CN115484177B - Multi-attribute MDP model service migration method for mobile edge computing - Google Patents
Multi-attribute MDP model service migration method for mobile edge computing Download PDFInfo
- Publication number
- CN115484177B CN115484177B CN202211171444.2A CN202211171444A CN115484177B CN 115484177 B CN115484177 B CN 115484177B CN 202211171444 A CN202211171444 A CN 202211171444A CN 115484177 B CN115484177 B CN 115484177B
- Authority
- CN
- China
- Prior art keywords
- user
- node
- service
- migration
- current
- 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
- 230000005012 migration Effects 0.000 title claims abstract description 89
- 238000013508 migration Methods 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 15
- 230000008901 benefit Effects 0.000 claims abstract description 15
- 230000009471 action Effects 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims abstract description 4
- 238000004891 communication Methods 0.000 claims description 18
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5003—Managing SLA; Interaction between SLA and QoS
- H04L41/5019—Ensuring fulfilment of SLA
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention belongs to the technical fields of edge calculation, mobile calculation and service migration, and particularly relates to a multi-attribute MDP model service migration method for mobile edge calculation. The migration times and the total service quality can be balanced under the condition that the user moves, and the service experience of the user during movement is greatly improved. Which comprises the following steps: constructing a transferable node list; constructing a multi-attribute-based profit function; and solving the migration strategy by solving the benefit function and utilizing Q-learning, establishing a Q-table according to the content, executing actions with highest Q values in each state in sequence, and finally completing the migration decision process of the current time slot.
Description
Technical Field
The invention relates to a multi-attribute MDP model service migration method oriented to mobile edge computing, and belongs to the technical fields of edge computing, mobile computing and service migration.
Background
The service migration research is based on a mobile edge computing technology, and the current state information of the terminal user and the communication distance between the terminal user and the current edge node are computed and analyzed, so that the migration time which does not affect the QoS of the user can be obtained, and the service is migrated from the current node to the next edge node to be moved by the user, thereby solving the problems of service interruption and great reduction of the QoS caused by the movement of the user in turn. This is very widely used in the field of vehicle edge network research.
However, in practical applications, a user may frequently pass through multiple edge service ranges due to high-speed movement, and the edge service needs to be frequently migrated between different nodes along with the movement of the user, so that a conventional single destination node and a service migration scheme only considering distance attributes often cause higher migration overhead and even service interruption, affect service quality, and cannot meet the current requirements.
Disclosure of Invention
The invention aims to provide a multi-attribute MDP model service migration method facing to mobile edge calculation, which can balance migration times and total service quality under the condition that a user moves, and greatly improves service experience when the user moves.
The invention aims to achieve the aim, and the aim is achieved by the following technical scheme:
A multi-attribute MDP model service migration method facing mobile edge calculation comprises the following steps:
s1, constructing a transferable node list
Tracking the user to obtain the current moving position and moving direction of the user, predicting the moving track of the user according to the position of the current time slot to obtain the position information of the user,
The current moving position of the user is x1 and y1, the moving direction is theta, and the position information after the user is x2 and y2;
According to the information encountered by the current time slot, the edge node passed by the user is obtained, a candidate list of the destination node is constructed, and then the calculation is carried out by combining the positions of the placed edge nodes, so that a movement track formula in the service range of the edge node under two conditions is obtained:
S2, constructing a multi-attribute-based profit function
S3, solving migration strategy
And 2, solving by using the Q-learning function through the benefit function constructed in the step 2, establishing a Q-table according to the content, executing actions with the highest Q value in each state in sequence, and finally completing the migration decision process of the current time slot.
Preferably, the following steps are performed after the creation of the list of migratable nodes at S1:
(1) Counting the distance between the current node and the user in the movable node list and the resource occupation condition of the node in the movable node list, and acquiring the computing resource requirement of the current service of the user;
(2) Establishing a maximum service quality function which can be provided by each node;
(3) Analyzing the real-time resource occupation condition and the current resource calculation requirement of each node, and correcting the profit function;
(4) Establishing a migration overhead function when migrating to each node;
(5) Establishing a residence time function of the user in each node according to the predicted user movement track in the S1;
(6) And integrating the previous steps to establish a total benefit function.
Preferably, the maximum quality of service function:
Wherein the method comprises the steps of Representing the highest value of the quality of service provided by the nodes to the user respectively, and alpha represents the discount factor when the user is within the range of the current communication node, wherein when the user is outside the service node, the backhaul network between the edge node clusters is used for communication, and therefore tau is used for representing the discount factor when the user is outside the range of the current communication node.
Preferably, step (3) is followed by the steps of: when (when)If a service migration is performed, a relatively large penalty value M is defined for the return function for the action, where Ca represents the available resource situation of the migratable node and the resource requirement of the Cd service.
Preferably, step (4) establishes a migration overhead function when migrating to each node as follows:
The migration overhead generally includes two parts, the first part being the cost of data transfer between the source node and the target node; the second part is the cost of starting service on the node after migration, wherein the migration cost of the first part is related to the transmission distance, and the transmission cost of the second part can define a constant, wherein Representing migration to the nth node in the migratable list,/>Indicating that no migration is performed.
Preferably, the residence time function of step (5) can be broadly divided into three cases, depending on the location of the user in the edge service area: ① When the user leaves the service range of the original node and does not migrate, the movement income of the user at the original node is 0; ② When the user is in the service range of the destination node and selects to migrate or the user is in the service range of the communication node and selects not to migrate; ③ When the user is not in the service range of the destination node and selects migration;
Where (x 1, y 1) represents the current location coordinates of the user, (x 2, y 2) represents the coordinates of the user when the user leaves the current service range, and where the distance between the user and the current node is equal to its service radius R, θ represents the angle at which the triangle is constructed with the diameters of the (x 1, y 1), (x 2, y 2) and the service range.
Preferably, the previous steps are combined to build a total benefit function, the specific function being as follows:
wherein ω is used to determine the proportion of the migration overhead, and ω represents the larger the migration overhead proportion, and ρ represents the proportion of the sports benefit, and ρ represents the larger the sports benefit proportion.
The invention has the advantages that:
1. the invention can complete service migration under the condition of uncertain migration nodes by constructing the transferable node list, thereby greatly reducing migration times and reducing the influence of migration cost on service quality.
2. The movement income, migration cost, service quality and calculation requirement are integrated, and migration times and total service quality can be balanced under the condition that a user moves. The service experience of the user during movement is greatly improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
FIG. 1 is a schematic diagram illustrating the effect of migration overhead on migration policy according to the present invention.
FIG. 2 is a schematic diagram showing the effect of the overhead factor, migration overhead and total system return according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As described in the background art, in practical applications, a user may frequently pass through multiple edge service ranges due to high-speed movement, and an edge service needs to frequently migrate between different nodes along with the movement of the user, so that a conventional single-purpose node and a service migration scheme only considering distance attributes often cause higher migration overhead and even service interruption, affect service quality, and cannot meet the current requirements.
In order to solve the problems, the invention adopts the following technical scheme:
A multi-attribute MDP model service migration method facing mobile edge calculation comprises the following steps:
s1, constructing a transferable node list
Tracking the user to obtain the current moving position and moving direction of the user, predicting the moving track of the user according to the position of the current time slot to obtain the position information of the user,
The current moving position of the user is x1 and y1, the moving direction is theta, and the position information after the user is x2 and y2;
According to the information encountered by the current time slot, the edge node passed by the user is obtained, a candidate list of the destination node is constructed, and then the calculation is carried out by combining the positions of the placed edge nodes, so that a movement track formula in the service range of the edge node under two conditions is obtained:
S2, constructing a multi-attribute-based profit function
S3, solving migration strategy
And 2, solving by using the Q-learning function through the benefit function constructed in the step 2, establishing a Q-table according to the content, executing actions with the highest Q value in each state in sequence, and finally completing the migration decision process of the current time slot.
After the list of migratable nodes is established at S1, the following steps are performed:
(1) And counting the distance between the current node and the user in the movable node list and the resource occupation condition of the node in the movable node list, and acquiring the computing resource requirement of the current service of the user.
(2) Establishing a maximum quality of service function that each node can provide
Wherein the method comprises the steps ofRepresenting highest values respectively representing the quality of service provided by the nodes for the user, wherein alpha represents a discount factor when the user is in the range of the current communication node, and when the user is out of the service node, the user communicates by adopting a backhaul network among the edge node clusters, so tau is used for representing the discount factor when the user is out of the range of the current communication node;
(3) Analyzing the real-time resource occupation condition and the current resource calculation requirement of each node, correcting the profit function, and when If the service migration is executed, defining a larger punishment value M for the return function of the action, wherein Ca represents the available resource condition of the transferable node and the resource requirement of the Cd service;
(4) Establishing migration overhead functions when migrating to each node
The migration overhead generally includes two parts, the first part being the cost of data transfer between the source node and the target node; the second part is the cost of starting service on the node after migration, wherein the migration cost of the first part is related to the transmission distance, and the transmission cost of the second part can define a constant, whereinRepresenting migration to the nth node in the migratable list,/>Indicating that no migration is performed;
(5) The residence time function of the user in each node is established according to the predicted movement track of the user in the step S1, and three situations can be generally classified according to the difference of the positions of the user in the edge service range: ① When the user leaves the service range of the original node and does not migrate, the movement income of the user at the original node is 0; ② When the user is in the service range of the destination node and selects to migrate or the user is in the service range of the communication node and selects not to migrate; ③ When the user is not in the service range of the destination node and selects migration;
wherein (x 1, y 1) represents the current position coordinates of the user, (x 2, y 2) represents the coordinates of the user when the user leaves the current service range, and when the distance between the user and the current node is equal to the service radius R thereof, θ represents the angle formed by the diameters of the (x 1, y 1), (x 2, y 2) and the service range,
(6) Combining the previous steps to build a total profit function
Wherein ω is used to determine the proportion of the migration overhead, and ω represents the larger the migration overhead proportion, and ρ represents the proportion of the sports benefit, and ρ represents the larger the sports benefit proportion.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
Taking the example when t=10 when the user moves among a plurality of edge nodes, 32 regularly distributed edge nodes are adopted, the user moves in the area with the speed of 1m/s, the farthest communication distance of each edge node is 15m, and the service range is circular. The processing steps are as follows:
1. Constructing a list of migratable nodes
Tracking the user to obtain the current moving position (5, 5V 3) and moving direction II/6 of the user, and predicting the moving track of the user according to the position information of the current time slot to obtain the position information (x 2, y 2) of the user.
According to the information encountered by the current time slot, obtaining the edge node passed by the user, and constructing a candidate list of the destination node. Then combining the positions of the placed edge nodes to calculate to obtain a movement track formula in the service range of the edge nodes under two conditions
2. Constructing a multi-attribute based revenue function
After the list of the migratable nodes is established in step 1, the following steps are performed:
(1) And counting the distance between the current node and the user in the movable node list, and counting the resource occupation condition and the network delay condition of the nodes in the movable node list. The size of the computing resource demand of the current service of the user is obtained.
(2) Establishing a maximum quality of service function that each node can provide
Wherein the method comprises the steps ofFor the distance between the user's current location and the edge node service center, assume the initial node as an example:
。
(3) Analyzing the real-time resource occupation condition and the current resource calculation requirement of each node, correcting the profit function, and when If, at the time, a service migration is performed, a relatively large penalty value 300 is defined for the reward function for the action, where/>Representing the available resource case of a migratable node,/>Resource requirements of the service.
(4) Establishing migration overhead functions when migrating to each node
The migration overhead generally includes two parts, the first part being the cost of data transfer between the source node and the target node; the second part is the cost of starting the service on the migrated node after the migration is completed. Wherein the migration overhead of the first part is related to the transmission distance and the transmission cost of the second part may define a constant, whereinRepresenting migration to the nth node in the migratable list,/>Indicating that no migration is performed.
(5) The residence time function of the user in each node is established according to the user movement track predicted in the step 1, and three situations can be generally classified according to the difference of the positions of the user in the edge service range: ① When the user leaves the service range of the original node and does not migrate, the movement income of the user at the original node is 0; ② When the user is in the service range of the destination node and selects to migrate or the user is in the service range of the communication node and selects not to migrate; ③ When the user is not within the service range of the destination node and selects migration.
Where (x 1, y 1) represents the current location coordinates of the user and (x 2, y 2) represents the coordinates of the user when the user leaves the current service range, and where the distance between the user and the current node is equal to its service radius R. θ represents the included angle of the triangle constructed with the diameters of the (x 1, y 1), (x 2, y 2) and service ranges.
(6) Combining the previous steps to build a total profit function
3. Solving migration policies
And 2, solving according to the Q-learning through the benefit function constructed in the step 2, establishing a Q-table according to the content, selecting the state a0 with the highest benefit when the current time slot is selected, and finally completing the migration decision of the current time slot.
| 33 | -53.85 | -81.3 | -431.87 | -583.44 | -799.6 | -974.09 |
As shown in fig. 1 and fig. 2, by changing the migration overhead coefficient ω in the return function to change the migration overhead size, a migration policy based on the communication distance d when the user performs migration for the first time can be obtained. The abscissa represents the specific gravity omega of the migration cost, the degree of importance of the migration cost when the migration strategy is performed is determined, and the larger omega represents the importance of the migration cost when the migration strategy is performed. The ordinate indicates the distance between the user and the original communication node when the migration policy is first executed. The larger ω means that the migration overhead occupies a larger space in the return function, so that the user tends to make a migration decision when the user is far away from the original communication node, and more communication cost is consumed.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. The multi-attribute MDP model service migration method for mobile edge calculation is characterized by comprising the following steps:
s1, constructing a transferable node list
Tracking the user to obtain the current moving position and moving direction of the user, predicting the moving track of the user according to the position of the current time slot to obtain the position information of the user,
The current moving position of the user is x1, y1, the moving direction is theta, the position information after the user is x2, y2 and vt represent the moving speed of the user at the moment t;
According to the information encountered by the current time slot, the edge node passed by the user is obtained, a candidate list of the destination node is constructed, and then the calculation is carried out by combining the positions of the placed edge nodes, so that a movement track formula in the service range of the edge node under two conditions is obtained:
S2, constructing a multi-attribute-based profit function
S3, solving migration strategy
Solving by utilizing Q-learning through the benefit function constructed in the step 2, establishing a Q-table according to the content, executing actions with highest Q value in each state in sequence, and finally completing the migration decision process of the current time slot;
After the list of migratable nodes is established at S1, the following steps are performed:
(1) Counting the distance between the current node and the user in the movable node list and the resource occupation condition of the node in the movable node list, and acquiring the computing resource requirement of the current service of the user;
(3) Establishing a maximum service quality function which can be provided by each node;
(3) Analyzing the real-time resource occupation condition and the current resource calculation requirement of each node, and correcting the profit function;
(4) Establishing a migration overhead function when migrating to each node;
(5) Establishing a residence time function of the user in each node according to the predicted user movement track in the S1, wherein the residence time function is different according to the positions of the user in the edge service range;
(6) Integrating the previous steps to establish a total profit function;
Maximum quality of service function:
Wherein q max represents the highest value of the quality of service provided by the node for the user respectively, st represents the state of the current environment at time t, and alpha represents the discount factor when the user is within the range of the current communication node, wherein when the user is out of the service node, the backhaul network between the edge node clusters is adopted for communication, so tau is used for representing the discount factor when the user is out of the range of the current communication node;
The step (3) is followed by the following steps: if Ca-Cd is less than 0, defining a relatively large punishment value M for the return function of the action if the service migration is executed, wherein Ca represents the available resource condition of the transferable node and the resource requirement of the Cd service;
Step (4) establishes a migration overhead function when migrating to each node as follows:
The migration overhead generally includes two parts, the first part being the cost of data transfer between the source node and the target node; the second part is the cost of starting the service on the node after the migration is finished, wherein the migration overhead of the first part is related to the transmission distance, and the transmission cost of the second part can define a constant, wherein a t =n represents the nth node in the migration list, and a t =0 represents that the migration is not performed;
The residence time function in step (5) can be broadly divided into three cases according to the location of the user in the edge service area: ① When the user leaves the service range of the original node and does not migrate, the movement income of the user at the original node is 0; ② When the user is in the service range of the destination node and selects to migrate or the user is in the service range of the communication node and selects not to migrate; ③ When the user is not in the service range of the destination node and selects migration;
Wherein (x 1, y 1) represents the current position coordinates of the user, (x 2, y 2) represents the coordinates when the user leaves the current service range, and when the distance between the user and the current node is equal to the service radius R of the user, θ represents an included angle formed by the diameters of the (x 1, y 1), (x 2, y 2) and the service range;
combining the previous steps, and establishing a total profit function, wherein the specific function is as follows:
wherein ω is used to determine the proportion of the migration overhead, and ω represents the larger the migration overhead proportion, and ρ represents the proportion of the sports benefit, and ρ represents the larger the sports benefit proportion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211171444.2A CN115484177B (en) | 2022-09-26 | 2022-09-26 | Multi-attribute MDP model service migration method for mobile edge computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211171444.2A CN115484177B (en) | 2022-09-26 | 2022-09-26 | Multi-attribute MDP model service migration method for mobile edge computing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115484177A CN115484177A (en) | 2022-12-16 |
| CN115484177B true CN115484177B (en) | 2024-04-26 |
Family
ID=84393162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211171444.2A Active CN115484177B (en) | 2022-09-26 | 2022-09-26 | Multi-attribute MDP model service migration method for mobile edge computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115484177B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113114722A (en) * | 2021-03-17 | 2021-07-13 | 重庆邮电大学 | Virtual network function migration method based on edge network |
| CN114357680A (en) * | 2022-01-06 | 2022-04-15 | 内蒙古大学 | Internet of vehicles edge computing road domain division service migration method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10142909B2 (en) * | 2015-10-13 | 2018-11-27 | The Board Of Trustees Of The University Of Alabama | Artificial intelligence-augmented, ripple-diamond-chain shaped rateless routing in wireless mesh networks with multi-beam directional antennas |
| US11132608B2 (en) * | 2019-04-04 | 2021-09-28 | Cisco Technology, Inc. | Learning-based service migration in mobile edge computing |
-
2022
- 2022-09-26 CN CN202211171444.2A patent/CN115484177B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113114722A (en) * | 2021-03-17 | 2021-07-13 | 重庆邮电大学 | Virtual network function migration method based on edge network |
| CN114357680A (en) * | 2022-01-06 | 2022-04-15 | 内蒙古大学 | Internet of vehicles edge computing road domain division service migration method and system |
Non-Patent Citations (3)
| Title |
|---|
| overview and framework of quality service metrics for cloud-based robptics platforms;Jie XuFeng;《IEEE Access》;20201012;全文 * |
| 地震大数据流式计算研究;王鹏辉;《电子测试》;20210415;全文 * |
| 郭辉 ; 芮兰兰 ; 高志鹏 ; .车辆边缘网络中基于多参数MDP模型的动态服务迁移策略.通信学报.(01),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115484177A (en) | 2022-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tang et al. | Joint optimization of network selection and task offloading for vehicular edge computing | |
| CN111083634B (en) | CDN and MEC-based vehicle networking mobility management method | |
| CN106102099B (en) | Heterogeneous Internet of vehicles switching method based on residence time | |
| CN111385226B (en) | Network resource allocation method, system and network equipment applied to online office | |
| CN114553661B (en) | Mobile user equipment clustering training method for wireless federal learning | |
| CN111147604B (en) | Load balancing method for edge calculation of Internet of vehicles | |
| Yin et al. | ISIATasker: Task Allocation for Instant-SensingߝInstant-Actuation Mobile Crowdsensing | |
| CN110933609A (en) | Service migration method and device based on dynamic environment perception | |
| CN113904923A (en) | Service function chain joint optimization method based on software defined network | |
| CN113076177A (en) | Dynamic migration method of virtual machine in edge computing environment | |
| Kumari et al. | Data-driven handover optimization in small cell networks | |
| Guo et al. | Deep reinforcement learning-based microservice selection in mobile edge computing | |
| CN115484177B (en) | Multi-attribute MDP model service migration method for mobile edge computing | |
| Lv et al. | Edge computing task offloading for environmental perception of autonomous vehicles in 6G networks | |
| Jie et al. | A DQN-based approach for online service placement in mobile edge computing | |
| Nguyen et al. | Parked vehicles task offloading in edge computing | |
| CN111626354B (en) | Clustering method applied to Internet of vehicles and based on task dependency | |
| Zhang et al. | Distributed pricing and bandwidth allocation in crowdsourced wireless community networks | |
| CN115988575A (en) | Mixed type edge data caching method | |
| CN114980127B (en) | Computing and unloading method based on federal reinforcement learning in fog wireless access network | |
| CN115834386A (en) | Intelligent service deployment method, system and terminal for edge computing environment | |
| CN114900870A (en) | Cache content updating algorithm based on vehicle clustering | |
| CN109831337B (en) | Grouping mapping method for adjacent nodes in wireless network virtualization | |
| CN114860396B (en) | Instant perception even execution task allocation method based on reinforcement learning | |
| Guo et al. | Access‐Selection Algorithm for Heterogeneous Wireless Networks Based on Uncertain Network Attribute Values |
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 |