CN111310964B - Load prediction method and device - Google Patents

Load prediction method and device Download PDF

Info

Publication number
CN111310964B
CN111310964B CN201811521010.4A CN201811521010A CN111310964B CN 111310964 B CN111310964 B CN 111310964B CN 201811521010 A CN201811521010 A CN 201811521010A CN 111310964 B CN111310964 B CN 111310964B
Authority
CN
China
Prior art keywords
load predicted
predicted value
model
bpnn
initial load
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
CN201811521010.4A
Other languages
Chinese (zh)
Other versions
CN111310964A (en
Inventor
刘松
刘鹏
崔亚明
俞石洪
横山隆一
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.)
Changchun University of Science and Technology
Original Assignee
Changchun University of Science and Technology
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 Changchun University of Science and Technology filed Critical Changchun University of Science and Technology
Priority to CN201811521010.4A priority Critical patent/CN111310964B/en
Publication of CN111310964A publication Critical patent/CN111310964A/en
Application granted granted Critical
Publication of CN111310964B publication Critical patent/CN111310964B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

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

Abstract

The invention discloses a load prediction method and a load prediction device, wherein the method comprises the following steps: receiving a first initial load predicted value currently output by at least two single prediction models; inputting each first initial load predicted value into a pre-trained Back Propagation Neural Network (BPNN) model; and determining a target load predicted value based on the BPNN model. In the embodiment of the invention, when the load prediction is carried out, the first initial load predicted value is firstly determined based on the single predicted model, then each first initial load predicted value is input into the pre-trained BPNN model, and the target load predicted value is determined by combining each first initial load predicted value based on the BPNN model, so that the problem that the single model is prone to being trapped into local optimization under the conditions of poor convergence, large fluctuation and influence of emergency on data sets is avoided, and the determined target load predicted value is more accurate.

Description

Load prediction method and device
Technical Field
The present invention relates to the field of load prediction technologies, and in particular, to a load prediction method and apparatus.
Background
Short-term load prediction is the basis for planning and normal operation of a power system, and is related to power generation, scheduling, decision-making and the like of the power system. Therefore, the short-term load prediction is always a hotspot of research of experts at home and abroad. The accuracy of short-term load prediction is improved, and the accuracy is important to the operation efficiency, benefit and safety of the power system.
In the prior art, when short-term load prediction is performed, the prediction is generally performed by a single method such as time sequence, regression analysis, support vector machine and the like. The prediction method in the prior art has a good prediction effect on the data set with obvious trend and strong convergence. However, when a single method predicts, the prediction method in the prior art often has the problem of being in local optimization under the conditions of poor convergence, large fluctuation and influence of an emergency, so that the accuracy of a prediction result is poor.
Disclosure of Invention
The embodiment of the invention provides a load prediction method and device, which are used for solving the problem of inaccurate load prediction in the prior art.
The embodiment of the invention provides a load prediction method, which comprises the following steps: receiving a first initial load predicted value currently output by at least two single prediction models;
Inputting each first initial load predicted value into a pre-trained Back Propagation Neural Network (BPNN) model;
and determining a target load predicted value based on the BPNN model.
Further, before the receiving the initial load predicted values output by the at least two single prediction models, the method further includes:
and respectively inputting the acquired data within the preset time length into at least two single prediction models.
Further, the determining a target load prediction value based on the BPNN model includes:
and determining a target load predicted value according to the first weight of each input layer, the second weight of each output layer and each input first initial load predicted value in the BPNN model.
Further, the training model of the BPNN model includes:
And inputting the second initial load predicted values of each group in the training set and the load true values corresponding to the second initial load predicted values of the group into a BPNN model, and training the BPNN model.
Further, the method further comprises:
Determining test load predicted values corresponding to the third initial load predicted values of each group of the third initial load predicted values of the preset number in the test set based on the BPNN model;
determining an error evaluation value of the BPNN model according to each test load predicted value and a load true value corresponding to each test load predicted value;
and judging whether the error evaluation value is smaller than a preset threshold value, and if so, determining that the BPNN model training is completed.
In another aspect, an embodiment of the present invention provides a load prediction apparatus, including:
The receiving module is used for receiving the first initial load predicted value currently output by the at least two single prediction models;
The first input module is used for inputting each first initial load predicted value into a pre-trained Back Propagation Neural Network (BPNN) model;
And the determining module is used for determining a target load predicted value based on the BPNN model.
Further, the apparatus further comprises:
the second input module is used for respectively inputting the acquired data within the preset time length into at least two single prediction models.
Further, the determining module is specifically configured to determine a target load predicted value according to the first weight of each input layer and the second weight of each output layer in the BPNN model, and each input first initial load predicted value.
Further, the apparatus further comprises:
And the training module is used for inputting the second initial load predicted values of each group in the training set and the load true values corresponding to the second initial load predicted values of the group into the BPNN model, and training the BPNN model.
Further, the training module is further configured to determine, for each set of third initial load predicted values of a preset number in the test set, a test load predicted value corresponding to the set of third initial load predicted values based on the BPNN model; determining an error evaluation value of the BPNN model according to each test load predicted value and a load true value corresponding to each test load predicted value; and judging whether the error evaluation value is smaller than a preset threshold value, and if so, determining that the BPNN model training is completed.
The embodiment of the invention provides a load prediction method and a load prediction device, wherein the method comprises the following steps: receiving a first initial load predicted value currently output by at least two single prediction models; inputting each first initial load predicted value into a pre-trained Back Propagation Neural Network (BPNN) model; and determining a target load predicted value based on the BPNN model.
In the embodiment of the invention, when the load prediction is carried out, the first initial load predicted value is firstly determined based on the single predicted model, then each first initial load predicted value is input into the pre-trained BPNN model, and the target load predicted value is determined by combining each first initial load predicted value based on the BPNN model, so that the problem that the single model is prone to being trapped into local optimization under the conditions of poor convergence, large fluctuation and influence of emergency on data sets is avoided, and the determined target load predicted value is more accurate.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a load prediction process according to embodiment 1 of the present invention;
fig. 2 is a schematic diagram of a load prediction flow provided in embodiment 2 of the present invention;
FIG. 3 is a schematic structural diagram of a BPNN model provided in embodiment 3 of the present invention;
fig. 4 is a schematic structural diagram of a load prediction apparatus according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail below with reference to the attached drawings, wherein it is apparent that the embodiments described are only some, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1:
Fig. 1 is a schematic diagram of a load prediction process according to an embodiment of the present invention, where the process includes the following steps:
s101: a first initial load predictor is received for a current output of the at least two single predictive models.
S102: each first initial load predictor is input to a pre-trained back propagation neural network BPNN model.
S103: and determining a target load predicted value based on the BPNN model.
The load prediction method provided by the embodiment of the invention is applied to electronic equipment, and the electronic equipment can be equipment such as a PC (personal computer), a tablet personal computer and the like. The load prediction method provided by the embodiment of the invention comprises, but is not limited to, a short-term load prediction method applied to a power system.
In the embodiment of the invention, at least two single prediction models which are trained in advance are stored in the electronic equipment, wherein the single prediction models can be an autoregressive integral moving average ARIMA model, a support vector machine SVM model and the like. Before the electronic equipment determines the target load predicted value, first receiving the first initial load predicted value currently output by at least two single prediction models. The process of determining the first initial load predicted value based on the single prediction model belongs to the prior art, and is not described herein in detail.
The electronic equipment further stores a pre-trained Back Propagation Neural Network (BPNN) model, and after receiving the first initial load predicted values currently output by the at least two single predicted models, each first initial load predicted value is input into the pre-trained BPNN model. And determining a target load predicted value based on the BPNN model.
In the embodiment of the invention, when the load prediction is carried out, the first initial load predicted value is firstly determined based on the single predicted model, then each first initial load predicted value is input into the pre-trained BPNN model, and the target load predicted value is determined by combining each first initial load predicted value based on the BPNN model, so that the problem that the single model is prone to being trapped into local optimization under the conditions of poor convergence, large fluctuation and influence of emergency on data sets is avoided, and the determined target load predicted value is more accurate.
Example 2:
On the basis of the foregoing embodiments, in an embodiment of the present invention, before the receiving the initial load predicted values output by at least two single prediction models, the method further includes:
and respectively inputting the acquired data within the preset time length into at least two single prediction models.
In the embodiment of the invention, the preset time length can be three days, four days and the like, and the data in the preset time length can be a load value in the preset time length, or can be a load value in the preset time length and weather data in the preset time length. The weather data may be data of average temperature, average humidity, etc. For example, the weather data includes an average temperature for the first three days, an average humidity for the first three days, an average temperature for the day, an average humidity for the day, and the like.
And the electronic equipment respectively inputs the acquired data within the preset time length into at least two single prediction models, and then outputs a first initial load predicted value based on each single prediction model.
Fig. 2 is a schematic diagram of a load prediction flow provided in an embodiment of the present invention, as shown in fig. 2, because interference data may exist in data within a preset time period, the accuracy of a target load predicted value finally determined is affected by the interference data, and in order to make the determined target load predicted value more accurate, data needs to be preprocessed before the data are respectively input into at least two single prediction models. Specifically, a smaller first threshold value and a larger second threshold value can be stored in the electronic device, data smaller than the first threshold value and data larger than the second threshold value in the data are used as interference data, the interference data are filtered, and then the rest data are respectively input into a single prediction model. As shown in FIG. 2, the single prediction model includes an ARIMA model, a multiple regression model, a random forest model, and an SVM model. It should be noted that the single prediction model in fig. 2 is merely an example, and in the embodiment of the present invention, the type and number of the single prediction model are not limited. The electronic equipment respectively inputs the acquired data within the preset time length into an ARIMA model, a multiple regression model, a random forest model and an SVM model, determines a first initial load predicted value based on each single predicted model, and then inputs each first initial load predicted value into a BPNN model to determine a target load predicted value.
Example 3:
on the basis of the foregoing embodiments, in an embodiment of the present invention, the determining, based on the BPNN model, a target load prediction value includes:
and determining a target load predicted value according to the first weight of each input layer, the second weight of each output layer and each input first initial load predicted value in the BPNN model.
FIG. 3 is a schematic structural diagram of a BPNN model, which works as follows: the values of the input signal and the output signal are first compared using a multi-layer neural network and the mean square error is obtained with the desired output value. Finally, the mean square error is counter-propagated, and the internal weight neurons are continuously adjusted until the error meets the requirement. The BPNN model consists of three different constituent layers: an input layer, a hidden layer, and an output layer, each of which is composed of a number of neurons, as shown in fig. 3.
Assuming d input layer neurons, i output layer neurons, q hidden layer neurons; the first weight between the ith neuron of the input layer and the jth neuron of the hidden layer is Vih, and the second weight between the jth neuron of the hidden layer and the jth neuron of the output layer is Whj.
Note that the h neuron of the hidden layer receives input from the input layer as α h:
Wherein X i is the input to the hidden layer ith neuron;
Note that the j-th neuron of the output layer receives input from the hidden layer as β j:
where b h is the output of the h neuron of the hidden layer.
The target load predicted value may be determined according to the above formula from each of the first initial load predicted values, each of the first weights, and each of the second weights input to the BPNN model.
Example 4:
on the basis of the foregoing embodiments, in an embodiment of the present invention, the training model of the BPNN model includes:
And inputting the second initial load predicted values of each group in the training set and the load true values corresponding to the second initial load predicted values of the group into a BPNN model, and training the BPNN model.
In the embodiment of the invention, the initial load predicted value in the training set is taken as a second initial load predicted value, and the electronic equipment groups the second initial load predicted values, for example, the second initial load predicted value output by each single prediction model on the same day is taken as a group. And inputting the second initial load predicted values of each group in the training set and the load true values corresponding to the second initial load predicted values of the group into the BPNN model. And adjusting the parameters of the BPNN model according to the difference value between the load predicted value and the load actual value output by the BPNN model until the training of the BPNN model is completed.
Example 5:
in order to ensure the accuracy of the BPNN model, on the basis of the foregoing embodiments, in an embodiment of the present invention, the method further includes:
Determining test load predicted values corresponding to the third initial load predicted values of each group of the third initial load predicted values of the preset number in the test set based on the BPNN model;
determining an error evaluation value of the BPNN model according to each test load predicted value and a load true value corresponding to each test load predicted value;
and judging whether the error evaluation value is smaller than a preset threshold value, and if so, determining that the BPNN model training is completed.
The electronic device stores a test set for checking the accuracy of the BPNN model. In the embodiment of the invention, the initial load predicted value in the test set is used as a third initial load predicted value. When the accuracy of the BPNN model is verified, a preset number of third initial load predicted values in the test set can be selected, and the preset number can be 50, 80 and the like. And determining test load predicted values corresponding to the third initial load predicted values based on the BPNN model according to the third initial load predicted values. And then determining an error evaluation value of the BPNN model according to each test load predicted value and the load true value corresponding to each test load predicted value.
Specifically, in the embodiment of the present invention, the error evaluation value may be an absolute average error, an average absolute percentage error, or an average variance.
The absolute average error is calculated as:
The calculation formula of the average absolute percentage error is as follows:
The calculation formula of the average variance is:
Wherein S i is the ith test load predicted value, And the load real value corresponding to the ith test load predicted value.
The electronic device stores a preset threshold value, which may be a small value, such as 0.1, 0.2, etc. After determining the error evaluation value of the BPNN model, the electronic equipment judges whether the error evaluation value is smaller than a preset threshold value, and if so, the electronic equipment determines that the training of the BPNN model is completed. Otherwise, the BPNN model is continued to be trained.
Fig. 4 is a schematic structural diagram of a load prediction apparatus according to an embodiment of the present invention, where the apparatus includes:
A receiving module 41, configured to receive a first initial load predicted value currently output by at least two single prediction models;
A first input module 42 for inputting each first initial load predictor into a pre-trained back propagation neural network BPNN model;
a determining module 43, configured to determine a target load predicted value based on the BPNN model.
The apparatus further comprises:
The second input module 44 is configured to input the acquired data within the preset time period into at least two single prediction models respectively.
The determining module 43 is specifically configured to determine a target load predicted value according to the first weight of each input layer and the second weight of each output layer in the BPNN model, and each input first initial load predicted value.
The apparatus further comprises:
The training module 45 is configured to input, for each set of second initial load predicted values in the training set, the set of second initial load predicted values and a load true value corresponding to the set of second initial load predicted values into a BPNN model, and train the BPNN model.
The training module 45 is further configured to determine, for each set of third initial load predicted values of the preset number in the test set, a test load predicted value corresponding to the set of third initial load predicted values based on the BPNN model; determining an error evaluation value of the BPNN model according to each test load predicted value and a load true value corresponding to each test load predicted value; and judging whether the error evaluation value is smaller than a preset threshold value, and if so, determining that the BPNN model training is completed.
The embodiment of the invention provides a load prediction method and a load prediction device, wherein the method comprises the following steps: receiving a first initial load predicted value currently output by at least two single prediction models; inputting each first initial load predicted value into a pre-trained Back Propagation Neural Network (BPNN) model; and determining a target load predicted value based on the BPNN model.
In the embodiment of the invention, when the load prediction is carried out, the first initial load predicted value is firstly determined based on the single predicted model, then each first initial load predicted value is input into the pre-trained BPNN model, and the target load predicted value is determined by combining each first initial load predicted value based on the BPNN model, so that the problem that the single model is prone to being trapped into local optimization under the conditions of poor convergence, large fluctuation and influence of emergency on data sets is avoided, and the determined target load predicted value is more accurate.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (2)

1. A method of load prediction, the method comprising:
Receiving a first initial load predicted value currently output by at least two single prediction models;
Inputting each first initial load predicted value into a pre-trained Back Propagation Neural Network (BPNN) model;
Determining a target load predicted value based on the BPNN model;
Before the receiving the initial load predicted values output by the at least two single prediction models, the method further comprises:
Respectively inputting the acquired data within the preset time length into at least two single prediction models;
the determining a target load predicted value based on the BPNN model includes:
determining a target load predicted value according to the first weight of each input layer, the second weight of each output layer and each input first initial load predicted value in the BPNN model;
The training model of the BPNN model comprises the following steps:
inputting a set of second initial load predicted values and load true values corresponding to the set of second initial load predicted values into a BPNN model aiming at each set of second initial load predicted values in a training set, and training the BPNN model;
the method further comprises the steps of:
Determining test load predicted values corresponding to the third initial load predicted values of each group of the third initial load predicted values of the preset number in the test set based on the BPNN model;
determining an error evaluation value of the BPNN model according to each test load predicted value and a load true value corresponding to each test load predicted value;
and judging whether the error evaluation value is smaller than a preset threshold value, and if so, determining that the BPNN model training is completed.
2. A load predicting apparatus, the apparatus comprising:
The receiving module is used for receiving the first initial load predicted value currently output by the at least two single prediction models;
The first input module is used for inputting each first initial load predicted value into a pre-trained Back Propagation Neural Network (BPNN) model;
The determining module is used for determining a target load predicted value based on the BPNN model;
The apparatus further comprises:
the second input module is used for respectively inputting the acquired data within the preset time length into at least two single prediction models;
The determining module is specifically configured to determine a target load predicted value according to the first weight of each input layer and the second weight of each output layer in the BPNN model, and each input first initial load predicted value;
The apparatus further comprises:
The training module is used for inputting the second initial load predicted values of each group in the training set and the load true values corresponding to the second initial load predicted values of the group into the BPNN model to train the BPNN model;
The training module is further configured to determine, for each set of third initial load predicted values of a preset number in the test set, a test load predicted value corresponding to the set of third initial load predicted values based on the BPNN model; determining an error evaluation value of the BPNN model according to each test load predicted value and a load true value corresponding to each test load predicted value; and judging whether the error evaluation value is smaller than a preset threshold value, and if so, determining that the BPNN model training is completed.
CN201811521010.4A 2018-12-12 2018-12-12 Load prediction method and device Active CN111310964B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811521010.4A CN111310964B (en) 2018-12-12 2018-12-12 Load prediction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811521010.4A CN111310964B (en) 2018-12-12 2018-12-12 Load prediction method and device

Publications (2)

Publication Number Publication Date
CN111310964A CN111310964A (en) 2020-06-19
CN111310964B true CN111310964B (en) 2024-04-26

Family

ID=71146600

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811521010.4A Active CN111310964B (en) 2018-12-12 2018-12-12 Load prediction method and device

Country Status (1)

Country Link
CN (1) CN111310964B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107169683A (en) * 2017-06-30 2017-09-15 上海电力学院 A kind of grid-connected photovoltaic power station short term power combination forecasting method of variable weight coefficient
CN107992968A (en) * 2017-11-29 2018-05-04 成都思晗科技股份有限公司 Electric energy meter measurement error Forecasting Methodology based on integrated techniques of teime series analysis

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107169683A (en) * 2017-06-30 2017-09-15 上海电力学院 A kind of grid-connected photovoltaic power station short term power combination forecasting method of variable weight coefficient
CN107992968A (en) * 2017-11-29 2018-05-04 成都思晗科技股份有限公司 Electric energy meter measurement error Forecasting Methodology based on integrated techniques of teime series analysis

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Hongzhan NIE等.Hybrid of ARIMA and SVMs for Short-Term Load Forecasting.Energy Procedia.2012,全文. *
黄青平等.基于模糊聚类与随机森林的短期负荷预测.电测与仪表.2017,全文. *

Also Published As

Publication number Publication date
CN111310964A (en) 2020-06-19

Similar Documents

Publication Publication Date Title
US11409347B2 (en) Method, system and storage medium for predicting power load probability density based on deep learning
CN103730006B (en) A kind of combination forecasting method of Short-Term Traffic Flow
CN104217258B (en) A kind of electric load sigma-t Forecasting Methodology
CN104899135A (en) Software defect prediction method and system
CN110794308B (en) Method and device for predicting train battery capacity
CN112712214B (en) Method, system, device and storage medium for predicting track of maritime search and rescue object
CN110866640A (en) Power load prediction method based on deep neural network
CN103489034A (en) Method and device for predicting and diagnosing online ocean current monitoring data
CN115098330A (en) Equipment anomaly detection system and method based on cloud edge collaborative mode
CN106067077A (en) A kind of load forecasting method based on neutral net and device
CN103514488B (en) Power-system short-term load forecasting device and method based on combination forecasting
Suryo et al. Improved time series prediction using LSTM neural network for smart agriculture application
CN111898867A (en) Airplane final assembly production line productivity prediction method based on deep neural network
CN112257914A (en) Aviation safety cause and effect prediction method based on random forest
Salgado et al. A short-term bus load forecasting system
CN106067075B (en) Building energy load prediction model building and load prediction method and device
CN113850439A (en) Energy consumption prediction method, device, equipment and storage medium for rail transit station equipment
CN111310964B (en) Load prediction method and device
Tian et al. Software reliability prediction using recurrent neural network with Bayesian regularization
CN109961160A (en) A kind of power grid future operation trend predictor method and system based on trend parameter
CN116822722A (en) Water level prediction method, system, device, electronic equipment and medium
CN111400964A (en) Fault occurrence time prediction method and device
CN106339357A (en) Optimizing parameterized network information security detection system and method
CN110543942A (en) Multi-space-time long and short memory depth network accurate prediction method
CN115115167A (en) Campus security system and operation method thereof

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
TA01 Transfer of patent application right

Effective date of registration: 20231120

Address after: No.7089 Weixing Road, Changchun City, Jilin Province 130000

Applicant after: CHANGCHUN University OF SCIENCE AND TECHNOLOGY

Address before: 212200 Daquan Road, Xinba Town, Yangzhong City, Zhenjiang City, Jiangsu Province

Applicant before: YANGZHONG INTELLIGENT ELECTRICAL INSTITUTE, NORTH CHINA ELECTRIC POWER University

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant