CN116011657B - Optimization method, device and system for power distribution network load prediction model based on miniature PMU - Google Patents

Optimization method, device and system for power distribution network load prediction model based on miniature PMU Download PDF

Info

Publication number
CN116011657B
CN116011657B CN202310043210.8A CN202310043210A CN116011657B CN 116011657 B CN116011657 B CN 116011657B CN 202310043210 A CN202310043210 A CN 202310043210A CN 116011657 B CN116011657 B CN 116011657B
Authority
CN
China
Prior art keywords
load forecasting
model
task
meta
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
CN202310043210.8A
Other languages
Chinese (zh)
Other versions
CN116011657A (en
Inventor
李亦言
严正
谢伟
徐潇源
方陈
柳劲松
刘舒
张彦芝
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.)
Shanghai Jiao Tong University
Original Assignee
Shanghai Jiao Tong University
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 Shanghai Jiao Tong University filed Critical Shanghai Jiao Tong University
Priority to CN202310043210.8A priority Critical patent/CN116011657B/en
Publication of CN116011657A publication Critical patent/CN116011657A/en
Application granted granted Critical
Publication of CN116011657B publication Critical patent/CN116011657B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70Smart grids as climate change mitigation technology in the energy generation sector
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of situation awareness, in particular to a power distribution network load prediction model optimization method, device and system based on a miniature PMU. The method comprises the steps of obtaining task data of a sample load prediction task and a feature set F of the sample load prediction task; training a plurality of load prediction models according to task data of sample load prediction tasks, and acquiring a corresponding optimal load prediction model for solving each sample load prediction task based on root mean square error to form an optimal load prediction model set phi; the feature set F and the optimal load prediction model set phi are combined to form metadata<F,Φ>The method comprises the steps of carrying out a first treatment on the surface of the Utilizing metadata<F,Φ>Training the plurality of meta learners respectively to obtain a plurality of trained meta learners; processing the load prediction task feature set by using a plurality of trained meta learners to obtain a plurality of model recommendation result data
Figure DDA0004051289010000011
Recommending multiple models to result data
Figure DDA0004051289010000012
Obtaining single model recommendation result data through a voter
Figure DDA0004051289010000013

Description

基于微型PMU的配电网负荷预测模型优选方法、装置及系统Distribution network load forecasting model optimization method, device and system based on micro PMU

技术领域Technical Field

本发明涉及态势感知技术领域,尤其涉及基于微型PMU的配电网负荷预测模型优选方法、装置及系统。The present invention relates to the field of situation awareness technology, and in particular to a method, device and system for optimizing a load forecasting model for a distribution network based on a micro PMU.

背景技术Background Art

电力系统负荷预测是态势感知的重要组成部分,也是系统调度运行的基础支撑技术之一。同步相量测量单元(Phasor Measurement Unit,PMU)是利用GPS全球定位系统秒脉冲作为同步时钟构成的相量测量单元,能够赋予系统内全局量测数据统一的时标,同时能够直接测量配电网中的相量信息,量测数据同步性与准确度均能够得到保障,可用于电力系统的动态监测、系统保护和系统分析和预测等领域。近年来,由于PMU大量接入电力系统,极大地影响了电力系统的运行与控制,如何利用好电网中的微型PMU,并以适应配网需求的微型PMU技术为基础,研究下一代配网自动化系统关键支撑技术,已经成为能源及电力系统领域的重大科学命题。Load forecasting of power systems is an important part of situational awareness and one of the basic supporting technologies for system dispatching and operation. Synchronous phasor measurement unit (PMU) is a phasor measurement unit that uses the second pulse of the GPS global positioning system as a synchronous clock. It can give a unified time scale to the global measurement data in the system, and can directly measure the phasor information in the distribution network. The synchronization and accuracy of the measurement data can be guaranteed, and it can be used in the fields of dynamic monitoring, system protection, system analysis and prediction of power systems. In recent years, due to the large-scale access of PMU to the power system, the operation and control of the power system have been greatly affected. How to make good use of the micro PMU in the power grid and study the key supporting technologies of the next generation of distribution network automation system based on the micro PMU technology that adapts to the needs of the distribution network has become a major scientific proposition in the field of energy and power systems.

随着分布式电源的大规模接入,当前配电网的运行方式日趋灵活。例如装设光伏与储能系统的楼宇可作为产销者实现电能自给自足;系统中部分含源网络可作为微电网脱网独立运行;系统的网络拓扑可根据需要实现动态重构等等。为满足这些多样化的运行需求,需要相应的负荷预测技术为其提供支撑。图1从数据分辨率、负荷水平、影响因素、预测窗口、历史数据长度等五个维度描述了配电网中不同的负荷预测任务。例如其中红色五边形结合在一起,定义了单个用户的日前负荷预测任务,其数据分辨率为1小时,可用历史数据长度为1年,并且可使用温度作为影响要素进行建模。With the large-scale access of distributed power sources, the current operation mode of the distribution network is becoming more and more flexible. For example, buildings equipped with photovoltaic and energy storage systems can achieve self-sufficiency in electricity as producers and sellers; some source networks in the system can be disconnected and operated independently as microgrids; the network topology of the system can be dynamically reconstructed as needed, etc. In order to meet these diverse operating needs, corresponding load forecasting technologies are needed to support them. Figure 1 describes different load forecasting tasks in the distribution network from five dimensions: data resolution, load level, influencing factors, forecast window, and historical data length. For example, the red pentagons are combined to define the day-ahead load forecasting task for a single user, with a data resolution of 1 hour, an available historical data length of 1 year, and temperature can be used as an influencing factor for modeling.

从图1中可以看出,这些异质的预测任务在数据特征、预测需求等方面存在着显著的差异。As can be seen from Figure 1, these heterogeneous prediction tasks have significant differences in data characteristics, prediction requirements, etc.

1995年,D.H.Wolpert等人提出没有免费午餐定理(No Free Lunch Theorem):任何一个预测函数,如果在一些训练样本上表现好,那么必然在另一些训练样本上表现不好;如果不对数据在特征空间的先验分布有一定假设,那么表现好与表现不好的情况一样多。根据“No Free Lunch Theory”,这些异质的预测任务很难用同一个预测模型很好地解决。In 1995, D.H.Wolpert et al. proposed the No Free Lunch Theorem: Any prediction function that performs well on some training samples must perform poorly on other training samples; if there is no assumption about the prior distribution of data in the feature space, there will be as many cases of good performance as bad performance. According to the "No Free Lunch Theory", these heterogeneous prediction tasks are difficult to solve well with the same prediction model.

现有技术长短期记忆(Long short-term memory,LSTM)是一种特殊的RNN,将隐藏层的RNN细胞替换为LSTM细胞,使其具有长期记忆能力。经过不断演化,目前应用最为广泛的LSTM细胞结构如图2所示,z为输入模块,其前向计算方法可表示为Existing Technology Long short-term memory (LSTM) is a special RNN that replaces the RNN cells in the hidden layer with LSTM cells to enable it to have long-term memory capabilities. After continuous evolution, the most widely used LSTM cell structure is shown in Figure 2. z is the input module, and its forward calculation method can be expressed as

it=σ(Wxixt+Whiht-1+Wcict-1+bi) (1)i t =σ(W xi x t +W hi h t-1 +W ci c t-1 +b i ) (1)

ft=σ(Wxfxt+Whfht-1+Wcfct-1+bf) (2)f t =σ(W xf x t +W hf h t-1 +W cf c t-1 +b f ) (2)

ct=ftct-1+ittanh(Wxcxt+Whcht-1+bc) (3)c t =f t c t-1 +i t tanh(W xc x t +W hc h t-1 +b c ) (3)

ot=σ(Wxoxt+Whoht-1+Wcoct+bo) (4)o t =σ(W xo x t +W ho h t-1 +W co c t +b o ) (4)

ht=ottanh(ct) (5)h t = o t tanh(c t ) (5)

式中,i、f、c、o分别为输入门、遗忘门、细胞状态、输出门;W和b分别为对应的权重系数矩阵和偏置项;σ和tanh分别为sigmoid和双曲正切激活函数。Where i, f, c, and o are the input gate, forget gate, cell state, and output gate, respectively; W and b are the corresponding weight coefficient matrix and bias term, respectively; σ and tanh are the sigmoid and hyperbolic tangent activation functions, respectively.

LSTM模型训练过程大致可以分为四个步骤:按照式(1)~式(5)的前向计算方法计算LSTM细胞的输出值;反向计算每个LSTM细胞的误差项,包括按时间和网络层级2个反向传播方向;根据相应的误差项,计算每个权重的梯度;应用基于梯度的优化算法更新权重。The LSTM model training process can be roughly divided into four steps: calculate the output value of the LSTM cell according to the forward calculation method of equations (1) to (5); reversely calculate the error term of each LSTM cell, including two back propagation directions according to time and network level; calculate the gradient of each weight according to the corresponding error term; and apply the gradient-based optimization algorithm to update the weight.

LSTM网络非常适合基于时间序列数据进行分类、处理和预测,但并不一定适用于配电网中所有的负荷预测任务。这是因为LSTM模型所需训练样本数量较多,计算时间较长,对于小样本、实时要求高的预测场景难以适用。此外,部分预测任务历史负荷序列较为平滑,可由更为简洁的预测模型加以解决,无需引入LSTM模型。以上例子表明,LSTM并不是一种万能的预测方法能够解决配电网中异质的预测任务。而本文提出的模型优选架构,可针对不同的预测任务甄选最佳的预测模型,较好地解决了模型的适配问题。LSTM networks are very suitable for classification, processing and prediction based on time series data, but they are not necessarily suitable for all load forecasting tasks in distribution networks. This is because the LSTM model requires a large number of training samples and a long calculation time, which makes it difficult to apply to forecasting scenarios with small samples and high real-time requirements. In addition, the historical load series of some forecasting tasks are relatively smooth and can be solved by a simpler forecasting model without the introduction of the LSTM model. The above examples show that LSTM is not a universal forecasting method that can solve heterogeneous forecasting tasks in distribution networks. The model optimization architecture proposed in this article can select the best forecasting model for different forecasting tasks, which better solves the model adaptation problem.

发明内容Summary of the invention

为了解决上述现有技术中存在的技术问题,本发明提供了一种基于微型PMU的配电网负荷预测模型优选方法、装置及系统。In order to solve the technical problems existing in the above-mentioned prior art, the present invention provides a method, device and system for optimizing a distribution network load prediction model based on a micro PMU.

为实现上述目的,本发明实施例提供了如下的技术方案:To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

第一方面,在本发明提供的一个实施例中,提供了基于微型PMU的配电网负荷预测模型优选方法,该方法包括以下步骤:In a first aspect, in one embodiment provided by the present invention, a method for optimizing a distribution network load forecasting model based on a micro PMU is provided, the method comprising the following steps:

获取样本负荷预测任务的任务数据和样本负荷预测任务的特征集F;Obtaining task data of a sample load forecasting task and a feature set F of the sample load forecasting task;

根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ;Training multiple load forecasting models according to the task data of the sample load forecasting task, and obtaining the corresponding optimal load forecasting model for solving each sample load forecasting task based on the root mean square error to form an optimal load forecasting model set Φ;

将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ>;利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器;The feature set F and the optimal load forecasting model set Φ together constitute metadata <F,Φ>; using the metadata <F,Φ> to train multiple meta-learners respectively to obtain multiple trained meta-learners;

利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据

Figure BDA0004051288990000031
将所述多个模型推荐结果数据
Figure BDA0004051288990000032
通过投票器,获得单一模型推荐结果数据
Figure BDA0004051288990000033
Use multiple trained meta-learners to process the load forecasting task feature set and obtain multiple model recommendation result data
Figure BDA0004051288990000031
The plurality of model recommendation result data
Figure BDA0004051288990000032
Obtain single model recommendation result data through the voting machine
Figure BDA0004051288990000033

作为本发明的进一步方案,所述样本负荷预测任务数据包括J个数据样本对<Xj,yj>,其中,Xj是负荷预测模型的输入数据,其维度为Nj×Mj;yj是真实的负荷值,其维度为Nj×1,其中j∈[1,..,J]。As a further solution of the present invention, the sample load prediction task data includes J data sample pairs <X j ,y j >, where X j is the input data of the load prediction model with a dimension of N j ×M j ; y j is the actual load value with a dimension of N j ×1, where j∈[1,..,J].

作为本发明的进一步方案,所述Xj包括

Figure BDA0004051288990000034
Figure BDA0004051288990000035
yj包括
Figure BDA0004051288990000036
Figure BDA0004051288990000037
As a further embodiment of the present invention, the Xj comprises
Figure BDA0004051288990000034
and
Figure BDA0004051288990000035
y j includes
Figure BDA0004051288990000036
and
Figure BDA0004051288990000037

其中,所述

Figure BDA0004051288990000038
通过如下公式进行计算:Among them, the
Figure BDA0004051288990000038
Calculate using the following formula:

Figure BDA0004051288990000039
Figure BDA0004051288990000039

其中

Figure BDA00040512889900000311
表示第n个样本的第m个属性。针对第j个负荷预测任务,将负荷预测模型iB生成的预测结果记为
Figure BDA00040512889900000310
in
Figure BDA00040512889900000311
represents the mth attribute of the nth sample. For the jth load forecasting task, the forecast result generated by the load forecasting model i B is recorded as
Figure BDA00040512889900000310

作为本发明的进一步方案,所述特征集F的维度为J×D。As a further solution of the present invention, the dimension of the feature set F is J×D.

作为本发明的进一步方案,所述负荷预测模型进行如下公式计算:As a further solution of the present invention, the load forecasting model is calculated by the following formula:

Figure BDA0004051288990000041
Figure BDA0004051288990000041

Figure BDA0004051288990000042
Figure BDA0004051288990000042

其中

Figure BDA0004051288990000043
为衡量预测结果和真实结果之间距离的损失函数,θ*则是负荷预测模型iB的最优参数集合。in
Figure BDA0004051288990000043
is the loss function that measures the distance between the predicted result and the actual result, and θ * is the optimal parameter set of the load forecasting model i B.

作为本发明的进一步方案,所述元数据<F,Φ>分为元数据训练集<Ftraintrain>和元数据测试集<Ftesttest>。As a further solution of the present invention, the metadata <F, Φ> is divided into a metadata training set <F train , Φ train > and a metadata test set <F test , Φ test >.

作为本发明的进一步方案,所述利用所述元数据<F,Φ>对多个元学习器进行训练,获得训练后的元学习器,还包括:As a further solution of the present invention, the step of training a plurality of meta-learners using the metadata <F, Φ> to obtain trained meta-learners further includes:

训练过程中多个所述元学习器生成对应的多个训练模型推荐结果数据

Figure BDA0004051288990000044
During the training process, multiple meta-learners generate corresponding multiple training model recommendation result data
Figure BDA0004051288990000044

将所述多个训练模型推荐结果数据

Figure BDA0004051288990000045
通过投票器,获得单一训练模型推荐结果数据
Figure BDA0004051288990000046
The plurality of training model recommendation result data
Figure BDA0004051288990000045
Obtain the recommendation result data of a single training model through the voting machine
Figure BDA0004051288990000046

第二方面,在本发明提供的又一个实施例中,提供了基于微型PMU的配电网负荷预测模型优选装置,该装置包括:数据获取模块、第一训练模块、第二训练模块和应用模块;In a second aspect, in another embodiment provided by the present invention, a distribution network load forecasting model optimization device based on a micro PMU is provided, the device comprising: a data acquisition module, a first training module, a second training module and an application module;

所述数据获取模块,用于获取样本负荷预测任务的任务数据和样本负荷预测任务的特征集F,其中所述样本负荷预测任务包括J个样本负荷预测任务;The data acquisition module is used to acquire task data of a sample load prediction task and a feature set F of the sample load prediction task, wherein the sample load prediction task includes J sample load prediction tasks;

所述第一训练模块,用于根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ;The first training module is used to train multiple load forecasting models according to the task data of the sample load forecasting task, and obtain the corresponding optimal load forecasting model for solving each sample load forecasting task based on the root mean square error to form an optimal load forecasting model set Φ;

所述第二训练模块,用于将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ>,利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器;The second training module is used to form metadata <F, Φ> by combining the feature set F and the optimal load forecasting model set Φ, and train multiple meta-learners respectively by using the metadata <F, Φ> to obtain multiple trained meta-learners;

所述应用模块,用于利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据

Figure BDA0004051288990000047
将所述多个模型推荐结果数据
Figure BDA0004051288990000048
通过投票器,获得单一模型推荐结果数据
Figure BDA0004051288990000049
The application module is used to use multiple trained meta-learners to process the load forecasting task feature set respectively to obtain multiple model recommendation result data
Figure BDA0004051288990000047
The plurality of model recommendation result data
Figure BDA0004051288990000048
Obtain single model recommendation result data through the voting machine
Figure BDA0004051288990000049

第三方面,在本发明提供的又一个实施例中,提供了基于微型PMU的配电网负荷预测模型优选系统,该系统包括:基础学习层、元学习层、应用层;In a third aspect, in another embodiment provided by the present invention, a distribution network load forecasting model optimization system based on a micro PMU is provided, the system comprising: a basic learning layer, a meta-learning layer, and an application layer;

所述基础学习层,用于获取样本负荷预测任务的任务数据,根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ;The basic learning layer is used to obtain task data of a sample load forecasting task, train multiple load forecasting models according to the task data of the sample load forecasting task, and obtain the corresponding optimal load forecasting model for solving each sample load forecasting task based on a root mean square error to form an optimal load forecasting model set Φ;

所述元学习层,用于获取样本负荷预测任务的特征集F,将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ>;利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器;The meta-learning layer is used to obtain a feature set F of a sample load forecasting task, and to form metadata <F, Φ> with the feature set F and the optimal load forecasting model set Φ; and to train a plurality of meta-learners respectively using the metadata <F, Φ> to obtain a plurality of trained meta-learners;

所述应用层,用于利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据

Figure BDA0004051288990000051
将所述多个模型推荐结果数据
Figure BDA0004051288990000052
通过投票器,获得单一模型推荐结果数据
Figure BDA0004051288990000053
The application layer is used to use multiple trained meta-learners to process the load forecasting task feature set respectively to obtain multiple model recommendation result data
Figure BDA0004051288990000051
The plurality of model recommendation result data
Figure BDA0004051288990000052
Obtain single model recommendation result data through the voting machine
Figure BDA0004051288990000053

本发明提供的技术方案,具有如下有益效果:The technical solution provided by the present invention has the following beneficial effects:

本发明提供的基于微型PMU的配电网负荷预测模型优选方法、装置及系统,本发明获取样本负荷预测任务的任务数据和样本负荷预测任务的特征集F;根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ;将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ>;利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器;利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据

Figure BDA0004051288990000054
将所述多个模型推荐结果数据
Figure BDA0004051288990000055
通过投票器,获得单一模型推荐结果数据
Figure BDA0004051288990000056
本发明采用元学习技术,对配电网中各个微型同步相量测量单元(Phasor Measurement Unit,PMU)推荐最优负荷预测模型,满足配电网中异质的负荷预测任务的要求,提升整体的预测精度。The present invention provides a method, device and system for optimizing a load forecasting model for a distribution network based on a micro PMU. The present invention obtains task data of a sample load forecasting task and a feature set F of the sample load forecasting task; trains multiple load forecasting models according to the task data of the sample load forecasting task, and obtains the corresponding optimal load forecasting model for solving each sample load forecasting task based on the root mean square error to form an optimal load forecasting model set Φ; the feature set F and the optimal load forecasting model set Φ together constitute metadata <F, Φ>; uses the metadata <F, Φ> to train multiple meta-learners respectively to obtain multiple trained meta-learners; uses the multiple trained meta-learners to process the load forecasting task feature set respectively to obtain multiple model recommendation result data
Figure BDA0004051288990000054
The plurality of model recommendation result data
Figure BDA0004051288990000055
Obtain single model recommendation result data through the voting machine
Figure BDA0004051288990000056
The present invention adopts meta-learning technology to recommend the optimal load forecasting model to each micro-synchronous phasor measurement unit (PMU) in the distribution network, so as to meet the requirements of heterogeneous load forecasting tasks in the distribution network and improve the overall forecasting accuracy.

本发明的这些方面或其他方面在以下实施例的描述中会更加简明易懂。应当理解的是,以上的一般描述和后文的细节描述仅是示例性和解释性的,并不能限制本发明。These and other aspects of the present invention will become more concise and understandable in the following description of the embodiments. It should be understood that the above general description and the following detailed description are only exemplary and explanatory and cannot limit the present invention.

附图说明BRIEF DESCRIPTION OF THE 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实施例。In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.

图1为配电网中异质的负荷预测任务。Figure 1 shows the heterogeneous load forecasting task in the distribution network.

图2为LSTM隐藏层细胞结构图。Figure 2 is a diagram of the LSTM hidden layer cell structure.

图3为本发明一个实施例的基于微型PMU的配电网负荷预测模型优选方法的流程图。FIG3 is a flow chart of a method for optimizing a distribution network load forecasting model based on a micro PMU according to an embodiment of the present invention.

图4为本发明一个实施例的基于微型PMU的配电网负荷预测模型优选装置中结构框图。FIG4 is a structural block diagram of a distribution network load forecasting model optimization device based on a micro PMU according to an embodiment of the present invention.

图5为本发明一个实施例的基于微型PMU的配电网负荷预测模型优选系统中结构框图。FIG5 is a structural block diagram of a distribution network load forecasting model optimization system based on a micro PMU according to an embodiment of the present invention.

图6为本发明一个实施例的基于微型PMU的配电网负荷预测模型优选系统中元学习器的投票器流程。FIG6 is a voting process of a meta-learner in a distribution network load forecasting model optimization system based on a micro-PMU according to an embodiment of the present invention.

图7为模型选择过程示例。Figure 7 shows an example of the model selection process.

图8为模型标记结果。Figure 8 shows the model labeling results.

图9为不同预测模型的SER比率。FIG9 shows the SER ratios of different prediction models.

图10为基于T分布的随机临近编码对该特征集进行降维处理图。FIG10 is a diagram showing the dimensionality reduction processing of the feature set based on random proximity coding of T distribution.

图11为元学习器在集群4的测试结果。Figure 11 shows the test results of the meta-learner in cluster 4.

图12为推荐模型预测结果a。Figure 12 shows the prediction result of the recommended model a.

图13为推荐模型预测结果b。Figure 13 shows the prediction results of the recommendation model b.

图中:数据获取模块-100、第一训练模块-200、第二训练模块-300、应用模块-400。In the figure: data acquisition module-100, first training module-200, second training module-300, application module-400.

具体实施方式DETAILED DESCRIPTION

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做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 be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

附图中所示的流程图仅是示例说明,不是必须包括所有的内容和操作/步骤,也不是必须按所描述的顺序执行。例如,有的操作/步骤还可以分解、组合或部分合并,因此实际执行的顺序有可能根据实际情况改变。The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations/steps, nor must they be executed in the order described. For example, some operations/steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

应当理解,在此本发明说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本发明。如在本发明说明书和所附权利要求书中所使用的那样,除非上下文清楚地指明其它情况,否则单数形式的“一”、“一个”及“该”意在包括复数形式。It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

具体地,下面结合附图,对本发明实施例作进一步阐述。Specifically, the embodiments of the present invention are further described below in conjunction with the accompanying drawings.

请参阅图3,图3是本发明实施例提供的一种基于微型PMU的配电网负荷预测模型优选方法的流程图,如图3所示,该基于微型PMU的配电网负荷预测模型优选方法包括步骤S10至步骤S40。Please refer to FIG. 3 , which is a flow chart of a method for optimizing a distribution network load forecasting model based on a micro PMU provided in an embodiment of the present invention. As shown in FIG. 3 , the method for optimizing a distribution network load forecasting model based on a micro PMU includes steps S10 to S40.

S10、获取样本负荷预测任务的任务数据和样本负荷预测任务的特征集F,其中所述样本负荷预测任务包括J个样本负荷预测任务。S10. Obtain task data of a sample load prediction task and a feature set F of the sample load prediction task, wherein the sample load prediction task includes J sample load prediction tasks.

在本发明的实施例中,所述样本负荷预测任务数据包括J个数据样本对<Xj,yj>,其中,Xj是负荷预测模型的输入数据,其维度为Nj×Mj;yj是真实的负荷值,其维度为Nj×1,其中j∈[1,..,J]。J的取值范围为正整数。In an embodiment of the present invention, the sample load forecasting task data includes J data sample pairs <X j ,y j >, where X j is the input data of the load forecasting model, and its dimension is N j ×M j ; y j is the actual load value, and its dimension is N j ×1, where j∈[1,..,J]. The value range of J is a positive integer.

在本发明的实施例中,为了对负荷预测模型进行训练,因此Xj包括

Figure BDA0004051288990000072
Figure BDA0004051288990000073
yj包括
Figure BDA0004051288990000074
Figure BDA0004051288990000075
In the embodiment of the present invention, in order to train the load forecasting model, Xj includes
Figure BDA0004051288990000072
and
Figure BDA0004051288990000073
y j includes
Figure BDA0004051288990000074
and
Figure BDA0004051288990000075

其中,所述

Figure BDA0004051288990000076
通过如下公式进行计算:Among them, the
Figure BDA0004051288990000076
Calculate using the following formula:

Figure BDA0004051288990000071
Figure BDA0004051288990000071

其中

Figure BDA0004051288990000077
表示第n个样本的第m个属性。针对第j个负荷预测任务,将负荷预测模型iB生成的预测结果记为
Figure BDA0004051288990000078
in
Figure BDA0004051288990000077
represents the mth attribute of the nth sample. For the jth load forecasting task, the forecast result generated by the load forecasting model i B is recorded as
Figure BDA0004051288990000078

S20、根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ。S20. Train multiple load forecasting models according to the task data of the sample load forecasting task, and obtain the corresponding optimal load forecasting model for solving each sample load forecasting task based on the root mean square error to form an optimal load forecasting model set Φ.

所述负荷预测模型的数量为IB个。其中IB的值可根据用户实际需求加以灵活配置。需要注意的是,所选的IB个模型应该具有不同的优势,以实现相互之间的互补,从而能够解决多样化的预测任务。The number of load forecasting models is I B. The value of I B can be flexibly configured according to the actual needs of users. It should be noted that the selected I B models should have different advantages to complement each other, so as to solve diverse forecasting tasks.

所述负荷预测模型进行如下公式计算:The load forecasting model is calculated using the following formula:

Figure BDA0004051288990000081
Figure BDA0004051288990000081

Figure BDA0004051288990000082
Figure BDA0004051288990000082

其中

Figure BDA0004051288990000088
为衡量预测结果和真实结果之间距离的损失函数,θ为预测模型的待定参数,θ*则是负荷预测模型iB的最优参数集合。当通过训练得到θ*后,则可通过计算在测试集上的RMSE误差来衡量预测精度,即in
Figure BDA0004051288990000088
is a loss function that measures the distance between the predicted result and the actual result. θ is the undetermined parameter of the prediction model, and θ * is the optimal parameter set of the load prediction model i B. After θ * is obtained through training, the prediction accuracy can be measured by calculating the RMSE error on the test set, that is,

Figure BDA0004051288990000083
Figure BDA0004051288990000083

Figure BDA0004051288990000084
Figure BDA0004051288990000084

在所有IB个备选负荷预测模型中,针对负荷预测任务j具有最高预测精度的模型将被标记为Φ(j)。Among all I B candidate load forecasting models, the model with the highest prediction accuracy for load forecasting task j will be labeled as Φ(j).

S30、将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ>;利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器。S30, the feature set F and the optimal load prediction model set Φ together form metadata <F, Φ>; use the metadata <F, Φ> to train multiple meta-learners respectively to obtain multiple trained meta-learners.

其中,所述特征集F的维度为J×D,D为特征集中特征的数量。The dimension of the feature set F is J×D, where D is the number of features in the feature set.

为了对元学习器进行训练,所述元数据<F,Φ>分为元数据训练集<Ftraintrain>和元数据测试集<Ftesttest>。In order to train the meta-learner, the metadata <F, Φ> is divided into a metadata training set <F train , Φ train > and a metadata test set <F test , Φ test >.

所述元学习器进行如下计算:The meta-learner performs the following computation:

Figure BDA0004051288990000085
Figure BDA0004051288990000085

Figure BDA0004051288990000086
Figure BDA0004051288990000086

其中gw表示元学习器,w为元学习的待训练的参数,

Figure BDA0004051288990000089
是元学习器的损失函数,用以衡量所推荐模型
Figure BDA00040512889900000810
与实际最优模型Φtrain之间的距离。将w经过训练之后所得到的最优参数记为w*。当元学习器通过训练获得其最优参数w*之后,可在测试集上对其精度进行测试,推荐精度ηiM通过如下公式进行计算:Where gw represents the meta-learner, w is the parameter to be trained for meta-learning,
Figure BDA0004051288990000089
is the loss function of the meta-learner, which is used to measure the recommended model
Figure BDA00040512889900000810
The distance between the actual optimal model Φ train . The optimal parameter obtained after training is recorded as w * . After the meta-learner obtains its optimal parameter w * through training, its accuracy can be tested on the test set, and the recommended accuracy η iM is calculated by the following formula:

Figure BDA0004051288990000087
Figure BDA0004051288990000087

Figure BDA0004051288990000091
Figure BDA0004051288990000091

其中,KM为元学习训练中的负荷预测任务个数。Among them, K M is the number of load forecasting tasks in meta-learning training.

具体的,元学习器本质是一个多分类机器学习模型,该模型的参数是w(例如,如果元学习器是一个神经网络,那么这里的w指的就是网络中各个神经元的权重)。w使用数据对模型经过训练之后,w才会慢慢收敛到最优值,也就是w*Specifically, the meta-learner is essentially a multi-classification machine learning model whose parameters are w (for example, if the meta-learner is a neural network, then w here refers to the weights of each neuron in the network). After the model is trained using data, w will slowly converge to the optimal value, that is, w * .

由于在本发明中采用了多个元学习器,则会产生多个模型推荐结果

Figure BDA0004051288990000093
Figure BDA0004051288990000094
通过本发明设计得投票器,可综合以上推荐结果并获得最终的推荐结果
Figure BDA0004051288990000095
相应的推荐精度为η。Since multiple meta-learners are used in the present invention, multiple model recommendation results will be generated.
Figure BDA0004051288990000093
Figure BDA0004051288990000094
The voting device designed by the present invention can synthesize the above recommendation results and obtain the final recommendation result.
Figure BDA0004051288990000095
The corresponding recommended accuracy is η.

Figure BDA0004051288990000092
Figure BDA0004051288990000092

在本发明的实施例中,所述利用所述元数据<F,Φ>对多个元学习器进行训练,获得训练后的元学习器,还包括:In an embodiment of the present invention, the step of training a plurality of meta-learners using the metadata <F, Φ> to obtain trained meta-learners further includes:

训练过程中多个所述元学习器生成对应的多个训练模型推荐结果数据

Figure BDA0004051288990000096
During the training process, the multiple meta-learners generate corresponding multiple training model recommendation result data
Figure BDA0004051288990000096

将所述多个训练模型推荐结果数据

Figure BDA0004051288990000097
通过投票器,获得单一训练模型推荐结果数据
Figure BDA0004051288990000098
The plurality of training model recommendation result data
Figure BDA0004051288990000097
Obtain the recommendation result data of a single training model through the voting machine
Figure BDA0004051288990000098

所述元学习器的数量为IM,其取值可根据用户实际需求加以灵活配置,最小取值为1。The number of the meta-learners is IM , and its value can be flexibly configured according to the actual needs of the user, and the minimum value is 1.

S40、利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据

Figure BDA0004051288990000099
将所述多个模型推荐结果数据
Figure BDA00040512889900000910
通过投票器,获得单一模型推荐结果数据
Figure BDA00040512889900000911
S40, using multiple trained meta-learners to process the load forecasting task feature set respectively, and obtain multiple model recommendation result data
Figure BDA0004051288990000099
The plurality of model recommendation result data
Figure BDA00040512889900000910
Obtain single model recommendation result data through the voting machine
Figure BDA00040512889900000911

本发明采用元学习技术,对配电网中各个微型同步相量测量单元(PhasorMeasurement Unit,PMU)推荐最优负荷预测模型,满足配电网中异质的负荷预测任务的要求,提升整体的预测精度。The present invention adopts meta-learning technology to recommend the optimal load forecasting model to each micro-synchronous phasor measurement unit (PMU) in the distribution network, so as to meet the requirements of heterogeneous load forecasting tasks in the distribution network and improve the overall prediction accuracy.

应该理解的是,上述虽然是按照某一顺序描述的,但是这些步骤并不是必然按照上述顺序依次执行。除非本文中有明确的说明,这些步骤的执行并没有严格的顺序限制,这些步骤可以以其它的顺序执行。而且,本实施例的一部分步骤可以包括多个步骤或者多个阶段,这些步骤或者阶段并不必然是在同一时刻执行完成,而是可以在不同的时刻执行,这些步骤或者阶段的执行顺序也不必然是依次进行,而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。It should be understood that, although described in a certain order, these steps are not necessarily performed in sequence in the above order. Unless there is clear explanation in this article, the execution of these steps does not have strict order restriction, and these steps can be performed in other orders. Moreover, a part of the steps of the present embodiment may include a plurality of steps or a plurality of stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a part of the steps or stages in other steps or other steps.

在一个实施例中,参见图4所示,在本发明的实施例中还提供了基于微型PMU的配电网负荷预测模型优选装置,该装置包括数据获取模块100、第一训练模块200、第二训练模块300和应用模块400。In one embodiment, as shown in FIG. 4 , a distribution network load forecasting model optimization device based on a micro PMU is also provided in an embodiment of the present invention. The device includes a data acquisition module 100 , a first training module 200 , a second training module 300 and an application module 400 .

所述数据获取模块100,用于获取样本负荷预测任务的任务数据和样本负荷预测任务的特征集F,其中所述样本负荷预测任务包括J个样本负荷预测任务。The data acquisition module 100 is used to acquire task data of a sample load prediction task and a feature set F of the sample load prediction task, wherein the sample load prediction task includes J sample load prediction tasks.

所述第一训练模块200,用于根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ。The first training module 200 is used to train multiple load forecasting models according to the task data of the sample load forecasting task, and obtain the corresponding optimal load forecasting model for solving each sample load forecasting task based on the root mean square error to form an optimal load forecasting model set Φ.

所述第二训练模块300,用于将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ>,利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器。The second training module 300 is used to form metadata <F, Φ> by combining the feature set F and the optimal load prediction model set Φ, and use the metadata <F, Φ> to train multiple meta-learners respectively to obtain multiple trained meta-learners.

所述应用模块400,用于利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据

Figure BDA0004051288990000101
将所述多个模型推荐结果数据
Figure BDA0004051288990000102
通过投票器,获得单一模型推荐结果数据
Figure BDA0004051288990000103
The application module 400 is used to process the load forecasting task feature set using multiple trained meta-learners to obtain multiple model recommendation result data
Figure BDA0004051288990000101
The plurality of model recommendation result data
Figure BDA0004051288990000102
Obtain single model recommendation result data through the voting machine
Figure BDA0004051288990000103

本发明采用元学习技术,对配电网中各个微型同步相量测量单元(PhasorMeasurement Unit,PMU)推荐最优负荷预测模型,满足配电网中异质的负荷预测任务的要求,提升整体的预测精度。The present invention adopts meta-learning technology to recommend the optimal load forecasting model to each micro-synchronous phasor measurement unit (PMU) in the distribution network, so as to meet the requirements of heterogeneous load forecasting tasks in the distribution network and improve the overall prediction accuracy.

在一个实施例中,参见图5所示,在本发明的实施例中还提供了基于微型PMU的配电网负荷预测模型优选系统,该系统包括基础学习层、元学习层、应用层。In one embodiment, as shown in FIG5 , a distribution network load forecasting model optimization system based on a micro PMU is also provided in an embodiment of the present invention. The system includes a basic learning layer, a meta-learning layer, and an application layer.

所述基础学习层,用于获取样本负荷预测任务的任务数据,根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ。The basic learning layer is used to obtain task data of sample load forecasting tasks, train multiple load forecasting models according to the task data of the sample load forecasting tasks, and obtain the corresponding optimal load forecasting model for solving each sample load forecasting task based on the root mean square error to form an optimal load forecasting model set Φ.

所述元学习层,用于获取样本负荷预测任务的特征集F,将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ〉;利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器。The meta-learning layer is used to obtain a feature set F for a sample load forecasting task, and to form metadata <F,Φ> with the feature set F and the optimal load forecasting model set Φ; and to train multiple meta-learners respectively using the metadata <F,Φ> to obtain multiple trained meta-learners.

所述应用层,用于利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据

Figure BDA0004051288990000112
将所述多个模型推荐结果数据
Figure BDA0004051288990000113
通过投票器,获得单一模型推荐结果数据
Figure BDA0004051288990000114
The application layer is used to use multiple trained meta-learners to process the load forecasting task feature set respectively to obtain multiple model recommendation result data
Figure BDA0004051288990000112
The plurality of model recommendation result data
Figure BDA0004051288990000113
Obtain single model recommendation result data through the voting machine
Figure BDA0004051288990000114

本发明采用元学习技术,对配电网中各个微型同步相量测量单元(PhasorMeasurement Unit,PMU)推荐最优负荷预测模型,满足配电网中异质的负荷预测任务的要求,提升整体的预测精度。The present invention adopts meta-learning technology to recommend the optimal load forecasting model to each micro-synchronous phasor measurement unit (PMU) in the distribution network, so as to meet the requirements of heterogeneous load forecasting tasks in the distribution network and improve the overall prediction accuracy.

示例性的,请提供一个实施例的基于微型PMU的配电网负荷预测模型优选系统的具体应用过程中,给定负荷预测模型、负荷预测任务特征集与负荷预测任务,其步骤如下:For example, please provide an embodiment of a specific application process of a distribution network load forecasting model optimization system based on a micro PMU, given a load forecasting model, a load forecasting task feature set and a load forecasting task, the steps are as follows:

步骤S100、创建样本负荷预测任务。Step S100: Create a sample load forecasting task.

将按照图1所示,从五个维度出发创建大量异质的样本负荷预测任务。As shown in Figure 1, a large number of heterogeneous sample load forecasting tasks will be created from five dimensions.

步骤S200、选择四类常用的负荷预测模型作为备选。其中所述负荷预测模型包括:带有季节特征的自回归差分滑动平均模型(Autoregressive Integrated MovingAverage,SARIMA),LSTM模型、支持向量回归模型(Support Vector Regression,SVR),以及相似日模型(Similar Day,SD)。四个负荷预测模型分别代表了时间序列预测、深度学习预测、关联因素预测以及聚类预测四种不同的思路。对SARIM模型设置6种不同的参数结构,LSTM模型设置2种不同的参数结构,以验证元学习器不仅能够选择大的模型类别,也可以选择出最优的模型结构。最终得到10个备选模型如表1所示。Step S200, select four commonly used load forecasting models as alternatives. The load forecasting models include: Autoregressive Integrated Moving Average (SARIMA) model with seasonal characteristics, LSTM model, Support Vector Regression (SVR), and Similar Day (SD) model. The four load forecasting models represent four different ideas of time series prediction, deep learning prediction, correlation factor prediction, and cluster prediction. Six different parameter structures are set for the SARIM model, and two different parameter structures are set for the LSTM model to verify that the meta-learner can not only select a large model category, but also select the optimal model structure. Finally, 10 candidate models are obtained as shown in Table 1.

表1备选负荷预测模型Table 1 Alternative load forecasting models

Table 1 Candidate load forecasting modelsTable 1 Candidate load forecasting models

Figure BDA0004051288990000111
Figure BDA0004051288990000111

Figure BDA0004051288990000121
Figure BDA0004051288990000121

步骤S300、负荷预测模型标记。Step S300: Load forecasting model marking.

为了给负荷预测任务j找到其最适配的预测模型Φ(j),公式(7)-(10)将重复Lj次,每次采用不同的训练与测试数据切分,从而获得最优负荷预测模型的分布Ωj。该过程持续进行,直至分布Ωj趋于稳定。皮尔逊相关系数Pcc可作为终止条件,即当Ωj(Lj)与Ωj(Lj-10)之间的Pcc大于0.95时,认为分布已达到稳定状态。具体算法详见算法1。In order to find the most suitable prediction model Φ(j) for load forecasting task j, formulas (7)-(10) will be repeated Lj times, each time using different training and test data segmentation, so as to obtain the distribution Ω j of the optimal load forecasting model. This process continues until the distribution Ω j tends to be stable. The Pearson correlation coefficient P cc can be used as a termination condition, that is, when P cc between Ω j (L j ) and Ω j (L j -10) is greater than 0.95, the distribution is considered to have reached a stable state. For details of the algorithm, see Algorithm 1.

Figure BDA0004051288990000122
Figure BDA0004051288990000122

步骤S400、设计包含16个特征的特征集,对负荷预测任务进行定量描述,如表2所示。Step S400: Design a feature set containing 16 features to quantitatively describe the load forecasting task, as shown in Table 2.

表2负荷预测任务特征集Table 2 Load forecasting task feature set

Table2 Feature set of forecasting tasksTable2 Feature set of forecasting tasks

Figure BDA0004051288990000123
Figure BDA0004051288990000123

Figure BDA0004051288990000131
Figure BDA0004051288990000131

峰度(Kurtosis)和偏度(Skewness)可通过式(16)与(17)计算获得,其中,y为历史负荷数据序列,N为数据序列长度,σ,

Figure BDA0004051288990000136
为历史负荷序列的标准差和均值,y(n)代表数据序列第n个值。Kurtosis and skewness can be calculated by equations (16) and (17), where y is the historical load data sequence, N is the length of the data sequence, σ,
Figure BDA0004051288990000136
are the standard deviation and mean of the historical load series, and y(n) represents the nth value of the data series.

Figure BDA0004051288990000132
Figure BDA0004051288990000132

Figure BDA0004051288990000133
Figure BDA0004051288990000133

波动性(Fickleness)衡量历史序列穿越其均值线的次数Volatility (Fickleness) measures the number of times a historical series crosses its mean line

Figure BDA0004051288990000134
Figure BDA0004051288990000134

最大自相关系数(H-ACF)和最大偏自相关系数(H-PACF)负荷序列的相关特征,对于决定SARIMA模型的结构十分重要。周期(Periodicity)则与数据的分辨率直接相关,例如对于小时分辨率的负荷序列,其周期多为24或168。而对于一天为分辨率的序列,周期则多为30。The correlation characteristics of the maximum autocorrelation coefficient (H-ACF) and the maximum partial autocorrelation coefficient (H-PACF) load series are very important for determining the structure of the SARIMA model. The period is directly related to the resolution of the data. For example, for a load series with an hourly resolution, the period is mostly 24 or 168. For a series with a daily resolution, the period is mostly 30.

步骤S500、元学习器选择及投票器。Step S500: Meta-learner selection and voting.

本发明中的元学习器实现任务特征F到最优负荷预测模型Φ(j)的映射,其本质为多分类问题。为提升元学习器的分类精度,本系统中元学习器包括4种不同的分类器。所述分类器包括随机森林(Random Forest,RF),K邻近(K-Nearest Neighbor,KNN),朴素贝叶斯(

Figure BDA0004051288990000135
Bayesian,NB),以及线性判别分析(Linear Discrimination,LD)。为了结合各个分类器的推荐结果,并获得最终的推荐模型,本发明基于集成学习的思想设计了投票器,如图6所示。The meta-learner in the present invention realizes the mapping from task feature F to optimal load forecasting model Φ(j), which is essentially a multi-classification problem. In order to improve the classification accuracy of the meta-learner, the meta-learner in this system includes 4 different classifiers. The classifiers include Random Forest (RF), K-Nearest Neighbor (KNN), Naive Bayes (
Figure BDA0004051288990000135
In order to combine the recommendation results of each classifier and obtain the final recommendation model, the present invention designs a voting machine based on the idea of ensemble learning, as shown in FIG6 .

每个元学习器实现分类的机理是基于内部的打分过程。例如,NB会计算每一类的后验概率作为其评分,而RF则计算内部包含的决策树的投票结果作为其评分。元学习器iM选择其打分最高的模型作为其输出。更高的打分意味着元学习器对于其推荐结果具有更高的置信度。根据该特性,我们建立评分

Figure BDA0004051288990000143
与分类精度
Figure BDA0004051288990000144
之间的映射关系The mechanism by which each meta-learner achieves classification is based on an internal scoring process. For example, NB calculates the posterior probability of each class as its score, while RF calculates the voting results of the decision trees contained internally as its score. The meta-learner iM selects its highest-scoring model as its output. A higher score means that the meta-learner has a higher confidence in its recommendation results. Based on this feature, we establish a scoring
Figure BDA0004051288990000143
And classification accuracy
Figure BDA0004051288990000144
The mapping relationship between

Figure BDA0004051288990000141
Figure BDA0004051288990000141

当为新的负荷预测任务进行模型推荐时,首先将每个元学习器的评分根据上式转换为其对应的推荐精度,并在此基础上选择具有最高推荐精度的模型作为最终的模型推荐When recommending models for a new load forecasting task, the score of each meta-learner is first converted into its corresponding recommendation accuracy according to the above formula, and on this basis, the model with the highest recommendation accuracy is selected as the final model recommendation.

结果

Figure BDA0004051288990000145
result
Figure BDA0004051288990000145

步骤S600、创建负荷预测任务。Step S600: Create a load forecasting task.

创建大量真实、异质的负荷预测任务是测试元学习有效性的基础。如表3所示,我们通过对图1所示的五个维度进行组合,以创建不同的负荷预测任务。Creating a large number of real and heterogeneous load forecasting tasks is the basis for testing the effectiveness of meta-learning. As shown in Table 3, we combine the five dimensions shown in Figure 1 to create different load forecasting tasks.

表3创建异质的负荷预测任务Table 3Heterogeneous forecasting taskcreationTable 3 Heterogeneous forecasting task creation

Figure BDA0004051288990000142
Figure BDA0004051288990000142

15分钟、30分钟精度的居民和商业负荷数据收集自北卡罗莱纳州,1分钟精度的数据则来自Pecan Street。小时精度的天气数据收集自NOAA网站。通过对表3中的五个维度特征进行组合,本文共获得846个不同的负荷预测任务。这些任务具有以下特点:1)主要包含居民和商业负荷,工业、农业负荷不在考虑范围;2)从单个用户到微电网,主要考虑最为常用的短期负荷预测以支撑其运行;3)在馈线层面,额外考虑中长期负荷预测任务;4)最多可获取到12个天气特征;5)考虑3种不同的历史数据长度,以反映实际工程应用中历史数据可获取性的差异。Residential and commercial load data with 15-minute and 30-minute accuracy are collected from North Carolina, and data with 1-minute accuracy are collected from Pecan Street. Weather data with hourly accuracy are collected from the NOAA website. By combining the five dimensional features in Table 3, this paper obtains a total of 846 different load forecasting tasks. These tasks have the following characteristics: 1) They mainly include residential and commercial loads, and industrial and agricultural loads are not considered; 2) From a single user to a microgrid, the most commonly used short-term load forecasting is mainly considered to support its operation; 3) At the feeder level, medium- and long-term load forecasting tasks are additionally considered; 4) Up to 12 weather features can be obtained; 5) Three different historical data lengths are considered to reflect the differences in the availability of historical data in actual engineering applications.

步骤S700、基础学习层获取模型优选结果。Step S700: The basic learning layer obtains the model optimization result.

针对这846个负荷预测任务,找到其最优的预测模型并进行标记。图7以一个负荷预测任务为例,展示其模型选择过程。随着迭代次数的增长,最优模型的分布逐渐趋于稳定。在60次迭代时,其与50次迭代的最优模型频率分布之间的相关系数达到0.98>0.95,因此迭代终止,具有最大频率的模型9被选为该负荷预测任务的最优模型。For these 846 load forecasting tasks, the optimal forecasting model is found and marked. Figure 7 shows the model selection process for a load forecasting task as an example. As the number of iterations increases, the distribution of the optimal model gradually stabilizes. At 60 iterations, the correlation coefficient between its frequency distribution and that of the optimal model at 50 iterations reaches 0.98>0.95, so the iteration is terminated and model 9 with the maximum frequency is selected as the optimal model for the load forecasting task.

对于所有846个负荷预测任务的模型标记结果如图8所示。需要注意的是,如果某个负荷预测任务的历史数据不足以训练模型,则认为该模型失败,并赋予该模型显著的预测误差,以避免其被选择。The model labeling results for all 846 load forecasting tasks are shown in Figure 8. It should be noted that if the historical data of a load forecasting task is insufficient to train the model, the model is considered to have failed and a significant prediction error is assigned to the model to prevent it from being selected.

从结果中可以看出,模型7,即LSTM(125),是最频繁被选择的模型。此外,模型10即相似日模型具有最短的训练时间,但其预测误差的均值和方差大于其它模型。由于SARIMA模型对于历史数据的要求较高,其训练失败的次数也相对较多,尤其是高阶SARIMA模型。但当SARIMA模型可以训练时,其具有较为良好的预测表现。From the results, we can see that model 7, LSTM (125), is the most frequently selected model. In addition, model 10, the similar day model, has the shortest training time, but the mean and variance of its prediction error are larger than those of other models. Since the SARIMA model has high requirements for historical data, the number of training failures is relatively large, especially for high-order SARIMA models. However, when the SARIMA model can be trained, it has a relatively good prediction performance.

为了进一步量化不同预测模型之间的差异,定义系统误差比率(System ErrorRatio,SER)In order to further quantify the differences between different prediction models, the system error ratio (SER) is defined

Figure BDA0004051288990000151
Figure BDA0004051288990000151

其中Eselect为推荐模型的RMSE,Ebest为最优模型的RMSE。该指标衡量了所推荐模型与实际最优模型之间的距离。图9展示了不同模型在负荷预测任务上的表现差异。可以看出,排序2-4的模型多数情况下与最优模型具有相似的表现,即SER接近1。然而,排序靠后的模型其表现则显著差于最优模型。这表明了开展模型选择工作的必要性。Where Eselect is the RMSE of the recommended model, and Ebest is the RMSE of the optimal model. This indicator measures the distance between the recommended model and the actual optimal model. Figure 9 shows the performance differences of different models in the load forecasting task. It can be seen that the models ranked 2-4 have similar performance to the optimal model in most cases, that is, the SER is close to 1. However, the performance of the models ranked lower is significantly worse than the optimal model. This shows the necessity of carrying out model selection work.

步骤S800、负荷预测任务相似度评估。Step S800: Load forecasting task similarity evaluation.

在元学习层,元学习器的输入为负荷预测任务的特征集F。我们应用基于T分布的随机临近编码(T-distributed Stochastic Neighbor Embedding,t-SNE)对该特征集进行降维,并在二维平面上绘制如图10所示。从图中可以看出,负荷预测任务大致聚类为5个集群,如表4所示。In the meta-learning layer, the input of the meta-learner is the feature set F of the load forecasting task. We apply T-distributed Stochastic Neighbor Embedding (t-SNE) to reduce the dimension of the feature set and plot it on a two-dimensional plane as shown in Figure 10. As can be seen from the figure, the load forecasting tasks are roughly clustered into 5 clusters, as shown in Table 4.

表4负荷预测任务集群特征Table 4 Load forecasting task cluster characteristics

Table 4 Features of each LF clusterTable 4 Features of each LF cluster

Figure BDA0004051288990000152
Figure BDA0004051288990000152

集群1,2,5代表馈线级别的负荷预测任务。其中集群1代表中长期以天为单位的负荷预测任务,其中最佳模型为SD。这是因为该类任务历史数据较少,复杂的模型难以得到很好的训练,而简单的SD模型足以提供较好的预测结果。集群2和5代表含有天气特征的短期负荷预测任务,其中最优模型为LSTM。集群3代表用户和变压器层面的短期负荷预测任务,SVR是其最优解决方案。集群4则代表微电网层级的短期负荷预测任务,最优模型为SARIMA。Clusters 1, 2, and 5 represent load forecasting tasks at the feeder level. Cluster 1 represents medium- and long-term load forecasting tasks in days, and the best model is SD. This is because there is less historical data for this type of task, and complex models are difficult to train well, while the simple SD model is sufficient to provide better forecasting results. Clusters 2 and 5 represent short-term load forecasting tasks with weather characteristics, and the best model is LSTM. Cluster 3 represents short-term load forecasting tasks at the user and transformer levels, and SVR is its optimal solution. Cluster 4 represents short-term load forecasting tasks at the microgrid level, and the best model is SARIMA.

步骤S900、元学习器的训练及验证结果。Step S900: training and verification results of the meta-learner.

为了对元学习器进行训练及测试,我们将846个负荷预测任务分为训练集(70%),验证集(20%),以及测试集(10%)。图11展示了训练完成的元学习器在集群4上的测试结果。可以看出,不同的元学习器具有各自选择成功的任务与失败的任务。将其进行有效地综合则可以提升整体的模型优选精度,如表5所示。In order to train and test the meta-learner, we divide the 846 load forecasting tasks into a training set (70%), a validation set (20%), and a test set (10%). Figure 11 shows the test results of the trained meta-learner on cluster 4. It can be seen that different meta-learners have their own successful and failed tasks. Effectively combining them can improve the overall model optimization accuracy, as shown in Table 5.

表5元学习器测试精度Table 5 Meta-learner test accuracy

Table 5 Accuracy of meta learnersTable 5 Accuracy of meta learners

Figure BDA0004051288990000161
Figure BDA0004051288990000161

在推荐最优模型的同时,本文所建立的推荐系统可给出所有备选模型在每个负荷预测任务上的排序,从而为运行人员提供参考。如表6所示,可以看出,排名前3的模型均具有较高的推荐成功率以及较低的SER误差比率,都可作为有效模型进行使用。该推荐系统推荐出有效模型的概率为76%。While recommending the optimal model, the recommendation system established in this paper can give the ranking of all candidate models for each load forecasting task, thus providing a reference for operators. As shown in Table 6, it can be seen that the top 3 models all have a high recommendation success rate and a low SER error ratio, and can all be used as effective models. The probability of the recommendation system recommending an effective model is 76%.

表6不同排序模型精度对比Table 6 Comparison of accuracy of different sorting models

Table6 Accuracy comparison of LF models under different rankingsTable6 Accuracy comparison of LF models under different rankings

排序Sorting 11 22 33 44 55 66 77 88 99 1010 精度Accuracy 46%46% 17%17% 13%13% 6%6% 4%4% 3%3% 3%3% 3%3% 2%2% 3%3% SERSER 1.141.14 1.271.27 1.341.34 1.461.46 4.184.18 2.892.89 4.484.48 3.613.61 2.612.61 3.093.09 失败次数Number of failures 00 00 22 1010 1010 1212 1212 1717 1414 1111

步骤S1000、在线应用测试。Step S1000: Online application test.

当推荐系统训练完成后,可进行在线应用从而为新的负荷预测任务进行预测模型推荐。本节考虑对2个新的负荷预测任务进行模型推荐测试,任务描述如表7所示。任务1为变压器级别的短期负荷预测,带有30天15分钟分辨率的历史数据;任务2为馈线级别的短期负荷预测,带有6个月1小时分辨率的历史数据。根据推荐系统,任务1推荐模型为SD,为真实最优模型;任务2推荐模型为SARIMA(5,1,5),为真实第2优模型。采用推荐模型进行预测,其结果如图12和图13所示。After the recommendation system is trained, it can be applied online to recommend prediction models for new load forecasting tasks. This section considers model recommendation tests for two new load forecasting tasks, and the task descriptions are shown in Table 7. Task 1 is short-term load forecasting at the transformer level, with historical data of 30 days and 15 minutes resolution; Task 2 is short-term load forecasting at the feeder level, with historical data of 6 months and 1 hour resolution. According to the recommendation system, the recommended model for Task 1 is SD, which is the true optimal model; the recommended model for Task 2 is SARIMA (5,1,5), which is the true second-best model. The recommended model is used for prediction, and the results are shown in Figures 12 and 13.

表7 2个新的测试任务Table 7 Two new test tasks

Table 7 Two testing LF tasksTable 7 Two testing LF tasks

Figure BDA0004051288990000171
Figure BDA0004051288990000171

还应当进理解,在本发明说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合,并且包括这些组合。It should be further understood that the term “and/or” used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

应当理解的是,在本文中使用的,除非上下文清楚地支持例外情况,单数形式“一个”旨在也包括复数形式。还应当理解的是,在本文中使用的“和/或”是指包括一个或者一个以上相关联地列出的项目的任意和所有可能组合。上述本发明实施例公开实施例序号仅仅为了描述,不代表实施例的优劣。It should be understood that, as used herein, the singular form "a" or "an" is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and/or" refers to any and all possible combinations of one or more of the items listed in association. The serial numbers of the embodiments disclosed in the above embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments.

所属领域的普通技术人员应当理解:以上任何实施例的讨论仅为示例性的,并非旨在暗示本发明实施例公开的范围(包括权利要求)被限于这些例子;在本发明实施例的思路下,以上实施例或者不同实施例中的技术特征之间也可以进行组合,并存在如上的本发明实施例的不同方面的许多其它变化,为了简明它们没有在细节中提供。因此,凡在本发明实施例的精神和原则之内,所做的任何省略、修改、等同替换、改进等,均应包含在本发明实施例的保护范围之内。A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the idea of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims (3)

1.一种基于微型PMU的配电网负荷预测模型优选方法,其特征在于,该方法包括:1. A method for optimizing a distribution network load forecasting model based on a micro PMU, characterized in that the method comprises: 获取样本负荷预测任务的任务数据和样本负荷预测任务的特征集F;Obtaining task data of a sample load forecasting task and a feature set F of the sample load forecasting task; 根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ;Training multiple load forecasting models according to the task data of the sample load forecasting task, and obtaining the corresponding optimal load forecasting model for solving each sample load forecasting task based on the root mean square error to form an optimal load forecasting model set Φ; 将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ>;利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器;The feature set F and the optimal load forecasting model set Φ together constitute metadata <F, Φ>; use the metadata <F, Φ> to train multiple meta-learners respectively to obtain multiple trained meta-learners; 利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据
Figure FDA0004255343370000011
将所述多个模型推荐结果数据
Figure FDA0004255343370000012
通过投票器,获得单一模型推荐结果数据
Figure FDA0004255343370000013
Use multiple trained meta-learners to process the load forecasting task feature set and obtain multiple model recommendation result data
Figure FDA0004255343370000011
The plurality of model recommendation result data
Figure FDA0004255343370000012
Obtain single model recommendation result data through the voting machine
Figure FDA0004255343370000013
所述样本负荷预测任务数据包括J个数据样本对<Xj,yj>,其中,Xj是负荷预测模型的输入数据,其维度为Nj×Mj;yj是真实的负荷值,其维度为Nj×1,其中j∈[1,..,J];The sample load forecasting task data includes J data sample pairs <X j ,y j >, where X j is the input data of the load forecasting model, and its dimension is N j ×M j ; y j is the real load value, and its dimension is N j ×1, where j∈[1,..,J]; 所述Xj包括
Figure FDA0004255343370000014
Figure FDA0004255343370000015
yj包括
Figure FDA0004255343370000016
Figure FDA0004255343370000017
The Xj includes
Figure FDA0004255343370000014
and
Figure FDA0004255343370000015
y j includes
Figure FDA0004255343370000016
and
Figure FDA0004255343370000017
其中,所述
Figure FDA0004255343370000018
通过如下公式进行计算:
Among them, the
Figure FDA0004255343370000018
Calculated using the following formula:
Figure FDA0004255343370000019
Figure FDA0004255343370000019
其中
Figure FDA00042553433700000110
表示第n个样本的第m个属性;针对第j个负荷预测任务,将负荷预测模型iB生成的预测结果记为
Figure FDA00042553433700000111
in
Figure FDA00042553433700000110
represents the mth attribute of the nth sample; for the jth load forecasting task, the forecast result generated by the load forecasting model i B is recorded as
Figure FDA00042553433700000111
所述特征集F的维度为J×D;The dimension of the feature set F is J×D; 所述负荷预测模型进行如下公式计算:The load forecasting model is calculated using the following formula:
Figure FDA00042553433700000112
Figure FDA00042553433700000112
Figure FDA00042553433700000113
Figure FDA00042553433700000113
其中
Figure FDA00042553433700000114
为衡量预测结果和真实结果之间距离的损失函数,θ*则是负荷预测模型iB的最优参数集合;
in
Figure FDA00042553433700000114
is the loss function that measures the distance between the predicted result and the true result, and θ * is the optimal parameter set of the load forecasting model i B ;
所述元数据<F,Φ>分为元数据训练集<Ftraintrain>和元数据测试集<Ftesttest>;The metadata <F, Φ> is divided into a metadata training set <F train , Φ train > and a metadata test set <F test , Φ test >; 所述利用所述元数据<F,Φ>对多个元学习器进行训练,获得训练后的元学习器,还包括:The step of training a plurality of meta-learners using the metadata <F, Φ> to obtain trained meta-learners further includes: 训练过程中多个所述元学习器生成对应的多个训练模型推荐结果数据
Figure FDA0004255343370000021
During the training process, the multiple meta-learners generate corresponding multiple training model recommendation result data
Figure FDA0004255343370000021
将所述多个训练模型推荐结果数据
Figure FDA0004255343370000022
通过投票器,获得单一训练模型推荐结果数据
Figure FDA0004255343370000023
The plurality of training model recommendation result data
Figure FDA0004255343370000022
Obtain the recommendation result data of a single training model through the voting machine
Figure FDA0004255343370000023
2.一种应用权利要求1所述方法的基于微型PMU的配电网负荷预测模型优选装置,其特征在于,该装置包括:数据获取模块、第一训练模块、第二训练模块和应用模块;2. A device for optimizing a load forecasting model for a distribution network based on a micro PMU using the method of claim 1, characterized in that the device comprises: a data acquisition module, a first training module, a second training module and an application module; 所述数据获取模块,用于获取样本负荷预测任务的任务数据和样本负荷预测任务的特征集F,其中所述样本负荷预测任务包括J个样本负荷预测任务;The data acquisition module is used to acquire task data of a sample load prediction task and a feature set F of the sample load prediction task, wherein the sample load prediction task includes J sample load prediction tasks; 所述第一训练模块,用于根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ;The first training module is used to train multiple load forecasting models according to the task data of the sample load forecasting task, and obtain the corresponding optimal load forecasting model for solving each sample load forecasting task based on the root mean square error to form an optimal load forecasting model set Φ; 所述第二训练模块,用于将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ>,利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器;The second training module is used to form metadata <F, Φ> by combining the feature set F and the optimal load forecasting model set Φ, and train multiple meta-learners respectively by using the metadata <F, Φ> to obtain multiple trained meta-learners; 所述应用模块,用于利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据
Figure FDA0004255343370000024
将所述多个模型推荐结果数据
Figure FDA0004255343370000025
通过投票器,获得单一模型推荐结果数据
Figure FDA0004255343370000026
The application module is used to use multiple trained meta-learners to process the load forecasting task feature set respectively to obtain multiple model recommendation result data
Figure FDA0004255343370000024
The plurality of model recommendation result data
Figure FDA0004255343370000025
Obtain single model recommendation result data through the voting machine
Figure FDA0004255343370000026
3.一种应用权利要求1所述方法的基于微型PMU的配电网负荷预测模型优选系统,其特征在于,该系统包括:基础学习层、元学习层、应用层;3. A distribution network load forecasting model optimization system based on micro PMU using the method described in claim 1, characterized in that the system comprises: a basic learning layer, a meta-learning layer, and an application layer; 所述基础学习层,用于获取样本负荷预测任务的任务数据,根据所述样本负荷预测任务的任务数据对多个负荷预测模型进行训练,且基于均方根误差获取解决每个样本负荷预测任务的对应的最优负荷预测模型,构成最优负荷预测模型集Φ;The basic learning layer is used to obtain task data of a sample load forecasting task, train multiple load forecasting models according to the task data of the sample load forecasting task, and obtain the corresponding optimal load forecasting model for solving each sample load forecasting task based on a root mean square error to form an optimal load forecasting model set Φ; 所述元学习层,用于获取样本负荷预测任务的特征集F,将所述特征集F与所述最优负荷预测模型集Φ共同构成元数据<F,Φ>;利用所述元数据<F,Φ>对分别多个元学习器进行训练,获得多个训练后的元学习器;The meta-learning layer is used to obtain a feature set F of a sample load forecasting task, and to form metadata <F,Φ> with the feature set F and the optimal load forecasting model set Φ; and to train a plurality of meta-learners respectively using the metadata <F,Φ> to obtain a plurality of trained meta-learners; 所述应用层,用于利用多个训练后的元学习器分别对负荷预测任务特征集进行处理,获得多个模型推荐结果数据
Figure FDA0004255343370000031
将所述多个模型推荐结果数据
Figure FDA0004255343370000032
通过投票器,获得单一模型推荐结果数据
Figure FDA0004255343370000033
The application layer is used to use multiple trained meta-learners to process the load forecasting task feature set respectively to obtain multiple model recommendation result data
Figure FDA0004255343370000031
The plurality of model recommendation result data
Figure FDA0004255343370000032
Obtain single model recommendation result data through the voting machine
Figure FDA0004255343370000033
CN202310043210.8A 2023-01-29 2023-01-29 Optimization method, device and system for power distribution network load prediction model based on miniature PMU Active CN116011657B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310043210.8A CN116011657B (en) 2023-01-29 2023-01-29 Optimization method, device and system for power distribution network load prediction model based on miniature PMU

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310043210.8A CN116011657B (en) 2023-01-29 2023-01-29 Optimization method, device and system for power distribution network load prediction model based on miniature PMU

Publications (2)

Publication Number Publication Date
CN116011657A CN116011657A (en) 2023-04-25
CN116011657B true CN116011657B (en) 2023-06-27

Family

ID=86023043

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310043210.8A Active CN116011657B (en) 2023-01-29 2023-01-29 Optimization method, device and system for power distribution network load prediction model based on miniature PMU

Country Status (1)

Country Link
CN (1) CN116011657B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110707763A (en) * 2019-10-17 2020-01-17 南京理工大学 AC/DC power distribution network load prediction method based on ensemble learning
CN112257868A (en) * 2020-09-25 2021-01-22 建信金融科技有限责任公司 Method and device for constructing and training integrated prediction model for predicting passenger flow
CN113159361A (en) * 2020-12-03 2021-07-23 安徽大学 Short-term load prediction method and system based on VDM and Stacking model fusion
CN113723844A (en) * 2021-09-06 2021-11-30 东南大学 Low-voltage transformer area theoretical line loss calculation method based on ensemble learning
CN114491028A (en) * 2022-01-18 2022-05-13 四川大学 A Small-Sample Text Classification Method Based on Regularization Meta-Learning
CN114970345A (en) * 2022-05-25 2022-08-30 武汉大学 Method, device, device and readable storage medium for constructing short-term load forecasting model
CN115240871A (en) * 2022-07-26 2022-10-25 南昌理工学院 Epidemic disease prediction method based on deep embedded clustering element learning
CN115276006A (en) * 2022-09-26 2022-11-01 江苏永鼎股份有限公司 Load prediction method and system for power integration system
CN115577746A (en) * 2022-09-15 2023-01-06 南京辰光融信技术有限公司 Network intrusion detection method based on meta-learning

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8251704B2 (en) * 2007-04-12 2012-08-28 Microsoft Corporation Instrumentation and schematization of learning application programs in a computerized learning environment
US7849043B2 (en) * 2007-04-12 2010-12-07 Microsoft Corporation Matching educational game players in a computerized learning environment
US11663523B2 (en) * 2019-09-14 2023-05-30 Oracle International Corporation Machine learning (ML) infrastructure techniques
US11556862B2 (en) * 2019-09-14 2023-01-17 Oracle International Corporation Techniques for adaptive and context-aware automated service composition for machine learning (ML)

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110707763A (en) * 2019-10-17 2020-01-17 南京理工大学 AC/DC power distribution network load prediction method based on ensemble learning
CN112257868A (en) * 2020-09-25 2021-01-22 建信金融科技有限责任公司 Method and device for constructing and training integrated prediction model for predicting passenger flow
CN113159361A (en) * 2020-12-03 2021-07-23 安徽大学 Short-term load prediction method and system based on VDM and Stacking model fusion
CN113723844A (en) * 2021-09-06 2021-11-30 东南大学 Low-voltage transformer area theoretical line loss calculation method based on ensemble learning
CN114491028A (en) * 2022-01-18 2022-05-13 四川大学 A Small-Sample Text Classification Method Based on Regularization Meta-Learning
CN114970345A (en) * 2022-05-25 2022-08-30 武汉大学 Method, device, device and readable storage medium for constructing short-term load forecasting model
CN115240871A (en) * 2022-07-26 2022-10-25 南昌理工学院 Epidemic disease prediction method based on deep embedded clustering element learning
CN115577746A (en) * 2022-09-15 2023-01-06 南京辰光融信技术有限公司 Network intrusion detection method based on meta-learning
CN115276006A (en) * 2022-09-26 2022-11-01 江苏永鼎股份有限公司 Load prediction method and system for power integration system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"基于PCC-ML深度学习的微电网多目标协调优化运行";李建杰 等;《电气传动》;第第53卷卷(第第5期期);17-24 *

Also Published As

Publication number Publication date
CN116011657A (en) 2023-04-25

Similar Documents

Publication Publication Date Title
Sun et al. Using Bayesian deep learning to capture uncertainty for residential net load forecasting
CN109063939B (en) A Wind Speed Prediction Method and System Based on Neighborhood Gate Long Short-Term Memory Network
Zhang et al. Predicting real-time locational marginal prices: A GAN-based approach
CN109146162B (en) A kind of probability wind speed forecasting method based on integrated Recognition with Recurrent Neural Network
CN109558975A (en) A kind of integrated approach of a variety of prediction results of electric load probability density
CN109460893B (en) A method and system for calculating weather type correlation index of photovoltaic power station
Chien et al. Tool allocation to smooth work-in-process for cycle time reduction and an empirical study
CN113723712B (en) Wind power prediction method, system, equipment and medium
Ghanbari et al. Multivariate time-series prediction using LSTM neural networks
Anh et al. Effect of gradient descent optimizers and dropout technique on deep learning LSTM performance in rainfall-runoff modeling
Wang et al. A novel two-step job runtime estimation method based on input parameters in HPC system
CN118780530A (en) Electric vehicle aggregation resource control method and device
CN116470491A (en) Photovoltaic power probability prediction method and system based on copula function
Cheng et al. Short-term fast forecasting based on family behavior pattern recognition for small-scale users load
Nguyen et al. Short-term forecasting electricity load by long short-term memory and reinforcement learning for optimization of hyper-parameters
Zhang et al. Building energy consumption prediction based on temporal-aware attention and energy consumption states
CN116011657B (en) Optimization method, device and system for power distribution network load prediction model based on miniature PMU
CN119518681A (en) Method for determining photovoltaic power generation, computer program product and electronic device
Yang et al. An improved spatial upscaling method for producing day‐ahead power forecasts for wind farm clusters
CN112330051A (en) Short-term load prediction method based on Kmeans and FR-DBN
Dan et al. Application of machine learning in forecasting energy usage of building design
Yang et al. Bayesian network approach to customer requirements to customized product model
CN112183846B (en) TVF-EMD-MCQRNN Load Probability Prediction Method Based on Fuzzy C-Means Clustering
Han et al. Research on Joint Forecasting Technology of Cold, Heat, and Electricity Loads Based on Multi-Task Learning.
Putra et al. Generating synthetic occupants for use in building performance simulation

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