CN111506408A - Edge computing task scheduling method based on associated data set - Google Patents
Edge computing task scheduling method based on associated data set Download PDFInfo
- Publication number
- CN111506408A CN111506408A CN202010295997.3A CN202010295997A CN111506408A CN 111506408 A CN111506408 A CN 111506408A CN 202010295997 A CN202010295997 A CN 202010295997A CN 111506408 A CN111506408 A CN 111506408A
- Authority
- CN
- China
- Prior art keywords
- data
- task
- association
- calculation
- nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/485—Task life-cycle, e.g. stopping, restarting, resuming execution
- G06F9/4856—Task life-cycle, e.g. stopping, restarting, resuming execution resumption being on a different machine, e.g. task migration, virtual machine migration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3017—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is implementing multitasking
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An edge computing task scheduling method based on a correlation data set comprises the following steps: 1) aiming at the current situation that the number of data and calculation tasks under the edge calculation environment is increased continuously, monitoring sensor data and migratable nodes in real time, and determining the number of data and the number and capacity of the migratable nodes; 2) monitoring the computing task request in real time, and binding data and the computing task based on the dependency relationship; 3) aggregating the data-task association items to form an overall data-task association set, and optimizing the overall data-task association set into an optimal migration set by taking the overall data association degree as a maximum target; 4) cutting the optimal migration set by taking the capacity of the migratable nodes as constraint to form a local optimal migration set; 5) and acquiring data and calculation tasks in the local optimal migration set, migrating the data and the calculation tasks to target nodes with corresponding capacities for execution, and repeatedly executing the steps 1-4. The invention provides a method for realizing efficient task scheduling through the method.
Description
Technical Field
The invention provides an edge computing task scheduling method based on a correlation data set, aiming at the influence of high task scheduling response time on the whole system in an edge computing environment.
Background
With the rapid development and application of the internet of things and big data technology and the rapid spread of 5G network construction in China, the traditional cloud computing mode cannot efficiently process massive computing tasks generated by network edge equipment, and edge computing is carried out at the same time. In the traditional task scheduling strategy, the problem of data dependency among different computing tasks is not considered at the beginning of design, so that node migration of each task is independent, and the migration efficiency is low. In recent years, with the continuous richness and complexity of edge computing scenarios, task scheduling techniques have been gradually developed. However, in the context of a sharp increase in the number of edge computing tasks, there are many challenges in how to implement efficient task scheduling.
Traditional task scheduling strategies, such as three strategies for Hadoop task scheduling, do not take into account the dependency relationship between tasks on data. Such scheduling strategies severely limit system response time, so that efficient task scheduling cannot be accomplished in the context of marginal computing when a large number of more complex computing tasks occur.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an edge computing task scheduling method based on a related data set. The strategy aims at the current situation that the number of data and calculation tasks is increased continuously in the marginal calculation environment, the data of a sensor and migratable nodes are monitored in real time, and the number of the data and the number and the capacity of the migratable nodes are determined; monitoring the calculation task request in real time, and binding the data and the calculation task based on the dependency relationship of each task on the data; aggregating the data-task association items to form an overall data-task association set, and optimizing the overall data-task association set into an optimal migration set by taking the overall data association degree as a maximum target; cutting the optimal migration set by taking the capacity of the migratable nodes as constraint to form a local optimal migration set; and acquiring data and calculation tasks in the local optimal migration set, migrating the data and the calculation tasks to target nodes with corresponding capacities for execution, and repeatedly executing the steps 1-4.
In order to achieve the purpose, the invention adopts the technical scheme that: the method for scheduling the edge computing task based on the associated data set is characterized by comprising the following steps of:
an edge computing task scheduling method based on a correlation data set comprises the following steps:
step 1), monitoring sensor data and migratable nodes in real time, and determining the data quantity, the quantity of the migratable nodes and the capacity of the migratable nodes;
step 2), monitoring the calculation task request in real time, and binding the data and the calculation task based on the dependency relationship of each task on the data;
step 3), aggregating the data-task association items to form a total data-task association set, and optimizing the total data-task association set into an optimal migration set by taking the maximum total data association degree as a target;
step 4), cutting the optimal migration set by taking the capacity of the migratable nodes as constraint to form a local optimal migration set;
and 5) acquiring data and calculation tasks in the local optimal migration set, migrating the data and the calculation tasks to target nodes with corresponding capacities for execution, and repeatedly executing the steps 1-4 until the central processing unit stops receiving the calculation task request.
In the step 1), the specific method comprises the following steps:
1.1) data real-time acquisition: acquiring data required in the edge computing environment by using a sensor;
1.2) acquiring node quantity information: obtaining the number n and capacity c of migratable nodes on an edge computing platform using a central processor or a sensorp(p ═ 1,2,..., n), information acquisition is performed;
1.3) dynamic collection processing: when the real-time data collection quantity of the sensor is larger than the standard data quantity
When the difference is large, the acquisition period T of the data is timely adjusted: when real-time data volumeWhen the standard data amount is 150% or more, the data acquisition period is shortened
When the real-time data volume is 65% or less of the standard data volume, the data acquisition cycle is prolonged to 2T;
1.4) storing the sensor data information and the migratable node information.
In the step 2), the specific method is as follows:
2.1) calculating the real-time monitoring of the task quantity: monitoring and collecting computing task requests on an edge computing platform, wherein the number of the computing tasks collected in a collecting period is I;
2.2) for each calculation task ti(I1, 2.. times.i), if it requires k items of data to execute, then the computing task associates r to each required item of dataiIs composed of
The relevance degree of the rest data is 0;
2.3) acquiring data S required by the calculation task from the global memory;
and 2.4) binding the data and the calculation tasks by utilizing the mapping relation between the data and the calculation tasks, and establishing S data-task association items d.
In the step 3), the specific method is as follows:
3.1) collecting data-task association items D, and converging the data-task association items D into an overall data-task association set D;
3.2) the calculation formula of the overall data relevance R is
Wherein d issRepresenting the s-th data-task association, tiRepresenting the computational tasks contained in the s-th data-task related item, rs-1Represents the degree of association of the computing task with the data in the previous data-task association item, and rs+1Representing the relevance of the calculation task and the data in the next data-task relevance item, wherein the sum of the two data-task relevance items represents the number of the calculation task and the adjacent data-task relevance itemAccording to the degree of association; carrying out recursive combination on the data-task association items in the overall data-task association set to obtain the corresponding overall data association degree R;
3.3) when the overall data relevancy R is maximum, the overall data-task relevancy set is the optimal migration set required.
In the step 4), the specific method is as follows:
4.1) obtaining the number n of migratable nodes and the corresponding capacity c from the global memoryp；
4.2) migratable nodes by capacity cpSorting from high to low;
4.3) adopting a high-capacity priority principle to sequentially cut the optimal migration set according to capacity constraints to form a local optimal migration set;
4.4) aggregation of locally optimal migrations with Capacity cpCarrying out one-to-one mapping;
4.5) continuing to put the uncut part in the set, and continuing to cut and execute when waiting for the migration node to be idle.
The invention has the beneficial effects that:
aiming at the existing problems, the invention provides an edge computing task scheduling method based on a related data set. The strategy aims at the current situation that the number of data and calculation tasks is increased continuously in the marginal calculation environment, the data of a sensor and migratable nodes are monitored in real time, and the number of the data and the number and the capacity of the migratable nodes are determined; monitoring the calculation task request in real time, and binding the data and the calculation task based on the dependency relationship of each task on the data; aggregating the data-task association items to form an overall data-task association set, and optimizing the overall data-task association set into an optimal migration set by taking the overall data association degree as a maximum target; cutting the optimal migration set by taking the capacity of the migratable nodes as constraint to form a local optimal migration set; and acquiring data and calculation tasks in the local optimal migration set, migrating the data and the calculation tasks to target nodes with corresponding capacities for execution, and repeatedly executing the steps 1-4.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
An edge computing task scheduling method based on a correlation data set comprises the following steps:
step 1), monitoring sensor data and migratable nodes in real time, and determining the data quantity, the quantity of the migratable nodes and the capacity of the migratable nodes;
1.1) data real-time acquisition: acquiring data required in the edge computing environment by using a sensor;
1.2) acquiring node quantity information: obtaining the number n and capacity c of migratable nodes on an edge computing platform using a central processor or a sensorp(p ═ 1,2,..., n), information acquisition is performed;
1.3) dynamic collection processing: when the real-time data collection quantity of the sensor is larger than the standard data quantity
When the difference is large, the acquisition period T of the data is timely adjusted: when the real-time data amount is 150% or more of the standard data amount, the data acquisition period is shortened
When the real-time data volume is 65% or less of the standard data volume, the data acquisition cycle is prolonged to 2T;
1.4) storing the sensor data information and the migratable node information.
Step 2), monitoring the calculation task request in real time, and binding the data and the calculation task based on the dependency relationship of each task on the data;
2.1) calculating the real-time monitoring of the task quantity: monitoring and collecting computing task requests on an edge computing platform, wherein the number of the computing tasks collected in a collecting period is I;
2.2) for each calculation task ti(I1, 2.. times.i), if it requires k items of data to execute, then the computing task associates r to each required item of dataiIs composed of
For the rest of the dataThe degree of association is 0;
2.3) acquiring data S required by the calculation task from the global memory;
and 2.4) binding the data and the calculation tasks by utilizing the mapping relation between the data and the calculation tasks, and establishing S data-task association items d.
Step 3), aggregating the data-task association items to form an overall data-task association set, and optimizing the overall data-task association set into an optimal migration set by taking the overall data association degree as a maximum target;
3.1) collecting data-task association items D, and converging the data-task association items D into an overall data-task association set D;
3.2) the calculation formula of the overall data relevance R is
Wherein d issRepresenting the s-th data-task association, tiRepresenting the computational tasks contained in the s-th data-task related item, rs-1Represents the degree of association of the computing task with the data in the previous data-task association item, and rs+1Representing the association degree of the calculation task and the data in the next data-task association item, wherein the sum of the two represents the association degree of the calculation task and the data in the adjacent data-task association item; carrying out recursive combination on the data-task association items in the overall data-task association set to obtain the corresponding overall data association degree R;
3.3) when the overall data relevancy R is maximum, the overall data-task relevancy set is the optimal migration set required.
Step 4), cutting the optimal migration set by taking the capacity of the migratable nodes as constraint to form a local optimal migration set;
4.1) obtaining the number n of migratable nodes and the corresponding capacity c from the global memoryp；
4.2) migratable nodes by capacity cpSorting from high to low;
4.3) adopting a high-capacity priority principle to sequentially cut the optimal migration set according to capacity constraints to form a local optimal migration set;
4.4) aggregation of locally optimal migrations with Capacity cpCarrying out one-to-one mapping;
4.5) continuing to put the uncut part in the set, and continuing to cut and execute when waiting for the migration node to be idle.
And 5) acquiring data and calculation tasks in the local optimal migration set, migrating the data and the calculation tasks to target nodes with corresponding capacities for execution, and repeatedly executing the steps 1-4 until the central processing unit stops receiving the calculation task request.
Example 1:
under the automatic driving environment, the vehicle sensor collects the data of the surrounding road conditions (such as the information of surrounding vehicles, road signal lamps, speed limit signs and the like) in real time, the collection period T is the reciprocal (unit is s) of the vehicle speed (Km/h), and the central processing unit of the vehicle is used for collecting the number n of edge processors which can be moved in the vehicle and in the driving route and the corresponding capacity cp thereof. If the real-time traffic data S is the standard traffic data due to the complex traffic (overpass, turntable, etc.) and the increased number of vehicles
150% or more, the data acquisition cycle is shortened to
If the real-time data volume S of the vehicle is the standard data volume due to good road conditions, few surrounding vehicles and few signal marks and the like
And 65% or less, the data acquisition cycle is extended to 2T. In the acquisition period, the vehicle receives the calculation tasks such as lane changing, front and rear vehicle distance, acceleration and deceleration operation judgment and the like to total I items, acquires road condition data and binds the acquired road condition data with the calculation tasks needing the data, and establishes a data-task association item. Gathering S data-task association items into a total data-task association set, putting the total data-task association set into a vehicle memory, and optimizing the total data-task association set to be optimal by utilizing a vehicle central processing unit when the total data association degree R is the maximum targetAnd migrating the collection. And taking the capacity of the edge processor available for migration in the vehicle interior and the driving route as a constraint, cutting the optimal migration set into a local optimal migration set by the central processing unit, and migrating the local optimal migration set to the corresponding edge processor for execution. During the running process of the vehicle, the operation is carried out according to the strategy at each time period until the vehicle reaches a specified place and is flamed out (the central processor in the vehicle does not receive calculation tasks any more).
Claims (5)
1. The method for scheduling the edge computing task based on the associated data set is characterized by comprising the following steps: the method comprises the following steps:
step 1), monitoring sensor data and migratable nodes in real time, and determining the data quantity, the quantity of the migratable nodes and the capacity of the migratable nodes;
step 2), monitoring the calculation task request in real time, and binding the data and the calculation task based on the dependency relationship of each task on the data;
step 3), aggregating the data-task association items to form a total data-task association set, and optimizing the total data-task association set into an optimal migration set by taking the maximum total data association degree as a target;
step 4), cutting the optimal migration set by taking the capacity of the migratable nodes as constraint to form a local optimal migration set;
and 5) acquiring data and calculation tasks in the local optimal migration set, migrating the data and the calculation tasks to target nodes with corresponding capacities for execution, and repeatedly executing the steps 1-4 until the central processing unit stops receiving the calculation task request.
2. The method for scheduling the edge calculation task based on the associated data set according to claim 1, wherein in the step 1), the specific method is as follows:
1.1) data real-time acquisition: acquiring data required in the edge computing environment by using a sensor;
1.2) acquiring node quantity information: obtaining the number n and capacity of migratable nodes on an edge computing platform using a central processor or a sensorQuantity cp(p ═ 1,2,..., n), information acquisition is performed;
1.3) dynamic collection processing: when the difference of the real-time data collection amount of the sensor is larger than the standard data amount S, the data collection period T is timely adjusted: when the real-time data amount is 150% or more of the standard data amount, the data acquisition period is shortened
When the real-time data volume is 65% or less of the standard data volume, the data acquisition cycle is prolonged to 2T;
1.4) storing the sensor data information and the migratable node information.
3. The method for scheduling an edge computing task based on an associated data set according to claim 1, wherein in the step 2), the specific method is as follows:
2.1) calculating the real-time monitoring of the task quantity: monitoring and collecting computing task requests on an edge computing platform, wherein the number of the computing tasks collected in a collecting period is I;
2.2) for each calculation task ti(I1, 2.. times.i), if it requires k items of data to execute, then the computing task associates r to each required item of dataiIs composed of
The relevance degree of the rest data is 0;
2.3) acquiring data S required by the calculation task from the global memory;
and 2.4) binding the data and the calculation tasks by utilizing the mapping relation between the data and the calculation tasks, and establishing S data-task association items d.
4. The method for scheduling an edge computing task based on an associated data set according to claim 1, wherein in the step 3), the specific method is as follows:
3.1) collecting data-task association items D, and converging the data-task association items D into an overall data-task association set D;
3.2) the calculation formula of the overall data relevance R is
Wherein d issRepresenting the s-th data-task association, tiRepresenting the computational tasks contained in the s-th data-task related item, rs-1Represents the degree of association of the computing task with the data in the previous data-task association item, and rs+1Representing the association degree of the calculation task and the data in the next data-task association item, wherein the sum of the two represents the association degree of the calculation task and the data in the adjacent data-task association item; carrying out recursive combination on the data-task association items in the overall data-task association set to obtain the corresponding overall data association degree R;
3.3) when the overall data relevancy R is maximum, the overall data-task relevancy set is the optimal migration set required.
5. The method for scheduling an edge calculation task based on an associated data set according to claim 1, wherein in the step 4), the specific method is as follows:
4.1) obtaining the number n of migratable nodes and the corresponding capacity c from the global memoryp；
4.2) migratable nodes by capacity cpSorting from high to low;
4.3) adopting a high-capacity priority principle to sequentially cut the optimal migration set according to capacity constraints to form a local optimal migration set;
4.4) aggregation of locally optimal migrations with Capacity cpCarrying out one-to-one mapping;
4.5) continuing to put the uncut part in the set, and continuing to cut and execute when waiting for the migration node to be idle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010295997.3A CN111506408B (en) | 2020-04-15 | 2020-04-15 | Edge computing task scheduling method based on associated data set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010295997.3A CN111506408B (en) | 2020-04-15 | 2020-04-15 | Edge computing task scheduling method based on associated data set |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111506408A true CN111506408A (en) | 2020-08-07 |
| CN111506408B CN111506408B (en) | 2023-06-16 |
Family
ID=71876054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010295997.3A Active CN111506408B (en) | 2020-04-15 | 2020-04-15 | Edge computing task scheduling method based on associated data set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111506408B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112698151A (en) * | 2020-12-07 | 2021-04-23 | 广东电网有限责任公司梅州供电局 | Fault management method, device and system for plant station |
| CN113703396A (en) * | 2021-07-26 | 2021-11-26 | 北京市机械施工集团有限公司 | Intelligent upgrading method of numerical control cutting equipment based on intelligent terminal |
| CN114637576A (en) * | 2022-03-22 | 2022-06-17 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for generating container allocation plans |
| CN114637576B (en) * | 2022-03-22 | 2024-07-09 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for generating container allocation schemes |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110081499A (en) * | 2010-01-08 | 2011-07-14 | 삼성전자주식회사 | System and method for dynamic task migration on a multiprocessor system |
| US20150200867A1 (en) * | 2014-01-15 | 2015-07-16 | Cisco Technology, Inc. | Task scheduling using virtual clusters |
| CN108242159A (en) * | 2018-03-09 | 2018-07-03 | 连云港杰瑞电子有限公司 | A kind of urban traffic area coordinated control system based on edge calculations node |
| CN109862592A (en) * | 2018-12-06 | 2019-06-07 | 北京邮电大学 | Resource management and dispatching method under a kind of mobile edge calculations environment based on multi-base station cooperative |
| CN110851429A (en) * | 2019-11-21 | 2020-02-28 | 嘉兴学院 | Edge computing credible cooperative service method based on influence self-adaptive aggregation |
-
2020
- 2020-04-15 CN CN202010295997.3A patent/CN111506408B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110081499A (en) * | 2010-01-08 | 2011-07-14 | 삼성전자주식회사 | System and method for dynamic task migration on a multiprocessor system |
| US20150200867A1 (en) * | 2014-01-15 | 2015-07-16 | Cisco Technology, Inc. | Task scheduling using virtual clusters |
| CN108242159A (en) * | 2018-03-09 | 2018-07-03 | 连云港杰瑞电子有限公司 | A kind of urban traffic area coordinated control system based on edge calculations node |
| CN109862592A (en) * | 2018-12-06 | 2019-06-07 | 北京邮电大学 | Resource management and dispatching method under a kind of mobile edge calculations environment based on multi-base station cooperative |
| CN110851429A (en) * | 2019-11-21 | 2020-02-28 | 嘉兴学院 | Edge computing credible cooperative service method based on influence self-adaptive aggregation |
Non-Patent Citations (1)
| Title |
|---|
| 邓晓衡等: "基于综合信任的边缘计算资源协同研究" * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112698151A (en) * | 2020-12-07 | 2021-04-23 | 广东电网有限责任公司梅州供电局 | Fault management method, device and system for plant station |
| CN113703396A (en) * | 2021-07-26 | 2021-11-26 | 北京市机械施工集团有限公司 | Intelligent upgrading method of numerical control cutting equipment based on intelligent terminal |
| CN114637576A (en) * | 2022-03-22 | 2022-06-17 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for generating container allocation plans |
| CN114637576B (en) * | 2022-03-22 | 2024-07-09 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for generating container allocation schemes |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111506408B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169567B (en) | Method and device for generating decision network model for automatic vehicle driving | |
| CN110766211B (en) | Method for creating vehicle path planning problem model under real-time road condition | |
| WO2019205020A1 (en) | Road condition recognition method, apparatus and device | |
| CN111192284A (en) | Vehicle-mounted laser point cloud segmentation method and system | |
| CN111506408A (en) | Edge computing task scheduling method based on associated data set | |
| WO2019047595A1 (en) | Evaluation method and device for comfort level of end-to-end-based automatic driving system | |
| CN109816027A (en) | Training method, device and the unmanned equipment of unmanned decision model | |
| CN107958451A (en) | Vision high accuracy map production method and device | |
| CN108459909A (en) | A kind of Multi-bodies Separation mesh overlay method and system suitable for parallel processing | |
| CN110001653A (en) | A kind of driving behavior appraisal procedure, server and computer-readable medium | |
| CN111739299A (en) | Sparse-track vehicle queuing length determination method, device, equipment and medium | |
| JP2022092047A (en) | Green wave speed determination method, green wave speed determination device, electronic device, storage medium, and computer program | |
| CN104598548B (en) | A kind of method and device of anal yzing agricul products price space relevance | |
| CN107301094A (en) | The dynamic self-adapting data model inquired about towards extensive dynamic transaction | |
| CN112329152B (en) | Driving data searching method, device and equipment | |
| CN112269827A (en) | Data processing method and device, computer equipment and computer readable storage medium | |
| CN116010400A (en) | Method, system, device, equipment and storage medium for storing time series data of vehicle | |
| CN116629425A (en) | Method and device for calculating vehicle energy consumption, computer readable medium and electronic equipment | |
| CN116050159A (en) | Simulation scene set generation method, device, equipment and medium | |
| CN116431281A (en) | Virtual machine migration method based on whale optimization algorithm | |
| CN116977943A (en) | Road element identification method, device, electronic equipment and computer storage medium | |
| CN113505188A (en) | Big data-based urban map mapping updating system and method | |
| CN113808388A (en) | Traffic jam analysis method comprehensively considering operation of cars and public traffic | |
| CN102880722B (en) | A kind of method for digging of authoritative website and device | |
| CN113344371A (en) | Intelligent public traffic scheduling method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |