前周期的同步稳定值;The power equipment parameter acquisition module 203 is used to acquire the synchronous stable value of the current period of the power equipment;

第二特征构建模块204,用于根据电力装备当前周期的同步稳定值,构建第二输入特征,其中,同步稳定值用于表征电力装备与风电场的连接稳定状态;The second feature construction module 204 is configured to construct a second input feature according to the synchronization stable value of the current cycle of the electric equipment, wherein the synchronization stable value is used to represent the stable state of the connection between the electric equipment and the wind farm;

预测模块205,用于将第一输入特征和第二输入特征,输入预先训练得到的风能数据预测模型,输出得到风电场下一周期的实际输出风能预测数据。The forecasting module 205 is configured to input the first input feature and the second input feature into the pre-trained wind energy data forecasting model, and output the actual output wind energy forecasting data of the next cycle of the wind farm.

在一种可行的实施方式中,电力装备参数获取模块包括:In a feasible implementation manner, the power equipment parameter acquisition module includes:

阻抗压降计算子模块,用于根据电力装备当前周期的电力运行参数,计算电力装备当前周期的阻抗压降参数;The impedance voltage drop calculation sub-module is used to calculate the impedance voltage drop parameter of the current cycle of the power equipment according to the power operation parameters of the current cycle of the power equipment;

无功补偿特性参数计算子模块,用于根据电力装备在执行无功补偿时,对风机设备的影响能力,计算电力装备当前周期的无功补偿特性参数;The reactive power compensation characteristic parameter calculation sub-module is used to calculate the reactive power compensation characteristic parameters of the current period of the electric power equipment according to the ability of the electric power equipment to influence the fan equipment when performing reactive power compensation;

同步稳定值计算子模块,用于根据电力装备当前周期的阻抗压降参数和电力装备当前周期的无功补偿特性参数,计算电力装备当前周期的同步稳定值。The synchronous stable value calculation sub-module is used to calculate the synchronous stable value of the current period of the electric equipment according to the impedance voltage drop parameter of the current period of the electric equipment and the reactive power compensation characteristic parameter of the current period of the electric equipment.

在一种可行的实施方式中,阻抗压降计算子模块包括:In a feasible implementation manner, the impedance drop calculation submodule includes:

机端电压计算单元,用于向量根据电网电压幅值和电力装备的机端电压额定值,计算电力装备的机端电压向量;The machine terminal voltage calculation unit is used to calculate the machine terminal voltage vector of the power equipment according to the grid voltage amplitude and the machine terminal voltage rating of the power equipment;

划分单元,用于将电力装备的机端电压向量分解为交轴方向的分量;The division unit is used to decompose the machine terminal voltage vector of the power equipment into components in the direction of the quadrature axis;

阻抗压降参数计算单元,用于根据电力装备的交轴分量,计算电力装备当前周期的阻抗压降参数。The impedance voltage drop parameter calculation unit is used to calculate the impedance voltage drop parameter of the current period of the electric equipment according to the quadrature axis component of the electric equipment.

在一种可行的实施方式中,系统还包括模型训练单元,模型训练模块包括:In a feasible implementation manner, the system also includes a model training unit, and the model training module includes:

第一特征获取子模块,用于获取风机设备的样本历史产能数据以及风电场所处区域的样本历史天气数据,并进行规整处理,获得第一输入特征样本;The first feature acquisition sub-module is used to acquire the sample historical production capacity data of the wind turbine equipment and the sample historical weather data of the area where the wind farm is located, and perform normalization processing to obtain the first input feature sample;

第二特征获取子模块,用于获取电力装备的样本历史同步稳定值,并进行规整处理,获得第二输入特征样本;The second feature acquisition sub-module is used to acquire the sample history synchronous stable value of the electric equipment, and perform normalization processing to obtain the second input feature sample;

训练子模块,用于根据第一输入特征样本和第二输入特征样本,对预设的随机森林模型进行训练和交叉验证,获得初始风能数据预测模型和风能数据预测模型的历史风能数据预测序列;The training sub-module is used to train and cross-validate the preset random forest model according to the first input feature sample and the second input feature sample, and obtain the initial wind energy data prediction model and the historical wind energy data prediction sequence of the wind energy data prediction model;

修正子模块,用于根据风能数据预测模型的历史风能数据预测序列,对初始风能数据预测模型进行修正,获得目标风能数据预测模型。The correction sub-module is used to correct the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model, and obtain the target wind energy data prediction model.

在一种可行的实施方式中,修正子模块包括:In a feasible implementation manner, the correction submodule includes:

获取单元,用于获取风力发电场的历史实际输出风能数据;The obtaining unit is used to obtain the historical actual output wind energy data of the wind farm;

误差确定单元,用于根据历史风能数据预测序列与历史实际输出风能数据,计算风力发电场的历史实际输出风能预测误差;The error determination unit is used to calculate the historical actual output wind energy prediction error of the wind farm according to the historical wind energy data prediction sequence and the historical actual output wind energy data;

模型修正单元,用于根据风力发电场的历史实际输出风能预测误差,对初始风能数据预测模型的修正。The model correction unit is used for correcting the initial wind energy data prediction model according to the historical actual output wind energy prediction error of the wind farm.

在一种可行的实施方式中,第一优化单元,用于将目标风能数据预测模型的预测错误率最低确定为第一优化函数的优化方向;In a feasible implementation manner, the first optimization unit is configured to determine the lowest prediction error rate of the target wind energy data prediction model as the optimization direction of the first optimization function;

第二优化单元,用于将目标风能数据预测模型的多样性指标值最高确定为所述第二优化函数的优化方向;The second optimization unit is configured to determine the highest diversity index value of the target wind energy data prediction model as the optimization direction of the second optimization function;

模型优化单元,用于根据及所述第一优化函数的优化方向和所述第二优化函数的优化方向,对所述目标风能数据预测模型进行优化。A model optimization unit, configured to optimize the target wind energy data prediction model according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.

基于同一发明构思,本申请的实施例还提出了一种电子设备,电子设备包括:Based on the same inventive concept, an embodiment of the present application also proposes an electronic device, which includes:

至少一个处理器;以及,与至少一个处理器通信连接的存储器;其中,存储器存储有可被至少一个处理器执行的指令,指令被至少一个处理器执行,以使至少一个处理器能够执行本申请实施例的风力发电场风能预测方法。At least one processor; and, a memory connected in communication with the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform the present application The wind energy forecasting method of the wind farm of the embodiment.

此外,为实现上述目的,本申请的实施例还提出了一种计算机可读存储介质,存储有计算机程序,计算机程序被处理器执行时实现本申请实施例的风力发电场风能预测方法。In addition, to achieve the above purpose, the embodiment of the present application also proposes a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for wind energy prediction of a wind farm in the embodiment of the present application is realized.

本领域内的技术人员应明白,本发明实施例的实施例可提供为方法、装置、或计算机程序产品。因此,本发明实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本发明实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用储存介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, devices, or computer program products. Accordingly, embodiments of the invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

本发明实施例是参照根据本发明实施例的方法、终端设备(装置)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理终端设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理终端设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。Embodiments of the present invention are described with reference to flowcharts and/or block diagrams of methods, terminal devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor or processor of other programmable data processing terminal equipment to produce a machine such that instructions executed by the computer or processor of other programmable data processing terminal equipment Produce means for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理终端设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the The instruction means implements the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

这些计算机程序指令也可装载到计算机或其他可编程数据处理终端设备上,使得在计算机或其他可编程终端设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程终端设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions can also be loaded into a computer or other programmable data processing terminal equipment, so that a series of operational steps are performed on the computer or other programmable terminal equipment to produce computer-implemented processing, thereby The instructions executed above provide steps for implementing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

最后,还需要说明的是,在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。“和/或”表示可以选择两者之中的任意一个,也可以两者都选择。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者终端设备不仅包括哪些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者终端设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者终端设备中还存在另外的相同要素。Finally, it should also be noted that in this text, relational terms such as first and second etc. are only used to distinguish one entity or operation from another, and do not necessarily require or imply that these entities or operations, any such actual relationship or order exists. "And/or" means that either one of the two can be selected, or both can be selected. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or terminal equipment that includes a set of elements not only includes those elements, but also includes elements not expressly listed. other elements identified, or also include elements inherent in such a process, method, article, or terminal equipment. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising said element.

以上对本发明所提供的一种风力发电场风能预测方法以及系统,进行了详细介绍,本文中应用了具体个例对本发明的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本发明的方法及其核心思想;同时,对于本领域的一般技术人员,依据本发明的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。The method and system for forecasting wind energy of a wind farm provided by the present invention have been introduced in detail above. In this paper, specific examples have been used to illustrate the principle and implementation of the present invention. The descriptions of the above embodiments are only used to help understanding The method of the present invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation and scope of application. In summary, the content of this specification should not be construed as a limitation of the invention.

Claims (8)

1. A method of wind energy prediction for a wind farm, the method comprising:
obtaining historical capacity data of fan equipment and estimated weather data of the next period of an area at a wind power station;
constructing a first input feature according to the historical capacity data of the fan equipment and the estimated weather data of the next period of the area of the wind power station;
acquiring a synchronous stable value of a current period of the electric power equipment, and constructing a second input characteristic according to the synchronous stable value of the current period of the electric power equipment, wherein the synchronous stable value is used for representing a connection stable state of the electric power equipment and the wind power plant;
Inputting the first input characteristic and the second input characteristic into a pre-trained wind energy data prediction model, and outputting to obtain actual output wind energy prediction data of the next period of the wind power plant;
the step of obtaining the synchronous stable value of the current period of the power equipment comprises the following steps:
calculating an impedance voltage drop parameter of the current period of the electric power equipment according to the electric power operation parameter of the current period of the electric power equipment;
calculating reactive compensation characteristic parameters of the current period of the electric power equipment according to the influence capacity of the electric power equipment on the fan equipment when reactive compensation is executed;
and calculating a synchronous stable value of the current period of the electric power equipment according to the impedance voltage drop parameter of the current period of the electric power equipment and the reactive compensation characteristic parameter of the current period of the electric power equipment.
2. The method of claim 1, wherein the power operating parameters include a grid voltage magnitude and a terminal voltage rating of the power equipment, and wherein the step of calculating an impedance drop parameter for a current cycle of the power equipment based on the power operating parameter for the current cycle of the power equipment comprises:
Calculating a machine-side voltage vector of the electric power equipment according to the power grid voltage amplitude and a machine-side voltage rated value of the electric power equipment;
decomposing a machine-side voltage vector of the electric power equipment into components in the quadrature axis direction;
and calculating the impedance voltage drop parameter of the current period of the electric power equipment according to the quadrature axis component of the electric power equipment.
3. The method of claim 1, wherein the wind energy data prediction model is obtained by:
acquiring sample historical capacity data of the fan equipment and sample historical weather data of an area at the wind power station, and performing normalization processing to obtain a first input characteristic sample;
acquiring a sample history synchronous stable value of the electric power equipment, and performing normalization processing to acquire a second input characteristic sample;
training and cross-verifying a preset random forest model according to the first input characteristic sample and the second input characteristic sample to obtain an initial wind energy data prediction model and a historical wind energy data prediction sequence of the wind energy data prediction model;
and correcting the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model to obtain a target wind energy data prediction model.
4. A method of wind energy prediction of a wind farm according to claim 3, wherein the step of modifying the initial wind energy data prediction model according to a historical wind energy data prediction sequence of the wind energy data prediction model comprises:
acquiring historical actual output wind energy data of a wind power plant;
according to the historical wind energy data prediction sequence and the historical actual output wind energy data, calculating a historical actual output wind energy prediction error of the wind power plant;
and correcting the initial wind energy data prediction model according to the wind energy prediction error actually output by the history of the wind power plant.
5. The method of wind farm wind energy prediction according to claim 4, wherein the step of modifying the initial wind energy data prediction model based on historical actual output wind energy prediction errors of the wind farm comprises:
modeling a historical actual output wind energy prediction error of the wind power plant based on a multivariate Gaussian distribution to realize correction of the initial wind energy data prediction model.
6. A method of wind energy prediction of a wind farm according to claim 3, wherein after the step of modifying the initial wind energy data prediction model to obtain a target wind energy data prediction model according to a historical wind energy data prediction sequence of the wind energy data prediction model, the method further comprises:
Determining the lowest prediction error rate of the target wind energy data prediction model as the optimization direction of a first optimization function;
determining the highest diversity index value of the target wind energy data prediction model as the optimization direction of a second optimization function;
and optimizing the target wind energy data prediction model according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.
7. A wind farm wind energy prediction system, the system comprising:
the wind power station comprises a wind power station, a wind power parameter acquisition module, a wind power generation module and a wind power generation module, wherein the wind power station is used for acquiring historical capacity data of wind power equipment and estimated weather data of the next period of an area of a wind power station;
the first characteristic construction module is used for constructing a first input characteristic according to the historical capacity data of the fan equipment and the estimated weather data of the next period of the area at the wind power station;
the power equipment parameter acquisition module is used for acquiring a synchronous stable value of the current period of the power equipment;
the second characteristic construction module is used for constructing a second input characteristic according to a synchronous stable value of the current period of the electric power equipment, wherein the synchronous stable value is used for representing the connection stable state of the electric power equipment and the wind power plant;
The prediction module is used for inputting the first input characteristic and the second input characteristic into a pre-trained wind energy data prediction model and outputting actual output wind energy prediction data of the next period of the wind power plant;
wherein, the electric power equipment parameter acquisition module includes:
the impedance voltage drop calculation sub-module is used for calculating the impedance voltage drop parameter of the current period of the electric power equipment according to the electric power operation parameter of the current period of the electric power equipment;
the reactive compensation characteristic parameter calculation submodule is used for calculating reactive compensation characteristic parameters of the current period of the electric power equipment according to the influence capacity of the electric power equipment on the fan equipment when reactive compensation is executed;
and the synchronous stable value calculation sub-module is used for calculating the synchronous stable value of the current period of the electric power equipment according to the impedance voltage drop parameter of the current period of the electric power equipment and the reactive compensation characteristic parameter of the current period of the electric power equipment.
8. The wind farm wind energy forecast system of claim 7, wherein the power operating parameters include grid voltage amplitude and terminal voltage rating of the power equipment, and wherein the impedance drop calculation submodule includes:
The machine end voltage calculation unit is used for calculating a machine end voltage vector of the electric power equipment according to the power grid voltage amplitude and the machine end voltage rated value of the electric power equipment;
the dividing unit is used for decomposing the machine-side voltage vector of the electric power equipment into components in the direction of the intersecting axis;
and the impedance voltage drop parameter calculation unit is used for calculating the impedance voltage drop parameter of the current period of the electric power equipment according to the quadrature axis component of the electric power equipment.
CN202211607577.XA 2022-12-14 2022-12-14 Wind energy forecasting method and system for a wind farm Active CN115936924B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211607577.XA CN115936924B (en) 2022-12-14 2022-12-14 Wind energy forecasting method and system for a wind farm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211607577.XA CN115936924B (en) 2022-12-14 2022-12-14 Wind energy forecasting method and system for a wind farm

Publications (2)

Publication Number Publication Date
CN115936924A CN115936924A (en) 2023-04-07
CN115936924B true CN115936924B (en) 2023-08-25

Family

ID=86553682

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211607577.XA Active CN115936924B (en) 2022-12-14 2022-12-14 Wind energy forecasting method and system for a wind farm

Country Status (1)

Country Link
CN (1) CN115936924B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119417071B (en) * 2025-01-09 2025-04-04 大连峰云智储科技有限公司 Virtual power plant capacity prediction method and system

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102842105A (en) * 2012-07-09 2012-12-26 中国电力科学研究院 Online transient state stability risk evaluating method for metering wind power uncertainty
CN103996087A (en) * 2014-06-09 2014-08-20 北京东润环能科技股份有限公司 Method and system for forecasting new energy power generation power
CN113361761A (en) * 2021-06-01 2021-09-07 山东大学 Short-term wind power integration prediction method and system based on error correction
WO2022033258A1 (en) * 2020-08-14 2022-02-17 中国科学院分子细胞科学卓越创新中心 Method and system for multi-step prediction of future wind speed based on automatic reservoir neural network
CN114418180A (en) * 2021-12-16 2022-04-29 广东电网有限责任公司 Ultra-short-term prediction method and device for wind power and storage medium
CN114465244A (en) * 2021-12-24 2022-05-10 国电南瑞科技股份有限公司 A method and device for controlling reactive power and voltage of large wind farms considering voltage regulation margin
CN114726009A (en) * 2022-06-09 2022-07-08 东南大学溧阳研究院 Wind power plant group reactive power hierarchical optimization control method and system considering power prediction
CN115081742A (en) * 2022-07-22 2022-09-20 北京东润环能科技股份有限公司 Ultra-short-term power prediction method for distributed wind power plant and related equipment

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6876406B2 (en) * 2016-10-20 2021-05-26 株式会社日立製作所 Voltage-disabled power operation support device and support method, and voltage-disabled power operation monitoring control device and monitoring control method
CN110892151B (en) * 2017-06-07 2021-04-30 维斯塔斯风力系统集团公司 Adaptive estimation of wind turbine available power

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102842105A (en) * 2012-07-09 2012-12-26 中国电力科学研究院 Online transient state stability risk evaluating method for metering wind power uncertainty
CN103996087A (en) * 2014-06-09 2014-08-20 北京东润环能科技股份有限公司 Method and system for forecasting new energy power generation power
WO2022033258A1 (en) * 2020-08-14 2022-02-17 中国科学院分子细胞科学卓越创新中心 Method and system for multi-step prediction of future wind speed based on automatic reservoir neural network
CN113361761A (en) * 2021-06-01 2021-09-07 山东大学 Short-term wind power integration prediction method and system based on error correction
CN114418180A (en) * 2021-12-16 2022-04-29 广东电网有限责任公司 Ultra-short-term prediction method and device for wind power and storage medium
CN114465244A (en) * 2021-12-24 2022-05-10 国电南瑞科技股份有限公司 A method and device for controlling reactive power and voltage of large wind farms considering voltage regulation margin
CN114726009A (en) * 2022-06-09 2022-07-08 东南大学溧阳研究院 Wind power plant group reactive power hierarchical optimization control method and system considering power prediction
CN115081742A (en) * 2022-07-22 2022-09-20 北京东润环能科技股份有限公司 Ultra-short-term power prediction method for distributed wind power plant and related equipment

Also Published As

Publication number Publication date
CN115936924A (en) 2023-04-07

Similar Documents

Publication Publication Date Title
Chang et al. A distributed robust optimization approach for the economic dispatch of flexible resources
CN112787329B (en) Optimal power flow calculation method containing wind power access based on robust cone planning
CN107689638B (en) A Transient Coordinated Control Method for Wind Power System Based on Phase Trajectory Analysis
Kamarposhti et al. Effect of wind penetration and transmission line development in order to reliability and economic cost on the transmission system connected to the wind power plant
CN113346484A (en) Power distribution network elasticity improving method and system considering transient uncertainty
CN116345565A (en) New energy and energy storage capacity combined optimization method, system, equipment and medium
CN115936924B (en) Wind energy forecasting method and system for a wind farm
CN104915788B (en) A method of considering the Electrical Power System Dynamic economic load dispatching of windy field correlation
Song et al. Korean renewables management system: copulas model-based adaptive droop control strategy for energy storage systems
Liu et al. A closed‐loop representative day selection framework for generation and transmission expansion planning with demand response
CN117134360B (en) Transmission and distribution cooperation high-convergence optimal power flow calculation method, device and medium
CN118017615A (en) Calculation method of electricity-hydrogen probabilistic energy flow considering uncertainty of wind-solar combined output
Paital et al. Reactive power compensation using PSO controlled UPFC in a microgrid with a DFIG based WECS
CN117371581A (en) New energy generated power prediction method, device and storage medium
CN116995740A (en) Distributed wind power and energy storage optimal configuration method and system for power distribution network
CN113484575B (en) Power angle search-based generator phase advance capability pre-evaluation method, equipment and medium
CN115456086A (en) An Accurate Equivalent Modeling Method for Wind Farm Based on Error Correction Model
Gao et al. A review of different methodologies for solving the problem of wind power's fluctuation
Ding et al. Multi-Objective optimial configuration of distributed wind-solar generation considering energy storage
CN115130923A (en) Intelligent energy management method and system for alternating current micro-grid
CN114649826A (en) A black-start zoning method and system considering wind farms
Cao et al. Equivalence method for wind farm based on clustering of output power time series data
Xu et al. A new approach for fast reliability evaluation of composite power system considering wind farm
Su et al. A novel data-driven robust method applied to OPF with uncertain wind power
Yang et al. Offshore Wind Power Prediction Based on Variational Mode Decomposition and Long Short Term Memory Networks

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant