CN111882114A - Short-term traffic flow prediction model construction method and prediction method - Google Patents
Short-term traffic flow prediction model construction method and prediction method Download PDFInfo
- Publication number
- CN111882114A CN111882114A CN202010628317.5A CN202010628317A CN111882114A CN 111882114 A CN111882114 A CN 111882114A CN 202010628317 A CN202010628317 A CN 202010628317A CN 111882114 A CN111882114 A CN 111882114A
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- short
- prediction
- time traffic
- data set
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000010276 construction Methods 0.000 title claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000003062 neural network model Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 210000002569 neuron Anatomy 0.000 claims description 2
- 238000003064 k means clustering Methods 0.000 abstract description 7
- 238000013528 artificial neural network Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- 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
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a short-time traffic flow prediction model construction method and a prediction method, wherein the short-time traffic flow prediction model construction method and the prediction method are used for clustering traffic flow data in a period of time, fully extracting data information and inputting the data information into a GRU neural network, taking the type of a short-time traffic flow mode as output, training the GRU neural network model, obtaining the short-time traffic flow prediction model after the training is finished, and realizing the prediction of the short-time traffic flow. Aiming at the fact that the influence of training set selection of the neural network on the prediction result of the short-time traffic flow is obvious, the K-Means clustering algorithm is adopted to cluster historical short-time traffic flow data, prediction is carried out in a targeted mode, and the accuracy of the prediction result is improved.
Description
Technical Field
The invention belongs to the field of intelligent traffic systems, and particularly relates to a short-time traffic flow prediction model construction method and a prediction method.
Background
The intelligent traffic system applies modern technical achievements to traffic planning and management, establishes an intelligent traffic management system, has the remarkable advantages of the intelligent traffic system in real time, is accurate and efficient, and can enable relevant departments to timely master traffic conditions of concerned areas through feedback of the intelligent traffic system, thereby effectively guiding traffic operation, reducing or even avoiding occurrence rate of traffic jam, and providing information support for urban road planning, energy conservation and emission reduction.
With the rise of artificial intelligence research enthusiasm, neural network models have achieved remarkable results in short-term traffic flow prediction. However, the short-time traffic flow time sequence distribution is greatly influenced by factors such as different road conditions, different weather conditions and different dates, so that the conventional neural network model cannot accurately predict the traffic flow.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a short-time traffic flow prediction method based on K-Means clustering and a GRU network, and solve the technical problem that the prior art cannot accurately predict the traffic flow.
In order to solve the technical problem, the application adopts the following technical scheme:
a short-time traffic flow prediction model construction method comprises the following steps:
step 4, training the training data set formed in the step 3 by using a GRU neural network model, and obtaining a short-time traffic flow prediction model after training is completed;
the GRU neural network model adopts a stack structure and comprises an input layer, a first GRU unit layer, a second GRU unit layer and a third GRU unit layer which are sequentially connected, and a dropout layer used for preventing over-fitting is connected behind the third GRU unit layer.
Specifically, the preprocessing in step 1 includes data deletion, data interpolation, data denoising, and normalization.
Specifically, the step 2 of clustering the short-time traffic flow data obtained in the step 1 by using a K-Means algorithm to obtain short-time traffic flow categories, and forming a short-time traffic flow category pattern library specifically includes: and selecting K points as an initial clustering center for clustering, wherein the value range of K is 2-7.
Specifically, the parameter setting of the GRU network in step 3 includes: prediction step size 8, number of hidden layer neurons 12, learning rate 0.02, and iteration number 800.
A short-term traffic flow prediction method, the method comprising the steps of:
and 2, inputting the preprocessed traffic flow data set to be predicted into the short-time traffic flow prediction model obtained by the short-time traffic flow prediction model construction method according to any one of claims 1 to 5, and obtaining the category of the short-time traffic flow to be predicted.
Compared with the prior art, the invention has the beneficial technical effects that:
according to the invention, a K-Means clustering method is combined with the GRU neural network, the influence of the training set selection of the neural network on the prediction result of the short-time traffic flow is obvious, the historical short-time traffic flow data is clustered by adopting a K-Means clustering algorithm, the prediction is carried out in a targeted manner, and the accuracy of the prediction result is improved.
Drawings
FIG. 1 is a flowchart of the process of the present invention;
FIG. 2 is a K-means clustering result graph obtained in example 1 of the present invention;
FIG. 3GRU prediction model flow diagram.
Fig. 4 is a diagram showing a result of predicting the short-term traffic flow obtained in embodiment 1 of the present invention, in which a solid line indicates an actual short-term traffic flow and a broken line indicates a predicted value;
FIG. 5 is a comparison graph of prediction errors for the KMeans-GRU model, the conventional GRU network model, the ARIMA model, and the SAEs model.
The invention is described in detail below with reference to the drawings and the detailed description.
Detailed Description
The overall technical concept and the technical principle of the invention are as follows: clustering traffic flow data in a period of time, fully extracting data information, inputting the data information into a GRU neural network, taking a short-time traffic flow mode type as output, training a GRU neural network model, and obtaining a short-time traffic flow prediction model after training is completed, so that accurate prediction of short-time traffic flow is realized.
The following definitions or conceptual connotations relating to the present invention are provided for illustration:
euclidean metric (also known as euclidean distance) is a commonly used definition of distance, referring to the true distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance of the point from the origin). The euclidean distance in two and three dimensions is the actual distance between two points.
A second norm: is 2 norm of the matrix A, is the square root value of the maximum characteristic root of the product of the transposed conjugate matrix of A and the matrix A, and is the linear distance between two vector matrixes in space.
In order to make the objects and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and examples, and the advantages of the present invention are shown by comparative analysis. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The principle of the K-means clustering algorithm is as follows: and dividing n objects into k clusters by taking k as a parameter, so that the clusters have higher similarity and the similarity among the clusters is lower. The processing procedure of the K-means clustering algorithm is as follows: first, randomly selecting k objects as centroids, each object initially representing the mean or center of a cluster; for each object remaining, it is assigned to the closest cluster based on its distance from the center of the cluster, and the algorithm then iterates between the data assignment step and the centroid update step until a stopping criterion is met (i.e., no data points change, or the sum of cluster distances is minimized, or some maximum number of iterations is reached).
KNN classification: the core idea of the KNN model is simple, the Euclidean distance is measured between each test set sample point and each sample in a training set, then K points with the nearest Euclidean distance are selected (K is the number of neighbor choices which can be manually defined, and the determination of K can influence the algorithm result), the frequency of the categories of the K training set sample points is counted, and the category with the highest frequency is classified into the prediction category of the test sample point.
The invention also adopts a plurality of model evaluation indexes to compare to evaluate the quality of the prediction result, including the square percentage error (MAPE), the square absolute error (MAE) and the Root Mean Square Error (RMSE).
For the errors of the square percentage error, the square absolute error and the root mean square error, the smaller the error, the better the prediction effect is.
Example (b):
this example
Step 1: and acquiring traffic flow data within a period of history and in a short time, and then performing data filling and deleting or data denoising and normalization related preprocessing to obtain a preprocessed traffic flow data set.
As a specific implementation mode of the invention, the acquisition of the traffic flow data can be directly downloaded to an official database or independently detected by the user. The historical traffic flow data in this embodiment is downloaded from the U.S. PeMS database, and includes 8928 pieces of data counted once from 1/2018 to 31/2018 in 1/month.
Step 11: for the input short-time traffic flow historical data, firstly, judging whether the short-time traffic flow historical data is a null value, if the short-time traffic flow historical data is the null value, executing deleting operation, and if the duty ratio of the traffic flow data in one day is more than 20%, deleting the completely filled traffic flow data;
step 12: if not, judging whether the data is abnormal data according to the formula (1).
Wherein q represents short-term traffic flow, C represents maximum road traffic capacity, T represents flow data acquisition time interval, and fcIndicating the correction factor. If the data is abnormal, the data is deleted and then interpolated by using the average value of the previous value and the next value.
Step 13: the min-max normalization method is used for processing short-time traffic flow data, and is as follows:
wherein, XiRepresenting the ith sample value, Xi' denotes a normalized value of the i-th sample, XmaxDenotes the maximum value, X, in the sampleminRepresenting the minimum value in the sample.
Step 2: and (3) clustering the data in the preprocessed traffic flow data set obtained in the step (1) by using a K-Means algorithm to obtain a short-time traffic flow mode type, and establishing a short-time traffic flow mode library.
Step 21: firstly, K points are selected as initial clustering centers (the value range of K is generally [2-7 ]). In this example, K is 3.
Step 22: and distributing the data in the preprocessed traffic flow data set.
Each centroid defines a cluster. In this step, the distance between the data points is calculated using the euclidean distance based on the 2 norm, assigning each data point to the centroid closest to its distance, as in equation (3). If c isiIs a set of centroids in set C, then point x in the data set will all be assigned to a centroid-based CiIn the cluster of (3).
Where dist () is the euclidean distance under a 2 norm.
Step 23: centroid updating
In this step, the centroid is updated by calculating the mean of all data points, as in equation (4):
and continuously iterating the step 1 and the step 2 until no data point changes the class cluster, and the sum of the prime distances of each data point in the cluster reaches the minimum or the maximum iteration number, as shown in fig. 2.
And step 3: and (3) selecting the short-time traffic flow of 24 time points (the first 2 hours) of the date to be predicted as a state vector, and taking the Euclidean distance between the short-time traffic flow of the 24 time points and the short-time traffic flow in the short-time traffic flow mode library obtained in the step (2) as an index for measuring the similarity of data.
Step 31: and calculating the Euclidean distance between all data points obtained in the interval from 0 point in 1 month and 1 day of 2018 to 24 points in 30 months and 1 month of 2018 and data obtained 24 moments before 0 point in 31 months and 0 points in 1 month of 2018.
Step 32: and (4) arranging the calculated Euclidean distances 24 moments before the 0 point of 31 days of 1 month and 31 months in 2018 from small to large.
Step 33: the N sample points with the smallest distance to the unknown sample are determined and selected (the range is selected to be 3-7 in the embodiment application example).
Step 34: the occurrence frequency of the category to which the selected N points belong is counted, and N is selected to be 5 in this embodiment.
Step 35: and taking the category with the highest frequency of occurrence as the category of the current sampling point.
And 4, step 4: and selecting data in the category most similar to the traffic flow mode of 31/1/2018 as training data of the GRU network, and then predicting by using the designed GRU network.
The GRU network comprises 1 input layer, 3GRU unit layers, 1 dropout layer and 1 output layer, and the structure is shown in figure 3. The GRU prediction model structure adopts a stack structure, and a multilayer structure can carry out deeper expression on data. Gru _1_ input the input 3 parameters none, 12, 1 in the input layer indicate the number of samples, time step and variable dimension of the input data of the input layer of the network, and the parameters of the output of the previous layer must be the same as the parameter dimension of the input of the next layer, as shown in fig. 4.5. The Dropout layer (with parameter value range of 0-0.2) connected behind the 3-layer GRU network is used for reducing overfitting of the GRU network, and the last Dense (full connection) layer converts multidimensional data output by the GRU into one-dimensional output.
The hyper-parameter settings for the GRU network are shown in table 1.
Table 1 GRU network hyper-parameter settings
Fig. 4 is a diagram of a prediction result using this method, in which a blue solid line indicates an actual short-time traffic flow and an orange solid line indicates a predicted value.
FIG. 5 is a graph comparing error of KMeans-GRU model, conventional GRU network model, ARIMA model and SAEs model.
Error pairs of the prediction results of the KMeans-GRU prediction model and the conventional GRU network model, ARIMA model and SAEs model are as shown in table 2:
table 2 evaluation index comparison table of model
Claims (5)
1. A short-time traffic flow prediction model construction method is characterized by comprising the following steps:
step 1, obtaining traffic flow data in a period of time to obtain a traffic flow data set; preprocessing the obtained traffic flow data set to obtain a preprocessed traffic flow data set;
step 2, clustering the data in the preprocessed traffic flow data set obtained in the step 1 by using a K-Means algorithm to obtain a short-time traffic flow mode type, and establishing a short-time traffic flow mode library;
step 3, determining a prediction date, acquiring short-time traffic flow data of N moments before the prediction date, sequentially determining feature vectors of short-time traffic flow modes of the N moments, respectively determining the short-time traffic flow modes corresponding to the feature vectors of the N moments by using a classification method, and selecting the traffic flow data corresponding to the traffic mode with the highest occurrence frequency of the short-time traffic flow modes corresponding to the N moments to form a training data set;
step 4, training the training data set formed in the step 3 by using a GRU neural network model, and obtaining a short-time traffic flow prediction model after training is completed;
the GRU neural network model adopts a stack structure and comprises an input layer, a first GRU unit layer, a second GRU unit layer and a third GRU unit layer which are sequentially connected, and a dropout layer used for preventing over-fitting is connected behind the third GRU unit layer.
2. The method for constructing a short-term traffic flow prediction model according to claim 1, wherein the preprocessing in the step 1 includes data deletion, data interpolation, data denoising and normalization.
3. The method for constructing a short-term traffic flow prediction model according to claim 1, wherein the step 2 of clustering the short-term traffic flow data obtained in the step 1 by using a K-Means algorithm to obtain the short-term traffic flow category specifically comprises: the value range of an initial clustering center K of the K-Means algorithm is 2-7.
4. The short-term traffic flow prediction model construction method according to claim 1, wherein the parameter setting of the GRU network of step 4 includes: prediction step size 8, number of hidden layer neurons 12, learning rate 0.02, and iteration number 800.
5. A short-term traffic flow prediction method, characterized in that the method comprises the steps of:
step 1, obtaining a traffic flow data set to be predicted and preprocessing the traffic flow data set to obtain a preprocessed traffic flow data set to be predicted;
step 2, inputting the preprocessed traffic flow data set to be predicted into the short-time traffic flow prediction model obtained by the short-time traffic flow prediction model construction method according to any one of claims 1 to 4, and obtaining the short-time traffic flow category to be predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010628317.5A CN111882114B (en) | 2020-07-01 | 2020-07-01 | Short-time traffic flow prediction model construction method and prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010628317.5A CN111882114B (en) | 2020-07-01 | 2020-07-01 | Short-time traffic flow prediction model construction method and prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111882114A true CN111882114A (en) | 2020-11-03 |
| CN111882114B CN111882114B (en) | 2023-10-31 |
Family
ID=73149869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010628317.5A Active CN111882114B (en) | 2020-07-01 | 2020-07-01 | Short-time traffic flow prediction model construction method and prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111882114B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561188A (en) * | 2020-12-22 | 2021-03-26 | 广州杰赛科技股份有限公司 | People flow prediction method and device |
| CN113763700A (en) * | 2021-04-26 | 2021-12-07 | 腾讯云计算（北京）有限责任公司 | Information processing method, information processing device, computer equipment and storage medium |
| CN114255591A (en) * | 2021-12-17 | 2022-03-29 | 重庆中信科信息技术有限公司 | Short-term traffic flow prediction method and device considering space-time correlation and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013128486A1 (en) * | 2012-02-29 | 2013-09-06 | 株式会社 日立製作所 | Traffic amount prediction system |
| CN105701571A (en) * | 2016-01-13 | 2016-06-22 | 南京邮电大学 | Short-term traffic flow prediction method based on nerve network combination model |
| CN106875511A (en) * | 2017-03-03 | 2017-06-20 | 深圳市唯特视科技有限公司 | A kind of method for learning driving style based on own coding regularization network |
| CN107154150A (en) * | 2017-07-25 | 2017-09-12 | 北京航空航天大学 | A kind of traffic flow forecasting method clustered based on road with double-layer double-direction LSTM |
| CN109711640A (en) * | 2019-01-23 | 2019-05-03 | 北京工业大学 | A kind of Short-time Traffic Flow Forecasting Methods based on fuzzy C-mean algorithm magnitude of traffic flow cluster and error feedback convolutional neural networks |
| CN110827544A (en) * | 2019-11-11 | 2020-02-21 | 重庆邮电大学 | Short-term traffic flow control method based on graph convolution recurrent neural network |
-
2020
- 2020-07-01 CN CN202010628317.5A patent/CN111882114B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013128486A1 (en) * | 2012-02-29 | 2013-09-06 | 株式会社 日立製作所 | Traffic amount prediction system |
| CN105701571A (en) * | 2016-01-13 | 2016-06-22 | 南京邮电大学 | Short-term traffic flow prediction method based on nerve network combination model |
| CN106875511A (en) * | 2017-03-03 | 2017-06-20 | 深圳市唯特视科技有限公司 | A kind of method for learning driving style based on own coding regularization network |
| CN107154150A (en) * | 2017-07-25 | 2017-09-12 | 北京航空航天大学 | A kind of traffic flow forecasting method clustered based on road with double-layer double-direction LSTM |
| CN109711640A (en) * | 2019-01-23 | 2019-05-03 | 北京工业大学 | A kind of Short-time Traffic Flow Forecasting Methods based on fuzzy C-mean algorithm magnitude of traffic flow cluster and error feedback convolutional neural networks |
| CN110827544A (en) * | 2019-11-11 | 2020-02-21 | 重庆邮电大学 | Short-term traffic flow control method based on graph convolution recurrent neural network |
Non-Patent Citations (3)
| Title |
|---|
| JINLEI Z.等: "Cluster-Based LSTM Network for Short-Term Passenger Flow Forecasting in Urban Rail Transit", IEEE ACCESS * |
| 刘明宇 等: "基于深度学习的交通流量预测", 系统仿真学报, pages 4100 - 4114 * |
| 徐秀娟;张文轩;陈谆悦;赵小薇;许真珍;: "城市交通重大事件的客流预测实验设计与实现", 实验室科学, no. 01 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561188A (en) * | 2020-12-22 | 2021-03-26 | 广州杰赛科技股份有限公司 | People flow prediction method and device |
| CN113763700A (en) * | 2021-04-26 | 2021-12-07 | 腾讯云计算（北京）有限责任公司 | Information processing method, information processing device, computer equipment and storage medium |
| CN114255591A (en) * | 2021-12-17 | 2022-03-29 | 重庆中信科信息技术有限公司 | Short-term traffic flow prediction method and device considering space-time correlation and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111882114B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
| CN111199016B (en) | Daily load curve clustering method for improving K-means based on DTW | |
| CN112508275B (en) | Power distribution network line load prediction method and equipment based on clustering and trend indexes | |
| CN109063911B (en) | Load aggregation grouping prediction method based on gated cycle unit network | |
| CN111882114B (en) | Short-time traffic flow prediction model construction method and prediction method | |
| CN107967542B (en) | Long-short term memory network-based electricity sales amount prediction method | |
| CN111105104A (en) | Short-term power load prediction method based on similar day and RBF neural network | |
| CN108388962B (en) | Wind power prediction system and method | |
| CN110674999A (en) | Cell load prediction method based on improved clustering and long-short term memory deep learning | |
| CN115270965A (en) | Power distribution network line fault prediction method and device | |
| CN110969290A (en) | Runoff probability prediction method and system based on deep learning | |
| CN111008726B (en) | Class picture conversion method in power load prediction | |
| CN111178585A (en) | Fault reporting amount prediction method based on multi-algorithm model fusion | |
| CN113537469B (en) | Urban water demand prediction method based on LSTM network and Attention mechanism | |
| CN112329990A (en) | User power load prediction method based on LSTM-BP neural network | |
| CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
| CN115564114A (en) | Short-term prediction method and system for airspace carbon emission based on graph neural network | |
| CN112330052A (en) | Distribution transformer load prediction method | |
| CN115860177A (en) | Photovoltaic power generation power prediction method based on combined machine learning model and application thereof | |
| CN115600729A (en) | Grid load prediction method considering multiple attributes | |
| CN112036598A (en) | Charging pile use information prediction method based on multi-information coupling | |
| CN115018200A (en) | Power load prediction method and system based on deep learning and considering multiple influence factors | |
| CN114819395A (en) | Industry medium and long term load prediction method based on long and short term memory neural network and support vector regression combination model | |
| CN109214610A (en) | A kind of saturation Methods of electric load forecasting based on shot and long term Memory Neural Networks | |
| CN115794805B (en) | Method for supplementing measurement data of medium-low voltage distribution network |
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 |