Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020063690 - ELECTRICAL POWER SYSTEM PREDICTION METHOD AND APPARATUS

Publication Number WO/2020/063690
Publication Date 02.04.2020
International Application No. PCT/CN2019/107947
International Filing Date 25.09.2019
IPC
G06Q 10/04 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10Administration; Management
04Forecasting or optimisation, e.g. linear programming, "travelling salesman problem" or "cutting stock problem"
G06Q 50/06 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
50Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
06Electricity, gas or water supply
G06N 3/12 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
12using genetic models
G06K 9/62 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
G06K 9/6269
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
6269based on the distance between the decision surface and training patterns lying on the boundary of the class cluster, e.g. support vector machines
G06N 3/126
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
12using genetic models
126Genetic algorithms, i.e. information processing using digital simulations of the genetic system
G06Q 10/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
10Administration; Management
04Forecasting or optimisation, e.g. linear programming, "travelling salesman problem" or "cutting stock problem"
G06Q 50/06
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
50Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
06Electricity, gas or water supply
Applicants
  • 新智数字科技有限公司 ENNEW DIGITAL TECHNOLOGY CO., LTD. [CN]/[CN]
Inventors
  • 刘胜伟 LIU, Shengwei
  • 黄信 HUANG, Xin
Agents
  • 北京嘉科知识产权代理事务所(特殊普通合伙) BEIJING JIAKE INTELLECTUAL PROPERTY LAW FIRM
Priority Data
201811113675.125.09.2018CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) ELECTRICAL POWER SYSTEM PREDICTION METHOD AND APPARATUS
(FR) PROCÉDÉ ET APPAREIL DE PRÉDICTION DE SYSTÈME D'ALIMENTATION ÉLECTRIQUE
(ZH) 一种电力系统预测的方法和装置
Abstract
(EN)
An electrical power system prediction method and apparatus, the method comprising: S1: initialising population parameters to generate population individuals; S2: assigning the parameters in S1 to a support vector machine and calculating the degree of adaption of each individual in the population; S3: on the basis of the degree of adaption of the individuals, calculating the selection probability of the individuals in the population and performing individual selection using said selection probability; S4: crossing and mutating the population individuals selected in S3; S5: determining whether the current population has reached a training termination condition and, if so, then acquiring an optimised support vector machine and executing S6; and if not, then executing S3; and S6: inputting a training sample into the optimised support vector machine for training to acquire a prediction model. The present method effectively increases the efficiency of load prediction performed by a support vector machine and increases the accuracy of the selected parameters, thereby reducing prediction error during actual prediction by the support vector machine model, and increasing the precision of load prediction.
(FR)
L'invention concerne un procédé et un appareil de prédiction de système d'alimentation électrique, le procédé comprenant les étapes consistant à : S1 : initialiser des paramètres de population pour générer des individus de population ; S2 : attribuer les paramètres en S1 à une machine à vecteurs de support et calculer le degré d'adaptation de chaque individu dans la population ; S3 : sur la base du degré d'adaptation des individus, calculer la probabilité de sélection des individus dans la population et effectuer une sélection d'individus à l'aide de ladite probabilité de sélection ; S4 : croiser et muter les individus de population sélectionnés en S3 ; S5 : déterminer si la population actuelle a atteint un critère de terminaison d'apprentissage et, si tel est le cas, acquérir ensuite une machine à vecteurs de support optimisée et exécuter S6 ; et si tel n'est pas le cas, alors exécuter S3 ; et S6 : entrer un échantillon d'apprentissage dans la machine à vecteurs de support optimisée pour l'apprentissage afin d'acquérir un modèle de prédiction. Le présent procédé augmente efficacement l'efficacité de prédiction de charge effectuée par une machine à vecteurs de support et augmente la précision des paramètres sélectionnés, réduisant ainsi une erreur de prédiction pendant une prédiction réelle par le modèle de machine à vecteurs de support, et augmentant la précision de prédiction de charge.
(ZH)
一种电力系统预测的方法和装置,该方法包括:S1:初始化种群参数,生成种群个体;S2:将S1中的参数赋值给支持向量机,计算种群中每个个体的适应度;S3:根据个体适应度,计算种群个体的选择概率,并以该选择概率进行个体选择;S4:对S3选择的种群个体进行交叉、变异;S5:判断当前种群是否达到训练终止条件,若是,则获得优化后的支持向量机,并执行S6;否则,执行S3;S6:将训练样本输入到优化后的支持向量机进行训练获得预测模型。该方法有效地提高了支持向量机进行负荷预测的效率,而且提高了选取的参数的准确性,从而降低支持向量机模型在实际预测时的预测误差,提高负荷预测的精度。
Also published as
Latest bibliographic data on file with the International Bureau