CN110445866B - Task migration and cooperative load balancing method in mobile edge computing environment - Google Patents
Task migration and cooperative load balancing method in mobile edge computing environment Download PDFInfo
- Publication number
- CN110445866B CN110445866B CN201910739002.5A CN201910739002A CN110445866B CN 110445866 B CN110445866 B CN 110445866B CN 201910739002 A CN201910739002 A CN 201910739002A CN 110445866 B CN110445866 B CN 110445866B
- Authority
- CN
- China
- Prior art keywords
- micro
- task
- cloud
- migration
- clouds
- 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
- 238000013508 migration Methods 0.000 title claims abstract description 59
- 230000005012 migration Effects 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004891 communication Methods 0.000 claims abstract description 12
- 238000005259 measurement Methods 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 230000008447 perception Effects 0.000 description 3
- 230000003190 augmentative effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
- Information Transfer Between Computers (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a task migration and cooperative load balancing method in a mobile edge computing environment, which comprises the following steps: periodically checking whether a new micro cloud enters a communication range of the micro cloud, and if so, updating a list of neighbor micro clouds; calculating the current load of each neighbor micro cloud, calculating the delay index of each neighbor micro cloud and broadcasting; calculating a delay parameter and a migration probability according to the obtained delay index, and determining an optimal migration object; migrating the task to a neighbor micro cloud of the optimal migration object; entering the next period and returning to the step one for execution until the computing task is finished; and calculating the maximum load, the unbalance measurement and the statistical skewness, and carrying out load balancing. The method comprises the steps of selecting an optimal task migration object for a mobile user according to current load information of a micro cloud; and aiming at the cooperative load balancing strategy of the micro-clouds, the load balancing among the mobile micro-clouds can be effectively realized only by acquiring local information.
Description
Technical Field
The invention relates to a task migration and cooperative load balancing method in a mobile edge computing environment, and belongs to the field of edge computing.
Background
With the explosive development of the internet of things and 5G technologies and various novel mobile applications, such as applications of augmented reality, online games, live video and the like. The demands of users on the quality of service of the network are also increasing. However, due to battery, storage capacity, and computing power limitations, it is difficult for mobile devices to meet the latency and reliability requirements of these resource intensive and delay sensitive applications. The mobile cloud computing has abundant cloud resources, and can process computing task requests of application programs for users more quickly and efficiently, so that the problems of battery energy consumption and resource shortage of mobile equipment are solved. However, migrating the task to a central cloud located in the core network may cause additional network delay while consuming bandwidth resources, making it difficult to guarantee satisfactory network quality of service requirements for the user.
To effectively solve the above challenges, a concept of mobile edge computing is proposed based on the conventional mobile cloud computing. And deploying a small-scale data center, namely micro cloud, at a network edge node, such as a base station and a wireless access point. By providing cloud computing services for mobile users in adjacent areas at the edge of the network, network delay can be effectively reduced, communication consumption can be saved, and congestion of a network center can be relieved. In addition, compared with the task of migrating to the central cloud, the user privacy can be better protected by processing on the micro-cloud close to the edge node.
In a conventional deployment strategy, once a micro cloud is built and deployed, the maximum available physical resource amount is also fixed, and a task migration request of a mobile device is usually processed by the nearest micro cloud. Such deployment strategies can cause cloudlet overload problems due to insufficient utilization of computing resources of the cloudlet and load imbalance. Thus, dynamic cloudlet networks with enhanced mobility are beginning to be of interest, and vehicles with dense urban areas are seen as mobile cloudlets with computing capabilities, and the dynamic cloudlet networks composed of these cloudlets can more efficiently handle task migration requests from mobile users.
Due to uncertainty of moving direction and speed of the vehicle, the indirectly connected mobile micro-cloud network may cause that task migration between micro-clouds cannot be continuously performed and transmission errors occur. In addition, the densities of mobile users in different areas are different, and the sent task migration requests can fluctuate continuously, so that the load balance among the mobile micro-clouds is directly influenced. For example, in a high-density area of users, the cloudiness is overloaded due to too many tasks, and the cloudiness in a loose crowd area is in a low-load state or even an idle state.
Disclosure of Invention
The invention aims to solve the technical problem of providing a task migration and cooperative load balancing method in a mobile edge computing environment aiming at the conditions of low computing resource ratio and long task response time of the current micro cloud system.
The invention adopts the following technical scheme for solving the technical problems:
the invention provides a task migration and cooperative load balancing method in a mobile edge computing environment, which specifically comprises the following steps:
step one, in periodInitial stage, micro-cloud ciChecking whether a new micro cloud enters the communication range of the micro cloud, and if so, updating the list of the neighbor micro clouds;
step two, calculating the current load of each neighbor micro cloud, further calculating the delay index of each neighbor micro cloud and broadcasting;
step three, calculating a delay parameter and a migration probability according to the delay index obtained in the step two, and determining an optimal migration object;
step four, migrating the task to a neighbor micro cloud of the optimal task migration object; entering the next period and returning to the step one for execution until the computing task is finished;
step five, calculating the maximum load, the unbalance measurement eta and the statistical skewness
And load balancing is performed.
The task migration and cooperative load balancing method in the mobile edge computing environment as described above, further, the expression for computing the current load of each neighbor cloudlet in step two is as follows:
wherein, γiIs a micro cloud ciK (x) assign an index function to the task if cloudlet ciProviding service for the user at the position x, wherein the task allocation index function value is 1, and otherwise, the task allocation index function value is 0;
τ (x) is the migration task density from the mobile user at the position x ∈ R, and τ (x) ═ λ (x) ω (x), where the migration task arrival rate at the moment at the mobile user at the position x ∈ R is λ (x), and the average task size is ω (x);
si(x) Is a micro cloud ciService rate provided for mobile user at position x, and
wherein
Representing micro clouds ciMaximum service rate provided, dis (x, c)i) Representing a mobile user and a micro-cloud c located at xiThe Euclidean distance between; α and β are parameters for adjusting the flexibility of the service rate for adapting to different network scenarios;
calculating a delay index: micro cloud ciAs the delay indicator Γi(γi) And has:
the task migration and cooperative load balancing method in the mobile edge computing environment as described above, further, the specific steps of step three include:
step 3.1, calculating a delay parameter: the starting moment of the h-th time interval is indicated by the superscript h, at which time cloudiness c occursiDelay parameter for broadcast
Expressed as:
step 3.2, calculating the migration probability: based on the delay parameter and the service rate provided by the micro cloud, the mobile user at x selects a proper micro cloud to process the task migration request of the mobile user, and the migration probability is expressed as:
wherein
For obtaining micro clouds ciInformation whether to serve mobile subscriber at x, si(x) Representing the service rate provided by the micro cloud i for the mobile user at x.
The method for task migration and cooperative load balancing in a mobile edge computing environment as described above, further, the imbalance metric η and the statistical skewness are calculated in step five
The method comprises the following specific steps:
step 5.1, randomly selecting d micro clouds from the n mobile micro clouds according to a d-choice principle; if the number of neighbors is larger than d, randomly selecting d micro clouds for task migration; otherwise, reducing the value d by half until the value d is less than the number of the current neighbors;
step 5.2, calculating the migration probability between the source micro cloud and the target micro cloud according to a proportional algorithm, and performing task migration according to the probability;
step 5.3, calculating the unbalance measurement eta and the statistical skewness
And outputs:
wherein L ismaxAnd
respectively representing the maximum load and the average load among the d neighbor micro clouds.
As mentioned above, the task migration and cooperative load balancing method in the mobile edge computing environment further includes the specific step of calculating the maximum load in step five:
randomly selecting the micro cloud with the minimum load from the d micro clouds to perform task migration, and if the relation between the number of the tasks and the number of the micro clouds is more than or equal to n log n, considering that the maximum load in all the micro clouds is as follows:
compared with the prior art, the invention adopting the technical scheme has the following advantages:
and designing a target selection strategy and a cooperative load balancing strategy for delay perception from the perspective of a user and a micro cloud respectively.
In the selection process of the migration object, each mobile micro cloud periodically broadcasts load information outwards, and a user can calculate an optimal task migration object according to the information broadcasted by the micro clouds. In a dynamic network composed of pure distributed mobile micro-clouds, the cost for acquiring global load information is very high, so that based on the characteristics of distributed tasks in the mobile micro-cloud network, only the load information of a plurality of random neighbor clouds in a communication area is selected and compared, and then the neighbor with the least load is selected for task redistribution.
Drawings
Fig. 1 is a diagram of a practical application scenario of the present invention.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the attached drawings:
in order to achieve the purposes of fully utilizing computing resources and reducing average task response time, a target selection strategy and a cooperative load balancing strategy of delay perception are designed respectively from the perspective of users and micro-clouds.
In a delay perception target selection strategy, each mobile micro-cloud regularly broadcasts load information outwards, and a user can calculate an optimal task migration object according to the information broadcasted by the micro-clouds. In a dynamic network composed of pure distributed mobile micro-clouds, the cost for acquiring global load information is very high, and based on the characteristics of distributed tasks in the mobile micro-cloud network, only the load information of partial random neighbor clouds in a communication area is selected and compared, and the neighbor with the least load is selected for task redistribution, so that the overall balance of micro-cloud load is realized.
Based on the actual situation, the invention designs a task migration and cooperative load balancing method in a mobile edge computing environment. Fig. 1 is a diagram of a practical application scenario of the present invention. Wherein the circular dotted line represents a communicable area of the mobile clouding, and the rectangular progress bar beside the vehicle represents the load and the current load condition of the mobile clouding. The more the shaded portion occupies the portion of the progress bar, the greater the proportion of the current load representing the mobile cloudlet to the total load capacity of the mobile cloudlet.
In the practical application process, the method is specifically executed as the following steps:
step one, calculating micro cloud ciThe service rate provided for the mobile user at the position x specifically comprises the following steps:
in a certain city center area G, assuming that there are N mobile clouds with computing power, the set C ═ C is used1,c2,...ci,...,cNDenotes wherein c isiRepresenting the ith mobile cloudlet. When cloudiness ciAnd micro cloud cjA distance d betweenijWithin the communication range R, it is possible to connect with each other through the wireless access point and provide low-delay and high-bandwidth wireless access and task processing for mobile users within the service area. The mobile user selects any micro cloud within the communication range to process the sent migration task, and the micro cloud determines to process the task request of the user locally or forward the task to other micro clouds in the same communication area according to the load of the micro cloud.
Micro cloud ciAnd cjInternal communication time tijObeying a paired rate αijSuch as:
at any two time intervals taAnd tbInner, micro cloud ciAnd cjThe encounter probability is:
consider that in a Wi-Fi connected micro-cloud network, the task migration execution time for some applications (e.g., augmented reality, face recognition) is about 10-4～10-2And second. It is therefore assumed that the time interval (including the execution time and the round trip delay of the radio transmission) is sufficiently long, i.e. the results of the task execution can be returned to the mobile user within the same time interval.
Assuming that the migration task arrival rate of the mobile user at the position x ∈ R at the moment is λ (x), and the average task size is ω (x), the migration task density from the user is τ (x) ═ λ (x) ω (x). It should be noted that the delay experienced by the migration task request is related to various factors, such as the maximum service rate that can be provided when the micro-cloud processes the task, the queue delay generated based on the current load of the micro-cloud, the communication delay caused by the distance between the user and the micro-cloud, and other network overhead. To simplify the analysis, suppose a micro-cloud ciThe service rate provided for the mobile user at location x is:
wherein
Representing micro clouds ciMaximum service rate provided, dis (x, c)i) Representing a mobile user and a micro-cloud c located at xiThe euclidean distance between them. Alpha and beta are parameters for adjusting service rate flexibility to accommodate a wide variety of network scenarios. From the above formula, it can be observed that the service rate that the cloudiness can provide to the mobile device is proportional to its maximum service rate and inversely proportional to the distance between the users.
Step two, the micro cloud ciAs the delay indicator ΓiQuantifying the system delay performance by the delay indicator:
introducing task assignmentsAnd the index function k (x) embodies the task allocation relation between the micro cloud and the mobile equipment. If cloudiness ciAnd providing service for the user at the position x, wherein the task allocation index function value is 1, and otherwise, the task allocation index function value is 0. Micro cloud load gammaiThe formula is as follows:
the load set γ of all the cloudiness is ═ γ (γ)1，γ2，...，γN) Can be defined as where ε represents any smallest positive number:
assuming that the arrival of the micro cloud forwarding task also obeys Poisson distribution, and the micro cloud is regarded as an M/G/1-processor shared queue, the average task flow of the micro cloud i is
In a stable system, the system delay is proportional to the average flow according to litter's law. Thus, the cloudiness c may be reducediAs the delay indicator Γi(γi) As shown in the following equation:
thirdly, quantifying the load in the mobile micro-cloud network according to the randomly distributed probability model and calculating the maximum load of all micro-clouds:
applying a classical probability model, assuming that m tasks need to be allocated to n mobile micro-clouds, if each task randomly selects the micro-cloud with the smallest load among the micro-clouds with the number d ≧ 2, the maximum load is approximately
In the design of a cooperative load balancing strategy algorithm, the micro cloud with the minimum load is randomly selected from the d micro clouds for task migration, and the selection scheme has two characteristics. The first is the high utility of random selection, even if simply selecting two objects at random for comparison, still more effectively achieves load balancing than selecting only one target. The second characteristic is the randomness of the target selection, and due to the indirect connection of the mobile micro-cloud network, the neighbors of each micro-cloud will be updated continuously over time interval iterations.
If m is greater than or equal to n log n, the maximum load is approximately
Therefore, the micro cloud with the minimum load is randomly selected from the d micro clouds to perform task migration, and meanwhile, the relation between the tasks and the number of the micro clouds is that m is larger than or equal to n log n, so that the maximum load in all the micro clouds is approximately as follows:
the maximum load is guaranteed to be minimum through the theory, and the strategy provided by the invention can be guaranteed to effectively reduce the maximum load, so that the purpose of load balancing is achieved.
And step four, calculating the optimal task migration object of the mobile user at the x position according to the information of the micro cloud broadcast. When the current time interval is about to end, the current load is again evaluated and the next delay indicator is broadcast:
the invention uses the superscript h to represent the starting moment of the h-th time interval, at which the cloudiness c occursiThe delay parameters for the broadcast are as follows:
based on the delay parameters and service rates provided by the micro-clouds, the mobile user at x will select the appropriate micro-cloud to handle his task migration request. As shown in the following equation:
wherein k isi(x) Representing acquisition of micro-clouds ciInformation whether to serve mobile subscriber at x, si(x) Then represent cloudiness ciThe service rate provided for the mobile user at x.
At the end of time interval h, cloudiness ciThe current load is again evaluated
The load information is then updated to broadcast the next delay indicator:
step five, calculating the unbalance measurement eta and the statistical skewness
To measure the load balancing situation in each time interval:
the "task" in the general task model refers to a program or a micro-service in an application program, and can be executed by any mobile micro-cloud, so that migration task requests from different mobile users can fluctuate continuously.
All the micro clouds check in the initial stage whether a new micro cloud enters its own communication range and update the neighbor list. If the number of neighbors is larger than d, randomly selecting d micro clouds for task migration; otherwise, the value of d is reduced by half until less than the current number of neighbors.
The second phase is task reallocation, with each cloudlet randomly selecting d neighbors in the current neighbor list, thenAnd comparing the task loads of the neighbor clouds, sequencing, and selecting the neighbor with the minimum load to execute task migration. And calculating the migration probability between the source micro cloud and the target micro cloud according to a proportional algorithm, and performing task migration according to the probability. Finally, the imbalance metric η and the statistical skewness are calculated
To measure the load balancing situation in each time interval:
Lmaxand
representing maximum load and average load, respectively. The imbalance metric can measure the balance degree of the load distribution, and the statistical skewness provides more detailed description of the distribution process for the load distribution, such as whether the distribution result has an abnormal value which is too high or too low.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (2)
1. A task migration and cooperative load balancing method in a mobile edge computing environment is characterized by comprising the following steps:
step one, in the initial stage of the period, the micro cloud ciChecking whether a new micro cloud enters the communication range of the micro cloud, and if so, updating the list of the neighbor micro clouds;
step two, calculating the current load of each neighbor micro cloud, wherein the expression is as follows:
wherein, γiIs a micro cloud ciK (x) assign an index function to the task if cloudlet ciProviding service for the user at the position x, wherein the task allocation index function value is 1, and otherwise, the task allocation index function value is 0;
τ (x) is the migration task density from the mobile user at the position x ∈ R, and τ (x) ═ λ (x) ω (x), where the migration task arrival rate at the moment at the mobile user at the position x ∈ R is λ (x), and the average task size is ω (x);
si(x) Is a micro cloud ciService rate provided for mobile user at position x, and
wherein
Representing micro clouds ciMaximum service rate provided, dis (x, c)i) Representing a mobile user and a micro-cloud c located at xiThe Euclidean distance between; α and β are parameters for adjusting the flexibility of the service rate for adapting to different network scenarios;
calculating a delay index: micro cloud ciAs the delay indicator Γi(γi) And has:
step three, calculating each micro cloud c according to the delay indexes obtained in the step twoiDelay parameters broadcast at respective time intervals h
And migration probability
Determining an optimal task migration object;
the expression is as follows:
where the superscript h denotes the start of the h-th time interval,
obtaining micro cloud ciInformation whether to serve mobile subscriber at x, si(x) Representing the service rate provided by the micro cloud i for the mobile user at x;
step four, migrating the task to a neighbor micro cloud of the optimal task migration object; entering the next period and returning to the step one for execution until the computing task is finished;
step five, calculating the maximum load, the unbalance measurement eta and the statistical skewness
And carrying out load balancing; the method comprises the following specific steps:
step 5.1, randomly selecting d micro clouds from the n mobile micro clouds according to a d-choice principle; if the number of neighbors is larger than d, randomly selecting d micro clouds for task migration; otherwise, reducing the value d by half until the value d is less than the number of the current neighbors;
step 5.2, calculating the migration probability between the source micro cloud and the target micro cloud according to a proportional algorithm, and performing task migration according to the probability;
step 5.3, calculating the unbalance measurement eta and the statistical skewness
And outputs:
wherein L ismaxAnd
respectively representing the maximum load and the average load among the d neighbor micro clouds.
2. The method for task migration and cooperative load balancing in a mobile edge computing environment as claimed in claim 1, wherein the specific step of calculating the maximum load in step five comprises:
randomly selecting the micro cloud with the minimum load from the d micro clouds to perform task migration, and if the relation between the number of the tasks and the number of the micro clouds is more than or equal to n log n, considering that the maximum load in all the micro clouds is as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910739002.5A CN110445866B (en) | 2019-08-12 | 2019-08-12 | Task migration and cooperative load balancing method in mobile edge computing environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910739002.5A CN110445866B (en) | 2019-08-12 | 2019-08-12 | Task migration and cooperative load balancing method in mobile edge computing environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110445866A CN110445866A (en) | 2019-11-12 |
| CN110445866B true CN110445866B (en) | 2021-11-30 |
Family
ID=68434604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910739002.5A Active CN110445866B (en) | 2019-08-12 | 2019-08-12 | Task migration and cooperative load balancing method in mobile edge computing environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110445866B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110896344B (en) * | 2019-11-15 | 2021-03-19 | 北京邮电大学 | Redundant service deployment method and device |
| CN111444009B (en) * | 2019-11-15 | 2022-10-14 | 北京邮电大学 | Resource allocation method and device based on deep reinforcement learning |
| CN111431941B (en) * | 2020-05-13 | 2021-08-27 | 南京工业大学 | Real-time video code rate self-adaption method based on mobile edge calculation |
| CN112187891B (en) * | 2020-09-16 | 2022-06-10 | 国网浙江省电力有限公司信息通信分公司 | Load optimization method and device of edge computing node set based on multiple services |
| CN112217742B (en) * | 2020-09-29 | 2022-11-29 | 广东石油化工学院 | Calculation migration method for cooperation between fog nodes |
| CN112579285B (en) * | 2020-12-10 | 2023-07-25 | 南京工业大学 | Distributed neural network collaborative optimization method for edge network |
| CN112511649B (en) * | 2020-12-21 | 2022-08-26 | 新疆品宣生物科技有限责任公司 | Multi-access edge calculation method and equipment |
| CN112815990B (en) * | 2020-12-28 | 2022-09-23 | 齐丰科技股份有限公司 | Power distribution equipment monitoring system based on internet of things |
| CN112817770B (en) * | 2021-03-09 | 2024-01-30 | 皖西学院 | Method for improving load balance of distributed edge computing system |
| CN114090238B (en) * | 2021-10-29 | 2024-10-29 | 国网江苏省电力有限公司信息通信分公司 | Edge node load prediction method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298557A (en) * | 2014-06-05 | 2015-01-21 | 中国人民解放军信息工程大学 | SOA dynamic load transferring method and system |
| CN106874108A (en) * | 2016-12-28 | 2017-06-20 | 广东工业大学 | Thin cloud is minimized in mobile cloud computing use number technology |
| CN108900628A (en) * | 2018-07-20 | 2018-11-27 | 南京工业大学 | Micro cloud computing resource allocation method based on pricing mechanism in edge computing environment |
| CN109104455A (en) * | 2018-04-16 | 2018-12-28 | 南京邮电大学 | A kind of method of pair of roadside thin cloud load balance optimization |
| CN109413615A (en) * | 2018-09-14 | 2019-03-01 | 重庆邮电大学 | The energy delay compromise proposal of Energy-aware unloading under car networking based on MEC |
| CN109639833A (en) * | 2019-01-25 | 2019-04-16 | 福建师范大学 | A kind of method for scheduling task based on wireless MAN thin cloud load balancing |
| CN109936614A (en) * | 2017-12-15 | 2019-06-25 | 财团法人工业技术研究院 | The migration management method for edge platform server and the user equipment content of taking action |
-
2019
- 2019-08-12 CN CN201910739002.5A patent/CN110445866B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298557A (en) * | 2014-06-05 | 2015-01-21 | 中国人民解放军信息工程大学 | SOA dynamic load transferring method and system |
| CN106874108A (en) * | 2016-12-28 | 2017-06-20 | 广东工业大学 | Thin cloud is minimized in mobile cloud computing use number technology |
| CN109936614A (en) * | 2017-12-15 | 2019-06-25 | 财团法人工业技术研究院 | The migration management method for edge platform server and the user equipment content of taking action |
| CN109104455A (en) * | 2018-04-16 | 2018-12-28 | 南京邮电大学 | A kind of method of pair of roadside thin cloud load balance optimization |
| CN108900628A (en) * | 2018-07-20 | 2018-11-27 | 南京工业大学 | Micro cloud computing resource allocation method based on pricing mechanism in edge computing environment |
| CN109413615A (en) * | 2018-09-14 | 2019-03-01 | 重庆邮电大学 | The energy delay compromise proposal of Energy-aware unloading under car networking based on MEC |
| CN109639833A (en) * | 2019-01-25 | 2019-04-16 | 福建师范大学 | A kind of method for scheduling task based on wireless MAN thin cloud load balancing |
Non-Patent Citations (1)
| Title |
|---|
| 车联网移动云系统虚拟机迁移技术研究;危湖贵;《无线互联科技》;20181112;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110445866A (en) | 2019-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110445866B (en) | Task migration and cooperative load balancing method in mobile edge computing environment | |
| CN107995660B (en) | Joint task scheduling and resource allocation method supporting D2D-edge server unloading | |
| CN110247793B (en) | Application program deployment method in mobile edge cloud | |
| CN108809695B (en) | Distributed uplink unloading strategy facing mobile edge calculation | |
| CN109547555B (en) | Non-equilibrium edge cloud network access and resource allocation method based on fairness criterion | |
| CN109862592B (en) | Resource management and scheduling method in mobile edge computing environment based on multi-base-station cooperation | |
| CN111274035B (en) | Resource scheduling method and device in edge computing environment and computer equipment | |
| CN109548031B (en) | Unbalanced edge cloud network access and resource allocation method | |
| CN112020103A (en) | Content cache deployment method in mobile edge cloud | |
| CN112148492B (en) | Service deployment and resource allocation method considering multi-user mobility | |
| CN113918240B (en) | Task unloading method and device | |
| Harvey et al. | Edos: Edge assisted offloading system for mobile devices | |
| CN109639833B (en) | Task scheduling method based on wireless metropolitan area network micro-cloud load balancing | |
| CN109951873A (en) | A kind of Internet of Things mist calculate in information asymmetry do not know lower task unloading mechanism | |
| CN111935205B (en) | Distributed resource allocation method based on alternating direction multiplier method in fog computing network | |
| CN115629865B (en) | Deep learning inference task scheduling method based on edge calculation | |
| CN113329432B (en) | Edge service arrangement method and system based on multi-objective optimization | |
| CN115865930A (en) | MEC dynamic adjustment method based on 5G power Internet of things | |
| Lovén et al. | A dark and stormy night: Reallocation storms in edge computing | |
| Li et al. | Suitability-based edge server placement strategy in 5G ultra-dense networks | |
| KR102056894B1 (en) | Dynamic resource orchestration for fog-enabled industrial internet of things networks | |
| Liu et al. | Computation offloading game for multi-task multi-helper fog networks | |
| CN114205830B (en) | Smart grid communication network planning method, system, equipment and storage medium | |
| Ye et al. | Toward dynamic computation offloading for data processing in vehicular fog based F-RAN | |
| CN115835301A (en) | Task unloading method and device, electronic equipment and storage medium |
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 |