CN116246463A - Traffic jam early warning method and system based on real-time big data - Google Patents
Traffic jam early warning method and system based on real-time big data Download PDFInfo
- Publication number
- CN116246463A CN116246463A CN202310085832.7A CN202310085832A CN116246463A CN 116246463 A CN116246463 A CN 116246463A CN 202310085832 A CN202310085832 A CN 202310085832A CN 116246463 A CN116246463 A CN 116246463A
- Authority
- CN
- China
- Prior art keywords
- derivative
- real
- time
- traffic flow
- traffic
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000001595 flow curve Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000013459 approach Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000012937 correction Methods 0.000 claims description 2
- 208000027744 congestion Diseases 0.000 description 36
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- 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
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Analytical Chemistry (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a traffic jam early warning method and a system based on real-time big data, wherein the method comprises the following steps: acquiring real-time traffic flow working condition big data, and extracting a real-time traffic flow typical characteristic value in a T period; obtaining a real-time traffic flow curve of a real-time traffic flow typical characteristic value-time sequence through data processing; based on the real-time traffic flow curve, obtaining a first derivative and a second derivative at the current moment; according to the variation trend of the first derivative and the second derivative, the first derivative is used for judging the traffic jam, the second derivative is used for judging the traffic jam trend, and the data information of the first derivative and the second derivative is integrated to judge the traffic jam condition and the traffic jam trend; and carrying out real-time early warning based on the judgment result. According to the invention, the real-time traffic flow curve of the traffic flow typical characteristic value-time sequence is obtained based on the real-time traffic flow working condition big data, the data characteristics represented by the first derivative and the second derivative of the curve are synthesized, the traffic jam condition is judged, and the timeliness and the foresight of traffic early warning are improved.
Description
Technical Field
The invention relates to the technical field of traffic engineering, in particular to a traffic jam early warning method and system based on real-time big data.
Background
In recent years, with the development of economy and society, the quantity of people-average cars is rapidly increased, and the traffic jam phenomenon is increasingly aggravated. Urban traffic jam not only can cause the extension of the passing time and inconvenient travel, but also can cause the discharge of more pollutants such as automobile exhaust. The prediction and management of urban traffic flow are long-term research objects, and are the origin of environmental protection and urban planning of various large cities.
The propagation of apparent information generated by urban traffic flow changes follows a certain diffusion rule, namely follows an information propagation dynamics principle and model, and is the most intuitive representation of various information generated by traffic jams, particularly information represented by average speed decline (or traffic flow rise) under the special condition caused by peak time or traffic accidents. The information represented by the traffic conditions has certain non-timeliness, namely certain hysteresis, and the hysteresis can in turn lead to more and more congestion, and the congestion peak is reached through successive propagation and conduction. After the traffic reaches the peak, the traffic is eliminated through artificial drainage or natural relief, and the urban traffic running condition is recovered. Therefore, in order to reduce adverse effects of traffic congestion on economic and social development, real-time prediction is performed on traffic congestion conditions, advanced congestion relief is flexibly and actively performed based on the prediction conditions, and the traffic congestion duration can be slowed down, so that prediction on the traffic congestion conditions is necessary.
Most of the existing traffic flow prediction modes are used for establishing a certain fitting function according to the characteristic of historical traffic big data through analysis and processing of the past data, and then predicting the trend of a period of time in the future by using the function. There are many current predictive methods tools such as linear regression, neural networks, random forests, etc. However, various prediction methods such as fitting, machine learning and the like collect data according to historical data, and the traffic condition can not be reflected basically in real time through modeling, automatic identification and prediction based on the minimum error; in addition, the prediction is performed through traffic video observation, resident report analysis and the like, so that the prediction needs to be manually identified, and the method is labor-consuming and labor-consuming, and has a large number of human factors.
That is, the existing prediction method has the following problems:
(1) The limitation and the lack of the historical data sample lead to a plurality of information shortages in the sample; moreover, not all cities have the ability to collect and store historical data.
(2) Although certain analogy exists in traffic conditions such as Monday, weekend, holiday and the like on specific dates, the history data and the real-time data have larger deviation finally due to the fact that the motor vehicle increases the variable day by day; in addition, in reality, because of the superposition influence of various weather, emergency and other factors, it is difficult to find the optimal independent variable and the direct mapping of the dependent variable;
(3) Some prediction methods, such as machine learning, have certain randomness in screening the features, pay attention to the goodness of fit to past data, cannot reasonably judge the sensitivity of each influence factor to the model, and too many features often cause the model to be over-fitted.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a traffic jam early warning method and a system based on real-time big data, which are characterized in that the obtained real-time traffic flow working condition big data are extracted to obtain a traffic flow typical characteristic value-time sequence real-time traffic flow curve in a set time period, the first derivative of the curve is used for judging traffic jam, the second derivative of the curve is used for judging traffic jam trend, so that real-time traffic jam prediction is realized, early warning is carried out based on the prediction result, the timeliness and the foresight of traffic early warning are improved, and the problem that the traffic condition cannot be reflected in real time in the existing method for predicting traffic flow based on historical data analysis processing is avoided.
In a first aspect, the present disclosure provides a traffic congestion early warning method based on real-time big data.
A traffic jam early warning method based on real-time big data comprises the following steps:
acquiring real-time traffic flow working condition big data, and extracting a real-time traffic flow typical characteristic value in a T period;
carrying out time sequence data processing on the typical characteristic value of the real-time traffic flow in the T period to obtain a real-time traffic flow curve of the typical characteristic value-time sequence of the real-time traffic flow;
obtaining a first derivative and a second derivative of the current moment based on a real-time traffic flow curve of a real-time traffic flow typical characteristic value-time sequence; according to the variation trend of the first derivative and the second derivative, the traffic jam judgment is made by the first derivative, the traffic jam trend judgment is made by the second derivative, and the real-time variation trend of the traffic flow is judged;
and carrying out real-time early warning based on the judgment result.
According to a further technical scheme, the typical characteristic values of the traffic flow are specific values corresponding to average speed per hour, congestion index, vehicle density, vehicle distance and vehicle flow.
Further technical scheme still includes:
data preprocessing is carried out on the extracted typical characteristic values of the real-time traffic flow, and the method comprises the following steps: and carrying out data complement and correction on the data with the typical characteristic value missing or abnormal of the real-time traffic flow in the T period.
According to a further technical scheme, when a typical characteristic value of the traffic flow is an average speed per hour, according to a real-time traffic flow curve of an average speed per hour-time sequence, a first derivative and a second derivative of the traffic flow at the current moment are obtained, traffic jam judgment is carried out by the first derivative according to the variation trend of the first derivative and the second derivative, traffic jam trend judgment is carried out by the second derivative, and the real-time variation trend of the traffic flow is judged by integrating data information of the first derivative and the second derivative, comprising:
when the first derivative y' < 0, gradually entering a crowded state, early warning is carried out in advance, and the early warning level is adjusted according to specific conditions;
when the first derivative y' =0, it indicates that a congestion spike is present;
when the first derivative y' is more than 0, the congestion peak gradually enters a smooth state, congestion is relieved, and the early warning level is lowered or the early warning is released.
According to a further technical scheme, when the first derivative y' is less than 0, the traffic flow average speed is gradually reduced to indicate that the traffic flow is gradually in a crowded state, early warning is carried out in advance, and the early warning level is adjusted according to specific conditions, and the method comprises the following steps:
when the first derivative y '< 0 and the second derivative y' < 0, the average speed per hour of the traffic flow is gradually reduced, the congestion degree has a aggravation trend, and low-level early warning is carried out;
when the first derivative y '< 0 and the second derivative y' =0, the average speed of traffic flow is rapidly reduced, the congestion degree is aggravated, the early warning level is improved to be one level higher, and early warning is carried out;
when the first derivative y '< 0 and the second derivative y' > 0, the average speed and the acceleration of the traffic flow are reduced, namely the congestion peak is reached, the early warning level is improved to the highest level, and the highest level early warning is carried out.
According to a further technical scheme, when y' is more than 0, the traffic flow average speed is gradually increased, the traffic flow average speed is gradually changed from a congestion peak to smooth, congestion is relieved, the early warning level is gradually reduced to the next level, early warning is carried out until the congestion is relieved, and the method comprises the following steps:
when the first derivative y 'is more than 0 and the second derivative y' > 0, the average speed of the traffic flow is gradually increased, the congestion degree has a relieving trend, and the early warning level is reduced from the highest level to the next level;
when the first derivative y '> 0 and the second derivative y' =0, the traffic flow is rapidly increased at uniform speed, the congestion degree is greatly relieved, namely, the traffic flow enters a smooth state, and the early warning level is reduced again;
when the first derivative y 'is more than 0 and the second derivative y' < 0, the average speed of the traffic flow is higher and higher, the average speed approaches to the average speed in the normal state, the congestion condition is basically eliminated, and the early warning is released.
In a second aspect, the present disclosure provides a traffic congestion warning system based on real-time big data.
A traffic congestion warning system based on real-time big data, comprising:
the data acquisition module is used for acquiring real-time traffic flow working condition big data;
the data processing module is used for extracting the typical characteristic value of the real-time traffic flow in the T period, and carrying out time sequence data processing on the typical characteristic value of the real-time traffic flow in the T period to obtain a real-time traffic flow curve of the typical characteristic value-time sequence of the real-time traffic flow;
the traffic jam pre-judging module is used for obtaining a first derivative and a second derivative at the current moment based on real-time traffic flow data processing of a real-time traffic flow typical characteristic value-time sequence; according to the variation trend of the first derivative and the second derivative, the first derivative is used for judging the traffic congestion degree, the second derivative is used for judging the traffic congestion trend, and the trend of the real-time variation trend of the traffic flow is judged;
and the early warning module is used for carrying out real-time early warning based on the judgment result.
According to a further technical scheme, when a typical characteristic value of the traffic flow is an average speed per hour, according to a real-time traffic flow curve of an average speed per hour-time sequence, a first derivative and a second derivative of the traffic flow at the current moment are obtained, according to the variation trend of the first derivative and the second derivative, the traffic congestion degree is judged by the first derivative, the traffic congestion trend is judged by the second derivative, and the real-time variation trend of the traffic flow is judged by integrating the data information of the first derivative and the second derivative, comprising:
when the first derivative y' is less than 0, the method is gradually in a crowded state, early warning can be performed in advance, and the early warning level can be adjusted according to specific conditions;
when the first derivative y' =0, it indicates that a congestion spike is present;
when the first derivative y' is more than 0, the congestion peak gradually enters a smooth state, congestion is relieved, and the early warning level is reduced or the early warning is released.
In a third aspect, the present disclosure also provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the steps of the method of the first aspect.
In a fourth aspect, the present disclosure also provides a computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the method of the first aspect.
The one or more of the above technical solutions have the following beneficial effects:
the invention provides a traffic jam early warning method and a system based on real-time big data, which are characterized in that real-time traffic flow working condition typical characteristics are converted into data information by acquiring real-time traffic flow working condition big data, traffic flow typical characteristic values in a set time period are extracted, a real-time traffic flow curve of a real-time traffic flow typical characteristic value-time sequence is obtained, further, the first derivative of the curve is used for judging the traffic jam degree, the second derivative of the curve is used for judging the traffic jam trend, the two data information are synthesized, the real-time traffic jam condition judgment is realized, and the early warning of proper level is carried out based on the judging condition, so that the timeliness and the foresight of traffic early warning are improved, and the problem that the traffic condition cannot be reflected in real time in the existing method for predicting traffic flow based on historical data analysis processing is avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a general flow chart of a traffic jam early warning method based on real-time big data according to an embodiment of the invention;
FIG. 2 is a graph showing average speed versus time for a traffic condition at an early stage of congestion in accordance with an embodiment of the present invention;
fig. 3 is a schematic average speed-time diagram of the traffic condition in the later period of congestion in the first embodiment of the invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Example 1
The embodiment provides a traffic jam early warning method based on real-time big data, as shown in fig. 1, comprising the following steps:
s1, acquiring real-time traffic flow working condition big data, and extracting a traffic flow typical characteristic value in a period T;
s2, performing time-series data processing on the typical characteristic values of the real-time traffic flow in the period T to obtain a real-time traffic flow curve of the typical characteristic values of the traffic flow-time series;
step S3, obtaining a first derivative and a second derivative of the current moment based on a real-time traffic flow curve of a real-time traffic flow typical characteristic value-time sequence; according to the variation trend of the first derivative and the second derivative, the traffic jam judgment is made by the first derivative, the traffic jam trend judgment is made by the second derivative, and the real-time variation trend of the traffic flow is judged;
and S4, carrying out real-time early warning based on the judgment result.
In the existing management facilities, a large number of monitoring devices are placed in public places and traffic facilities by cities or traffic management departments, and the monitoring devices comprise traffic system detection devices such as microwave radar devices, traffic electronic police, radio frequency detection devices and the like, and more modern visual data platforms such as various public transportation wisdom, mobile phone traffic APP and the like. Through the monitoring equipment and/or the public transportation intelligent platform, and the like, massive real-time traffic flow working condition big data can be better obtained, and a great deal of convenience is brought to traffic flow prediction work.
In the step S1, real-time traffic flow condition big data of traffic system monitoring equipment, public traffic intelligent platform and the like are obtained, the obtained big data is more in quantity and type, the big data type comprises, but is not limited to, vehicle density, vehicle distance, vehicle flow, average speed per hour, congestion index and the like, typical real-time traffic flow condition characteristic values in the big data in a period T are extracted, and traffic flow typical characteristic values are selected according to urban road attribute differences. In this embodiment, the average speed per hour in the T period is extracted as a traffic flow typical characteristic value. In addition, the time T is generally preferably 5 minutes (the time T includes and is not limited to 5 minutes here) so as to facilitate the subsequent immediate processing of the data.
And on the basis of extracting the real-time traffic flow typical characteristic values, carrying out data preprocessing on the extracted traffic flow typical characteristic values. Specifically, according to a corresponding mathematical algorithm or data processing method, data of the typical characteristic value deficiency or abnormality of the traffic flow in the period T is optimized or data complement is carried out, so that the integrity of the data is improved.
In the step S2, the traffic flow typical characteristic value in the period T is processed in time series, and a real-time traffic flow curve of the real-time traffic flow typical characteristic value-time series is obtained by fitting. In this embodiment, when the typical characteristic value of the traffic flow is the average speed per hour, a real-time traffic flow curve of the average speed per hour-time sequence is obtained by fitting, and is used for expressing real-time traffic conditions: (1) Earlier, the traffic leveling average speed is slowly reduced, as shown in fig. 2; (2) Later, the traffic leveling average speed slowly rises until the average speed is restored, as shown in fig. 3. Typical big cities such as Beijing and the like, under normal conditions, the free average speed is about 70-80km/h, the average speed at the moment of congestion peak is about 10km/h, under extreme conditions such as traffic accidents and the like, the average speed is likely to approach 0, and then the average speed is recovered from low to high.
In this embodiment, only the average speed per hour is taken as an example, and the real-time trend of the traffic flow is not limited to be determined only according to the real-time traffic flow curve of the average speed per hour-time sequence.
As another implementation mode, the typical characteristic values of traffic flows such as vehicle density and the like can be selected, a real-time traffic flow curve of the vehicle density-time sequence is obtained through fitting, namely, the vehicle density of the early traffic flow slowly rises, the vehicle density of the later traffic flow slowly decreases, and the trend of the real-time change trend of the traffic flow is judged based on the curve.
Then, in the above steps S3 and S4, first, the change of the average speed of time is divided into two typical cases, and then, based on the real-time traffic flow curve (function y) of the average speed of time-time sequence obtained by fitting, the first derivative y' of the function y and the second derivative y″ data information thereof are calculated and obtained. Specifically, firstly, calculating a first derivative and a second derivative of the real-time traffic flow based on a real-time traffic flow curve of a real-time traffic flow typical characteristic value-time sequence, then, according to the variation trend of the first derivative and the second derivative, judging the traffic jam by using the first derivative, judging the traffic jam trend by using the second derivative, integrating the data information of the first derivative and the second derivative, judging whether the real-time variation direction of the traffic flow is changed into jam or unblocked, and corresponding variation degree, and carrying out real-time early warning based on the analysis of the judgment result.
In this embodiment, the determining and early warning method includes:
(1) When y' < 0, namely:
at this time, the traffic leveling speed is lower and lower, the traffic leveling speed is gradually in a crowded state, early warning is performed in advance, and the early warning level is adjusted according to specific conditions, and the method comprises the following steps:
when y' < 0 and y "< 0, namely:
and->
At the moment, the traffic flow average speed is predicted to be lower and lower, and the congestion degree has a aggravation trend, so that preliminary low-level early warning can be performed in advance;
when y' < 0 and y "=0, i.e.:
and->
At this time, the traffic leveling speed is reduced rapidly, the congestion degree is increased, the congestion peak is predicted to be reached after the time t, and the early warning level can be improved to be higher than the early warning level by one level or even higher than the early warning level. In this embodiment, the time t is different according to the traffic conditions of each typical city or typical road;
when y isWhen'< 0 and y' > 0, namely:
and->
At this time, the average speed and the acceleration of the traffic flow are reduced, which means that the congestion will reach the congestion peak. For example, during a certain period of time, y' < 0, while y″ is greater than 0, and y″ is substantially constant, at this time, the pre-warning level may be increased to the highest level, and the highest level pre-warning is performed.
(2) When y' =0, namely:
at the moment, the traffic flow average speed is the lowest value, which indicates that the traffic flow is at the congestion peak at the moment;
(3) When y' > 0, namely:
at this time, the traffic flow average speed gradually increases, which means that the traffic flow gradually changes from the congestion peak to smooth, the congestion is relieved, the early warning can be gradually reduced to the next level, and the early warning is carried out until the congestion is relieved, and the method comprises the following steps:
when y' > 0 and y "> 0, namely:
and->
When the average speed is gradually increased, the congestion is well relieved, the congestion degree has a relieving trend, and at the moment, the early warning level can be reduced to the next level;
when y' > 0 and y "=0, i.e.:
and->
At the moment, the traffic flow average speed is further improved, the congestion situation is greatly relieved, the situation is about to enter a smooth state, and the situation can be expected to be recovered to a normal state after t time; at this time, the early warning level can be lowered again;
when y' > 0 and y "< 0, namely:
and->
At the moment, the average speed of the traffic flow is higher and higher, the average speed approaches to the average speed in the normal state, the congestion condition is basically eliminated, and the early warning level can be further reduced or the early warning can be relieved.
In this embodiment, real-time early warning is performed based on a judgment result, the early warning information is early-warned in digital, graphic, audio and video modes and the like, and corresponding management measures are taken.
According to the embodiment, the obtained real-time traffic flow working condition big data are extracted to obtain the traffic flow typical characteristic value in the set time period, the real-time traffic flow curve of the real-time traffic flow typical characteristic value-time sequence is obtained, the first derivative of the curve is used for judging the traffic congestion degree, the second derivative of the curve is used for judging the traffic congestion trend, and the information data of the two is integrated, so that real-time traffic congestion prediction is realized, early warning is carried out based on the prediction result, the timeliness and the foresight of traffic early warning are improved, and the problem that the traffic condition cannot be reflected in real time in the existing method for predicting the traffic flow based on historical data analysis processing is avoided.
Example two
The embodiment provides a traffic jam early warning system based on real-time big data, which comprises:
the data acquisition module is used for acquiring real-time traffic flow working condition big data;
the data processing module is used for extracting the traffic flow typical characteristic values in the T time period, carrying out time sequence data processing on the traffic flow typical characteristic values in the T time period, and fitting to obtain a real-time traffic flow curve of the traffic flow typical characteristic values-time sequence;
the traffic jam pre-judging module is used for obtaining a first derivative and a second derivative at the current moment based on a real-time traffic flow curve of a traffic flow typical characteristic value-time sequence; according to the variation trend of the first derivative and the second derivative, the traffic jam judgment is made by the first derivative, the traffic jam trend judgment is made by the second derivative, and the real-time variation trend of the traffic flow is judged;
and the early warning module is used for carrying out real-time early warning based on the judgment result.
Example III
The embodiment provides an electronic device, which comprises a memory, a processor and computer instructions stored on the memory and running on the processor, wherein the computer instructions complete the steps in the traffic congestion early warning method based on real-time big data when being run by the processor.
Example IV
The present embodiment also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, perform the steps in the traffic congestion warning method based on real-time big data as described above.
The steps involved in the second to fourth embodiments correspond to the first embodiment of the method, and the detailed description of the second embodiment refers to the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media including one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that is capable of causing the processor to perform any one of the methods of the present invention as described above.
It will be appreciated by those skilled in the art that the steps or modules of the invention described above may be implemented by general-purpose computer means, alternatively they may be implemented by program code executable by computing means, whereby they may be stored in storage means for execution by computing means, or they may be made into individual integrated circuit modules separately, or a plurality of modules or steps in them may be made into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (10)
1. A traffic jam early warning method based on real-time big data is characterized by comprising the following steps:
acquiring real-time traffic flow working condition big data, and extracting a real-time traffic flow typical characteristic value in a T period;
carrying out time sequence data processing on the typical characteristic value of the real-time traffic flow in the T period to obtain a real-time traffic flow curve of the typical characteristic value-time sequence of the real-time traffic flow;
obtaining a first derivative and a second derivative of the current moment based on a real-time traffic flow curve of a real-time traffic flow typical characteristic value-time sequence; according to the variation trend of the first derivative and the second derivative, the traffic jam judgment is made by the first derivative, the traffic jam trend judgment is made by the second derivative, and the real-time variation trend of the traffic flow is judged;
and carrying out real-time early warning based on the judgment result.
2. The traffic congestion early warning method based on real-time big data according to claim 1, wherein the typical characteristic values of the traffic flow are specific values corresponding to average speed per hour, congestion index, vehicle density, vehicle distance and vehicle flow.
3. The traffic congestion warning method based on real-time big data according to claim 1, further comprising:
data preprocessing is carried out on the extracted typical characteristic values of the real-time traffic flow, and the method comprises the following steps: and carrying out data complement and correction on the data with the typical characteristic value missing or abnormal of the real-time traffic flow in the T period.
4. The traffic congestion pre-warning method based on real-time big data according to claim 1, wherein when the typical characteristic value of the traffic flow is average speed of time, according to the real-time traffic flow curve of the average speed of time-time sequence, the first derivative and the second derivative of the traffic flow at the current moment are obtained, according to the variation trend of the first derivative and the second derivative, the traffic congestion judgment is made by the first derivative, the traffic congestion trend judgment is made by the second derivative, the data information of the two is integrated, and the real-time variation trend of the traffic flow is judged, comprising:
when the first derivative y' < 0, gradually entering a crowded state, early warning is carried out in advance, and the early warning level is adjusted according to specific conditions;
when the first derivative y' =0, it indicates that a congestion spike is present;
when the first derivative y' is more than 0, the congestion peak gradually enters a smooth state, congestion is relieved, and the early warning level is lowered or the early warning is released.
5. The traffic congestion pre-warning method based on real-time big data according to claim 4, wherein when the first derivative y' < 0, the traffic flow average speed gradually decreases, which means gradually entering a congestion state, pre-warning is performed in advance, and the pre-warning level is adjusted according to specific conditions, comprising:
when the first derivative y '< 0 and the second derivative y' < 0, the average speed per hour of the traffic flow is gradually reduced, the congestion degree has a aggravation trend, and low-level early warning is carried out;
when the first derivative y '< 0 and the second derivative y' =0, the average speed of traffic flow is rapidly reduced, the congestion degree is aggravated, the early warning level is improved to be one level higher, and early warning is carried out;
when the first derivative y '< 0 and the second derivative y' > 0, the average speed and the acceleration of the traffic flow are reduced, namely the congestion peak is reached, the early warning level is improved to the highest level, and the highest level early warning is carried out.
6. The traffic congestion pre-warning method based on real-time big data according to claim 4, wherein when y' is more than 0, the traffic flow average speed is gradually increased, which means that the congestion peak is gradually changed to be smooth, the congestion is relieved, the pre-warning level is gradually reduced to the next level, and the pre-warning is performed until the congestion pre-warning is released, and the method comprises the following steps:
when the first derivative y 'is more than 0 and the second derivative y' > 0, the average speed of the traffic flow is gradually increased, the congestion degree has a relieving trend, and the early warning level is reduced from the highest level to the next level;
when the first derivative y '> 0 and the second derivative y' =0, the traffic flow is rapidly increased at uniform speed, the congestion degree is greatly relieved, namely, the traffic flow enters a smooth state, and the early warning level is reduced again;
when the first derivative y 'is more than 0 and the second derivative y' < 0, the average speed of the traffic flow is higher and higher, the average speed approaches to the average speed in the normal state, the congestion condition is basically eliminated, and the early warning is released.
7. A traffic jam early warning system based on real-time big data is characterized by comprising:
the data acquisition module is used for acquiring real-time traffic flow working condition big data;
the data processing module is used for extracting the typical characteristic value of the real-time traffic flow in the T period, and carrying out time sequence data processing on the typical characteristic value of the real-time traffic flow in the T period to obtain a real-time traffic flow curve of the typical characteristic value-time sequence of the real-time traffic flow;
the traffic jam pre-judging module is used for obtaining a first derivative and a second derivative at the current moment based on real-time traffic flow data processing of a real-time traffic flow typical characteristic value-time sequence; according to the variation trend of the first derivative and the second derivative, the first derivative is used for judging the traffic congestion degree, the second derivative is used for judging the traffic congestion trend, and the trend of the real-time variation trend of the traffic flow is judged;
and the early warning module is used for carrying out real-time early warning based on the judgment result.
8. The traffic congestion warning system based on real-time big data according to claim 7, wherein when the typical characteristic value of the traffic flow is the average speed of time, according to the real-time traffic flow curve of the average speed of time-time sequence, the first derivative and the second derivative of the traffic flow at the current moment are obtained, according to the variation trend of the first derivative and the second derivative, the first derivative is used for determining the traffic congestion degree, the second derivative is used for determining the traffic congestion trend, the two data information are integrated, and the real-time variation trend of the traffic flow is determined, comprising:
when the first derivative y' is less than 0, the method is gradually in a crowded state, early warning can be performed in advance, and the early warning level can be adjusted according to specific conditions;
when the first derivative y' =0, it indicates that a congestion spike is present;
when the first derivative y' is more than 0, the congestion peak gradually enters a smooth state, congestion is relieved, and the early warning level is reduced or the early warning is released.
9. An electronic device, characterized by: comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the steps of a traffic congestion warning method based on real-time big data as claimed in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized by: for storing computer instructions which, when executed by a processor, perform the steps of a traffic congestion warning method based on real-time big data as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310085832.7A CN116246463A (en) | 2023-01-31 | 2023-01-31 | Traffic jam early warning method and system based on real-time big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310085832.7A CN116246463A (en) | 2023-01-31 | 2023-01-31 | Traffic jam early warning method and system based on real-time big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116246463A true CN116246463A (en) | 2023-06-09 |
Family
ID=86625518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310085832.7A Pending CN116246463A (en) | 2023-01-31 | 2023-01-31 | Traffic jam early warning method and system based on real-time big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116246463A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117875558A (en) * | 2024-01-16 | 2024-04-12 | 青岛交通科技信息有限公司 | Multi-dimensional traffic planning scene evaluation system and method based on big data |
-
2023
- 2023-01-31 CN CN202310085832.7A patent/CN116246463A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117875558A (en) * | 2024-01-16 | 2024-04-12 | 青岛交通科技信息有限公司 | Multi-dimensional traffic planning scene evaluation system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107798876B (en) | Road traffic abnormal jam judging method based on event | |
| CN115578015B (en) | Sewage treatment whole process supervision method, system and storage medium based on Internet of things | |
| CN111275333B (en) | Pollution data processing method and device | |
| CN110718057B (en) | Road network operation state evaluation method and device, electronic equipment and medium | |
| CN101720453A (en) | System and method for predictive maintenance of a battery assembly using temporal signal processing | |
| CN111881243B (en) | Taxi track hot spot area analysis method and system | |
| CN112684133A (en) | Water quality monitoring and early warning method and system based on big data platform and storage medium | |
| CN116246463A (en) | Traffic jam early warning method and system based on real-time big data | |
| CN112434260A (en) | Road traffic state detection method and device, storage medium and terminal | |
| CN113806370A (en) | Environmental data supervision method, device, equipment and storage medium based on big data | |
| CN116596402A (en) | Air quality research and judgment, pollution tracing and emergency management and control suggestion generation method and system | |
| CN117093943A (en) | Power consumption monitoring and early warning method and device | |
| CN116679221A (en) | Battery abnormality detection and battery maintenance management method and device | |
| CN114708728B (en) | Method for identifying traffic peak period, electronic equipment and storage medium | |
| CN113990078B (en) | Multi-source information judgment-based highway vehicle overrun detection method and system and storage medium | |
| CN113254733B (en) | Information analysis method, system and storage medium based on big data platform | |
| CN114419894A (en) | Method and system for setting and monitoring use of parking space in road | |
| CN112529311A (en) | Road flow prediction method and device based on graph convolution analysis | |
| CN111741042A (en) | Oil consumption, driving track and safe driving integrated remote monitoring system | |
| CN117227551B (en) | New energy equipment safety monitoring method, device, equipment and readable storage medium | |
| CN117079460A (en) | Method for predicting urban short-time traffic flow by ARIMA model oriented to time sequence | |
| CN116579677B (en) | Full life cycle management method and system for high-speed railway electric service vehicle-mounted equipment | |
| CN117894181B (en) | Global traffic abnormal condition integrated monitoring method and system | |
| CN116912069B (en) | Data processing method applied to smart city and electronic equipment | |
| CN115019551B (en) | Correction method of redundant bits of field library, training method and device of redundant bit prediction model |
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 |