CN112363829B - User resource dynamic allocation method based on elastic scale aggregation - Google Patents
User resource dynamic allocation method based on elastic scale aggregation Download PDFInfo
- Publication number
- CN112363829B CN112363829B CN202011210750.3A CN202011210750A CN112363829B CN 112363829 B CN112363829 B CN 112363829B CN 202011210750 A CN202011210750 A CN 202011210750A CN 112363829 B CN112363829 B CN 112363829B
- Authority
- CN
- China
- Prior art keywords
- task
- aggregation
- user
- edge server
- total
- 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
- 230000002776 aggregation Effects 0.000 title claims abstract description 67
- 238000004220 aggregation Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000008859 change Effects 0.000 claims abstract description 23
- 238000013468 resource allocation Methods 0.000 claims abstract description 8
- 230000004931 aggregating effect Effects 0.000 claims abstract description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000003993 interaction Effects 0.000 abstract description 5
- 230000004044 response Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 6
- 230000002068 genetic effect Effects 0.000 description 3
- 238000002922 simulated annealing Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a dynamic user resource allocation method based on elastic scale aggregation. According to the method and the system for dynamically aggregating the service resources, the elastic scale is calculated according to the hot degree and the change trend of the user task, the service resources are dynamically aggregated on the edge server, the requirements of the user are met in a cooperative mode, and therefore the application response delay of the user is effectively reduced, and the user experience is optimized. Compared with the existing dynamic resource allocation method, the method has stronger operability, can effectively reduce interaction delay when the user accesses the service, and provides high-quality user experience.
Description
Technical Field
The invention belongs to the technical field of edge computing and service computing, relates to a user resource dynamic allocation method, and in particular relates to a user resource dynamic allocation method based on elastic scale aggregation.
Background
With the continuous popularization of 5G technology, numerous intelligent Web applications are deployed in mobile devices, and these applications bring great convenience to the fields of life, entertainment, social contact and the like of people, and redefine the life style of current people. But these applications do not run smoothly on current mobile devices due to their low performance. Thus, many Web application servers offload the tasks of user applications to a near-end edge server with a widely popular edge computing framework, freeing up the performance limitations of mobile devices by allocating sufficient service resources.
Such a strategy exposes a number of drawbacks in the actual operation process. If in a user-intensive area, excessive task offloading needs may result in insufficient service resources of nearby edge servers, and thus, the user's request cannot be responded to in time, resulting in increased delay. While edge servers in the rare areas of remote users are idle because of lack of enough user requests.
In addition, users within a certain geographic range are dynamically changed, tasks of different user groups are different, and nearby edge servers need to add more types of service resources to meet the requirements of new users. In fact, the service resource types of the edge servers in one user area are limited, and more new demands can cause resource contention, so that tasks are congested, and user experience is greatly affected.
Accordingly, there is a need to provide an improved dynamic allocation method of resources that overcomes the above-mentioned drawbacks.
Disclosure of Invention
In order to solve the technical problems, the invention provides a dynamic user resource allocation method based on elastic scale aggregation. According to the method and the system for dynamically aggregating the service resources, the elastic scale is calculated according to the hot degree and the change trend of the user task, the service resources are dynamically aggregated on the edge server, the requirements of the user are met in a cooperative mode, and therefore the application response delay of the user is effectively reduced, and the user experience is optimized.
The technical scheme adopted by the invention is as follows: a dynamic allocation method of user resources based on elastic scale aggregation is characterized by comprising the following steps:
step 1: establishing a tracking file of each edge server and collecting all historical user service resource requirement records in the area in charge of each edge server;
step 2: for a given time interval T, calculating the total task request quantity of each edge server in the time interval;
step 3: initializing and calculating an elastic scale according to the total task request quantity, aggregating all edge servers, and constructing an aggregation set;
step 4: initializing allocation service resources;
step 5: calculating the importance of each aggregation set and the change trend of the task demands of each edge server in a given time interval t;
step 6: based on importance optimization, calculating an elastic scale, and re-polymerizing each edge server;
step 7: dynamically adjusting the resource allocation based on the change trend of the task demand;
step 8: repeating steps 5-7, continuously and dynamically allocating resources.
The invention provides a dynamic user resource allocation method based on elastic scale aggregation by considering the hot degree and the change trend of user tasks. Compared with the existing dynamic resource allocation method, the method has stronger operability, can effectively reduce interaction delay when the user accesses the service, and provides high-quality user experience.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a schematic diagram of an aggregation set constructed based on elastic dimensions in an embodiment of the present invention;
FIG. 3 is a data result 1 comparing the method (DBLR) of the present invention with the prior methods (genetic algorithm GA, simulated annealing SA, random algorithm Random and Greedy algorithm Greedy) according to an embodiment of the present invention;
FIG. 4 is a data result 2 comparing the method (DBLR) of the present invention with the prior methods (genetic algorithm GA, simulated annealing SA, random algorithm Random and Greedy algorithm Greedy) according to an embodiment of the present invention.
Detailed Description
In order to facilitate the understanding and practice of the invention, those of ordinary skill in the art will now make further details with reference to the drawings and examples, it being understood that the examples described herein are for the purpose of illustration and explanation only and are not intended to limit the invention thereto.
Referring to fig. 1, the method for dynamically allocating user resources based on elastic scale aggregation provided by the invention comprises the following steps:
step 1: establishing a tracking file of each edge server and collecting all historical user service resource requirement records in the area in charge of each edge server;
the tracking file of the edge server in this embodiment includes the total bandwidth resource, longitude and latitude coordinates of the server and the average data transmission rate; the historical user service resource requirement record includes the total number of users, the total number of task requests, and the minimum amount of service resources required for each task request.
The minimum amount of service resources required for each task request of the present embodiment includes the minimum amount of computing resources required for each task request and the minimum amount of storage resources required for each task request.
Step 2: for a given time interval T, calculating the total task request quantity of each edge server in the time interval;
in this embodiment, the total task request amount of each edge server in the time interval T is calculated by the following formula;
wherein,representing the total task request amount of the edge server i in the period T, M representing the total number of task types,/->Representing the total request amount of task type m in edge server i during period T. .
Step 3: initializing and calculating an elastic scale according to the total task request quantity, aggregating all edge servers, and constructing an aggregation set;
in this embodiment, the elastic scale is calculated by the following formula;
wherein,the total task request quantity of the edge server i in the period T is represented, n represents the total number of the edge servers, lambda is a weight coefficient, and the value range is (0, 1)]。
Please refer to fig. 2, in this embodiment, each edge server is aggregated to construct an aggregate set; the specific implementation comprises the following substeps:
step 3.1: sorting in descending order according to total task request quantity of each edge server, and selecting pre-Clu T The edge server with the highest rank is used as an aggregation center; wherein Clu is T Representing the elastic dimension; see S1 in fig. 2;
step 3.2: for the rest edge servers, respectively calculating the geographic distance between each edge server and different aggregation centers, selecting the nearest aggregation center to add the aggregation set, and finally forming Clu T A collection of aggregates; see S2 and S3 in fig. 2.
The calculation formula of the geographic distance is as follows:
Distance ij ＝R*cos -1 [sin(Mlat i )*sin(Mlat j )*cos(Mlon i -Mlon j )+cos(Mlat i )*cos(Mlat j )]*π÷180；
Distance ij the distance between the edge server i and the aggregation center j is represented, R represents the average radius of the earth, the value is 6371.004km, and pi represents the circumference ratio; mlat i Representing the calculated latitude value of the edge server i, if the geographic location is northern hemisphere, mlat i ＝90-lat i The method comprises the steps of carrying out a first treatment on the surface of the If the geographic position is southern hemisphere, mlat i ＝90+lat i The method comprises the steps of carrying out a first treatment on the surface of the Wherein lat i The true latitude value of the edge server i is obtained by GPS data, and Mlat j Computing method of (2) and Mlat i Consistent;
Mlon i calculated longitude values representing edge server i, mlon if the geographic location is the eastern hemisphere i ＝lon i The method comprises the steps of carrying out a first treatment on the surface of the If the geographic position is a western hemisphere, mlon i ＝-lon i The method comprises the steps of carrying out a first treatment on the surface of the Wherein lon i Is the true longitude value of the edge server i, obtained from GPS data, mlon j Calculation method of (2) and Mlon i And consistent.
Step 4: initializing allocation service resources;
the specific implementation of this embodiment includes the following sub-steps:
step 4.1: for each aggregation set, calculating the total request quantity of each type of user task in the aggregation subset, and carrying out descending order sequencing;
wherein, the total request quantity calculation formula of each type of user task is as follows:
wherein,representing the total request amount of task type m in aggregate j within T period, K representing the total number of edge servers in aggregate j, +.>Representing the total request amount of the task type m in the aggregate set j by the edge server i in the period T.
Step 4.2: selecting the highest-ranking user task type, and determining the number of edge servers required to be allocated for service resources corresponding to the user task type according to the average bandwidth resource total amount of the edge servers in the aggregate subset;
the calculation method comprises the following steps:
representing the number of edge servers needed to be allocated for service m at time T, B avg Representing average bandwidth of edge servers within a collection, b i Representing the bandwidth of edge server i in aggregate j;
step 4.3: randomly selecting edge servers meeting the quantity requirement from the aggregation subset to allocate service resources;
step 4.4: for the rest edge servers which are not allocated with the service, calculating the time delay between each edge server and the aggregation center, and selecting the edge server with the smallest delay to allocate the service resource;
the time delay calculation method comprises the following steps:
t ij ＝0.5+0.1*Distance ij
t ij representing the time delay between edge server i and aggregation center j.
Step 4.5: the next ordered user task is selected and steps 4.2-4.4 are repeated until all types of user tasks are selected.
Step 5: calculating the importance of each aggregation set and the change trend of the task demands of each edge server in a given time interval t;
in this embodiment, the importance of each aggregation set in the time interval t is calculated by the following formula;
wherein,the importance degree of the aggregation j in the time interval t is represented; />Representing the total number of users in aggregate j in time interval t,/->Representing the total number of users of the edge server k in the aggregation set j in the time interval t; k represents the total number of edge servers in aggregate j; />Representing the aggregate j aggregate task request volume during period t.
In this embodiment, the change trend of the task demands of each edge server in the time interval t is calculated according to the following formula;
wherein,the change trend of the task m in the aggregation set j in the time interval t is shown; />Representing the change trend of the task m on the edge server k in the aggregation set j in the time interval t; k represents the total number of edge servers in aggregate j; alpha and beta are weight coefficients; />Representing the total request quantity of task type m in aggregate set j during period t,/>Representing the total request quantity of task type m in aggregate set j during period T,/>And (5) representing the change trend of the task m in the aggregation set j in the time zone T.
Step 6: based on importance optimization, calculating an elastic scale, and re-polymerizing each edge server;
in this embodiment, the elastic scale is optimally calculated by the following formula;
wherein Clu is T+t Representing the elasticity after optimization within time interval tThe dimensions of the product are set,indicating the importance of the aggregate j in time interval t,/->The importance of the aggregate j in the time interval T is shown.
In this embodiment, the method includes the following steps:
step 6.1: sorting in descending order according to the total number of users of each edge server, and selecting pre-Clu T+t The edge servers with highest rank are used as aggregation centers to form Clu T+t New aggregate sets;
step 6.2: and for the rest edge servers, respectively calculating the geographic distance between each edge server and different aggregation centers, and selecting the nearest aggregation center to add into the aggregation set.
Step 7: dynamically adjusting the resource allocation based on the change trend of the task demand;
in this embodiment, the specific steps of step 7 include the following sub-steps:
step 7.1: for each new aggregation set, calculating the overall change trend of each type of user task in the set, and sorting in descending order;
step 7.2: selecting tasks with positive change trend and top ranking theta to form a task set to be updated according to the sorting result;
step 7.3: calculating the number of edge servers of service resources required by each task in the task set to be updated;
step 7.4: randomly selecting a satisfactory number of edge servers from within the aggregate set;
step 7.5: for the selected edge server, if the existing user task has a change trend of a negative value, corresponding service resources are recovered from the server; if the user task in the task set to be updated is already served in the server, reserving corresponding service resources; if the user task in the task set to be updated is not served by the server, adding corresponding service resources.
Step 8: repeating steps 5-7, continuously and dynamically allocating resources.
The invention can effectively reduce the interaction delay when the user accesses the service and provide high-quality user experience. The data results of the method (DBLR) of the present invention were compared with the existing methods (genetic algorithm GA, simulated annealing SA, random algorithm Random and Greedy algorithm Greedy). As can be seen from FIG. 3, the present invention achieves a minimum user average interaction delay for different aggregation sets than the prior art. As can be seen from fig. 4, as the total number of edge servers increases, the method of the present invention is hardly affected, the average interaction delay of the user is the lowest, and the effect is significantly better than the other four methods, which proves the superiority of the method of the present invention.
It should be understood that parts of the specification not specifically set forth herein are all prior art.
It should be understood that the foregoing description of the preferred embodiments is not intended to limit the scope of the invention, but rather to limit the scope of the claims, and that those skilled in the art can make substitutions or modifications without departing from the scope of the invention as set forth in the appended claims.
Claims (8)
1. A dynamic allocation method of user resources based on elastic scale aggregation is characterized by comprising the following steps:
step 1: establishing a tracking file of each edge server and collecting all historical user service resource requirement records in the area in charge of each edge server;
step 2: for a given time interval T, calculating the total task request quantity of each edge server in the time interval;
step 3: initializing and calculating an elastic scale according to the total task request quantity, aggregating all edge servers, and constructing an aggregation set;
wherein, calculate the elastic scale through the following formula;
wherein,the total task request quantity of the edge server i in the period T is represented, n represents the total number of the edge servers, lambda is a weight coefficient, and the value range is (0, 1)]；
The edge servers are aggregated to construct an aggregation set; the specific implementation comprises the following substeps:
step 3.1: sorting in descending order according to total task request quantity of each edge server, and selecting pre-Clu T The edge server with the highest rank is used as an aggregation center; wherein Clu is T Representing the elastic dimension over a period T;
step 3.2: for the rest edge servers, respectively calculating the geographic distance between each edge server and different aggregation centers, selecting the nearest aggregation center to add the aggregation set, and finally forming Clu T A collection of aggregates;
step 4: initializing allocation service resources;
step 5: calculating the importance of each aggregation set and the change trend of the task demands of each edge server in a given time interval t;
step 6: based on importance optimization, calculating an elastic scale, and re-polymerizing each edge server;
step 7: dynamically adjusting the resource allocation based on the change trend of the task demand;
step 8: repeating steps 5-7, continuously and dynamically allocating resources.
2. The method for dynamically allocating user resources based on elastic scale aggregation according to claim 1, wherein: the tracking file of the edge server in the step 1 comprises the total bandwidth resource, longitude and latitude coordinates of the server and the average data transmission rate; the historical user service resource requirement record includes the total number of users, the total number of task requests, and the minimum amount of service resources required for each task request.
3. The method for dynamically allocating user resources based on elastic scale aggregation according to claim 2, wherein: the minimum amount of service resources required for each task request includes a minimum amount of computing resources required for each task request and a minimum amount of storage resources required for each task request.
4. The method for dynamically allocating user resources based on elastic scale aggregation according to claim 1, wherein: in step 2, calculating the total task request quantity of each edge server in the time interval T by the following formula;
wherein,representing the total task request amount of the edge server i in the period T, M representing the total number of task types,/->Representing the total request amount of task type m in edge server i during period T.
5. The method for dynamically allocating user resources based on elastic scale aggregation according to claim 1, wherein the specific implementation of step 4 comprises the following sub-steps:
step 4.1: for each aggregation set, calculating the total request quantity of each type of user task in the aggregation subset, and carrying out descending order sequencing;
step 4.2: selecting the highest-ranking user task type, and determining the number of edge servers required to be allocated for service resources corresponding to the user task type according to the average bandwidth resource total amount of the edge servers in the aggregate subset;
step 4.3: randomly selecting edge servers meeting the quantity requirement from the aggregation subset to allocate service resources;
step 4.4: for the rest edge servers which are not allocated with the service, calculating the time delay between each edge server and the aggregation center, and selecting the edge server with the smallest delay to allocate the service resource;
step 4.5: the next ordered user task is selected and steps 4.2-4.4 are repeated until all types of user tasks are selected.
6. The method for dynamically allocating user resources based on elastic scale aggregation according to claim 1, wherein: in step 5, calculating importance of each aggregation set in the time interval t by the following formula;
wherein,the importance degree of the aggregation j in the time interval t is represented; />Representing the total number of users in aggregate j in time interval t,/->Representing the total number of users of the edge server k in the aggregation set j in the time interval t; k represents the total number of edge servers in aggregate set j；/>Representing the total task request quantity of the aggregation set j in the period t;
in step 5, calculating the change trend of the task demands of the edge servers in the time interval t according to the following formula;
wherein,the change trend of the task m in the aggregation set j in the time interval t is shown; />Representing the change trend of the task m on the edge server k in the aggregation set j in the time interval t; k represents the total number of edge servers in aggregate j; alpha and beta are weight coefficients; />Representing the total request quantity of task type m in aggregate set j during period t,/>Representing the total request quantity of task type m in aggregate set j during period T,/>And (5) representing the change trend of the task m in the aggregation set j in the time zone T.
7. The method for dynamically allocating user resources based on elastic scale aggregation according to claim 1, wherein: in step 6, the elastic scale is optimally calculated through the following formula;
wherein Clu is T+t Represents the optimized elastic dimension within the time interval t,indicating the importance of the aggregate j in time interval t,/->The importance degree of the aggregation j in the time interval T is represented;
the step 6 of re-polymerizing each edge server specifically comprises the following sub-steps:
step 6.1: sorting in descending order according to the total number of users of each edge server, and selecting pre-Clu T+t The edge servers with highest rank are used as aggregation centers to form Clu T+t New aggregate sets;
step 6.2: and for the rest edge servers, respectively calculating the geographic distance between each edge server and different aggregation centers, and selecting the nearest aggregation center to add into the aggregation set.
8. The method for dynamically allocating user resources based on elastic scale aggregation according to any of claims 1-7, wherein step 7 specifically comprises the following sub-steps:
step 7.1: for each new aggregation set, calculating the overall change trend of each type of user task in the set, and sorting in descending order;
step 7.2: selecting tasks with positive change trend and top ranking theta to form a task set to be updated according to the sorting result;
step 7.3: calculating the number of edge servers of service resources required by each task in the task set to be updated;
step 7.4: randomly selecting a satisfactory number of edge servers from within the aggregate set;
step 7.5: for the selected edge server, if the existing user task has a change trend of a negative value, corresponding service resources are recovered from the server; if the user task in the task set to be updated is already served in the server, reserving corresponding service resources; if the user task in the task set to be updated is not served by the server, adding corresponding service resources.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011210750.3A CN112363829B (en) | 2020-11-03 | 2020-11-03 | User resource dynamic allocation method based on elastic scale aggregation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011210750.3A CN112363829B (en) | 2020-11-03 | 2020-11-03 | User resource dynamic allocation method based on elastic scale aggregation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112363829A CN112363829A (en) | 2021-02-12 |
| CN112363829B true CN112363829B (en) | 2024-03-29 |
Family
ID=74512681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011210750.3A Active CN112363829B (en) | 2020-11-03 | 2020-11-03 | User resource dynamic allocation method based on elastic scale aggregation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112363829B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114116156B (en) * | 2021-10-18 | 2022-09-09 | 武汉理工大学 | Cloud-edge cooperative double-profit equilibrium taboo reinforcement learning resource allocation method |
| CN114816584B (en) * | 2022-06-10 | 2022-09-27 | 武汉理工大学 | Optimal carbon emission calculation unloading method and system for multi-energy supply edge system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107921761A (en) * | 2016-05-10 | 2018-04-17 | 道格拉斯·迈克尔·特伦查得 | Solar energy reacts epiphragma |
| WO2019024445A1 (en) * | 2017-07-31 | 2019-02-07 | 上海交通大学 | Collaborative optimization method for geographic distribution interactive service cloud resource |
| CN110213097A (en) * | 2019-05-31 | 2019-09-06 | 浙江大学 | A kind of edge service supply optimization method based on Resource dynamic allocation |
| CN110290011A (en) * | 2019-07-03 | 2019-09-27 | 中山大学 | Dynamic Service laying method based on Lyapunov control optimization in edge calculations |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9566758B2 (en) * | 2010-10-19 | 2017-02-14 | Massachusetts Institute Of Technology | Digital flexural materials |
| US9537973B2 (en) * | 2012-11-01 | 2017-01-03 | Microsoft Technology Licensing, Llc | CDN load balancing in the cloud |
-
2020
- 2020-11-03 CN CN202011210750.3A patent/CN112363829B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107921761A (en) * | 2016-05-10 | 2018-04-17 | 道格拉斯·迈克尔·特伦查得 | Solar energy reacts epiphragma |
| WO2019024445A1 (en) * | 2017-07-31 | 2019-02-07 | 上海交通大学 | Collaborative optimization method for geographic distribution interactive service cloud resource |
| CN110213097A (en) * | 2019-05-31 | 2019-09-06 | 浙江大学 | A kind of edge service supply optimization method based on Resource dynamic allocation |
| CN110290011A (en) * | 2019-07-03 | 2019-09-27 | 中山大学 | Dynamic Service laying method based on Lyapunov control optimization in edge calculations |
Non-Patent Citations (1)
| Title |
|---|
| 基于云平台的计算机开放式实验教学与管理模式研究;饶文碧;王云华;杨焱超;袁景凌;熊盛武;;计算机教育;20161010(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112363829A (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112363829B (en) | User resource dynamic allocation method based on elastic scale aggregation | |
| CN109857546B (en) | Multi-server mobile edge computing unloading method and device based on Lyapunov optimization | |
| CN105407004B (en) | The method and device of content distribution is carried out based on edge hotspot | |
| KR100723896B1 (en) | Grade of service and fairness policy for bandwidth reservation system | |
| US20170126583A1 (en) | Method and electronic device for bandwidth allocation based on online media services | |
| CN104796422A (en) | Online customer service staff equilibrium assignment method and online customer service staff equilibrium assignment device | |
| CN104619029B (en) | It is a kind of centralization cellular network architecture under baseband pool resource allocation methods and device | |
| CN102984280A (en) | Data backup system and method for social cloud storage network application | |
| CN108876646B (en) | D2D caching method based on node social characteristics | |
| CN111163178A (en) | Game theory-based service deployment and task unloading method in edge computing | |
| US9817698B2 (en) | Scheduling execution requests to allow partial results | |
| CN111901145A (en) | Power Internet of things heterogeneous shared resource allocation system and method | |
| CN102264109A (en) | Method of distributing bandwidth for service and for terminal service execution, and equipment thereof | |
| CN103281374A (en) | Method for rapid data scheduling in cloud storage | |
| CN113407249A (en) | Task unloading method facing to position privacy protection | |
| CN114327811A (en) | Task scheduling method, device and equipment and readable storage medium | |
| CN115629865A (en) | Deep learning inference task scheduling method based on edge calculation | |
| CN115550370A (en) | Computing power resource optimal scheduling allocation method based on multi-factor strategy | |
| CN115878227A (en) | Edge calculation task unloading method based on crowd classification | |
| CN114938372A (en) | Federal learning-based micro-grid group request dynamic migration scheduling method and device | |
| CN112104682A (en) | Intelligent distribution method and system for cloud desktop server, storage medium and central control server | |
| CN116546053A (en) | Edge computing service placement system in resource-constrained Internet of things scene | |
| CN116321189A (en) | Server deployment method based on deep reinforcement learning in edge-oriented computing | |
| CN113918323A (en) | High-energy-efficiency computing task allocation method and device in edge computing | |
| CN110138863A (en) | Adaptive consistency protocol optimization method based on Multi-Paxos grouping |
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 |