CN110647398A - Intersection control task scheduling method facing edge calculation and based on task criticality and timeliness - Google Patents
Intersection control task scheduling method facing edge calculation and based on task criticality and timeliness Download PDFInfo
- Publication number
- CN110647398A CN110647398A CN201910880534.0A CN201910880534A CN110647398A CN 110647398 A CN110647398 A CN 110647398A CN 201910880534 A CN201910880534 A CN 201910880534A CN 110647398 A CN110647398 A CN 110647398A
- Authority
- CN
- China
- Prior art keywords
- task
- tasks
- edge
- scheduling
- sig
- 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
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
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
Abstract
The patent discloses an edge-computing-oriented intersection control task scheduling method based on task criticality and timeliness, which comprises the following steps: step one, calculating the execution requirement of a control task of a lower intersection by an edge; step two, dividing the control task categories of the intersections; step three, defining different control task attribute parameters; defining attribute parameters of the edge calculation server; step five, calculating the processing time of each task on different edge calculation servers, and constructing a selection matrix; step six, establishing priorities of different control tasks; step seven, establishing an intersection control task scheduling model; eighthly, controlling task scheduling of the intersection based on the Hungarian algorithm; and step nine, obtaining a scheduling scheme and minimum task execution completion time based on the scheduling result. According to the technical scheme, the road network self-consistency control under the incomplete vehicle-road cooperative environment can be realized by combining the edge computing technology in the incomplete vehicle-road cooperative environment.
Description
Technical Field
The invention belongs to the technical field of cloud computing, and particularly relates to an intersection control task scheduling method facing edge computing and based on task criticality and timeliness.
Background
With the development of information technologies such as car networking, big data and artificial intelligence, road traffic systems are also developing towards networking, collaboration and automation. The vehicle-road cooperation technology is used for acquiring information between vehicles and roads based on technologies such as wireless communication and sensing detection, information interaction and sharing are carried out between vehicles and road side equipment, cooperation and cooperation between the vehicles and intelligent road side facilities are achieved, and the purposes of optimizing utilization of system resources, improving road traffic safety and relieving traffic jam are achieved. The edge computing technology is an effective support for development of a vehicle-road cooperation technology, and bears various tasks such as vehicle-road communication, vehicle passing assistance, road network running state coordination and the like. As a key technology of cloud computing and 5G, the edge computing technology moves computing tasks from a cloud to an edge network closest to the terminal device, which means that tasks running in the traffic system can be responded to more quickly, and therefore the edge computing technology plays an important role in the vehicle-road coordination system.
But the edge compute servers have limited computing power. And the road traffic system has social attributes, a long period is needed for the intelligent vehicle penetration replacement and the comprehensive arrangement of intelligent roadside facilities, the complete vehicle-road cooperative system is difficult to be deployed at once, and the vehicle-road cooperative system can be in an incomplete vehicle-road cooperative state of mixed running of intelligent vehicles of different grades and traditional vehicles for a long time in the future. Under the incomplete vehicle-road cooperative state, due to the fact that the criticality and the effectiveness of the intersection control optimization task of the common vehicle are inconsistent with those of the real-time scheduling optimization task of the intelligent vehicle, and the criticality and the effectiveness of different control tasks are not considered in the existing resource optimization and coordination research, the important tasks are not distributed with enough resources to wait in a queue, and the passing efficiency is seriously influenced.
Aiming at the difficult problem of traffic control under the incomplete vehicle-road cooperative state, the patent provides an intersection control task scheduling method facing to edge calculation and based on task criticality timeliness, so that important tasks can be preferentially executed under the edge calculation environment with limited calculation resources, and meanwhile, the minimum task processing time is realized, and therefore intersection calculation resources are reasonably optimized.
Disclosure of Invention
In order to make up for the deficiency of related research, the invention discloses an edge-computing-oriented intersection control task scheduling method based on task criticality and timeliness, aiming at determining the priority of respective execution by defining the criticality and timeliness values of different control tasks and ensuring the priority execution of the tasks with high priority.
The invention relates to an edge-calculation-oriented intersection control task scheduling method based on task criticality and timeliness, which comprises the following steps of:
step one, calculating the execution requirement of a control task of a lower intersection by an edge;
step two, dividing the control task categories of the intersections;
step three, defining different control task attribute parameters;
defining attribute parameters of the edge calculation server;
step five, calculating the processing time of each task on different edge calculation servers, and constructing a selection matrix;
step six, establishing priorities of different control tasks;
step seven, establishing an intersection control task scheduling model;
eighthly, controlling task scheduling of the intersection based on the Hungarian algorithm;
and step nine, obtaining a scheduling scheme and minimum task execution completion time based on the scheduling result.
As a further technical solution of the present invention, the first step specifically includes the following contents: the application scene of the invention is that the control task scheduling of the intersection calculated towards the edge under the incomplete vehicle path cooperative state, each intersection is provided with an edge calculation server, the vehicle and the edge calculation servers can communicate with each other, the vehicle can access the adjacent edge calculation server when entering the intersection service range, the task is distributed to the formulated edge calculation server to be executed through the scheduling calculation, the calculation result is returned to the vehicle, the edge calculation server can only execute one task at a time, and each task can not be divided and can only be executed by one edge calculation server.
As a further technical solution of the present invention, the second step specifically includes the following contents: the invention divides vehicles running in a road network into four types, namely intelligent vehicles, common vehicles, buses and emergency vehicles such as ambulances and fire trucks, wherein the intelligent vehicles can communicate with roadside equipment, the emergency vehicles and the buses obey the unified scheduling of a management department, can upload the running states of the emergency vehicles and the buses in real time, and can communicate by default, and the common vehicles assume that the communication cannot be carried out and need to identify the types of vehicles and the number of the vehicles through a road detector. Each vehicle has different calculation tasks according to different types, each intelligent vehicle is defined to represent a scheduling task, all common vehicles in a crossing represent a signal timing optimization task, each emergency vehicle represents a first-pass task, and each bus represents an adjustment task.
As a further technical solution of the present invention, the third step specifically includes the following contents: if there are n tasks in the road network in one period, the task set t (n) ═ t1,t2,tn,ti_t) Task tiThere are the following parameter expressions, each task has the following parameter composition ti=(ti_memory,ti_m,…,ti_bw),ti_memoryIndicating the memory required for task processing, ti_mIndicating the size of the task, ti_bwRepresenting the required bandwidth, ti_tThe aging property values are shown.
As a further technical solution of the present invention, the fourth step specifically includes the following contents: the network has m edge computation servers, and the edge computation server set sig (m) ═ sig1,sig2,…,sigm) Each edge compute server has the following parameters to form sigj=(sigj_memory,sigj_capacity,sigj_bw)。sigj_memoryIndicating memory size, sigj_capacityRepresenting computing power, sigj_bwIndicating that transmission bandwidth may be provided.
As a further technical solution of the present invention, the step five specifically includes the following contents: and calculating the processing time of each task on different edge calculation servers, and constructing a selection matrix S. The time of the edge computing server for processing the task can be obtained by the following formula:
as a further technical solution of the present invention, the sixth step specifically includes the following contents: the priority of the tasks is determined based on the task criticality and timeliness, and the task with the high priority is guaranteed to be executed preferentially. The criticality of the task is represented by Pi, and the criticality of the defined long-term running task is low, and the criticality of the emergency is high. And each task calculates the distance from the server according to the vehicle running speed and the distance from the edge to obtain a time efficiency value Li, which indicates that the task needs to be submitted and processed within Li time, and the smaller Li represents the more urgent the task. Defining the priority of each task according to the criticality and timeliness values of the tasks as follows:
ωi=Pi·Di/Li (2)
as a further technical solution of the present invention, the seventh step specifically includes the following contents: the scheduling model of the invention is as follows: introducing variable XijIf task i is tuned to edge compute server j for execution, Xij1, otherwise Xij0, thus describing the problem as:
an objective function:
constraint conditions are as follows:
formula (4) one task selects at most one edge calculation server in one selection, and formula (5) one edge calculation server can only select one task at a time.
As a further technical solution of the present invention, the step eight specifically includes the following contents: the model provided by the invention is a typical 0-1 allocation problem, and Hungarian algorithm is commonly used for solving the problem. But according to the Hungarian algorithm, the number of tasks and the number of servers are the same when the allocation is carried out because m is far smaller than n, so that the algorithm needs to be improved. Therefore, whether the number n of tasks can divide m completely is judged, if not, the remainder x is calculated, the (m-x) virtual zero tasks are introduced, then the tasks are arranged from large to small according to the priority of the tasks, the previous m tasks are selected from n to execute the Hungarian algorithm, and the tasks which are not distributed to the edge computing server continue to compete when waiting for next distribution until all the tasks are scheduled.
As a further technical solution of the present invention, the step nine specifically includes the following contents: according to the model provided by the invention, an optimal scheduling scheme in a period can be obtained, the task with high priority is guaranteed to be executed preferentially, the minimum time consumed by calculation of all tasks can be obtained, and then the edge calculation server processes the tasks according to the scheduling scheme.
The invention has the advantages that:
(1) the application scene of the invention is incomplete vehicle-road cooperative environment, the edge computing technology is combined, the vehicle-vehicle and the edge computing server carry out information interaction through the vehicle-vehicle, and the vehicle-edge computing server constructs the space-time state feedback matrix, and the self-consistent control of the road network under the incomplete vehicle-road cooperative environment can be realized.
(2) Under the incomplete vehicle-road cooperative state, intelligent vehicles of different grades are mixed with traditional vehicles, the control difficulty is very high, and a resource optimization and coordination method needs to be changed aiming at different control tasks.
(3) The method has the advantages that the intersection control task scheduling problem is refined into a 0-1 allocation problem, then assignment scheduling of all tasks is completed with the lowest processing time consumption while the task priority is guaranteed by combining the Hungarian algorithm, and priority response to tasks with high criticality and timeliness under the incomplete vehicle road state is realized.
Drawings
FIG. 1 is an application scenario of an intersection control task scheduling method facing edge computing according to the present invention;
FIG. 2 is a flowchart of an algorithm of an intersection control task scheduling method facing edge computing.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and practical examples.
An edge-computing-oriented intersection control task scheduling method based on task criticality and timeliness comprises the following steps:
the first step is as follows: and determining the execution requirement of the intersection control task under the edge calculation.
The application scene of the invention is the control task scheduling of the intersection calculated towards the edge under the incomplete vehicle-road cooperative state, as shown in figure 1, a road network is set to comprise 4 intersections, each intersection is provided with an edge calculation server, the vehicle and the edge calculation servers can communicate with each other, the vehicle can access the adjacent edge calculation servers when entering the intersection service range, the tasks are distributed to the established edge calculation servers to be executed through scheduling calculation, the calculation result is returned to the vehicle, the edge calculation servers can only execute one task at a time, and each task cannot be divided and can only be executed by one edge calculation server.
The second step is that: and dividing the intersection control task categories.
The invention divides vehicles running in a road network into four types, namely intelligent vehicles, common vehicles, buses and emergency vehicles such as ambulances and fire trucks, wherein the intelligent vehicles can communicate with roadside equipment, the emergency vehicles and the buses obey the unified scheduling of a management department, can upload the running states of the emergency vehicles and the buses in real time, and can communicate by default, and the common vehicles assume that the communication cannot be carried out and need to identify the types of vehicles and the number of the vehicles through a road detector. Each vehicle has different calculation tasks according to different types, each intelligent vehicle is defined to represent a scheduling task, all the vehicles generally represent a signal timing optimization task, each vehicle represents a priority traffic task, and each bus represents an adjustment task.
The third step: different control task attribute parameters are defined.
The permeability of 50 vehicles, intelligent vehicles, buses and emergency vehicles in a certain period in the road network is respectively 30%, 10% and 2%, so that 1 priority traffic task, 15 scheduling tasks and 5 adjusting tasks exist in the road network, and one intersection represents one signal control optimization task, so that 4 signal control optimization tasks exist. Task set T (25) ═ T1,t2,…,t25) Each task ti=(ti_memory,ti_m,ti_bw,ti_t),ti_memoryIndicating the memory required for task processing, ti_mIndicating the size of the task, ti_bwRepresenting the required bandwidth, ti_tThe aging property values are shown. The various types of task parameters are defined as follows:
TABLE 1 priority pass task Attribute
Parameter(s) | Value of |
Number of tasks | 1 |
Bandwidth requirement | 5Mhz |
Occupying memory | 250 |
Task size | 80 |
Age value Li | 5s |
TABLE 2 scheduling task attributes
Parameter(s) | Value of |
Number of tasks | 15 |
Bandwidth requirement | 5-10Mhz |
Occupying memory | 100-200 |
Task size | 100-200 |
Age value Li | 3-20s |
TABLE 3 adjusting task attributes
Parameter(s) | Value of |
Number of tasks | 5 |
Bandwidth requirement | 5-10Mhz |
Occupying memory | 50-100 |
Task size | 10-50 |
Age value Li | 15-50s |
TABLE 4 Signal control optimization task Attribute
Parameter(s) | Value of |
Number of tasks | 4 |
Bandwidth requirement | 8-15Mhz |
Occupying memory | 500-1000 |
Task size | 500-1000 |
Age value Li | 10-100s |
The fourth step: defining edge compute server attribute parameters.
There are 4 edge computing servers in the road network, and the edge computing server set Sig (4) ═ Sig1,sig2,sig3,sig4) Each edge computing server is composed of the following parameters The size of the memory is represented by the size of the memory,the power of the calculation is represented by,indicating that transmission bandwidth may be provided. The edge compute server parameters are defined as follows:
TABLE 5 edge compute Server attributes
Parameter(s) | Value of |
Edge computing server | 4 |
Range of bandwidth | 10-20Mhz |
Storage capacity | 1000-2000 |
Processing capacity | 500-1000 |
The fifth step: and calculating the processing time of each task on different edge computing servers, and constructing a selection matrix.
And calculating the processing time of each task on different edge calculation servers, and constructing a selection matrix S. The time of the edge computing server for processing the task can be obtained by the following formula:
and a sixth step: the priorities of the different control tasks are constructed.
The invention determines the priority of the tasks based on the task criticality and the timeliness, and ensures that the tasks with high priority are executed preferentially. The criticality of the tasks is represented by Pi, the criticality of the defined long-term running tasks is low, the criticality of the emergency is high, and the criticality of the four types of tasks is defined as shown in the following table 6. And each task calculates the distance from the server according to the vehicle running speed and the distance from the edge to obtain a time efficiency value Li, which indicates that the task needs to be submitted and processed within Li time, and the smaller Li represents the more urgent the task. Defining the priority of each task according to the criticality and timeliness values of the tasks as follows:
ωi=Pi·Di/Li (7)
TABLE 6 criticality values of various tasks
The seventh step: and establishing an intersection control task scheduling model.
The scheduling model of the invention is as follows: introducing variable XijIf task i is tuned to edge compute server j for execution, Xij1, otherwise Xij0, thus describing the problem as:
an objective function:
constraint conditions are as follows:
formula (9) one task selects at most one edge calculation server in one selection, formula (10) one edge calculation server can only select one task at a time
Eighth step: and controlling task scheduling of the intersection based on the Hungarian algorithm.
The model provided by the invention is a typical 0-1 allocation problem, and Hungarian algorithm is commonly used for solving the problem. But according to the Hungarian algorithm, the number of tasks and the number of servers are the same when the allocation is carried out because m is far smaller than n, so that the algorithm needs to be improved. As shown in fig. 2, an algorithm flow chart firstly judges whether the task number n can divide m completely, if not, calculates a remainder x, and introduces (m-x) virtual zero tasks; then initializing a selection matrix S, randomly generating various tasks and labeling according to parameter setting, and calculating the processing time of each task on each edge calculation server to construct the selection matrix S; determining the priority of the tasks according to the criticality and the timeliness value of the tasks, arranging the tasks from big to small according to the priority of the tasks, and selecting the first m tasks; executing the Hungarian algorithm; and judging whether the number of the remaining tasks is 0 or not, and continuing to participate in competition for the next time by the unallocated tasks until all the tasks finish scheduling.
The ninth step: and obtaining a scheduling scheme and a task execution minimum completion time based on the scheduling result.
According to the model provided by the invention, based on the parameter settings of the third step, the fourth step and the sixth step, an optimal scheduling scheme in the period is obtained according to the scheduling algorithm designed in the eighth step, as shown in the following table 7, the total calculation time is 7.853s, the task with high priority is guaranteed to be executed preferentially, the minimum calculation time consumption of all tasks can be obtained, and then the edge calculation server processes the tasks according to the scheduling scheme.
TABLE 7 scheduling scheme
Claims (2)
1. An edge-computing-oriented intersection control task scheduling method based on task criticality and timeliness is characterized by comprising the following steps:
step one, calculating intersection control task execution requirements under edge
An edge calculation server is arranged at each intersection, and the vehicles can communicate with the edge calculation servers and the edge calculation servers; the method comprises the following steps that a vehicle enters an intersection service range and is accessed to a nearby edge computing server, tasks are distributed to a specified edge computing server to be executed through scheduling computation, and a computing result is returned to the vehicle; the edge computing server can only execute one task at a time, and each task cannot be divided and can only be handed to one edge computing server to be executed;
step two, dividing control task categories of intersections
Vehicles running in a road network are classified into four types, namely intelligent vehicles, ordinary vehicles, buses and emergency vehicles; the intelligent vehicle is communicated with the road side equipment, the emergency vehicles and the buses are subjected to unified scheduling to upload running states of the emergency vehicles and the buses in real time, the common vehicles are set to be incapable of communicating, and the quantity of the common vehicles is identified through the road detector. Each vehicle has different calculation tasks according to different types, each intelligent vehicle is defined to represent a scheduling task, all common vehicles in a crossing represent a signal timing optimization task, each emergency vehicle represents a first-pass task, and each bus represents an adjustment task;
step three, defining attribute parameters of different control tasks
Defining n tasks in a road network in a period, wherein a task set T (n) ═ t1,t2,tn,ti_t) Where t, ti_tIndicating the timeliness value indicates the task for the ith task ti=(ti_memory,ti_m,…,ti_bw) Wherein t isi_memoryIndicating the memory required for task processing, ti_mIndicates the task size, ti_bwRepresenting the required bandwidth;
step four, defining edge calculation server attribute parameters
When there are m edge calculation servers in the road network, the edge calculation server set sig (m) ═ sig1,sig2,…,sigm) Each edge computing a server sigj=(sigj_memory,sigj_capacity,sigj_bw) (ii) a Wherein sigj_memoryIndicating memory size, sigj_capacityRepresenting computing power, sigj_bwIndicating the transmission bandwidth that can be provided;
step five, calculating the processing time of each task on different edge calculation servers, and constructing the time for selecting the edge calculation server to process the tasks
Calculating the processing time of each task on different edge calculation servers, and constructing a selection matrix S;
step six, establishing priorities of different control tasks
The criticality of the task is represented by Pi, the long-term operation task is defined as low criticality, and the emergency is defined as high criticality; each task obtains an timeliness value Li according to the vehicle running speed and the distance from the distance edge calculation server, the fact that the task needs to be submitted and processed within Li time is shown, and the smaller Li is, the more urgent is the task; defining the priority of each task according to the criticality and timeliness values of the tasks as follows: pi · Di/Li (2);
step seven, establishing an intersection control task scheduling model
The scheduling model is as follows: introducing variable XijWhen task i is called to the edge computing server j for execution, Xij1, otherwise Xij0, the objective function of the scheduling model is therefore:the constraint conditions of the scheduling model are as follows:in formula (4), one task can select at most one edge calculation server in one selection, and in formula (5), one edge calculation server can only select one task at a time;
and step eight, controlling task scheduling of the intersection based on the Hungarian algorithm.
And judging whether the number m of the edge computing servers can be divided by the number n of the tasks, if not, calculating a remainder x, introducing (m-x) virtual zero tasks, then arranging the tasks from large to small according to the priority of the tasks, selecting the previous m tasks from the n to execute a Hungarian algorithm, and continuing to compete when the tasks which are not distributed to the edge computing servers wait for next distribution until all the tasks are scheduled.
2. The intersection control task scheduling method facing edge computing and based on task criticality and timeliness is characterized in that,
the method further comprises the following steps: and step nine, obtaining a scheduling scheme and minimum task execution completion time based on the scheduling result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910880534.0A CN110647398A (en) | 2019-09-18 | 2019-09-18 | Intersection control task scheduling method facing edge calculation and based on task criticality and timeliness |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910880534.0A CN110647398A (en) | 2019-09-18 | 2019-09-18 | Intersection control task scheduling method facing edge calculation and based on task criticality and timeliness |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110647398A true CN110647398A (en) | 2020-01-03 |
Family
ID=69010720
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910880534.0A Pending CN110647398A (en) | 2019-09-18 | 2019-09-18 | Intersection control task scheduling method facing edge calculation and based on task criticality and timeliness |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110647398A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111614561A (en) * | 2020-05-28 | 2020-09-01 | 北京瑞华赢科技发展有限公司 | Intelligent road side data transmission method and device based on edge calculation and distributed system |
CN111737006A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Full network traffic scheduling optimization method, device, computer equipment and storage medium |
CN112685161A (en) * | 2020-12-31 | 2021-04-20 | 杭州当虹科技股份有限公司 | Unified task scheduling system |
CN112905327A (en) * | 2021-03-03 | 2021-06-04 | 湖南商务职业技术学院 | Task scheduling method, edge server, computer medium and edge cloud collaborative computing system |
CN113381511A (en) * | 2021-06-02 | 2021-09-10 | 深圳市莱达四维信息科技有限公司 | Online intelligent inspection system of transformer substation |
CN114691230A (en) * | 2020-12-28 | 2022-07-01 | 深圳Tcl新技术有限公司 | Task unloading method and device, intelligent terminal and computer readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101692208A (en) * | 2009-10-15 | 2010-04-07 | 北京交通大学 | Task scheduling method and task scheduling system for processing real-time traffic information |
US20190011927A1 (en) * | 2017-07-06 | 2019-01-10 | GM Global Technology Operations LLC | Calibration methods for autonomous vehicle operations |
CN109582448A (en) * | 2018-10-17 | 2019-04-05 | 中国电子科技集团公司第二十八研究所 | A kind of edge calculations method for scheduling task towards criticality and timeliness |
CN109637163A (en) * | 2018-12-26 | 2019-04-16 | 江苏理工学院 | A kind of dynamic dispatching traffic control system and its management method |
CN110198278A (en) * | 2019-04-15 | 2019-09-03 | 湖南大学 | A kind of Lyapunov optimization method in car networking cloud and the scheduling of edge Joint Task |
CN110231984A (en) * | 2019-06-06 | 2019-09-13 | 湖南大学 | Multi-workflow method for allocating tasks, device, computer equipment and storage medium |
-
2019
- 2019-09-18 CN CN201910880534.0A patent/CN110647398A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101692208A (en) * | 2009-10-15 | 2010-04-07 | 北京交通大学 | Task scheduling method and task scheduling system for processing real-time traffic information |
US20190011927A1 (en) * | 2017-07-06 | 2019-01-10 | GM Global Technology Operations LLC | Calibration methods for autonomous vehicle operations |
CN109582448A (en) * | 2018-10-17 | 2019-04-05 | 中国电子科技集团公司第二十八研究所 | A kind of edge calculations method for scheduling task towards criticality and timeliness |
CN109637163A (en) * | 2018-12-26 | 2019-04-16 | 江苏理工学院 | A kind of dynamic dispatching traffic control system and its management method |
CN110198278A (en) * | 2019-04-15 | 2019-09-03 | 湖南大学 | A kind of Lyapunov optimization method in car networking cloud and the scheduling of edge Joint Task |
CN110231984A (en) * | 2019-06-06 | 2019-09-13 | 湖南大学 | Multi-workflow method for allocating tasks, device, computer equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
王云鹏; 鲁光泉; 于海洋: "车路协同环境下的交通工程", 《中国工程科学》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111614561A (en) * | 2020-05-28 | 2020-09-01 | 北京瑞华赢科技发展有限公司 | Intelligent road side data transmission method and device based on edge calculation and distributed system |
CN111737006A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Full network traffic scheduling optimization method, device, computer equipment and storage medium |
CN114691230A (en) * | 2020-12-28 | 2022-07-01 | 深圳Tcl新技术有限公司 | Task unloading method and device, intelligent terminal and computer readable storage medium |
CN112685161A (en) * | 2020-12-31 | 2021-04-20 | 杭州当虹科技股份有限公司 | Unified task scheduling system |
CN112685161B (en) * | 2020-12-31 | 2024-04-23 | 杭州当虹科技股份有限公司 | Unified task scheduling system |
CN112905327A (en) * | 2021-03-03 | 2021-06-04 | 湖南商务职业技术学院 | Task scheduling method, edge server, computer medium and edge cloud collaborative computing system |
CN112905327B (en) * | 2021-03-03 | 2024-03-22 | 湖南第一师范学院 | Task scheduling method, edge server, computer medium and edge cloud cooperative computing system |
CN113381511A (en) * | 2021-06-02 | 2021-09-10 | 深圳市莱达四维信息科技有限公司 | Online intelligent inspection system of transformer substation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110647398A (en) | Intersection control task scheduling method facing edge calculation and based on task criticality and timeliness | |
CN110852486B (en) | Task planning method for autonomous cooperation of unmanned aerial vehicle cluster | |
CN101237469B (en) | Method for optimizing multi-QoS grid workflow based on ant group algorithm | |
CN112328378B (en) | Task scheduling method, computer device and storage medium | |
CN110570075B (en) | Power business edge calculation task allocation method and device | |
CN103699433B (en) | One kind dynamically adjusts number of tasks purpose method and system in Hadoop platform | |
CN105373426B (en) | A kind of car networking memory aware real time job dispatching method based on Hadoop | |
CN103701894A (en) | Method and system for dispatching dynamic resource | |
CN113316116B (en) | Vehicle calculation task unloading method | |
CN116700993B (en) | Load balancing method, device, equipment and readable storage medium | |
CN110489218A (en) | Vehicle-mounted mist computing system task discharging method based on semi-Markovian decision process | |
CN102745192B (en) | Task allocation system for distributed control system of hybrid vehicle | |
CN114721806A (en) | Task scheduling and executing method and system based on digital twin | |
CN109301936B (en) | Intelligent substation operation and maintenance information monitoring system based on container scheduling framework | |
CN112949987A (en) | Taxi dispatching and matching method, system, equipment and medium based on prediction | |
CN116599028A (en) | Multi-source data fusion-based method and system for autonomous and cooperative control of edge of platform | |
CN114968601B (en) | Scheduling method and scheduling system for AI training jobs with resources reserved in proportion | |
CN102774376A (en) | Task allocation method of distributed control system of hybrid power vehicle | |
CN115208892A (en) | Vehicle-road cooperative online task scheduling method and system based on dynamic resource demand | |
CN113946440A (en) | Resource scheduling method in green cloud environment | |
CN114675963A (en) | Multi-task processing method based on equipment priority in photovoltaic 5G base station system | |
CN114035919A (en) | Task scheduling system and method based on power distribution network layered distribution characteristics | |
CN112799829A (en) | Knowledge-driven network resource arrangement method | |
CN111796932A (en) | GPU resource scheduling method | |
CN117042047B (en) | Resource allocation method, device, controller and system based on task priority |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200103 |
|
WD01 | Invention patent application deemed withdrawn after publication |