CN108737569B - Service selection method facing mobile edge computing environment - Google Patents
Service selection method facing mobile edge computing environment Download PDFInfo
- Publication number
- CN108737569B CN108737569B CN201810652390.9A CN201810652390A CN108737569B CN 108737569 B CN108737569 B CN 108737569B CN 201810652390 A CN201810652390 A CN 201810652390A CN 108737569 B CN108737569 B CN 108737569B
- Authority
- CN
- China
- Prior art keywords
- service
- chromosome
- edge server
- fitness
- service request
- 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
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
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/123—DNA computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
Abstract
The invention discloses a service selection method facing a mobile edge computing environment, which comprises the following steps: (1) collecting all equipment information, service information and connection information among equipment in the system; (2) receiving a service request; (3) selecting a service for the service request by applying a GAME algorithm; (4) and calculating the destination edge server according to the service selection scheme and the user path. Compared with the prior art, the invention considers the position movement of the user in the service selection process, and integrates the movement information of the user into the service selection, thereby not only reducing the total service response time through the service selection, but also providing the selection scheme of the target edge server and further reducing the service response time; in addition, the temperature control mechanism of the simulated annealing method is introduced into the genetic algorithm, so that the search range of the algorithm can be expanded at the initial stage of the algorithm, the local optimum is effectively avoided, the convergence speed is increased at the termination stage of the algorithm, and the efficiency of the algorithm is improved.
Description
Technical Field
The invention belongs to the technical field of software optimization, and particularly relates to a service selection method facing a mobile edge computing environment.
Background
With the development of mobile devices and mobile communication technologies, mobile devices are becoming more and more popular, which brings great convenience to work, life and study. At the same time, increasingly complex and diverse mobile applications place increasingly higher demands on computing, communication, storage and other capabilities of mobile devices, and these applications are often beyond the capabilities of mobile devices. To meet these needs, mobile edge computing has been proposed that aims to extend the capabilities of mobile devices by serving them on edge devices of the network. The edge device refers to a router, a switch, a base station and other devices at the edge of the network, and the purpose of expanding the capability of the mobile device is achieved by deploying and providing services on the devices. Compared with the cloud service, the edge service can greatly shorten the service response time, relieve the communication pressure of the backbone network and reduce the network congestion to a certain extent because the data transmission does not pass through the backbone network.
Although the way of providing services by the edge device has the advantages compared with the cloud server, the edge server has limited resources and can only deploy limited services, so that only part of the service requests can be satisfied, and not all the service requests can be satisfied. Therefore, when the edge server receives a service request which cannot be met by the edge server, the service request can only be transmitted to other edge servers or cloud servers with the service deployed for execution; at this time, how to select a service for the service request becomes a key issue. In addition, in a mobile environment, while a service is executing, a user is moving; therefore, after the service execution is completed, an edge server which can cover the current position of the user needs to be searched, and the result service execution result is transmitted to the edge server and fed back to the user.
While mobile technology has evolved, mobile applications have become increasingly complex, with complex mobile applications typically involving multiple subtasks. In the mobile edge computing system, these subtasks can be executed independently by different devices and combined in the form of service combination, so service selection requires selecting a service satisfying its requirement for each subtask in the service request, which undoubtedly increases the difficulty of service selection in the mobile edge computing environment.
Disclosure of Invention
In view of the above, the present invention provides a service selection method for a mobile edge computing environment, which can solve the problem of service selection in the mobile edge computing environment.
A method for mobile edge computing environment oriented service selection, comprising the steps of:
(1) collecting all equipment information, service information of equipment and connection information among the equipment in a system, wherein the equipment comprises an edge server and a cloud server;
(2) receiving, by an edge server, a service request;
(3) applying a GAME (Combined Genetic Algorithm and structured indexing Algorithm for Service Selection in Mobile Edge Computing systems) Algorithm to select services for each subtask in the Service request;
(4) and calculating and determining a destination edge server according to the service selection scheme and the moving path of the user, and transmitting a service execution result to the user by the destination edge server.
Further, the device information in step (1) includes a coverage area of the edge server and a service deployed on the edge server, the service information includes a service type, a function, a service execution time, and an input and output data amount deployed on the edge server and the cloud server, and the connection information includes a data transmission rate between any two edge servers and a data transmission rate between each edge server and the cloud server.
Further, the service request in the step (2) includes a plurality of subtasks, a combination relationship (sequence, concurrency, etc.) between the subtasks, a reception time of the service request, and a movement path of the user.
Further, the specific implementation process of the game algorithm in the step (3) is as follows:
3.1 initializing a population of a certain scale, calculating the fitness of each chromosome in the population, and taking the chromosome with the highest fitness as an optimal chromosome; the chromosome comprises n genes, wherein n is the number of subtasks in the service request, the genes and the subtasks are in corresponding relation, namely, the genes and the subtasks are expressed as service numbers selected by the corresponding subtasks, and then the chromosome corresponds to a whole set of service selection scheme of all the subtasks in the service request;
3.2, carrying out cross variation on chromosomes in the population, and for any child chromosome generated in the cross variation process, calculating the fitness of the child chromosome and comparing the fitness with a corresponding parent chromosome, wherein if the fitness of the child chromosome is less than or equal to the fitness of the parent chromosome, the child chromosome replaces the parent chromosome according to a probability η, if the fitness of the child chromosome is greater than the fitness of the parent chromosome, the child chromosome replaces the parent chromosome, and further the child chromosome is subjected to fitness comparison with the optimal chromosome, and if the fitness of the child chromosome is greater than the fitness of the optimal chromosome, the child chromosome replaces the optimal chromosome;
3.3, cooling the current temperature in the simulated annealing algorithm at a set cooling rate;
and 3.4, repeatedly carrying out genetic iteration according to the steps 3.2-3.3 until the temperature is reduced to a set minimum temperature threshold value, outputting the optimal chromosomes in the population and selecting optimal services for each subtask in the service request according to the corresponding service selection scheme.
Further, in step 3.1, for the gene of each chromosome of the initialization population, the gene is randomly selected from the candidate service set capable of executing the corresponding subtask, and the number of the selected service is assigned to the corresponding gene.
Further, in the step 3.1, the fitness of each chromosome is calculated, that is, a service selection scheme corresponding to the chromosome is adopted to select a service for each subtask in the service request, and a total response time of the service request, in which the target edge server transmits the result to the user, is selected, where the total response time is a time interval from the time when the service request is provided to the time when all subtasks are executed, and the time interval returns the execution result, specifically includes a sum of time when the user uploads data to the edge server, time when the device executes each subtask, and time when the execution result is fed back to the user, and the lower the total response time of the service request is, the higher the fitness is.
Further, the calculation expression for determining the probability η based on the simulated annealing algorithm in step 3.2 is as follows:
wherein: k is a given constant, T is the current temperature, IsAnd IfFitness of the child chromosome and the parent chromosome, respectively.
The invention applies genetic algorithm to continuously generate new service selection schemes, then selects a target edge server for each selection scheme and calculates the whole service response time, selects the selection schemes, reserves a better scheme, eliminates a poorer scheme, repeats an iterative process, and carries out crossing, variation, evaluation and selection on the selection schemes, thereby finally obtaining the final selection scheme and the target edge server.
Compared with the prior art, the method can select the service request in the environment with complex service request, namely comprising a plurality of subtasks and sensitive service response time in the mobile edge computing environment, and select the target edge server to transmit the service execution result; in the service selection process, the position movement of the user is considered, and the movement information of the user is merged into the service selection; the invention not only reduces the total service response time through service selection, but also provides a selection scheme of a target edge server, thereby further reducing the service response time; the invention adopts a heuristic method, introduces a temperature control mechanism of a simulated annealing method into a genetic algorithm, can enlarge the search range of the algorithm at the initial stage of the algorithm, effectively avoids the trapping of local optimization, accelerates the convergence speed at the termination stage of the algorithm, and improves the efficiency of the algorithm.
Drawings
FIG. 1 is a schematic overall flow chart of the method of the present invention.
Detailed Description
In order to more specifically describe the present invention, the following detailed description is provided for the technical solution of the present invention with reference to the accompanying drawings and the specific embodiments.
The existing service selection method is not suitable for the edge computing environment, and researches show that on one hand, the cloud server has strong functions, defaults to the functions capable of meeting all user requests, and service requests do not need to be transferred to other servers; on the other hand, in the traditional fixed network environment, the transmission rate of data is relatively stable in the service calling process, and the geographic positions of the service input parameters uploaded by the user and the service execution results are consistent. Compared with the traditional fixed network environment, the edge server has limited functions and cannot meet all service requests, the service requests need to be transferred to other equipment, and in the mobile edge computing environment, a user moves continuously, and the data transmission rate changes continuously due to the influence of the position and the connected edge server. In addition, the movement of the user causes changes in the location and associated server, and therefore, the edge server that transmits the service execution result needs to be searched after the service execution is completed. To this end, the present invention proposes a service selection method facing a mobile edge computing environment, in which a service is selected in the mobile edge computing environment, and a target edge server for transmitting a service execution result is searched after the selection is completed, so that the overall response time of the service is minimized.
As shown in FIG. 1, the service selection method facing the mobile edge computing environment of the present invention comprises the following steps:
(1) collecting all equipment information in the system, service information on the equipment and connection information among the equipment; the device information refers to a coverage area of each edge device and a service deployed by the edge device, the service information on the device refers to information such as service types, functions, service execution time, input/output data volumes and the like deployed on all the edge devices and the cloud server, and the connection information between the devices mainly refers to a data transmission rate between any two devices, including a data transmission rate between the edge devices and a data transmission rate between each edge device and the cloud service center.
(2) The edge server receives a service request, wherein the service request comprises information of all subtasks, the combination relationship (sequence, concurrency and the like) among the subtasks, the receiving time of the request, the moving path of the user and the like. For convenience of calculation, the path of the user is divided into a plurality of small segments, the segments are small enough to approximately consider that the user is stationary in the range, the moving path of the user is specifically represented as discrete time segments, each time segment corresponds to a geographic position, an edge server and a data transmission rate, and represents the geographic position, the connected edge server and the data transmission rate between the edge servers of the user in the time segment.
(3) Selecting a service for the service request by applying a GAME algorithm, which specifically comprises the following steps:
s301: the service selection problem is modeled as a genetic model. The chromosomes represent feasible solutions, and correspond to service selection schemes; the genes correspond to services meeting the corresponding service request subtasks, namely the services deployed on the edge server or the services deployed on the cloud server; the location of the gene corresponds to a subtask in the service request; the fitness of the chromosome represents the overall response time of the service request, and a higher fitness of the chromosome represents a lower overall response time of the service request corresponding to the service selection scheme.
S302: initializing the GAME algorithm, including initial population size, crossover probability, mutation probability, initial temperature, minimum temperature, cooling rate, etc., and selecting appropriate parameters according to the scale of the service selection problem.
S303: and generating an initial population according to the initialization data, wherein each chromosome in the initial population represents a feasible service selection scheme and comprises a plurality of genes, the number of the genes is the same as that of the subtasks contained in the service request, each position on the chromosome corresponds to one subtask, and the gene at the position is represented as the service selected by the corresponding subtask. The size of the initialized population is determined in the initialization parameter setting of the algorithm, candidate genes are randomly selected for each position of each chromosome during initialization, and the candidate genes correspond to all services which can meet corresponding subtasks, namely the services on the edge equipment also include the services on the cloud server.
S304: and evaluating and selecting the initial population, thereby retaining the superior individuals and eliminating the inferior individuals. The population optimization process is influenced by the fitness of each chromosome, the higher the fitness is, the higher the possibility that the chromosomes are reserved is, and the higher the possibility that the chromosomes with lower fitness are eliminated is; the total response time of the service request in the service selection scheme corresponding to the fitness, that is, the time interval from the service request being submitted to the end of execution of all the services to return the execution result, specifically includes the time for the user to upload data to the edge server, the time for the edge system to execute all the services, and the time for feeding back the result to the user.
The time of the edge system executing the service needs to combine the response time of each subtask, and for the sequentially executed subtasks, the response time is summed to obtain the combined response time; for the sub-services executed concurrently, the longer response time is taken as the combined response time, the response times of the sub-services are combined continuously, and finally the total response time of the service request can be obtained.
For each subtask, the response time is the sum of the service execution time and the input/output data transmission time of the service, the service execution time is the attribute of the service and is not influenced by other factors, and the data transmission time of the service can be calculated by dividing the transmission data amount by the data transmission rate between the servers.
S305: performing a crossover operation on the retained individuals, thereby generating new individuals; the process of crossing, i.e., the process of gene recombination, involves two chromosomes. The invention adopts the classical single-point crossing operation, namely, a point location is selected on chromosomes, genes positioned in front of the point location on two chromosomes are kept unchanged, and genes behind the point location are exchanged. Each crossover will result in two new individuals that have recombined genes from both parents, which may be more adaptive than both parents. Therefore, chromosomes with higher fitness may be generated by crossing, which in turn results in a better service selection scheme in the problem.
The number of crossing is determined by the crossing probability generated during initialization, specifically, a real number between 0 and 1 is randomly generated for each chromosome, and if the real number is smaller than the crossing probability, another chromosome is randomly selected for crossing operation.
S306: mutation operation is carried out on individuals, and the mutation process is also the process of generating new chromosomes. The difference is that the mutation process only involves one chromosome, and the mutation operation also selects a point on the chromosome and randomly replaces the gene on the point with another gene; each mutation will produce a new individual, which has mutated the maternal gene and may be more adaptive than the maternal. Thus, by mutation, a more adaptive chromosome may be generated, which in turn results in a better service selection scheme, i.e. a lower overall response time for service requests.
The number of mutations is determined by the probability of mutation generated during initialization, which is to randomly generate a real number between 0 and 1 for each chromosome, and perform mutation operation on the chromosome if the real number is smaller than the probability of mutation.
S307: selecting a target edge server according to the service selection scheme, wherein the target edge server determines the time required for feeding back the service execution result to the user, and the specific selection process comprises the following steps: calculating the time of completing service execution according to the service selection scheme, finding the position of the user at the time, then calculating the time for transmitting the service execution result to the position, and if the time is earlier than the time for the user to leave the position, the edge server covering the position is the destination edge server; if the time is later than the time when the user leaves the position, finding the next position of the movement track of the user, calculating the time for transmitting the service execution result to the edge server covering the position, comparing the time with the time when the user leaves the position, and repeating the calculation until finding the position when the service execution result reaches the time earlier than the time when the user leaves the position, wherein the edge server covering the position is the target edge server.
S308: evaluating and selecting a new population; after the destination server is determined, the fitness of the new chromosome generated by crossing and mutation can be calculated; replacing the original chromosome with the new chromosome if the fitness of the generated new chromosome is higher than the fitness of the original chromosome; if the fitness of the derived new chromosome is lower than the original chromosome, a replacement probability is calculated:
replacement probability ═ exp (- (child chromosome fitness-parent chromosome fitness)/kx current temperature)
Wherein: k is a fixed constant; the selection principle is that the original chromosome is replaced by the new chromosome with higher fitness, and the original chromosome can be replaced by the chromosome with lower fitness with high probability under the condition that the fitness of the chromosome is not greatly different from that of the original chromosome or the current temperature is high. Therefore, the advantages and the disadvantages can be realized, the temperature attribute can be fully utilized, the search range is expanded when the temperature is higher in the initial stage of the algorithm, the local optimum is prevented from being trapped, the convergence speed is accelerated when the temperature is lower in the termination stage of the algorithm, and the efficiency of the algorithm is improved.
S309: and continuously repeating the genetic iteration process until the temperature is reduced to the minimum temperature to obtain the optimal service selection scheme. Genetic iteration is a continuous intersection, variation and optimization process, which is a main process of the GAME algorithm, and after each iteration, the temperature is reduced according to the cooling speed so as to reduce the searching range of the algorithm and improve the convergence speed. The genetic iteration process of the GAME algorithm is to continuously and repeatedly execute the crossing, variation and selection processes, after one iteration is finished, if the temperature is not reduced to the lowest temperature, the algorithm is continued, and a new round of iteration execution is started; if the temperature has reached the minimum temperature, the iterative process is complete, the historical optimal chromosome is returned, and the algorithm ends.
(4) And calculating a target edge server according to the service selection scheme and the user path, namely determining the target edge server according to a target edge server searching method in the service selection process and transmitting a service execution result.
The embodiments described above are presented to enable a person having ordinary skill in the art to make and use the invention. It will be readily apparent to those skilled in the art that various modifications to the above-described embodiments may be made, and the generic principles defined herein may be applied to other embodiments without the use of inventive faculty. Therefore, the present invention is not limited to the above embodiments, and those skilled in the art should make improvements and modifications to the present invention based on the disclosure of the present invention within the protection scope of the present invention.
Claims (3)
1. A method for mobile edge computing environment oriented service selection, comprising the steps of:
(1) collecting all equipment information, service information of equipment and connection information among the equipment in a system, wherein the equipment comprises an edge server and a cloud server;
(2) receiving, by an edge server, a service request;
(3) selecting services for each subtask in the service request by applying a GAME algorithm, wherein the specific execution process is as follows:
3.1 initializing a population of a certain scale, calculating the fitness of each chromosome in the population, and taking the chromosome with the highest fitness as an optimal chromosome; the chromosome comprises n genes, wherein n is the number of subtasks in the service request, the genes and the subtasks are in corresponding relation, namely, the genes and the subtasks are expressed as service numbers selected by the corresponding subtasks, and then the chromosome corresponds to a whole set of service selection scheme of all the subtasks in the service request;
randomly selecting genes of each chromosome of the initialized population from a candidate service set capable of executing corresponding subtasks, and assigning the number of the selected service to the corresponding gene;
calculating the fitness of each chromosome, namely selecting services for each subtask in a service request by adopting a service selection scheme corresponding to the chromosome, and selecting the total response time of the service request of a target edge server for transmitting a result to a user, wherein the total response time is the time interval from the service request to the completion of the execution of all subtasks and returning the execution result, and specifically comprises the sum of the time of uploading data to the edge server by the user, the time of executing each subtask by equipment and the time of feeding back the execution result to the user, and the lower the total response time of the service request is, the higher the fitness is;
3.2, carrying out cross variation on chromosomes in the population, and for any child chromosome generated in the cross variation process, calculating the fitness of the child chromosome and comparing the fitness with a corresponding parent chromosome, wherein if the fitness of the child chromosome is less than or equal to the fitness of the parent chromosome, the child chromosome replaces the parent chromosome according to the probability η;
the probability η is determined based on a simulated annealing algorithm, and a specific calculation expression is as follows:
wherein: k is a given constant, T is the current temperature, IsAnd IfFitness of the child chromosome and the parent chromosome respectively;
3.3, cooling the current temperature in the simulated annealing algorithm at a set cooling rate;
3.4, repeatedly carrying out genetic iteration according to the steps 3.2-3.3 until the temperature is reduced to a set minimum temperature threshold value, outputting the optimal chromosomes in the population and selecting optimal services for each subtask in the service request according to the corresponding service selection scheme;
(4) and calculating and determining a destination edge server according to the service selection scheme and the moving path of the user, and transmitting a service execution result to the user by the destination edge server.
2. The service selection method of claim 1, wherein: the device information in the step (1) includes a coverage area of the edge server and a service deployed on the edge server, the service information includes a service type, a function, a service execution time and an input and output data amount deployed on the edge server and the cloud server, and the connection information includes a data transmission rate between any two edge servers and a data transmission rate between each edge server and the cloud server.
3. The service selection method of claim 1, wherein: the service request in the step (2) includes a plurality of subtasks, a combination relationship between the subtasks, a reception time of the service request, and a movement path of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810652390.9A CN108737569B (en) | 2018-06-22 | 2018-06-22 | Service selection method facing mobile edge computing environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810652390.9A CN108737569B (en) | 2018-06-22 | 2018-06-22 | Service selection method facing mobile edge computing environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108737569A CN108737569A (en) | 2018-11-02 |
| CN108737569B true CN108737569B (en) | 2020-04-28 |
Family
ID=63930582
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810652390.9A Active CN108737569B (en) | 2018-06-22 | 2018-06-22 | Service selection method facing mobile edge computing environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108737569B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110266744A (en) * | 2019-02-27 | 2019-09-20 | 中国联合网络通信集团有限公司 | Location-based edge cloud resource dispatching method and system |
| CN110287035B (en) * | 2019-08-20 | 2019-12-13 | 中国人民解放军国防科技大学 | request scheduling method, device and equipment for hybrid edge computing and storage medium |
| CN111586762B (en) * | 2020-04-29 | 2023-02-17 | 重庆邮电大学 | Task unloading and resource allocation joint optimization method based on edge cooperation |
| CN111768851B (en) * | 2020-06-22 | 2023-10-03 | 杭州电子科技大学 | Multi-level home care scheduling method and system under dynamic demand |
| CN113515367B (en) * | 2020-08-23 | 2022-08-30 | 浪潮工业互联网股份有限公司 | Data integration method based on big data and edge calculation and storage medium |
| CN112969144B (en) * | 2021-02-02 | 2022-04-26 | 武汉大学 | Micro-service pre-deployment method and system for mobile edge calculation |
| CN114745394B (en) * | 2022-04-07 | 2023-07-07 | 山东理工大学 | Mobile service selection method based on moth fire suppression optimization algorithm in cloud and edge environments |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101237469A (en) * | 2008-02-27 | 2008-08-06 | 中山大学 | Method for optimizing multi-QoS grid workflow based on ant group algorithm |
| CN104735166A (en) * | 2015-04-13 | 2015-06-24 | 李金忠 | Skyline service selection method based on MapReduce and multi-target simulated annealing |
| CN107612987A (en) * | 2017-09-08 | 2018-01-19 | 浙江大学 | A kind of service provision optimization method based on caching towards edge calculations |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101826167B (en) * | 2010-03-31 | 2012-09-05 | 北京航空航天大学 | Multi-core adaptive & parallel simulated annealing genetic algorithm based on cloud controller |
| US9247386B2 (en) * | 2013-12-18 | 2016-01-26 | International Business Machines Corporation | Location-based mobile application and service selection |
| US10122547B2 (en) * | 2015-08-14 | 2018-11-06 | Nec Corporation | Enabling high-bandwidth, responsive mobile applications in LTE networks |
| EP3456000A1 (en) * | 2016-05-09 | 2019-03-20 | Nokia Solutions and Networks Oy | Policy control with mobile edge computing |
| CN107465748B (en) * | 2017-08-18 | 2020-07-31 | 东南大学 | Dynamic resource allocation method based on evolution game in mobile edge cloud computing system |
| CN107743307B (en) * | 2017-10-30 | 2021-01-05 | 中国联合网络通信集团有限公司 | Method and equipment for processing MEC (Mec) based on position |
-
2018
- 2018-06-22 CN CN201810652390.9A patent/CN108737569B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101237469A (en) * | 2008-02-27 | 2008-08-06 | 中山大学 | Method for optimizing multi-QoS grid workflow based on ant group algorithm |
| CN104735166A (en) * | 2015-04-13 | 2015-06-24 | 李金忠 | Skyline service selection method based on MapReduce and multi-target simulated annealing |
| CN107612987A (en) * | 2017-09-08 | 2018-01-19 | 浙江大学 | A kind of service provision optimization method based on caching towards edge calculations |
Non-Patent Citations (1)
| Title |
|---|
| 基于模拟退火遗传算法的服务选择;曹云健等;《计算机工程与设计》;20111231;第32卷(第10期);正文摘要以及正文第1节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108737569A (en) | 2018-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108737569B (en) | Service selection method facing mobile edge computing environment | |
| CN108874525B (en) | Service request distribution method facing edge computing environment | |
| CN110134493B (en) | Service function chain deployment algorithm based on resource fragment avoidance | |
| CN113300960A (en) | Delay deterministic transmission method based on routing scheduling and joint optimization | |
| CN113098714A (en) | Low-delay network slicing method based on deep reinforcement learning | |
| CN112784362A (en) | Hybrid optimization method and system for unmanned aerial vehicle-assisted edge calculation | |
| CN111988787B (en) | Task network access and service placement position selection method and system | |
| CN109445386A (en) | A kind of most short production time dispatching method of the cloud manufacturing operation based on ONBA | |
| CN111885493B (en) | Micro-cloud deployment method based on improved cuckoo search algorithm | |
| CN111510334B (en) | Particle swarm algorithm-based VNF online scheduling method | |
| He et al. | RTHop: Real-time hop-by-hop mobile network routing by decentralized learning with semantic attention | |
| CN113472671A (en) | Method and device for determining multicast route and computer readable storage medium | |
| Wang | Collaborative task offloading strategy of UAV cluster using improved genetic algorithm in mobile edge computing | |
| CN108289115B (en) | Information processing method and system | |
| Henna et al. | Distributed and collaborative high-speed inference deep learning for mobile edge with topological dependencies | |
| Wang et al. | Multi-objective joint optimization of communication-computation-caching resources in mobile edge computing | |
| Asheralieva et al. | Efficient dynamic distributed resource slicing in 6g multi-access edge computing networks with online admm and message passing graph neural networks | |
| CN116484976A (en) | Asynchronous federal learning method in wireless network | |
| CN113810916B (en) | Multi-server mixed deployment architecture and method in 5G/6G edge computing scene | |
| Krishna Priya et al. | Crossover-based improved sine cosine algorithm for multimedia content distribution in cloud environment | |
| CN116185523A (en) | Task unloading and deployment method | |
| CN115866626A (en) | NSGA-II and simulated annealing based service deployment method under edge environment | |
| CN111935824B (en) | Wireless resource allocation strategy updating method, device, equipment and storage medium | |
| CN108921354A (en) | A method of the ant colony algorithm for solving TSP problems based on particle group optimizing | |
| CN104955059B (en) | Cellular network base stations state time-varying model method for building up based on Bayesian network |
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 |