WO2022077693A1 - 负荷预测模型的训练方法及训练装置、存储介质、设备 - Google Patents

负荷预测模型的训练方法及训练装置、存储介质、设备 Download PDF

Info

Publication number
WO2022077693A1
WO2022077693A1 PCT/CN2020/129507 CN2020129507W WO2022077693A1 WO 2022077693 A1 WO2022077693 A1 WO 2022077693A1 CN 2020129507 W CN2020129507 W CN 2020129507W WO 2022077693 A1 WO2022077693 A1 WO 2022077693A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
load
training
charging station
prediction model
Prior art date
Application number
PCT/CN2020/129507
Other languages
English (en)
French (fr)
Inventor
杨之乐
朱俊丞
郭媛君
冯伟
张艳辉
Original Assignee
中国科学院深圳先进技术研究院
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 中国科学院深圳先进技术研究院 filed Critical 中国科学院深圳先进技术研究院
Publication of WO2022077693A1 publication Critical patent/WO2022077693A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06Energy or water supply

Definitions

  • the invention belongs to the technical field of battery management, and in particular, relates to a training method and a prediction device for a load prediction model of an electric vehicle charging station, a computer-readable storage medium, and computer equipment.
  • the existing traditional technical solutions such as the autoregressive moving average model and the autoregressive integral moving average model do not have the ability to extract nonlinear features.
  • the shallow neural network has the problems of model overfitting, sensitivity to random initialization weights, and easy convergence to the local optimum. Therefore, the prediction results are often inaccurate and the error is too large.
  • Deep reinforcement learning is a subfield of machine learning, a method that combines deep learning with reinforcement learning, and has a wide range of applications. Deep reinforcement learning combines the ability of deep learning to extract hidden features of nonlinear data and the decision-making ability of reinforcement learning, and has the advantages of both.
  • the technical problem solved by the present invention is: how to consider multiple external factors in the model training process to improve the model prediction accuracy.
  • a training method for a load prediction model of an electric vehicle charging station comprising:
  • the weight data sets of the load prediction model to be trained are trained by using multiple sets of the predicted load data and the real load data.
  • the training method further includes:
  • Phase space reconstruction is performed on the multiple types of the historical load state data to generate multiple types of reconstructed variable data and reconstructed real load data.
  • the method of using a preset model to sequentially predict each type of historical variable data at each moment individually to generate multiple sets of predicted load data includes:
  • Each type of reconstructed variable data at each moment is input into the cyclic gate unit network model in turn, and the cyclic gate unit network model outputs multiple sets of predicted load data.
  • the reinforcement learning method is a Q-learning method
  • the method for training the weight data groups of the load prediction model to be trained by using multiple sets of the predicted load data and the real load data includes:
  • the state matrix executes the action matrix according to the preset strategy to update the weight data set
  • the calculation formula of the loss function is:
  • w 1 , w 2 ... w i are weight data groups to be trained
  • X i are multi-class historical variable data
  • f(X 1 ), f(X 2 )...f(X i ) are multiple Group predicted load data
  • Y is the real load data
  • N is the number of groups of historical variable data.
  • the invention also discloses a training device for a load prediction model of an electric vehicle charging station, the training device comprising:
  • an acquisition module used for acquiring historical load status data of the charging station at several moments, the historical load status data at each moment including multiple types of historical variable data and corresponding real load data;
  • the forecasting module is used to make separate forecasts for each type of historical variable data at each moment in turn to generate multiple sets of forecasted load data;
  • the training module is used for training the weight data groups of the load prediction model to be trained according to the reinforcement learning method and using multiple sets of the predicted load data and the real load data.
  • the training device further comprises:
  • the data reconstruction module is used for performing phase space reconstruction on the multiple types of the historical load state data to generate multiple types of reconstructed variable data and reconstructed real load data.
  • the training module includes:
  • an initialization unit configured to construct and initialize a state matrix and an action matrix, wherein the state matrix is composed of the weight data group to be trained, and the action matrix is composed of the variation of the weight;
  • an execution unit used to make the state matrix execute the action matrix according to the preset strategy to update the weight data group
  • a calculation unit configured to calculate a loss function according to the updated weight data group, multiple groups of predicted load data and the reconstructed real load data, and calculate a reward factor according to the loss function
  • an update unit configured to update the state matrix and the action matrix according to the reward factor.
  • the invention also discloses a computer-readable storage medium storing a training program for a load prediction model of an electric vehicle charging station, and the training program for a load prediction model of an electric vehicle charging station When executed by a processor, the above-described training method for a load prediction model for an electric vehicle charging station is implemented.
  • the invention also discloses a computer device, the computer device comprises a computer-readable storage medium, a processor and a training program for a load prediction model of an electric vehicle charging station stored in the computer-readable storage medium, When the training program for the load prediction model for the electric vehicle charging station is executed by the processor, the above-mentioned training method for the load prediction model for the electric vehicle charging station is implemented.
  • the training method for the load prediction model of the electric vehicle charging station disclosed in the present invention solves the problem that the prediction result is inaccurate because some methods do not consider various factors by using various historical variable data.
  • the phase space reconstruction technique is used to extract more useful information from the input data, which improves the computational performance of the model.
  • the GRU neural network is also used to predict the input data, which solves the problems of traditional LSTM with many parameters and slow calculation speed.
  • the Q-learning algorithm using the ⁇ -greedy strategy is used to train the combined weights of the prediction results of the model, which improves the prediction accuracy of the model.
  • FIG. 1 is a flowchart of a training method for a charging station load prediction model according to Embodiment 1 of the present invention
  • FIG. 2 is another flowchart of the training method of the charging station load prediction model according to the first embodiment of the present invention
  • FIG. 3 is a schematic diagram of a GRU model according to Embodiment 1 of the present invention.
  • Embodiment 4 is a Q-learning training flow chart of Embodiment 1 of the present invention.
  • FIG. 5 is a schematic diagram of a training device according to Embodiment 2 of the present invention.
  • FIG. 6 is a schematic diagram of a training module according to Embodiment 2 of the present invention.
  • FIG. 7 is a schematic diagram of an overall training process of the training device according to the second embodiment of the present invention.
  • FIG. 8 is a schematic block diagram of a computer device according to an embodiment of the present invention.
  • the electric vehicle charging station load has a strong correlation with external factors, and there are various external factors, but the existing method only considers a single external factor
  • This application first obtains multiple types of historical variable data, that is, a variety of external factors, and predicts each historical variable data separately, and then uses the reinforcement learning method to train to obtain the best weight combination. The influence of various variables can improve the prediction accuracy of the model.
  • the training method for a load prediction model of an electric vehicle charging station includes the following steps:
  • Step S10 obtaining historical load status data of the charging station at several moments, the historical load status data at each moment including multiple types of historical variable data and corresponding real load data;
  • Step S20 using the preset model to perform separate prediction on each type of historical variable data at each moment in turn to generate multiple sets of predicted load data;
  • Step S30 According to the reinforcement learning method, training is performed on the weight data sets of the load prediction model to be trained by using multiple sets of the predicted load data and the real load data.
  • step S10 collect external factor data for 90 consecutive days and collect the charging data of all charging piles in the charging station, that is, external factor data and charging data are taken together as historical variable data, wherein historical variable data includes weather information, External data such as time-of-day information, holiday information, real-time prices and traffic flow, and charging station data including charge volume, charge duration, and charge power.
  • historical variable data includes weather information
  • External data such as time-of-day information, holiday information, real-time prices and traffic flow
  • charging station data including charge volume, charge duration, and charge power.
  • the real load data in the first embodiment refers to the superimposed load of all the charging piles of the charging station, that is, the load data of the charging station for a whole day.
  • Select the historical variable data of the previous 90 days as the input X, and the input X can be expanded in the time dimension.
  • step S11 is further included: preprocessing the historical load state data.
  • the historical variable data is divided into a training set and a test set, the training set is used to train model parameters, and the test set is used to test the accuracy of the model; the reason for abnormal data is that due to some interference factors, the data is missing or wrong , the processing method is: for the missing data, if the time interval before and after is less than or equal to the set threshold, the mean value of the data before and after is used to make up; if the time interval before and after is greater than the set threshold, the previous data is used to replace it.
  • the data of the same date type should be used; if a certain type of data is Null, delete the data in the column or complete it with 0; If the variation range of the data is greater than a certain threshold, the average value of the before and after values is taken instead; finally, the input data is normalized.
  • x is the historical variable data before normalization
  • x' represents the normalized historical variable data
  • step S12 is further included: performing phase space reconstruction on the preprocessed historical variable data.
  • input multiple sequences X [x 1 , x 2 ,...,x N ], where N is the number of elements in the input sequence.
  • Input variables can include weather information, time period information, holiday information, real-time price, traffic flow, charging amount, charging time, charging power, etc.
  • the phase space is reconstructed using the delay sequence, and each column in the phase space X has a phase point X t .
  • the delay time ⁇ and the embedding dimension m are determined using the C-C method.
  • the associated integral is defined as:
  • the delay time is ⁇
  • the serial correlation of the time series is expressed as:
  • the correlation interval difference is expressed as:
  • ⁇ S(m, ⁇ ) max ⁇ S(m,r j , ⁇ ) ⁇ -min ⁇ S(m,r j , ⁇ ) ⁇
  • the cyclic gate unit network model (GRU) is used to independently predict each type of historical variable data, that is, what is the corresponding power station load state data when only one variable is considered.
  • the predicted load data corresponding to each variable is f is the GRU model function, a total of i historical variable data are input, the GRU model independently predicts each historical variable data, and the prediction result after weight combination is expressed as w 1 , w 2 ... w i are weight data groups to be trained, X 1 , X 2 ... X i are multi-class historical variable data, f(X 1 ), f(X 2 )...f(X i ) are multiple Group forecast load data.
  • GRU Gate Recurrent Unit
  • LSTM Long Short Term Memory
  • the GRU model consists of an input layer, a hidden layer, and an output layer, where the hidden layer consists of a reset gate r t and an update gate z t . Both gates depend on the previous hidden state ht -1 and the current input xt .
  • the reset gate rt determines the new hidden state obtained after using the filtered information and the current input x t How many previous hidden states h t-1 have been filtered before.
  • the update gate zt controls the previous hidden state ht -1 and the next hidden state , so as to ensure that valid information can flow to the next GRU unit, and each sequence constructed is input into the GRU network to obtain the desired prediction result.
  • the activation functions in the hidden layer of the GRU network include the sigmoid function and the tanh function, whose expressions are:
  • the GRU processing formula is as follows:
  • W z is the updated gate weight matrix
  • W r is the reset gate weight matrix
  • W is the hidden state weight matrix
  • the reinforcement learning method is a Q learning method, and a method for training the weight data groups of the load prediction model to be trained by using multiple groups of the predicted load data and the real load data.
  • Step S31 Construct and initialize a state matrix and an action matrix, wherein the state matrix S is composed of the weight data set to be trained, and the action matrix a is composed of the variation of the weight.
  • the state matrix S is the horizontal row of the Q table, and the action matrix a is the vertical column of the Q table.
  • Step S32 The state matrix S executes the action matrix a according to the preset strategy to update the weight data set.
  • the ⁇ -greedy strategy is used:
  • is a random value in the range (0, 1). Exploration with the probability of ⁇ (Exploration) is to randomly select the action a, and with the probability of 1- ⁇ (Exploitation) to select the action a with the largest Q value.
  • Step S33 Calculate a loss function according to the updated weight data set, multiple sets of predicted load data and real load data, and calculate a reward factor according to the loss function.
  • w 1 , w 2 ... w i are weight data groups to be trained
  • X 1 , X 2 ... X i are multi-class historical variable data
  • f(X 1 ), f(X 2 )...f(X i ) are multiple Group predicted load data
  • Y is the real load data
  • N is the number of groups of historical variable data, that is, N groups data.
  • Step S34 Update the state matrix and the action matrix according to the reward factor
  • the agent After the agent performs action a, it calculates the loss function L, calculates and obtains the reward factor R, calculates the Q value and updates the Q table and state S.
  • is the learning rate and ⁇ is the discount factor. The larger the learning rate, the less effective it is to retain previous training.
  • test data is input into the trained model for prediction, and the final prediction result is obtained, and then inverse normalization is performed, that is, the load of the charging station in the future is obtained.
  • the test data also needs to be reconstructed in phase space.
  • the training method of the load forecasting model disclosed in the first embodiment solves the problem of inaccurate forecasting results caused by some methods failing to consider various factors by using various historical variable data.
  • the phase space reconstruction technique is used to extract more useful information from the input data, which improves the computational performance of the model.
  • the GRU neural network is also used to predict the input data, which solves the problems of traditional LSTM with many parameters and slow calculation speed.
  • the Q-learning algorithm using the ⁇ -greedy strategy is used to train the combined weights of the prediction results of the model, which improves the prediction accuracy of the model.
  • a training device for a load prediction model of an electric vehicle charging station includes an acquisition module 100 , a prediction module 200 , and a training module 300 .
  • the acquisition module 100 is used to acquire historical load status data of the charging station at several moments, and the historical load status data at each moment includes multiple types of historical variable data and corresponding real load data;
  • the prediction module 200 is used for sequentially Each type of historical variable data is independently predicted to generate multiple sets of predicted load data;
  • the training module 300 is used for the weight of the load prediction model to be trained by using multiple sets of the predicted load data and the real load data according to the reinforcement learning method data set for training.
  • the training device further includes a data reconstruction module 500, and the data reconstruction module 500 is configured to perform phase space reconstruction on the multiple types of the historical variable data to generate multiple types of reconstructed variable data.
  • the data reconstruction module 500 is configured to perform phase space reconstruction on the multiple types of the historical variable data to generate multiple types of reconstructed variable data.
  • the training module 400 includes an initialization unit 401 , an execution unit 402 , a calculation unit 403 and an update unit 404 .
  • the initialization unit 401 is used to construct and initialize the state matrix and the action matrix, wherein the state matrix is composed of the weight data group to be trained, and the action matrix is composed of the variation of the weight;
  • the execution unit 402 is used to make the state matrix according to The preset strategy execution action matrix is used to update the weight data group;
  • the calculation unit 403 is configured to calculate a loss function according to the updated weight data group, multiple groups of predicted load data and real load data, and calculate the reward factor according to the loss function; update
  • update The unit 404 is configured to update the state matrix and the action matrix according to the reward factor.
  • Embodiment 1 For the specific training process of the training module 400, refer to Embodiment 1, which will not be repeated here.
  • the overall training process of the training device for the load prediction model of the second embodiment is shown in FIG. 7 .
  • the present application also discloses a computer-readable storage medium, where the computer-readable storage medium stores a training program for a load prediction model of an electric vehicle charging station, and the training program for a load prediction model of an electric vehicle charging station When executed by a processor, the above-described training method for a load prediction model for an electric vehicle charging station is implemented.
  • the present application also discloses a computer device.
  • the terminal includes a processor 12 , an internal bus 13 , a network interface 14 , and a computer-readable storage medium 11 .
  • the processor 12 reads the corresponding computer program from the computer-readable storage medium and then executes it, forming a request processing device on a logical level.
  • the computer-readable storage medium 11 stores a training program for a load prediction model of an electric vehicle charging station.
  • Computer-readable storage media includes both persistent and non-permanent, removable and non-removable media, and storage of information can be implemented by any method or technology.
  • Information may be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage , magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by computing devices.
  • PRAM phase-change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • ROM read-only memory Memory

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Software Systems (AREA)
  • Marketing (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明公开了用于电动汽车充电站的负荷预测模型的训练方法及训练装置、存储介质、设备。训练方法包括:获取充电站若干时刻的历史负荷状态数据,每一时刻的历史负荷状态数据包括多类历史变量数据以及相应的真实负荷数据;利用预设模型依次对每一时刻的每一类历史变量数据进行单独预测,以生成多组预测负荷数据;根据强化学习方法,并利用多组预测负荷数据和真实负荷数据对待训练的负荷预测模型的权重数据组进行训练。通过使用多种历史变量数据,提升了预测精度。同时使用相空间重构技术,从输入数据中提取更多有用的信息,提高了模型的计算性能。使用GRU神经网络对输入数据进行预测,加快了计算速度,并结合Q学习算法,提升了模型的预测精度。

Description

负荷预测模型的训练方法及训练装置、存储介质、设备 技术领域
本发明属于电池管理技术领域,具体地讲,涉及一种用于电动汽车充电站的负荷预测模型的训练方法及预测装置、计算机可读存储介质、计算机设备。
背景技术
能源短缺与气候变化是全世界正面临的重大挑战。以传统化石燃料作为动力的内燃机汽车排放的废气不仅对空气的造成了极大的污染,还进一步加重了温室效应。世界各国都亟需采取有效的应对措施和政策。大力发展电动汽车能够有效地解决这些问题。电动汽车是一种零排放***,由电力驱动,在行驶过程中不会产生任何污染环境的物质。电动汽车还可使用多样化的能源包括风能、太阳能等清洁能源,因此大大降低了石化资源的消耗。同时,电动汽车的动力总成和电动机比传统的内燃机汽车更加高效和环保。
电动汽车行业的发展是大势所趋,必然会给电力能源领域带来新的变革和新的问题。随着电动汽车数量的增多,充电站的需求量自然会随之增加。充电站将会面临持续不间断使用的情况,电力***也会面临负荷过大的问题。为了保证客户的充电需求和电力***的稳定运行,对电动汽车充电站的负荷预测是极其必要且关键的。准确的负荷预测可以帮助电力公司合理的分配和开发电力基础设施以及载荷配置。
现有的传统技术方案如自回归滑动平均模型、自回归积分滑动平均模型不具备提取非线性特征的能力。而浅层的神经网络存在模型过拟合、随机初始化权重敏感和容易收敛于局部最优等问题。因此常导致预测结果不够准确,误差过大。
深度强化学习是机器学习中的子领域,是将深度学习与强化学习相结合的一种方法,其应用十分广泛。深度强化学习将深度学习对非线性数据隐藏特征的提取能力和强化学习的决策能力相结合,同时具有两者的优点。
传统的负荷预测算法存在的问题一般是预测性能差,鲁棒性和适应性差。电动汽车充电站负荷与外部因素有很强的相关性,而现有的方法通常只考虑单一的外部因素,会导致预测精度低。
发明内容
(一)本发明所要解决的技术问题
本发明解决的技术问题是:如何在模型训练过程中考虑多个外部因素,以提高模型预测精度。
(二)本发明所采用的技术方案
一种用于电动汽车充电站的负荷预测模型的训练方法,所述训练方法包括:
获取充电站若干时刻的历史负荷状态数据,每一时刻的所述历史负荷状态数据包括多类历史变量数据以及相应的真实负荷数据;
利用预设模型依次对每一时刻的每一类历史变量数据进行单独预测,以生成多组预测负荷数据;
根据强化学习方法,并利用多组所述预测负荷数据和所述真实负荷数据对待训练的负荷预测模型的权重数据组进行训练。
优选地,获取所述充电站的历史负荷状态数据之后,所述训练方法还包括:
对多类所述历史负荷状态数据进行相空间重构,以生成多类重构变量数据和重构后的真实负荷数据。
优选地,利用预设模型依次对每一时刻的每一类历史变量数据进行单独预测,以生成多组预测负荷数据的方法包括:
将每一时刻的每一类重构变量数据依次输入到循环门单元网络模型,循环门单元网络模型输出多组预测负荷数据。
优选地,所述强化学习方法为Q学习方法,利用多组所述预测负荷数据和所述真实负荷数据对待训练的负荷预测模型的权重数据组进行训练的方法包括:
构建并初始化状态矩阵和动作矩阵,其中所述状态矩阵由待训练的权重数据组构成,所述动作矩阵由权重的变化量构成;
状态矩阵按照预设策略执行动作矩阵,以更新权重数据组;
根据更新后的权重数据组、多组预测负荷数据和重构后真实负荷数据计算损失函数,并根据所述损失函数计算奖励因子;
根据所述奖励因子更新状态矩阵和动作矩阵;
重复上述步骤直至满足迭代条件。
优选地,所述损失函数的计算公式为:
Figure PCTCN2020129507-appb-000001
其中,
Figure PCTCN2020129507-appb-000002
w 1,w 2…w i为待训练的权重数据组,X 1,X 2…X i为多类历史变量数据,f(X 1),f(X 2)…f(X i)为多组预测负荷数据,Y为真实负荷数据,N为历史变量数据的组数。
本发明还公开了一种用于电动汽车充电站的负荷预测模型的训练装置,所述训练装置包括:
获取模块,用于获取充电站若干时刻的历史负荷状态数据,每一时刻的所述历史负荷状态数据包括多类历史变量数据以及相应的真实负荷数据;
预测模块,用于依次对每一时刻的每一类历史变量数据进行单独预测,以生成多组预测负荷数据;
训练模块,用于根据强化学习方法,并利用多组所述预测负荷数据和所述真实负荷数据对待训练的负荷预测模型的权重数据组进行训练。
优选地,所述训练装置还包括:
数据重构模块,用于对多类所述历史负荷状态数据进行相空间重构,以生成多类重构变量数据和重构后的真实负荷数据。
优选地,所述训练模块包括:
初始化单元,用于构建并初始化状态矩阵和动作矩阵,其中所述状态矩阵由待训练的权重数据组构成,所述动作矩阵由权重的变化量构成;
执行单元,用于使状态矩阵按照预设策略执行动作矩阵,以更新权重数据组;
计算单元,用于根据更新后的权重数据组、多组预测负荷数据和重构后的真实负荷数据计算损失函数,并根据所述损失函数计算奖励因子;
更新单元,用于根据所述奖励因子更新状态矩阵和动作矩阵。
本发明还公开了一种计算机可读存储介质,所述计算机可读存储介质存储有用于电动汽车充电站的负荷预测模型的训练程序,所述用于电动汽车充电站的负荷预测模型的训练程序被处理器执行时实现上述的用于电动汽车充电站的负荷预测模型的训练方法。
本发明还公开了一种计算机设备,所述计算机设备包括计算机可读存储介质、处理器和存储在所述计算机可读存储介质中的用于电动汽车充电站的负荷预测模型的训练程序,所述用于电动汽车充电站的负荷预测模型的训练程序被处理器执行时实现上述的用于电动汽车充电站的负荷预测模型的训练方法。
(三)有益效果
本发明公开的用于电动汽车充电站的负荷预测模型的训练方法,通过使用多种历史变量数据,解决了部分方法未考虑多种因素导致预测结果不准确的问题。同时使用相空间重构技术,从输入数据中提取更多有用的信息,提高了模型的计算性能。还使用了GRU神经网络对输入数据进行预测,解决了传统LSTM参数多和计算速度慢的问题。最后使用了采取ε‐greedy策略的Q‐learning算法训练模型预测结果的组合权重,提升了模型的预测精度。
附图说明
图1为本发明的实施例一的充电站负荷预测模型的训练方法的流程图;
图2为本发明的实施例一的充电站负荷预测模型的训练方法的另一流程图;
图3为本发明的实施例一的GRU模型示意图;
图4为本发明的实施例一的Q学习训练流程图;
图5为本发明的实施例二的训练装置的示意图;
图6为本发明的实施例二的训练模块的示意图;
图7为本发明的实施例二的训练装置的整体训练过程示意图;
图8为本发明的实施例的计算机设备的原理框图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
在详细描述本申请的技术方案前,首先简单描述本申请的发明构思:电动汽车充电站负荷与外部因素有很强的相关性,并且外部因素具有多样,然而现有的方法只考虑了单一外部因素,导致预测精度降低,本申请首先获取多类历史变量数据,即多种外部因素,并对每种历史变量数据进行单独预测,然后利用强化学习方法训练得到最佳的权重组合,通过考虑多种变量的影响,可以提高模型预测精度。
具体的,如图1所示,本实施例一的用于电动汽车充电站负荷预测模型的训练方法包括如下步骤:
步骤S10:获取充电站若干时刻的历史负荷状态数据,每一时刻的所述历史负荷状态数据包括多类历史变量数据以及相应的真实负荷数据;
步骤S20:利用预设模型依次对每一时刻的每一类历史变量数据进行单独预测,以生成多组预测负荷数据;
步骤S30:根据强化学习方法,并利用多组所述预测负荷数据和所述真实负荷数据对待训练的负荷预测模型的权重数据组进行训练。
示例性地,在步骤S10中,收集连续90天的外部因素数据并收集充电站所有充电桩的充电数据,即外部因素数据和充电数据共同作为历史变量数据,其中,历史变量数据包括天气信息、时段信息、假日信息、实时价格和交通流量等外部数据,以及包括充电量、充电时长和充电功率等充电站数据。考虑到充电站24小时均可使用,且充电车辆进入充电站和充电起始时间的随机性。本实施例一的真实负荷数据,是指充电站所有充电桩的叠加负荷,即充电站一整天的负荷数据。选择日前90天的历史变量数据作为输入X,且输入X可以在时间维度上展开。
作为另一实施例,在步骤S10之后,还包括步骤S11:对历史负荷状态数据进行预处理。具体来说,对历史变量数据划分训练集和测试集,训练集用于训练模型参数,测试集用于测试模型准确度;出现异常数据的原因是由于某些干扰因素,导致数据缺失或者出现错误,对其处理方式为:对于缺失的数据,如果前后时间间隔小于等于设定阈值,采用前后数据的均值将其补上;如果前后 时间间隔大于设定阈值,采用之前的数据来代替,此时要采用相同日期类型的数据;对于某一类型数据出现Null的情况,删除该列数据或者用0补全;对于出现错误的数据,将某一时刻的真实负荷和其前后真实负荷值进行比较,如果数据的变化范围大于某一阈值,则取前后值的平均值代替;最后对输入数据进行归一化。
Figure PCTCN2020129507-appb-000003
其中,x为归一化前的历史变量数据,x’表示归一化后的历史变量数据。
作为另一实施例,在步骤S11之后,还包括步骤S12:对预处理之后历史变量数据进行相空间重构。具体来说,输入多个序列X=[x 1,x 2,…,x N],N为输入序列中元素的个数。输入的变量可包括天气信息,时段信息,假日信息,实时价格,交通流量,充电量,充电时长,充电功率等。
延迟序列即相点为X t=(x t,x (t+τ),x (t+2τ),…,x [t+(m-1)τ]) T,t=1,2,…,N-(m-1)τ。使用延迟序列进行重构相空间,相空间X中每一列为一个相点X t
Figure PCTCN2020129507-appb-000004
使用C-C方法确定延迟时间τ和嵌入维数m。
具体来说,关联积分的定义为:
Figure PCTCN2020129507-appb-000005
Figure PCTCN2020129507-appb-000006
其中r为空间距离,||X i-X j||为欧几里德距离。
延迟时间为τ,时间序列的序列相关性表示为:
Figure PCTCN2020129507-appb-000007
局部最优延迟时间τ *为第一个S(m,r,τ)=0或达到最小值的时间。在局部最优延迟时间τ *处,重构的相空间处于接近均匀的点分布下。
相关区间差量表示为:
ΔS(m,τ)=max{S(m,r j,τ)}-min{S(m,r j,τ)}
当N大于3000时,m=2,3,4,5,
Figure PCTCN2020129507-appb-000008
j=m-1,s为输入序列的标准差。
计算
Figure PCTCN2020129507-appb-000009
的全局最小点得出τ w,即可根据τ w=(m-1)τ *求取最优相空间维度m *
进一步地,上述历史变量数据对应的真实负荷数据Y也进行相应的预处理和相空间重构,在此不进行赘述。
进一步地,在步骤S20中,采用循环门单元网络模型(GRU)对每一类历史变量数据进行独立预测,即在只考虑一种变量的情况下,所对应的电站负荷状态数据是什么。每种变量对应的预测负荷数据为
Figure PCTCN2020129507-appb-000010
f为GRU模式函数,一共输入i个历史变量数据,GRU模型对每个历史变量数据独立预测,再经过权重组合的预测结果表示为
Figure PCTCN2020129507-appb-000011
w 1,w 2…w i为待训练的权重数据组,X 1,X 2…X i为多类历史变量数据,f(X 1),f(X 2)…f(X i)为多组预测负荷数据。
具体地,如图3所示,GRU(循环门单元)是LSTM(长短期记忆)的一种改进模型,通过丢弃存储单元机制并引入更新门来替换输入和忘记门来简化LSTM的结构。GRU模型由输入层,隐藏层,输出层构成,其中隐藏层由重置门r t和更新门z t组成。两个门都取决于先前的隐藏状态h t-1和当前输入x t。重置门r t确定在使用滤波后的信息和当前输入x t获得新的隐藏状态
Figure PCTCN2020129507-appb-000012
之前,已过滤了多少先前的隐藏状态h t-1
更新门z t控制前一个隐藏状态h t-1和下一个隐藏状态
Figure PCTCN2020129507-appb-000013
的比例,从而确保有效的信息可以流到下一个GRU单元,将构建好的每个序列输入到GRU网络中,得出所需的预测结果。
GRU网络隐藏层中的激活函数包括sigmoid函数和tanh函数,其表达式分别为:
Figure PCTCN2020129507-appb-000014
Figure PCTCN2020129507-appb-000015
GRU处理公式如下:
z t=σ(U zh t-1+x tW z)
r t=σ(U rh t-1+x tW r)
Figure PCTCN2020129507-appb-000016
Figure PCTCN2020129507-appb-000017
其中h t为隐藏状态
Figure PCTCN2020129507-appb-000018
为新的隐藏状态,W z为更新门权重矩阵,W r为重置门权重矩阵,W为隐藏状态权重矩阵。
利用GRU模型对历史变量数据进行预测的具体过程为现有技术,在此不进行赘述。
进一步地,如图4所示,在步骤S30中,强化学习方法为Q学习方法,利用多组所述预测负荷数据和所述真实负荷数据对待训练的负荷预测模型的权重数据组进行训练的方法包括:
步骤S31:构建并初始化状态矩阵和动作矩阵,其中所述状态矩阵S由待训练的权重数据组构成,所述动作矩阵a由权重的变化量构成。状态矩阵S作为Q表的横行,动作矩阵a作为Q表的纵列。
S=[w 1,w 2,…,w i]
a=[Δw 1,Δw 2,…,Δw i]
步骤S32:状态矩阵S按照预设策略执行动作矩阵a,以更新权重数据组。
作为优选实施例,采用ε‐greedy策略:
Figure PCTCN2020129507-appb-000019
ε为范围(0,1)的随机数值。以ε的概率探索(Exploration)即随机选择动作a,以1-ε的概率利用(Exploitation)选择Q值最大的动作a。
步骤S33:根据更新后的权重数据组、多组预测负荷数据和真实负荷数据计 算损失函数,并根据所述损失函数计算奖励因子。
所述损失函数L的计算公式为:
Figure PCTCN2020129507-appb-000020
其中,
Figure PCTCN2020129507-appb-000021
w 1,w 2…w i为待训练的权重数据组,X 1,X 2…X i为多类历史变量数据,f(X 1),f(X 2)…f(X i)为多组预测负荷数据,Y为真实负荷数据,N为历史变量数据的组数,即N组
Figure PCTCN2020129507-appb-000022
数据。
奖励因子R的计算公式如下:
Figure PCTCN2020129507-appb-000023
步骤S34:根据所述奖励因子更新状态矩阵和动作矩阵;
Figure PCTCN2020129507-appb-000024
智能体执行动作a后,计算损失函数L,计算并获得奖励因子R,计算Q值并更新Q表和状态S。其中α是学习率,γ是折扣因子。学习率越大,保留之前训练的效果就越少。
重复上述步骤直至满足迭代条件,即可获得最佳的状态矩阵S,从而获得最佳的权重数据组。
实际应用中,将测试数据输入到训练完毕的模型中进行预测,得到最终的预测结果,再进行逆归一化,即得到未来一天充电站的负荷。其中,测试数据也需要进行相空间重构。
本实施例一公开的负荷预测模型的训练方法,通过使用多种历史变量数据,解决了部分方法未考虑多种因素导致预测结果不准确的问题。同时使用相空间重构技术,从输入数据中提取更多有用的信息,提高了模型的计算性能。还使用了GRU神经网络对输入数据进行预测,解决了传统LSTM参数多和计算速度慢的问题。最后使用了采取ε‐greedy策略的Q‐learning算法训练模型预测结果的组合权重,提升了模型的预测精度。
实施例二
如图5所示,本实施例二提供的一种用于电动汽车充电站的负荷预测模型的训练装置包括获取模块100、预测模块200、训练模块300。获取模块100用于获取充电站若干时刻的历史负荷状态数据,每一时刻的所述历史负荷状态数据包括多类历史变量数据以及相应的真实负荷数据;预测模块200用于依次对每一时刻的每一类历史变量数据进行单独预测以生成多组预测负荷数据;训练模块300用于根据强化学习方法,并利用多组所述预测负荷数据和所述真实负荷数据对待训练的负荷预测模型的权重数据组进行训练。
进一步地,所述训练装置还包括数据重构模块500,数据重构模块500用于对多类所述历史变量数据进行相空间重构,以生成多类重构变量数据。相空间重构的具体过程参照实施例一中的描述,在此不进行赘述。
进一步地,如图6所示,所述训练模块400包括初始化单元401、执行单元402、计算单元403和更新单元404。其中,初始化单元401用于构建并初始化状态矩阵和动作矩阵,其中所述状态矩阵由待训练的权重数据组构成,所述动作矩阵由权重的变化量构成;执行单元402用于使状态矩阵按照预设策略执行动作矩阵,以更新权重数据组;计算单元403用于根据更新后的权重数据组、多组预测负荷数据和真实负荷数据计算损失函数,并根据所述损失函数计算奖励因子;更新单元404用于根据所述奖励因子更新状态矩阵和动作矩阵。训练模块400的具体训练过程参照实施例一,在此不进行赘述。
本实施例二的负荷预测模型的训练装置的整体训练过程如图7所示。
本申请还公开了一种计算机可读存储介质,所述计算机可读存储介质存储有用于电动汽车充电站的负荷预测模型的训练程序,所述用于电动汽车充电站的负荷预测模型的训练程序被处理器执行时实现上述的用于电动汽车充电站的负荷预测模型的训练方法。
本申请还公开了一种计算机设备,在硬件层面,如图8所示,该终端包括处理器12、内部总线13、网络接口14、计算机可读存储介质11。处理器12从计算机可读存储介质中读取对应的计算机程序然后运行,在逻辑层面上形成请求处理装置。当然,除了软件实现方式之外,本说明书一个或多个实施例并不排除其他实现方式,比如逻辑器件抑或软硬件结合的方式等等,也就是说以下处理流程的执行主体并不限定于各个逻辑单元,也可以是硬件或逻辑器件。所述计算机可读存储介质11上存储有用于电动汽车充电站的负荷预测模型的训练程序,所述用于电动汽车充电站的负荷预测模型的训练程序被处理器执行时实 现上述的用于电动汽车充电站的负荷预测模型的训练方法。
计算机可读存储介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机可读存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带、磁盘存储、量子存储器、基于石墨烯的存储介质或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算设备访问的信息。
上面对本发明的具体实施方式进行了详细描述,虽然已表示和描述了一些实施例,但本领域技术人员应该理解,在不脱离由权利要求及其等同物限定其范围的本发明的原理和精神的情况下,可以对这些实施例进行修改和完善,这些修改和完善也应在本发明的保护范围内。

Claims (10)

  1. 一种用于电动汽车充电站的负荷预测模型的训练方法,其特征在于,所述训练方法包括:
    获取充电站若干时刻的历史负荷状态数据,每一时刻的所述历史负荷状态数据包括多类历史变量数据以及相应的真实负荷数据;
    利用预设模型依次对每一时刻的每一类历史变量数据进行单独预测,以生成多组预测负荷数据;
    根据强化学习方法,并利用多组所述预测负荷数据和所述真实负荷数据对待训练的负荷预测模型的权重数据组进行训练。
  2. 根据权利要求1所述的用于电动汽车充电站的负荷预测模型的训练方法,其特征在于,获取所述充电站的历史负荷状态数据之后,所述训练方法还包括:
    对多类所述历史负荷状态数据进行相空间重构,以生成多类重构变量数据和重构后的真实负荷数据。
  3. 根据权利要求2所述的用于电动汽车充电站的负荷预测模型的训练方法,其特征在于,利用预设模型依次对每一时刻的每一类历史变量数据进行单独预测,以生成多组预测负荷数据的方法包括:
    将每一时刻的每一类重构变量数据依次输入到循环门单元网络模型,循环门单元网络模型输出多组预测负荷数据。
  4. 根据权利要求1所述的用于电动汽车充电站的负荷预测模型的训练方法,其特征在于,所述强化学习方法为Q学习方法,利用多组所述预测负荷数据和所述真实负荷数据对待训练的负荷预测模型的权重数据组进行训练的方法包括:
    构建并初始化状态矩阵和动作矩阵,其中所述状态矩阵由待训练的权重数据组构成,所述动作矩阵由权重的变化量构成;
    状态矩阵按照预设策略执行动作矩阵,以更新权重数据组;
    根据更新后的权重数据组、多组预测负荷数据和重构后的真实负荷数据计算损失函数,并根据所述损失函数计算奖励因子;
    根据所述奖励因子更新状态矩阵和动作矩阵;
    重复上述步骤直至满足迭代条件。
  5. 根据权利要求4所述的用于电动汽车充电站的负荷预测模型的训练方法, 其特征在于,所述损失函数的计算公式为:
    Figure PCTCN2020129507-appb-100001
    其中,
    Figure PCTCN2020129507-appb-100002
    w 1,w 2…w i为待训练的权重数据组,X 1,X 2…X i为多类历史变量数据,f(X 1),f(X 2)…f(X i)为多组预测负荷数据,Y为真实负荷数据,N为历史变量数据的组数。
  6. 一种用于电动汽车充电站的负荷预测模型的训练装置,其特征在于,所述训练装置包括:
    获取模块,用于获取充电站若干时刻的历史负荷状态数据,每一时刻的所述历史负荷状态数据包括多类历史变量数据以及相应的真实负荷数据;
    预测模块,用于依次对每一时刻的每一类历史变量数据进行单独预测,以生成多组预测负荷数据;
    训练模块,用于根据强化学习方法,并利用多组所述预测负荷数据和所述真实负荷数据对待训练的负荷预测模型的权重数据组进行训练。
  7. 根据权利要求6所述的用于电动汽车充电站的负荷预测模型的训练装置,其特征在于,所述训练装置还包括:
    数据重构模块,用于对多类所述历史负荷状态数据进行相空间重构,以生成多类重构变量数据和重构后的真实负荷数据。
  8. 根据权利要求6所述的用于电动汽车充电站的负荷预测模型的训练装置,其特征在于,所述训练模块包括:
    初始化单元,用于构建并初始化状态矩阵和动作矩阵,其中所述状态矩阵由待训练的权重数据组构成,所述动作矩阵由权重的变化量构成;
    执行单元,用于使状态矩阵按照预设策略执行动作矩阵,以更新权重数据组;
    计算单元,用于根据更新后的权重数据组、多组预测负荷数据和重构后真实负荷数据计算损失函数,并根据所述损失函数计算奖励因子;
    更新单元,用于根据所述奖励因子更新状态矩阵和动作矩阵。
  9. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质存储有用于电动汽车充电站的负荷预测模型的训练程序,所述用于电动汽车充电站的负荷预测模型的训练程序被处理器执行时实现权利要求1至5任一项所述的用于电动汽车充电站的负荷预测模型的训练方法。
  10. 一种计算机设备,其特征在于,所述计算机设备包括计算机可读存储介质、处理器和存储在所述计算机可读存储介质中的用于电动汽车充电站的负荷预测模型的训练程序,所述用于电动汽车充电站的负荷预测模型的训练程序被处理器执行时实现权利要求1至5任一项所述的用于电动汽车充电站的负荷预测模型的训练方法。
PCT/CN2020/129507 2020-10-15 2020-11-17 负荷预测模型的训练方法及训练装置、存储介质、设备 WO2022077693A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011101284.5A CN112200373A (zh) 2020-10-15 2020-10-15 负荷预测模型的训练方法及训练装置、存储介质、设备
CN202011101284.5 2020-10-15

Publications (1)

Publication Number Publication Date
WO2022077693A1 true WO2022077693A1 (zh) 2022-04-21

Family

ID=74009574

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/129507 WO2022077693A1 (zh) 2020-10-15 2020-11-17 负荷预测模型的训练方法及训练装置、存储介质、设备

Country Status (2)

Country Link
CN (1) CN112200373A (zh)
WO (1) WO2022077693A1 (zh)

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114744662A (zh) * 2022-06-13 2022-07-12 华北电力大学 一种基于多类型电动汽车的电网调峰方法及***
CN114792177A (zh) * 2022-06-24 2022-07-26 中煤科工开采研究院有限公司 综采工作面的多液压支架载荷预测方法、装置及电子设备
CN115498629A (zh) * 2022-09-06 2022-12-20 清华大学 一种场景增强型电力负荷运行控制方法及装置
CN115790804A (zh) * 2023-02-08 2023-03-14 福建省智能交通信息工程有限公司 动态汽车衡状态监测方法、介质、设备及装置
CN115865716A (zh) * 2022-11-16 2023-03-28 杭州颉码能源科技有限公司 一种网络状态分析方法、***及计算机可读介质
CN116384568A (zh) * 2023-03-16 2023-07-04 南方科技大学 一种电动汽车充电负荷预测方法、***、设备及介质
CN116415510A (zh) * 2023-06-12 2023-07-11 国网江西省电力有限公司电力科学研究院 基于相空间重构和神经网络的断路器温升预测方法及***
CN116701949A (zh) * 2023-08-07 2023-09-05 苏州思萃融合基建技术研究所有限公司 一种基于区域环境数据的空间点位监测模型的训练方法
CN116872780A (zh) * 2023-09-08 2023-10-13 国网浙江省电力有限公司杭州供电公司 一种电动汽车充电供应控制方法、装置、终端及介质
CN117220417A (zh) * 2023-11-07 2023-12-12 国网山西省电力公司信息通信分公司 消费端电负荷动态监测方法及***
CN117239731A (zh) * 2023-09-21 2023-12-15 山东工商学院 基于混合模型的节假日短期电力负荷预测方法
CN117239743A (zh) * 2023-11-15 2023-12-15 青岛鼎信通讯股份有限公司 一种电能表用电负荷获取方法、装置、设备及介质
CN117236800A (zh) * 2023-11-14 2023-12-15 齐信科技(北京)有限公司 一种多场景自适应的用电负荷预测方法及***
CN117584790A (zh) * 2023-11-23 2024-02-23 北京海蓝云联技术有限公司 一种无增容充电桩控制***
CN117669993A (zh) * 2024-01-30 2024-03-08 南方科技大学 一种渐进式充电设施规划方法、装置、终端及存储介质
CN117833353A (zh) * 2023-11-30 2024-04-05 国家电网有限公司华东分部 电网有功控制智能体的仿真训练方法、装置及设备
CN117909928A (zh) * 2024-03-19 2024-04-19 国网四川省电力公司成都供电公司 基于大数据分析的空调负荷预测方法及***

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113837480B (zh) * 2021-09-29 2023-11-07 河北工业大学 基于改进gru和差分误差补偿的冲击性负荷预测方法
CN114498634B (zh) * 2022-02-17 2023-08-29 四川大学 一种基于电表数据的电动汽车充电负荷预测方法
CN114919433B (zh) * 2022-05-27 2022-12-09 深圳先进技术研究院 电动汽车集群充放电控制方法、***及相关设备
CN114966413B (zh) * 2022-05-27 2023-03-24 深圳先进技术研究院 一种储能电池包的荷电状态预测方法
CN117040028B (zh) * 2023-09-28 2024-01-09 泰豪科技(深圳)电力技术有限公司 一种工商业园区光储充微电网的控制策略优化方法及***
CN117937475A (zh) * 2024-03-21 2024-04-26 合肥工业大学 基于多模态时序学习的负荷预测模型、方法和***

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130110756A1 (en) * 2011-10-31 2013-05-02 Siemens Corporation Short-term Load Forecast Using Support Vector Regression and Feature Learning
CN109711620A (zh) * 2018-12-26 2019-05-03 浙江大学 一种基于gru神经网络和迁移学习的短期电力负荷预测方法
CN110263984A (zh) * 2019-06-04 2019-09-20 南瑞集团有限公司 基于相空间重构和深度神经网络的超短期净负荷预测方法
CN110633867A (zh) * 2019-09-23 2019-12-31 国家电网有限公司 一种基于gru和注意力机制的超短期负荷预测模型
CN111476435A (zh) * 2020-04-30 2020-07-31 国核电力规划设计研究院有限公司 基于密度峰值的充电桩负荷预测方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130110756A1 (en) * 2011-10-31 2013-05-02 Siemens Corporation Short-term Load Forecast Using Support Vector Regression and Feature Learning
CN109711620A (zh) * 2018-12-26 2019-05-03 浙江大学 一种基于gru神经网络和迁移学习的短期电力负荷预测方法
CN110263984A (zh) * 2019-06-04 2019-09-20 南瑞集团有限公司 基于相空间重构和深度神经网络的超短期净负荷预测方法
CN110633867A (zh) * 2019-09-23 2019-12-31 国家电网有限公司 一种基于gru和注意力机制的超短期负荷预测模型
CN111476435A (zh) * 2020-04-30 2020-07-31 国核电力规划设计研究院有限公司 基于密度峰值的充电桩负荷预测方法

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114744662B (zh) * 2022-06-13 2022-08-26 华北电力大学 一种基于多类型电动汽车的电网调峰方法及***
CN114744662A (zh) * 2022-06-13 2022-07-12 华北电力大学 一种基于多类型电动汽车的电网调峰方法及***
CN114792177A (zh) * 2022-06-24 2022-07-26 中煤科工开采研究院有限公司 综采工作面的多液压支架载荷预测方法、装置及电子设备
CN115498629A (zh) * 2022-09-06 2022-12-20 清华大学 一种场景增强型电力负荷运行控制方法及装置
CN115865716A (zh) * 2022-11-16 2023-03-28 杭州颉码能源科技有限公司 一种网络状态分析方法、***及计算机可读介质
CN115790804B (zh) * 2023-02-08 2023-04-21 福建省智能交通信息工程有限公司 动态汽车衡状态监测方法、介质、设备及装置
CN115790804A (zh) * 2023-02-08 2023-03-14 福建省智能交通信息工程有限公司 动态汽车衡状态监测方法、介质、设备及装置
CN116384568A (zh) * 2023-03-16 2023-07-04 南方科技大学 一种电动汽车充电负荷预测方法、***、设备及介质
CN116384568B (zh) * 2023-03-16 2024-01-30 南科智慧能源(深圳)有限公司 一种电动汽车充电负荷预测方法、***、设备及介质
CN116415510A (zh) * 2023-06-12 2023-07-11 国网江西省电力有限公司电力科学研究院 基于相空间重构和神经网络的断路器温升预测方法及***
CN116415510B (zh) * 2023-06-12 2023-09-12 国网江西省电力有限公司电力科学研究院 基于相空间重构和神经网络的断路器温升预测方法及***
CN116701949A (zh) * 2023-08-07 2023-09-05 苏州思萃融合基建技术研究所有限公司 一种基于区域环境数据的空间点位监测模型的训练方法
CN116701949B (zh) * 2023-08-07 2023-10-20 苏州思萃融合基建技术研究所有限公司 一种基于区域环境数据的空间点位监测模型的训练方法
CN116872780B (zh) * 2023-09-08 2023-12-15 国网浙江省电力有限公司杭州供电公司 一种电动汽车充电供应控制方法、装置、终端及介质
CN116872780A (zh) * 2023-09-08 2023-10-13 国网浙江省电力有限公司杭州供电公司 一种电动汽车充电供应控制方法、装置、终端及介质
CN117239731A (zh) * 2023-09-21 2023-12-15 山东工商学院 基于混合模型的节假日短期电力负荷预测方法
CN117239731B (zh) * 2023-09-21 2024-02-27 山东工商学院 基于混合模型的节假日短期电力负荷预测方法
CN117220417A (zh) * 2023-11-07 2023-12-12 国网山西省电力公司信息通信分公司 消费端电负荷动态监测方法及***
CN117220417B (zh) * 2023-11-07 2024-02-09 国网山西省电力公司信息通信分公司 消费端电负荷动态监测方法及***
CN117236800A (zh) * 2023-11-14 2023-12-15 齐信科技(北京)有限公司 一种多场景自适应的用电负荷预测方法及***
CN117236800B (zh) * 2023-11-14 2024-02-20 齐信科技(北京)有限公司 一种多场景自适应的用电负荷预测方法及***
CN117239743A (zh) * 2023-11-15 2023-12-15 青岛鼎信通讯股份有限公司 一种电能表用电负荷获取方法、装置、设备及介质
CN117239743B (zh) * 2023-11-15 2024-02-27 青岛鼎信通讯股份有限公司 一种电能表用电负荷获取方法、装置、设备及介质
CN117584790A (zh) * 2023-11-23 2024-02-23 北京海蓝云联技术有限公司 一种无增容充电桩控制***
CN117833353A (zh) * 2023-11-30 2024-04-05 国家电网有限公司华东分部 电网有功控制智能体的仿真训练方法、装置及设备
CN117669993A (zh) * 2024-01-30 2024-03-08 南方科技大学 一种渐进式充电设施规划方法、装置、终端及存储介质
CN117909928A (zh) * 2024-03-19 2024-04-19 国网四川省电力公司成都供电公司 基于大数据分析的空调负荷预测方法及***
CN117909928B (zh) * 2024-03-19 2024-05-28 国网四川省电力公司成都供电公司 基于大数据分析的空调负荷预测方法及***

Also Published As

Publication number Publication date
CN112200373A (zh) 2021-01-08

Similar Documents

Publication Publication Date Title
WO2022077693A1 (zh) 负荷预测模型的训练方法及训练装置、存储介质、设备
CN110341690B (zh) 一种基于确定性策略梯度学习的phev能量管理方法
Kanarachos et al. Instantaneous vehicle fuel consumption estimation using smartphones and recurrent neural networks
CN112686464A (zh) 短期风电功率预测方法及装置
Huang et al. Ensemble learning for charging load forecasting of electric vehicle charging stations
CN109920248B (zh) 一种基于gru神经网络的公交到站时间预测方法
Kim et al. Idle vehicle relocation strategy through deep learning for shared autonomous electric vehicle system optimization
CN115425680B (zh) 一种多能源联合发电***的功率预测模型构建及预测方法
Petkevicius et al. Probabilistic deep learning for electric-vehicle energy-use prediction
CN115063184A (zh) 电动汽车充电需求建模方法、***、介质、设备及终端
CN116298936A (zh) 在不完全电压范围内的锂离子电池智能健康状态预测方法
CN112036598A (zh) 一种基于多信息耦合的充电桩使用信息预测方法
CN114692956A (zh) 基于多层优化核极限学习机的充电设施负荷预测方法及***
Shi et al. Load Forecasting of Electric Vehicle Charging Stations: Attention Based Spatiotemporal Multi-Graph Convolutional Networks
He et al. Neural computing for grey Richards differential equation to forecast traffic parameters with various time granularity
CN112527547A (zh) 一种基于自动卷积神经网络的机械智能故障预测方法
CN117150334A (zh) 一种基于优化后的BiLSTM神经网络的锂电池多状况预测方法和装置
CN116486611A (zh) 一种城市道路车辆速度预测方法
CN115511203A (zh) 基于锂电池荷电状态估计电动船舶航程优化方法及***
CN114566048A (zh) 一种基于多视角自适应时空图网络的交通控制方法
Heimrath et al. Reflex-augmented reinforcement learning for operating strategies in automotive electrical energy management
CN116628395B (zh) 一种基于城市地形特征的道路车辆碳排放测算方法及***
Minjie et al. Short-term wind speed prediction based on improved CEEMD-FOA-LSSVM
Jing et al. SOC Estimation of Lithium Batteries Based on Cluster-Growing Leaky Intergrator Echo State Network
Guo et al. Optimization Analysis of Hydrogen Fuel Cell Hybrid Power Based on Neural Network and Sensor Networks

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20957467

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20957467

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20957467

Country of ref document: EP

Kind code of ref document: A1