CN105571604B - Coevolution method for optimizing route under dynamic road network environment - Google Patents
Coevolution method for optimizing route under dynamic road network environment Download PDFInfo
- Publication number
- CN105571604B CN105571604B CN201610021915.XA CN201610021915A CN105571604B CN 105571604 B CN105571604 B CN 105571604B CN 201610021915 A CN201610021915 A CN 201610021915A CN 105571604 B CN105571604 B CN 105571604B
- Authority
- CN
- China
- Prior art keywords
- road network
- network environment
- optimization
- node
- coevolution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
Abstract
Coevolution method for optimizing route under dynamic road network environment.Belong to computerized algorithm and management optimization field.The purpose is to solve under a specific dynamic road network environment (i.e., assuming that the variation of road network environment is foreseeable), it (can be offline to be calculated only by disposable optimization, calculated without constantly carrying out real-time online optimization), it is ensured that the technical issues of the theoretical optimality for route (from origination data to terminal) of actually passing by.In the single path optimization calculating process of the method for the present invention, road network environment is not static constant, but it can change by given road network environment changing rule with calculating process, that is, road network environment in single optimization the calculates coevolution with calculating process；Because road network environment can coevolution, during path optimization allow can not sensible node and link before waiting behavior.The routing problem that the method for the present invention can be used in real physical network and abstract virtual network.
Description
Technical field：
The present invention provides the coevolution method for optimizing route under a kind of dynamic road network environment, belong to computerized algorithm and
Management optimization field.
Background technology：
Routing problem is seen everywhere in daily production and life, it is to reducing cost, improving efficiency with important
Effect.Most classical routing problem is static path optimization problem, i.e.,：A changeless road network environment (can
To be the physical network of reality, such as network of highways can also be abstract virtual network, such as decision tree) in find optimal path.So
And actual conditions are：Road network environment be typically can it is continually changing (such as：The disaster region of mobile barrier, diffusion, no
Stop the traffic lights of switching, the functional fault of node and other uncertain factors in road network environment).Therefore, it often needs
Optimal path is found in the road network environment of time-varying, this generates dynamic path optimization problems.Solving, dynamic route is excellent
When change problem, current way is：When changing road network environment, recalculate from movable body current location to terminal
Optimal path (or re-optimization arrives the path in some following time window, in the time window from current location
Differ and surely reach home), then continue to move ahead by newest path optimizing, until road network environment changes again, then weigh
New optimization is from the path of new current location, repeatedly, until movable body is reached home.If it is calculating from present bit
The optimal path of terminal is set, then the dynamic path optimization problem referred to as under global optimization strategy；If it is optimization from present bit
The path in some following time window is set, then the dynamic path optimization problem being known as under sliding horizon strategy.Either
Which class dynamic path optimization problem, there is the basic characteristics that following four is common：(1) it needs ceaselessly to repeat to exist in real time
Line optimization calculates, therefore requires online computing capability very high；(2) when carrying out real-time online optimization calculating every time, road network ring
Border is fixed to the practical road network environment observed by the calculating moment or measured, that is, in each real-time online optimization process,
Road network environment used is changeless in fact, is static, therefore, each real-time online optimization, which calculates, really to be solved
Static path optimization problem；(3) it in path optimization's calculating process, does not take into account that generally or movable body is allowed sensible can not to tie
Point and link before waiting behavior (because the road network environment used in single path optimization calculating process be it is changeless,
So it is nonsensical to wait for, node and the access of link in single optimization calculating process will not become with the stand-by period
Change)；(4) when movable body is reached home, if we turn around again, the analysis practical route passed by of movable body is (from original
Point arrives terminal) with the change histories of road network environment, it will usually find the route (from origination data to terminal) actually passed by not
With theoretical optimality, in other words, dynamic path optimization problem can only ensure on the plan road that each calculating moment is calculated
The optimality of diameter (from current location to terminal, or in some following time window), and under specific dynamic road network environment
There is no relationships for the optimality of route of actually passing by.In fact, the focus that dynamic path optimization problem is studied is not just practical
It passes by the optimality of route, but how to quickly complete real-time on-line optimization and calculate.So, the science of an essence and
Practical problems just produce：Under a specific dynamic road network environment (i.e., it is assumed that the variation of road network environment is can to predict
), if it may not be needed to carry out real-time on-line optimization calculating, but calculated only by disposable offline optimization, just
It can guarantee the theoretical optimality for route (from origination data to terminal) of actually passing byThe method of the present invention seeks to answer and solve
This problem.The essential defect of dynamic path optimization problem is that：When each real-time online optimizes and calculates, used road
Net environment is static constant, that is, the road network environment in single optimization calculates is static constant.The method of the present invention is then wanted
Break through this essential defect：When carrying out path optimization's calculating, used road network environment is can be with the process of calculating
And change by the changing rule of oneself, in other words, in single path optimization calculating process, road network environment is not static
Constant, but can be with calculating process collaborative variation or coevolution.Exactly because this " road in single optimization calculates
The characteristics of net environment coevolution with calculating process ", be just called the " collaboration under dynamic road network environment with the inventive method
Evolutionary approaches optimization method ".
Invention content：
The invention aims to provide the coevolution method for optimizing route under a kind of dynamic road network environment.With answer and
It solves under a specific dynamic road network environment (i.e., it is assumed that the variation of road network environment is foreseeable), only by one
The optimization of secondary property calculates (can be offline, calculated without constantly repeating real-time on-line optimization), can protect
Confirm border pass by route (from origination data to terminal) theoretical optimality science and practical problems.
The present invention by following schemes to solve the above problems, by being realized：In the single path of the method for the present invention
Optimize in calculating process, road network environment is not static constant, can be as calculating process is by given road network environment variation
Rule and change, that is, single optimization calculate in road network environment with calculating process coevolution；Exactly because road network environment
Can coevolution, so the present invention method path optimization's calculating process in allow wouldn't can sensible node and link before
Waiting behavior (because wait for may more save time and distance than detouring)；Consider the optimization of road network environment coevolution
Actually the pass by optimality in path and the timeliness of calculating can be effectively ensured in calculating process.
The one-off optimization calculating process of the method for the present invention includes following key step：(1) description road network is determined
The rule of environmental change；(2) a sufficiently small chronomere is selected；(3) road network environment of the initialization in origination data, choosing
A fixed travelling speed constant value, and calculate from origination data and be linked at institute's energy in chronomere's length in road network
The current front reached；(4) if including terminal in current front, step (7) is gone to, otherwise, goes to step (5)；(5) basis
The rule of road network environment variation updates road network environment by chronomere's length computation；(6) it is based on newer road network environment simultaneously
Consider movable body wouldn't can sensible node and link before possibility wait for behavior, calculate from current front along road network
It is linked at the new current front that can be reached in chronomere's length, is then back to step (4)；(7) according to current battle array
The history of evolution in face, backtracking is until origination data since terminal, so that it is determined that optimal path.
Current front sometime in above-mentioned steps refers to movable body after origination data, by selected travelling speed
Spend constant value movement, the set for all positions that may be reached when moving to the moment point.
It needs to be emphasized that：In the one-off optimization calculating process of the method for the present invention, step (5) introduces road
The changing rule of net environment, thus the road network environment in optimization calculating process is not static constant, as optimization calculates
Process and change by given road network environment changing rule；Step (6) needs to consider to move when calculating new current front
Body wouldn't can sensible node and link before possibility wait for behavior.The present invention method the step of (5) and step (6) this two
A feature, be the optimized method in conventional dynamic road single optimization calculating process in it is unexistent.
Coevolution method for optimizing route under the dynamic road network environment of the present invention has the advantages that：In a spy
Under fixed dynamic road network environment (i.e., it is assumed that the variation of road network environment is foreseeable), method of the invention can ensure reality
Border is passed by the theoretical optimality of route (from origination data to terminal)；If the rule for describing road network environment variation is to immobilize
(i.e. road network environment can change, but the rule changed is to determine), then method of the invention only by disposably from
Line optimization, which calculates, can solve the problems, such as that (offline optimization, which calculates, means to have the sufficient time that various calculating is made full use of to provide
Source, so as to effectively solve large-scale routing problem), without constantly repeating real-time on-line optimization meter
It calculates (to not limited by the various times and computing resource that on-line optimization calculates)；If describing the rule of road network environment variation
Be change over time (such as：The movement speed of barrier is starting in 3 hours to be 10 kilometers/hour, later 5 hours
Inside become 15 kilometers/hour), then method of the invention only needed at road network environment changing rule changed each moment point
Not carry out path optimization calculate, this calculating process can be completed, can also be completed online offline, because road network environment becomes
The variation of law is slow for the variation of road network environment itself, so even in line computation, also has and compares
Sufficient calculating time (such as：Assuming that the variation in every 3 hours of the movement speed of barrier is primary, then twice in succession in line computation
Time interval just has 3 hours).
Description of the drawings：
Attached drawing provides the schematic diagram of the coevolution method for optimizing route under the dynamic road network environment of the present invention：
Fig. 1：The key step schematic diagram of coevolution method for optimizing route under dynamic road network environment.
Fig. 2：The solution procedure schematic diagram of coevolution method for optimizing route under dynamic road network environment.
Fig. 3：The solution effect diagram of coevolution method for optimizing route under dynamic road network environment.
Specific implementation mode：
Below in conjunction with the accompanying drawings, it is to solve one to the coevolution method for optimizing route under the dynamic road network environment of the present invention
Under a specific dynamic road network environment, calculated only by disposable optimization, it is ensured that actually passing by route (from original
Point is to terminal) theoretical optimality science and practical problems used by preferred embodiment be described further.
Fig. 1 gives the key step included by the method for the present invention：
(step 1)：Determine the rule of description road network environment variation；
(step 2)：A sufficiently small chronomere is selected, to guarantee effectively to describe given road network environment
Change procedure；
(step 3)：The road network environment in origination data is initialized, selectes a travelling speed constant value, and calculate from original
Beginning starting point sets out and is linked at all positions that can be reached in chronomere's length in road network, by all these positions
It is denoted as current front, and forerunner's node of all the points in current front is labeled as origination data, that is, each of current front
Point is all come over from origination data；
(step 4)：If including terminal in current front, (step 7) is gone to, otherwise, is gone to (step 5)；
(step 5)：According to the rule that road network environment changes, road network environment is updated by chronomere's length computation；
(step 6)：Based on newer road network environment, calculate from current front in road network when being linked at one
Between all former positions never reached that can reach in unit length, be denoted as new current front, and according to calculating
Journey mark is poured in forerunner's node of each point in new current front, that is, some point in new current front is from upper one
Which of current front point is come over；If some point in new current front can be from a upper current front
In multiple points reached in this current chronomere's length, then forerunner's node of the point should be labeled as one it is current
Reach that point of the point in front earliest in this current chronomere's length；Special emphasis is, new calculating
Current front when, need to consider movable body wouldn't can be sensible node and link before waiting behavior (because sometimes hindering
Waiting more saves time and distance than the cut-through area that detours before hindering area), in other words, if certain in upper one current front
The front of a point in this current chronomere's length there are one wouldn't can be sensible node or link (according to newer road
Net environment), then can also include the point from this point and in the new current front of formation, i.e. movable body can have in the point
Wait for behavior；It is then back to (step 4).
(step 7)：Since terminal, pushed away until origination data by forerunner's node is counter successively, so that it is determined that optimal path,
Then optimization calculating process terminates.
Fig. 2 gives a solution procedure for disposably solving optimal path under dynamic road network environment in the present inventive method
Example.In the disposable solution procedure of example shown in Fig. 2, need in view of following 5 moment, road network environment will be in this 5 futures
Moment is each different, i.e., road network environment in disposable solution procedure is changed with the variation of future time instance.Such as
Fruit changes traditional optimized method in dynamic road into, then corresponding to each future time instance in its real-time online solution procedure
Road network environment be all identical.
In the disposable solution procedure of example shown in Fig. 2, the current front of future time instance 1 is all from origination data edge
It sensible can be linked at the position reached in a unit interval length in 1 road network of future time instance, including node 2 and chain
Connect a point on (1,9)；Forerunner's node of all the points is all origination data on the current front of future time instance 1, i.e. node 1.
The current front of future time instance 2 is then leading in 2 road network of future time instance from the point on the current front of future time instance 1
Up to be linked at reached in a unit interval length before the position that did not reach, including node 4, (its forerunner ties
Point is node 2), link point (its on the point (its forerunner's node is node 2) on (2,3), and link (1,9)
Forerunner's node is origination data).The current front of future time instance 3 is then from the point edge on the current front of future time instance 2
It sensible can be linked at the former position not reached reached in a unit interval length in 3 road network of future time instance,
Including node 5 (its forerunner's node is node 4), (its forerunner ties for node 3 (its forerunner's node is node 2) and node 9
Point is origination data).The current front of future time instance 4 be then from the point on the current front of future time instance 3 along future when
Carving in 4 road networks sensible can be linked at the former position not reached reached in a unit interval length, wherein wrapping
Node 6 (its forerunner's node is node 3 or node 5) is included, node 7 (its forerunner's node is node 5) and node 9 are (before it
It is origination data to drive node)；It note that because node 9 is the point on the current front of future time instance 3, and node 9 will be at future
Carving can not be sensible in 4 road network, it is contemplated that movable body can be waited for before node 9, so the current front of future time instance 4
Still contain node 9.The current front of future time instance 5 be then from the point on the current front of future time instance 4 along future when
Carving in 5 road networks sensible can be linked at the former position not reached reached in a unit interval length, wherein wrapping
Node 8 (its forerunner's node is node 6 or node 7) is included, the point (its forerunner's node is node 9) on (9,10) is linked,
And node 10, i.e. terminal (its forerunner's node is node 7).Because terminal is contained in the current front of future time instance 5, from end
Point starts, and is pushed away until origination data by forerunner's node is counter successively, so as to find out the optimal road under given dynamic road network environment
Diameter is exactly 1 → 2 → 4 → 5 → 7 → 10, so solution procedure terminates.
If changing traditional optimized method in dynamic road into solve the problem exemplified by Fig. 2, movable body can be first along chain
(1,9) is connect to move to node 9, but when movable body reaches node 9, just catching up with that node 9 becomes can not be sensible, due to tradition
The no-wait behavior of the optimized method in dynamic road, movable body has to along link (1,9) to 1 return movement of node.This
It returns, the hourage actually passed by corresponding to route eventually led under the optimized method in conventional dynamic road greatly increases.
Fig. 3 gives the result of the method for one group of present invention and the contrast experiment of the optimized method in conventional dynamic road.
As seen from Figure 3, in contrast experiment, because the barrier zone of incipient stage is in the central area of road network,
So the optimized method plan in conventional dynamic road is along close to cornerwise line-of-road movement.But when movable body is moved close to road network
When central area, barrier zone has been moved into the central area of road network, to block the optimized method in conventional dynamic road
The route previously planned.Thus, the optimized method in conventional dynamic road is had to the current location re-optimization based on movable body
Subsequent moving line.In the quite a while, the result of the optimized method real-time online re-optimization in conventional dynamic road is all
It is attempt to right-hand rotation cut-through region (optimal result that the static road network based on the on-line optimization moment is calculated).But due to
Barrier zone ceaselessly moves from left to right, so the movement road that the optimized method real-time online re-optimization in conventional dynamic road goes out
Line is always blocked by mobile barrier zone.It has crossed for a long time, the optimized method in conventional dynamic road just calculates left-hand rotation cut-through
The moving line in region.As a result, in the contrast experiment of Fig. 3, the route of actually passing by under the optimized method in conventional dynamic road
Length is 4517.3.
According to the method for the present invention, it is only necessary to carry out disposable optimization from origination data and calculate.As seen from Figure 3,
Due to considering the coevolution of road network environment in disposably optimization calculating process and wouldn't can sensible node and chain
Waiting behavior before connecing, the path optimizing that method of the invention is obtained from origination data when just turn left properly to keep away
Open mobile barrier zone.As a result, the length of the route of actually passing by under the method for the present invention is only 3280.8, much smaller than tradition
The length of route of actually passing by under the optimized method in dynamic road.
Claims (6)
1. the coevolution method for optimizing route under a kind of dynamic road network environment, to solve the variation rule in a road network environment
Rule is calculated only by disposable optimization, it is ensured that the institute from origination data to terminal under known dynamic road network environment
Actually pass by route theoretical optimality the technical issues of, it is characterized in that：In single path optimization calculating process, road network environment
It is static not constant, it can change by given road network environment changing rule with calculating process, that is, optimize in single
Road network environment in the calculating coevolution with calculating process；Road network environment coevolution can cause node and link to become wouldn't
Can be sensible, can consider in path optimization's calculating process movable body wouldn't can sensible node and link before waiting behavior；Consider
The optimization calculating process of road network environment coevolution can be effectively ensured actually the pass by optimality in path and the timeliness of calculating；
The method includes mainly following steps：(1) rule of description road network environment variation is determined；(2) one is selected enough
Small chronomere, to guarantee effectively to describe the change procedure of given road network environment；(3) initialization is in origination data
Road network environment, select a travelling speed constant value, and calculate and from origination data be linked at a time in road network
All these positions are denoted as current front by all positions that can be reached in unit length, and by all the points in current front
Forerunner's node be labeled as origination data, that is, current front is each put and comes over from origination data；(4) if
Include terminal in current front, goes to step (7), otherwise, go to step (5)；(5) rule changed according to road network environment, is pressed
One chronomere's length computation updates road network environment；(6) it is based on newer road network environment, is calculated from current front along road
All former positions never reached that being linked in net can reach in chronomere's length are denoted as new current
Front, and marked according to calculating process forerunner's node of each point in new current front, that is, certain in new current front
One point is come over from which of upper one current front point；If some point in new current front can be with
It is reached in this current chronomere's length from multiple points in upper one current front, then forerunner's node of the point should
It is labeled as reaching that point of the point in a current front earliest in this current chronomere's length；It is calculating
When new current front, need to consider movable body wouldn't can be sensible node and link before waiting behavior, that is, if more
In new road network environment, front of some point in upper one current front in this current chronomere's length there are one
Wouldn't can be sensible node or link, then can also include from this point the point in the new current front that is formed, that is, move
Body can have waiting behavior in the point；It is then back to step (4)；(7) it since terminal, is pushed away until original by forerunner's node is counter successively
Beginning starting point, so that it is determined that optimal path, then optimizes calculating process and terminate.
2. the coevolution method for optimizing route under dynamic road network environment according to claim 1, it is characterized in that：If retouched
The rule for stating road network environment variation is changeless known, then the method is only by disposable offline optimization meter
Calculation can solve the problems, such as, be calculated without constantly repeating real-time on-line optimization.
3. the coevolution method for optimizing route under dynamic road network environment according to claim 1, it is characterized in that：If retouched
The rule for stating road network environment variation is also to change over time, then the method only needs to occur in road network environment changing rule
Each moment of variation carries out disposable path optimization's calculating respectively.
4. the coevolution method for optimizing route under dynamic road network environment according to claim 1, it is characterized in that：Described
Method can be applied to the routing problem in real physical network.
5. the coevolution method for optimizing route under dynamic road network environment according to claim 1, it is characterized in that：Described
Method can be applied to the routing problem in abstract virtual network.
6. the coevolution method for optimizing route under dynamic road network environment according to claim 1, it is characterized in that：Described
Various appropriate hardware computing devices and software programming technique may be used to realize in method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610021915.XA CN105571604B (en) | 2016-01-14 | 2016-01-14 | Coevolution method for optimizing route under dynamic road network environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610021915.XA CN105571604B (en) | 2016-01-14 | 2016-01-14 | Coevolution method for optimizing route under dynamic road network environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105571604A CN105571604A (en) | 2016-05-11 |
| CN105571604B true CN105571604B (en) | 2018-08-14 |
Family
ID=55882007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610021915.XA Active CN105571604B (en) | 2016-01-14 | 2016-01-14 | Coevolution method for optimizing route under dynamic road network environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105571604B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110119839B (en) * | 2019-04-24 | 2021-05-14 | 华南理工大学 | Urban road traffic accident emergency rescue path planning method |
| CN112270438A (en) * | 2020-10-28 | 2021-01-26 | 中国民航大学 | Many-to-many path optimization method under dynamic road network environment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103994768A (en) * | 2014-05-23 | 2014-08-20 | 北京交通大学 | Method for seeking for overall situation time optimal path under dynamic time varying environment |
| CN104197948A (en) * | 2014-09-11 | 2014-12-10 | 东华大学 | Navigation system and method based on traffic information prediction |
| CN104567907A (en) * | 2015-01-22 | 2015-04-29 | 四川汇源吉迅数码科技有限公司 | Method for real-time path planning based on dynamic feedback |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060161337A1 (en) * | 2005-01-19 | 2006-07-20 | Ping-Chung Ng | Route planning process |
| EP2757504B1 (en) * | 2013-01-17 | 2022-06-01 | Google LLC | Route planning |
-
2016
- 2016-01-14 CN CN201610021915.XA patent/CN105571604B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103994768A (en) * | 2014-05-23 | 2014-08-20 | 北京交通大学 | Method for seeking for overall situation time optimal path under dynamic time varying environment |
| CN104197948A (en) * | 2014-09-11 | 2014-12-10 | 东华大学 | Navigation system and method based on traffic information prediction |
| CN104567907A (en) * | 2015-01-22 | 2015-04-29 | 四川汇源吉迅数码科技有限公司 | Method for real-time path planning based on dynamic feedback |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105571604A (en) | 2016-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jindal et al. | SeDaTiVe: SDN-enabled deep learning architecture for network traffic control in vehicular cyber-physical systems | |
| Zhang et al. | Digital twin empowered content caching in social-aware vehicular edge networks | |
| WO2008130828A3 (en) | Interactive mpls traffic engineering | |
| Zhong et al. | Routing without routing algorithms: an AI-based routing paradigm for multi-domain optical networks | |
| CN105571604B (en) | Coevolution method for optimizing route under dynamic road network environment | |
| CN104301812A (en) | Optical network system and network function visualizing method | |
| Xue et al. | Optimal routing for waste collection: a case study in Singapore | |
| Li et al. | A dynamic and scalable user-centric route planning algorithm based on polychromatic sets theory | |
| CN103218478A (en) | Heuristic search method and search system for eliminating topological isolated island from power distribution network | |
| Nguyen et al. | ACO-based approach on dynamic MSMD routing in IoV environment | |
| Yu et al. | Multi visual GRU based survivable computing power scheduling in metro optical networks | |
| CN106980953A (en) | A kind of dynamic path planning method of Logistics Oriented | |
| Desai et al. | Adaptive routing based on predictive reinforcement learning | |
| Wang et al. | Development of an adaptive traffic signal control framework for urban signalized interchanges based on infrastructure detectors and CAV technologies | |
| Chen et al. | Machine-learning based routing pre-plan for sdn | |
| CN103501346A (en) | Non-structured P2P (Peer-to-Peer) resource searching method based on machine learning and network node reputation | |
| CN101840229A (en) | Logical network automatic operation control system, automation control system and application method | |
| CN116153117A (en) | Traffic guiding method, device, electronic equipment and storage medium | |
| CN106507377B (en) | A kind of optimal site selecting method of communication network relay | |
| CN109474506A (en) | Establish the method and device of Virtual Private Network vpn service | |
| Zhu et al. | An edge-assisted vehicle routing method based on game-theoretic multiagent learning | |
| DE602007006794D1 (en) | PROCESS PROCESS FOR TRANSPORT CONNECTION INFORMATION | |
| Kulakov et al. | Modified Method of Traffic Engineering in DCN with a Ramified Topology | |
| Gillani et al. | Machine learning based data collection protocol for intelligent transport systems: a real-time implementation on Dublin M50, Ireland | |
| CN104579971B (en) | For the method and apparatus for the route transferred in the network architecture of software definition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 100088 room 6, unit 7, 8 hospital, new street, Xicheng District, Beijing, 7 Applicant after: Beijing Normal University Applicant after: Liao Jianqin Address before: 100875 room 702, 10 building, Beijing Normal University, 19 new street, Haidian District, Beijing. Applicant before: Beijing Normal University Applicant before: Liao Jianqin |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |