CN116564087A - Road network balance control method and system based on big data - Google Patents
Road network balance control method and system based on big data Download PDFInfo
- Publication number
- CN116564087A CN116564087A CN202310527136.7A CN202310527136A CN116564087A CN 116564087 A CN116564087 A CN 116564087A CN 202310527136 A CN202310527136 A CN 202310527136A CN 116564087 A CN116564087 A CN 116564087A
- Authority
- CN
- China
- Prior art keywords
- road
- network
- data
- road network
- sub
- 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 59
- 230000011218 segmentation Effects 0.000 claims abstract description 13
- 238000009826 distribution Methods 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000011217 control strategy Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000002457 bidirectional effect Effects 0.000 claims description 2
- 238000004891 communication Methods 0.000 claims description 2
- 230000000295 complement effect Effects 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 238000011144 upstream manufacturing Methods 0.000 claims description 2
- 239000006185 dispersion Substances 0.000 claims 2
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- TZCXTZWJZNENPQ-UHFFFAOYSA-L barium sulfate Chemical compound [Ba+2].[O-]S([O-])(=O)=O TZCXTZWJZNENPQ-UHFFFAOYSA-L 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
-
- 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
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a road network balance control method and system based on big data. The method comprises the following steps: acquiring and analyzing a road network space topological structure, and acquiring the layout of detection equipment, equipment types, detectable parameters and the like on the road network; calculating state indexes of road network nodes such as all intersections, road sections and the like in the road network; according to the association degree of each node in the road network, adopting a clustering method to carry out space segmentation on the road network to form relatively independent road sub-networks; classifying the running states of the sub-networks of the channels according to the state indexes, and calculating the bearing capacity of each sub-network of the channels in the crowded state; and identifying key nodes in and outside the controlled subnetwork, and implementing an equilibrium control strategy. The invention is beneficial to balancing the vehicle distribution in the road network space and improving the traffic efficiency of the road network vehicles.
Description
Technical Field
The invention belongs to the technical field of traffic control and big data analysis, and particularly relates to a road network balance control method, system and equipment based on big data.
Background
With the development of the economy of China, the maintenance quantity of motor vehicles is continuously increased, so that the congestion of a road network is increased, the travel of vehicles is slow, and under the conditions of limited urban space resources and high cost, the situation of unbalanced supply and demand of urban traffic in China is not realistic by simply relying on road extension. Therefore, the solution to the unbalanced traffic supply and demand condition is also approaching to improving traffic management efficiency and optimizing traffic planning direction.
Conventionally, traffic management mainly focuses on the time sequence change process of traffic states in local areas, involves less large-scale road networks and considers the connection of traffic states among roads, and can alleviate the problem of unbalanced supply and demand in a certain range by passively adapting to the change of traffic demands during traffic adjustment, but the mode cannot be used when the traffic demands exceed the capacity of intersections, road sections or areas as vehicles continuously gather. In general, the state that the road network runs at full load in all space-time ranges does not exist, if the real-time traffic information on the road network can be obtained, the accurate traffic running state can be mastered, and scientific and reasonable traffic control measures are adopted to induce the road network, so that the vehicles can efficiently utilize the space-time resources of the road. Thus, solutions should be sought from a more macroscopic perspective for the problem of supply-demand imbalance. In terms of the whole urban road network, the spatial characteristics and the topological structure of the road network determine the distribution of traffic flow in urban space to a certain extent, the traffic flow demand distribution on the road network is unbalanced, and the unbalanced degree can be accurately analyzed. Therefore, the unbalance of the supply and the demand of the local area is balanced in a larger area range, and the traffic problem can be relieved to a certain extent.
The large and medium-sized cities initially form a large data environment which is mainly based on urban vehicle output behaviors and combines dynamic and static multi-source data. The available big data comprise parameters such as flow, speed, occupancy rate, head interval, head time interval and the like of the traffic flow, which can be acquired in real time by a loop coil detector, a video bayonet detector, an RFID, a microwave and other fixed detectors. The mobile detection equipment such as mobile phone signaling, internet of vehicles data, mobile interconnection data and the like can acquire traffic big data such as vehicle tracks, vehicle driving states and the like in real time. These traffic data allow the urban traffic information to be presented more fully. The acquisition of the multi-source data provides data support for traffic state analysis and research, so that the method can be used for excavating a traffic jam formation mechanism, controlling traffic running states in real time and dynamically predicting future traffic flow. The correlation among the areas is analyzed spatially, a spatial structure analysis and topology characteristic recognition method of the urban road network is introduced, the relation between the regional capacity of the urban local road network and the traffic state is comprehensively recognized by means of urban big data analysis technology, the evolution rule of the traffic state along with time change is analyzed, and the set of the related areas of the traffic state of the affected area is recognized by utilizing the spatial proximity and topological structure equivalence of the areas, so that traffic flows are distributed in adjacent areas more effectively.
Disclosure of Invention
The invention aims to provide a road network balance control method, a system and equipment based on big data aiming at the defects existing in the prior art.
The technical solution for realizing the purpose of the invention is as follows: in one aspect, a road network equalization control method based on big data is provided: acquiring and analyzing a road network space topological structure, acquiring attribute parameters of intersections and road sections, and acquiring the layout of detection equipment, equipment types and detectable parameters on the road network;
calculating the state index of each road network node in the road network by combining the road network space topological structure;
according to the association degree of each node in the road network, adopting a clustering method to segment the space of the road network into different road sub-networks;
classifying the running states of the sub-networks of the channels according to the state indexes, identifying the controlled sub-networks, and calculating the bearing capacity of the controlled sub-networks;
and according to the segmentation result, combining the spatial characteristics of the road network, identifying key nodes in and out of the controlled subnetwork, and implementing a control strategy.
In another aspect of the disclosure, a method for calculating a road sub-network bearing capacity is provided, and a proper state index is selected for an intersection and a road section in a road network; a polynomial fitting method is adopted to form a traffic state-on-road vehicle relation function; classifying the characteristics of the function curve, and dividing the state into three sections of smooth, slow running and crowding; adopting a clustering method to correlate and combine intersections and road sections in the road network, and dividing the intersections and the road sections into road sub-networks; and calculating the state boundary value of the road sub-network, and obtaining the bearing capacity of the road sub-network in the crowded state.
In still another aspect of the disclosure, a method for generating a traffic state-on-road vehicle relationship function is provided, traffic flow data of a road network is selected and analyzed, a data processing flow is formulated, the data are preprocessed to form a data set of traffic state indexes and on-road vehicle numbers, and a polynomial fitting method is adopted to fit the traffic state-on-road vehicle relationship function.
In still another aspect of the disclosure, a traffic running state segmentation method is provided, according to historical traffic data of a road network for a week, carrying in a traffic state-on-road vehicle relation function, obtaining a data sample set, sliding to calculate curvature of the data sample, forming a curvature data sample set, classifying the curvature data sample by adopting a time sequence clustering method, and forming three state intervals of smoothness, creep and congestion, so as to calculate a network node bearing capacity interval range.
In still another aspect of the disclosure, a method for calculating association degree between nodes of a road network is provided, a two-layer network model is constructed to express the road network, an upper layer network represents a traffic flow distribution model, and a lower layer represents a space structure model; and constructing a relevance calculating model, and calculating a relevance matrix among the road network nodes.
In yet another aspect of the disclosure, a road sub-network segmentation method based on graph clustering is provided, a road network graph is constructed according to a crowded node set, a road sub-network segmentation model is constructed, and a sub-network set is calculated; and forming a final road sub-network set through the coincidence degree judging rule.
In yet another aspect of the disclosure, a road subnetwork balancing control method is provided, identifying a subset of controlled subnetworks from a set of road subnetworks according to historical data, calculating external ingress nodes associated with the controlled subnetworks, and ordering; layering treatment is carried out on the external access nodes of the sub-network according to the association degree relation to form a limiting area, a buffer area and a shunting area; acquiring vehicle running track data in a road network in real time, and calculating a sub-network G i Is a vehicle data of the in-transit vehicle; the green time of the limiting area is reduced, and the running speed of the buffer area vehicle is reduced; and issuing guidance information in the diversion area, providing an alternative path, and guiding the vehicle to change the driving path. According to the association relation, carrying out hierarchical processing on nodes such as intersections, road sections and the like in the subnetwork to form a key node and a non-key node set; calculating traffic state indexes of key nodes in real time, taking space bearing vehicles of all nodes as targets, rapidly guiding the associated flow directions of the key nodes by intelligent guiding means, and controlling the state indexes of all the nodes within an optimized target interval range.
In yet another aspect of the disclosure, a road network equalization control system based on big data is provided, which includes a data receiving module, a data processing module, a data service module, and a control optimizing module. The data receiving module is used for receiving real-time traffic flow data acquired by the road network front-end detection equipment; the data processing module is used for preprocessing the real-time traffic data, guaranteeing the data quality and transmitting the data to the data service module; request history data, combining space road network data, analyzing and processing the data, calculating state indexes, and identifying traffic states; the data service module is a data bus of the system, bears the task of data input and output storage, and realizes the task of data interaction with other modules; the control optimization module acquires real-time index data and control subnet data from the data module in real time, generates an optimization control instruction in real time, and sends the optimization control instruction to the front-end execution equipment.
In yet another aspect of the disclosure, an electronic device is provided that includes a memory for storing computer instructions; and the processor is connected with the memory and is used for executing the computer instructions in the memory.
Compared with the prior art, the invention has the remarkable advantages that: according to the historical data, identifying a functional relation between the traffic state and the road network on-road vehicles, and identifying a state change inflection point; therefore, the road network is segmented, and an effective balance control strategy is formulated according to the real-time state change trend. The equalization control method and the equalization control system are beneficial to equalizing vehicle distribution in road network space and improving traffic efficiency of road network vehicles.
The invention is described in further detail below with reference to the accompanying drawings.
Drawings
Fig. 1 is a flow chart of a road network equalization control based on big data in one embodiment.
FIG. 2 is a flow diagram of road network model construction in one embodiment.
Fig. 3 is a schematic diagram of a result of channel subnet splitting in one embodiment.
Fig. 4 is a flow diagram of a split-up of a trace subnetwork in one embodiment.
FIG. 5 is a flow diagram of traffic state-in-transit vehicle relationship function generation in one embodiment.
FIG. 6 is a flow diagram of a relationship function state interval calculation in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
In one embodiment, in conjunction with fig. 1, a road network equalization control method based on big data is provided, which includes the following steps:
step 101: acquiring and analyzing a road network space topological structure, and acquiring attribute parameters of intersections and road sections, wherein the parameters comprise: intersection shape, number of exits and exits, lane type and number, etc.; the layout of detection equipment on the road network, equipment type, detectable parameters, equipment position and the like are obtained;
step 102: according to the detectable traffic flow data of the detector, the state indexes of road network nodes such as all intersections, road sections and the like in the road network are calculated by combining the road network space topological structure;
in the embodiment of the disclosure, single or composite indexes such as saturation, vehicle delay, queuing length and the like are selected as state indexes at the intersection.
In the embodiment of the disclosure, the road section selects a single or coincidence index of travel time, travel speed, parking times, saturation and the like as the state index.
Step 103: according to the association degree of each node in the road network, a clustering method is adopted to segment the road network into different road sub-networks, and the segmentation result is shown in fig. 3.
In the embodiment of the disclosure, a double-layer network model is designed to express a road network, wherein an upper layer network represents a traffic flow distribution model, a lower layer represents a space structure model, points represent intersections and connecting lines between the points represent road sections;
in the disclosed embodiment, the lower layer road network topology relationship N A = (R, L, α). Wherein R is an intersection point set; l represents a road segment set connected with an upstream and a downstream road junction; alpha is a static association degree set, and represents the spatial association between intersections in a road network, and influence factors of the association include: road section length and width, traffic capacity, accessibility and the like;
in the embodiment of the disclosure, the upper network is a traffic flow distribution model, and the travel network N B = (O, D, β), where O is the starting point; d is a destination point, beta is a dynamic association degree, and influencing factors comprise traffic flow, running time and the like.
Referring to fig. 2, the steps specifically include the following steps:
step 201: according to different control time periods of the whole day, in each time period, delta t is calculated l ，Δt l Is equal to or more than 15 minutes at intervalsPerforming row slicing, and searching out the moment slice with the most crowded nodes in each period as an analysis period;
step 202: acquiring analysis period crowded node set N S ＝(P S ，L S W), where P S L is a crowded intersection point set S And (3) performing graph clustering analysis on the nodes for a road segment edge set between the intersections, wherein w is the association degree between the nodes, so that independent road sub-networks are formed in the road network space.
Obtaining a relevance calculating model according to the double-layer network model:
w i,j ＝α i,j *β i,j
wherein w is i,j The degree of association between the finger nodes is higher than 0.5.
Wherein: alpha i,j Static degree of association, alpha i,j ＝1/d i,j ，d i,j Mean communication distance between nodes i and j of the road network; beta i,j Dynamic association degree, beta i,j ＝Q ij /Q i +Q j ，q ij Refers to the two-way association traffic volume between two road network nodes; q (Q) i 、Q j Is the nominal traffic between nodes i, j.
Wherein: nominal traffic volumen refers to the number of key nodes, such as intersections, road segments, etc.; q i The weight of the selected key point is indicated; q i Is the corresponding traffic flow.
In the embodiment of the disclosure, according to the crowded node set N S ＝(P S ，L S W), constructing a road network graph g= (P, L), wherein P represents all congestion nodes (P 1 ，P 2 ，…，P n ) For any two nodes in P, the nodes are connected through edges, the road network is bidirectional, and w i,j ≠w j,i And forming association degree matrixes W 'and W':
with reference to fig. 4, the spatial division of the road network into different road sub-networks by using the clustering method includes the following steps:
step 301: constructing a road sub-network segmentation model, and cutting a road network into road sub-networks which are not linked with each other:
in the formula, the road network graph G is cut into k road sub-networks which are not connected with each other, and the set of the road sub-networks is g= (G) 1 ，G 2 ，…，G k )，G i 、G j For the ith and j-th road sub-network, the method satisfies the following conditionsAnd G is 1 ∪G 2 ∪…∪G k =g; w is W 'or W', and->Is a complement;
step 302: respectively selecting a correlation matrix W 'and a correlation matrix W' to be brought into a segmentation model for calculation to obtain a subnet set C 'and a subnet set C';
step 303: combining the subnet sets C ' and C ' through a coincidence degree judging rule, and if the coincidence area of each subnet element in the subnet set is larger than delta C, combining to form a new subnet set C ';
step 304: merging the overlapped subnet elements in the region of C 'to form a final channel subnet set C' = (G) 1 ，G 2 ，…，G m ) M represents the number of road subnetworks in the road subnetwork set C' ".
Step 104: classifying running states of the sub-networks according to the state indexes, defining the sub-network of the road in the crowded state as a controlled sub-network, and calculating bearing capacity of each sub-network in the crowded state; the specific process comprises the following steps:
selecting proper state indexes I for intersections and road sections in a road network, and defining a value range [0, 100];
a polynomial fitting method is adopted to form a traffic state-on-road vehicle relation function curve
For traffic conditions-on-road vehicle relationship function curveClassifying the characteristics, and dividing traffic states into three state intervals of smooth, slow running and crowding;
defining a road sub-network in a crowded state as a controlled sub-network;
calculating state boundary value of the sub-network of the channel to obtain bearing capacity v of the sub-network to be controlled c 。
In the embodiment of the disclosure, a polynomial fitting method is adopted to form a traffic state-on-road vehicle relation function curveReferring to fig. 5, the specific calculation steps are as follows:
step 401: selecting and analyzing traffic flow data of one week of road network, and using delta t l ，Δt l Calculating time sequence state indexes I of each day and each road sub-network at intervals of more than or equal to 5 minutes, and obtaining the number v of vehicles in transit in the sub-network to form a data set A d ＝((v 0 ,I 0 ),(v 1 ,I 1 )…(v n ,I n ) D=1,..7, n=288 represent 288 data in one day, (v 0 ,I 0 ) Representing an on-road vehicle v 0 Corresponding state index is I 0 Wherein Δt is l Not less than 5 minutes;
step 402: data set A d Sequencing, namely sequencing from small to large according to the number of vehicles in transit; if v is the same, sorting is carried out according to the time sequence to form a new data set A' d ；
Step 403: data set A' d Processing the abnormal data of the model (a), identifying singular values and replacing the singular values; merging the elements with the same v, and averaging the I values; forming a new data set A' d ；
Step 404: data set A' d Fitting a traffic state-on-road vehicle relation function by adopting a polynomial fitting method,wherein: -a->Representing the state index I, x representing the number of vehicles in transit.
In the embodiment of the disclosure, the traffic state-on-road vehicle relation function curve is classified into three stages of smooth, creep and crowding, and the specific calculation steps are as follows in combination with the illustration of fig. 6;
step 501: acquiring the minimum value v of the number of vehicles in transit according to the historical traffic data of one week min And maximum v max Constructing a numerical value range of the in-transit vehicle, [ v ] min ,1.2*v max ]；
Step 502: constructing a sample set (v) with Δv as an interval min +Δv，v min +2*Δv，…,1.2*v max ) Bringing in the relation function, calculating the traffic state index value to form a data sample C= (v) i ,I i ),i＝1.2.3…m；
Step 503: with sliding window Deltav l ，Δv l And (5) and moving the curvature of the calculated data sample C to form a curvature data sample K= (K) 1 ,K 2 ,…K n )；
Step 504: analyzing the curvature data sample by adopting a time sequence clustering method, and sequencing the curvature data from small to large to form three state intervals of smoothness, creep and congestion, wherein the three state intervals are [ K ] 1 ，K s1 )，[K s1 ,K s2 ]，(K s2 ,K n ]。
In the embodiment of the disclosure, the bearing capacity interval [ v ] is calculated 1 ，v s1 )，[v s1 ,v s2 ]，(v s2 ,v n ]Therefore, the number of the bearing vehicles corresponding to the road subnetwork under different crowded states can be obtained.
And 105, according to the segmentation result, combining the spatial characteristics of the road network, identifying key nodes in and outside the controlled subnetwork, and implementing a control strategy.
In an embodiment of the present disclosure, a controlled set of subnets in a road network is identified from historical data. Calculating external access nodes associated with the controlled subnetwork, and sequencing; layering processing is carried out on the external access nodes of the sub-network according to the association degree relation to form a limiting area, a buffer area and a shunting area (wherein the association degree is higher than a first preset threshold value and is divided into limiting areas, the association degree is lower than a second preset threshold value and is divided into shunting areas, and the other nodes are divided into buffer areas); calculating the association degree of nodes such as intersections and road sections in the sub-network to form a key node and a non-key node set (wherein nodes with association degree higher than a third preset threshold value form the key node set);
in the embodiment of the disclosure, in actual operation, vehicle running track data in a road network is acquired in real time, and a subnet G is calculated i Is the in-transit vehicle data v i The method comprises the steps of carrying out a first treatment on the surface of the Judging Δv=v i -v c When Deltav approaches the threshold value, the green light time of the limiting zone is reduced, and the running speed of the buffer zone vehicle is reduced; in the diversion area, issuing guidance information, providing a substituted road, and guiding the vehicle to change the driving path;
in the embodiment of the disclosure, traffic state indexes of key nodes in a subnet are calculated in real time, balancing of space bearing vehicles of all nodes is taken as a target, and the associated flow directions of the key nodes are rapidly dredged by intelligent dredging means, so that the state indexes of all the nodes are controlled within an optimized target interval.
In one embodiment, a road network equalization control system based on big data is provided, which comprises a data receiving module, a data processing module, a data service module and a control optimizing module.
The data receiving module is used for receiving real-time traffic flow data acquired by the road network front-end detection equipment;
the data processing module is used for preprocessing the real-time traffic data, guaranteeing the data quality and transmitting the data to the data service module; request history data, combining space road network data, analyzing and processing the data, calculating state indexes, and identifying traffic states;
the data service module is a data bus of the system and bears the task of data input and output; and realizing the data interaction task with other modules;
the control optimization module acquires real-time index data and control subnet data from the data module in real time, generates an optimization control instruction in real time, and controls the execution equipment at the front end of the issuing channel.
For specific limitations on the big data based road network equalization control system, reference may be made to the above limitation on the big data based road network equalization control method, and the details are not repeated here. The modules in the road network equalization control system based on big data can be all or partially realized by software, hardware and the combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, an electronic device is provided that includes a memory for storing computer instructions; and the processor is connected with the memory and is used for executing the computer instructions in the memory and realizing the road network balance control method based on big data when executing the computer instructions.
The equalization control method and the equalization control system are beneficial to equalizing vehicle distribution in road network space and improving traffic efficiency of road network vehicles.
The foregoing has outlined and described the basic principles, features, and advantages of the present invention. It will be understood by those skilled in the art that the foregoing embodiments are not intended to limit the invention, and the above embodiments and descriptions are meant to be illustrative only of the principles of the invention, and that various modifications, equivalent substitutions, improvements, etc. may be made within the spirit and scope of the invention without departing from the spirit and scope of the invention.
Claims (10)
1. The road network balance control method based on big data is characterized by comprising the following steps:
acquiring and analyzing a road network space topological structure, acquiring attribute parameters of intersections and road sections, and acquiring the layout of detection equipment, equipment types and detectable parameters on the road network;
calculating the state index of each road network node in the road network by combining the road network space topological structure;
according to the association degree of each node in the road network, adopting a clustering method to segment the space of the road network into different road sub-networks;
classifying the running states of the sub-networks of the channels according to the state indexes, identifying the controlled sub-networks, and calculating the bearing capacity of the controlled sub-networks;
and according to the segmentation result, combining the spatial characteristics of the road network, identifying key nodes in and out of the controlled subnetwork, and implementing a control strategy.
2. The big data based road network equalization control method of claim 1, wherein the attribute parameters include: intersection shape, number of exits, lane type and number.
3. The big data-based road network equalization control method of claim 1, wherein the road network nodes comprise intersections and road segments, wherein the status indicators of the intersections comprise single or composite indicators of saturation, vehicle delay, queuing length, and the status indicators of the road segments comprise single or composite indicators of travel time, travel speed, number of stops, and saturation.
4. The road network equalization control method based on big data according to claim 1, wherein the calculation method of the association degree of each node in the road network is as follows:
constructing a double-layer network model to represent a road network, wherein an upper layer network represents a traffic flow distribution model, a lower layer network represents a space structure, points represent intersections, and lines between the points represent road sections;
wherein, the topological relation N of the lower network A = (R, L, α), where R is the intersection set; l is a road section set connected with an upstream and a downstream road junction; alpha is static association degree and represents the spatial association between intersections in the road network;
wherein, the upper layer network topological relation N B = (O, D, β), where O is the starting point; d is a destination point, beta is a dynamic association degree, and influencing factors comprise traffic flow and running time;
according to different control time periods of the whole day, in each control time period, delta t is calculated l Slicing at intervals, and searching out the time slice with most crowded nodes in each control period as an analysis period; wherein Δt is l Not less than 15 minutes;
acquiring analysis period crowded node set N S ＝(P S ，L S W), wherein w is the degree of association between crowded nodes, P S L is a crowded intersection point set S Is a road section edge set between intersections;
obtaining a relevance calculating model according to the double-layer network model:
w i，j ＝α i，j *β i，j
wherein w is i，j For the degree of association between road network nodes i, j, alpha i，j Is static association degree alpha i，j ＝1/d i，j ，d i，j The average communication distance between the road network nodes i and j is; beta i，j To be dynamic association degree, beta i，j ＝Q ij /Q i +Q j ，Q ij Is the two-way association traffic volume between two road network nodes i, j; q (Q) i 、Q j Nominal traffic for nodes i, j, respectively;
the calculation formula of the nominal traffic volume is as follows:
wherein n is the number of key nodes, g i Weight q of selected key node i And the traffic flow corresponding to the key node.
5. The big data based road network equalization control method of claim 4, wherein the clustering method is used for space division of the road network into different road sub-networks, and the specific process comprises:
from crowded node set N S ＝(P S ，L S W), constructing a road network graph g= (P, L), wherein P represents all congestion nodes (P 1 ，P 2 ，...，P n ) For any two nodes in P, the nodes are connected through edges, the road network is bidirectional, and w i，j ≠w j，i And forming a correlation matrix W 'and W':
constructing a road sub-network segmentation model:
in the formula, the road network graph G is cut into k road sub-networks which are not connected with each other, and the set of the road sub-networks is g= (G) 1 ，G 2 ，...，G k )，G i 、G j For the ith and j-th road sub-network, the method satisfies the following conditionsAnd G is 1 ∪G 2 ∪...∪G k =g; w is W 'or W',is a complement;
substituting the association degree matrixes W 'and W' into the road subnet segmentation model to calculate so as to obtain a subnet set C 'and C';
combining the sub-network sets C 'and C' through the coincidence judging rule: aiming at the closed areas constructed by all the subnet elements in the subnet collection, if the overlapping area of the two closed areas is larger than a set threshold delta C, merging to form a new subnet collection C';
merging the subnet elements overlapping the closed areas in the new subnet set C' "to form a final channel subnet set C" = (G 1 ，G 2 ，...，G m ) M represents the number of road subnetworks in the road subnetwork set C' ".
6. The big data based road network equalization control method of claim 5, wherein said classifying the running state of the road sub-network according to the state index, identifying the controlled sub-network, and calculating the carrying capacity of the controlled sub-network comprises the following steps:
selecting proper state indexes I for intersections and road sections in a road network, and defining a value range [0, 100];
a polynomial fitting method is adopted to form a traffic state-on-road vehicle relation function curve
For traffic conditions-on-road vehicle relationship function curveClassifying the characteristics, and dividing traffic states into three state intervals of smooth, slow running and crowding;
defining a road sub-network in a crowded state as a controlled sub-network;
calculating state boundary value of the sub-network of the channel to obtain bearing capacity v of the sub-network to be controlled c 。
7. The big data based road network equalization control method of claim 6, wherein said using polynomial fitting method forms a traffic state-on-road vehicle relationship function curveThe specific process comprises the following steps:
selecting and analyzing traffic flow data of one week of road network, and using delta t l Calculating time sequence state indexes I of each road sub-network for each day at intervals, and obtaining the number v of vehicles in transit in the road sub-network to form a data set A d ＝((v 0 ，I 0 )，(v 1 ，I 1 )...(v n ，I n ) D=1,..7, n=288 represent 288 data in one day, (v 0 ，I 0 ) Representing an on-road vehicle v 0 Corresponding state index is I 0 Wherein Δt is l Not less than 5 minutes;
data set A d Sequencing, namely sequencing from small to large according to the number of vehicles in transit; if v is the same, sorting is carried out according to the time sequence to form a new data set A' d ；
Data set A' d Processing the abnormal data of the model (a), identifying singular values and replacing the singular values; merging the elements with the same v, and averaging the I values; form a new data set A d ；
Data set A d Fitting a traffic state-on-road vehicle relation function by adopting a polynomial fitting method, wherein: />Representing the state index I, x representing the number of vehicles in transit.
8. The big data based road network equalization control method of claim 7, wherein said pair traffic status-on-road vehicle relationship function curveThe method comprises the steps of classifying the characteristics, and dividing traffic states into three state intervals of smooth, slow running and crowding, wherein the specific process comprises the following steps:
acquiring the minimum value v of the number of vehicles in transit according to the historical traffic data of one week min And maximum v max Constructing a numerical value range of the in-transit vehicle: [ v min ，1.2*v max ]；
Constructing a sample set (v) with Δv as an interval min +Δv，v min +2*Δv，...，1.2*v max ) Substituting the traffic state-on-road vehicle relation function, calculating a state index to form a data sample C= (v) i ，I i )，i＝1,2,3，...，m；
With sliding window Deltav l ，Δv l And (5) and moving the curvature of the calculated data sample C to form a curvature data sample K= (K) 1 ，K 2 ，...K n )；
Analyzing the curvature data sample by adopting a time sequence clustering method, and sequencing the curvature data from small to large to form three state intervals of smoothness, creep and congestion, wherein the three state intervals are [ K ] 1 ，K s1 )，[K s1 ，K s2 ]，(K s2 ，K n ]；
Thereby obtaining the bearing capacity interval [ v ] corresponding to the three state intervals 1 ，v s1 )，[v s1 ，v s2 ]，(v s2 ，v n ]。
9. The big data based road network balance control method of claim 8, wherein the specific process includes, according to the segmentation result, combining the road network spatial characteristics, identifying key nodes inside and outside the controlled subnetwork, and implementing a control policy:
identifying a controlled sub-network set according to the historical data, calculating external access nodes connected with the controlled sub-gateways, and sorting and grading;
layering the external access nodes associated with the controlled sub-network according to the association relationship to form a limiting area, a buffer area and a shunting area; the method comprises the steps of dividing a limit area with the association degree higher than a first preset threshold value, dividing a shunt area with the association degree lower than a second preset threshold value, and dividing other buffer areas; the first preset threshold value is larger than the second preset threshold value;
acquiring vehicle running position and track data in a road network in real time, and calculating a sub-network G i Is the in-transit vehicle data v i ；
Judging Δv=v i -v c When Deltav is close to a preset threshold value, the green light time of the limiting zone is reduced, and the running speed of the buffer zone vehicle is reduced; in the diversion area, issuing guidance information, providing a substituted road, and guiding the vehicle to change the driving path;
according to the association relation, carrying out hierarchical processing on intersections and road section nodes in the subnetwork to form a key node set and a non-key node set; wherein, the nodes with the association degree higher than the third preset threshold value form a key node set;
calculating traffic state indexes of key nodes in real time, aiming at balancing of space bearing vehicles of all nodes, conducting dispersion on the associated flow directions of the key nodes through intelligent dispersion means, and controlling the state indexes of all the nodes in an optimization target interval range.
10. The big data based road network equalization control system based on the method of any of claims 1 to 9, characterized in that the system comprises a data receiving module, a data processing module, a data service module and a control optimizing module.
The data receiving module is used for receiving real-time traffic flow data acquired by the road network front-end detection equipment;
the data processing module is used for preprocessing the real-time traffic data and transmitting the data to the data service module; meanwhile, requesting traffic history data, analyzing and processing the traffic history data by combining with space road network data, calculating state indexes, and identifying traffic states;
the data service module is used for bearing the task of data input and output storage of a data bus of the multidimensional system; and realizing the data interaction task with other modules;
the control optimization module is used for acquiring real-time index data and control subnet data from the data processing module in real time, generating an optimization control instruction in real time and transmitting the optimization control instruction to the front-end control execution equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310527136.7A CN116564087A (en) | 2023-05-11 | 2023-05-11 | Road network balance control method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310527136.7A CN116564087A (en) | 2023-05-11 | 2023-05-11 | Road network balance control method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116564087A true CN116564087A (en) | 2023-08-08 |
Family
ID=87491154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310527136.7A Pending CN116564087A (en) | 2023-05-11 | 2023-05-11 | Road network balance control method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116564087A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117198081A (en) * | 2023-09-11 | 2023-12-08 | 深圳源谷科技有限公司 | Intelligent GPS positioning data analysis management system and method |
| CN118015857A (en) * | 2024-04-08 | 2024-05-10 | 北京悦知未来科技有限公司 | Road traffic planning method |
-
2023
- 2023-05-11 CN CN202310527136.7A patent/CN116564087A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117198081A (en) * | 2023-09-11 | 2023-12-08 | 深圳源谷科技有限公司 | Intelligent GPS positioning data analysis management system and method |
| CN118015857A (en) * | 2024-04-08 | 2024-05-10 | 北京悦知未来科技有限公司 | Road traffic planning method |
| CN118015857B (en) * | 2024-04-08 | 2024-06-07 | 北京悦知未来科技有限公司 | Road traffic planning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116564087A (en) | Road network balance control method and system based on big data | |
| CN107330547B (en) | Urban public transport dynamic scheduling optimization method and system | |
| Ouallane et al. | Overview of road traffic management solutions based on IoT and AI | |
| WO2017166474A1 (en) | Method and system for intersection group-based traffic control | |
| CN101719315B (en) | Method for acquiring dynamic traffic information based on middleware | |
| Sun et al. | Dynamic path planning algorithms with load balancing based on data prediction for smart transportation systems | |
| CN112629533B (en) | Fine path planning method based on road network rasterization road traffic prediction | |
| Hossan et al. | Fog-based dynamic traffic light control system for improving public transport | |
| CN111091295B (en) | Urban area boundary control system | |
| Dai et al. | A balanced assignment mechanism for online taxi recommendation | |
| CN111105613B (en) | Traffic distribution method and system based on multi-source data | |
| Torabi et al. | A collaborative agent-based traffic signal system for highly dynamic traffic conditions | |
| CN109816978B (en) | Regional group traffic guidance system and method considering dynamic response behaviors of drivers | |
| CN113763713B (en) | Road network bottleneck road section excavation and management method and device | |
| CN117671992A (en) | Intelligent bus dispatching method and system | |
| CN111311038A (en) | Evaluation method of traffic management and control service index | |
| Ali et al. | Big data analysis and cloud computing for smart transportation system integration | |
| Coll et al. | A linear programming approach for adaptive synchronization of traffic signals | |
| Li et al. | A traffic congestion aware vehicle-to-vehicle communication framework based on Voronoi diagram and information granularity | |
| Lakshminarasimhan | Advanced traffic management system using Internet of Things | |
| Ye et al. | Fairlight: Fairness-aware autonomous traffic signal control with hierarchical action space | |
| Zhu et al. | A prediction-based route guidance method toward intelligent and green transportation system | |
| Jain et al. | Enhance traffic flow prediction with real-time vehicle data integration | |
| CN111611332B (en) | Optimization method and system for route transfer | |
| Nicoleta Mocofan et al. | Comparative assessment of traffic control parameters within an UTC-distributed system |
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 |