CN109104455B - Method for optimizing road edge micro-cloud load balance - Google Patents
Method for optimizing road edge micro-cloud load balance Download PDFInfo
- Publication number
- CN109104455B CN109104455B CN201810335686.8A CN201810335686A CN109104455B CN 109104455 B CN109104455 B CN 109104455B CN 201810335686 A CN201810335686 A CN 201810335686A CN 109104455 B CN109104455 B CN 109104455B
- Authority
- CN
- China
- Prior art keywords
- micro
- cloud
- task
- response time
- 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
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
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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
- H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
-
- 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
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Abstract
The invention discloses a method for optimizing road edge micro-cloud load balance, which comprises the following steps: constructing a vehicle-mounted network system model based on micro-clouds arranged on the roadside; under the condition that the number of tasks is set for each micro cloud, the average task response time of each micro cloud under the corresponding task is represented by using a function; searching and obtaining the numerical value of the average response time by using a bisection method, and setting a threshold value for judging whether each clout has an overload condition; if the micro cloud is overloaded, calculating the task flow from the overloaded micro cloud to the light load micro cloud meeting the condition by using a transmission method, and calculating the total network delay caused by redirecting the task flow; selecting the light-load micro-clouds of the optimal redirection flow according to the total network delay, and ensuring that the response time of each micro-cloud under the condition of the total task number is close to the average response time; the method and the device can obviously reduce the maximum response time of the micro-cloud task in the vehicle-mounted network and improve the utilization rate of resources in the vehicle-mounted network.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a method for optimizing road edge micro-cloud load balance.
Background
With the development of Internet of Things (IoT) in recent years, the development of modern transportation industry is rising like bamboo shoots in spring. As one of the trends in the development of the modern transportation industry, Intelligent Transport Systems (ITS) is receiving attention. The intelligent traffic system technology covers advanced technologies such as data communication transmission technology, computer processing technology, sensor technology, information technology and the like, and the technologies are effectively and uniformly applied to the fields of traffic transmission, service and the like, so that the connection between vehicles and roads, between vehicles and between vehicles and people can be effectively enhanced, the traffic safety is guaranteed, the traffic efficiency is improved, the environment is improved, and resources are saved. A Vehicular Ad Hoc Network (VANET) is a combination of IoT and intelligent traffic, and as an indispensable part of intelligent traffic development, it will also promote the continuous development of smart cities. The VANET can improve the driving experience of vehicle owners, and optimizes the scheduling of traffic resources through the interconnection and intercommunication of 'human-vehicle-road-environment', so that the problems caused by various factors influencing the driving experience of the vehicle owners are solved. Cloud computing, one of the emerging information technologies that have been developed rapidly in the present year, has been applied to various fields of social science due to its powerful computing and storage capabilities, and plays an unusual role and influence.
With the continuous progress of wireless communication technology, the demand of vehicle-mounted networks for resource optimization is increasing. Although vehicle devices may capture a wide variety of promising applications, their computing resources are still limited by their size. Cloud computing platforms have powerful computing resources, that is, we can solve the problem of resource optimization by performing compute-intensive tasks remotely on nearby clustered computers. More and more vehicles in the vehicle-mounted network have the requirement of accessing the internet, and it is conceivable that in the near future, drivers can enjoy fast and safe cloud services in the vehicle-mounted network. The traditional concept of understanding the cloud as an independent box data center is outdated, does not give users a good experience, and is inefficient.
Disclosure of Invention
The invention mainly aims to solve the problems in the prior art and provides a method for optimizing the roadside micro-cloud load balance, which has the following specific technical scheme:
a method for optimizing roadside micro-cloud load balancing, the method comprising the following steps:
constructing a vehicle-mounted network system model based on micro-clouds arranged on the roadside;
under the condition that the number of tasks is set for each micro cloud, the average task response time of each micro cloud under the corresponding task is represented by using a function;
searching and obtaining the numerical value of the average response time by using a bisection method, and setting a threshold value for judging whether each clout has an overload condition;
if the micro cloud is overloaded, calculating the task flow from the overloaded micro cloud to the light load micro cloud meeting the condition by using a transmission method, and calculating the total network delay caused by redirecting the task flow;
and selecting the light-load micro-cloud of the optimal redirection flow according to the size of the total network delay, and ensuring that the response time of each micro-cloud under the condition of the total task number is close to the average response time.
The invention is further improved in that: assuming that the number of tasks of each micro cloud is lambda, each cloud i has niA server, each server having a service rate muiThe function is TiThen can use the formula
To represent the average response time, wherein,
in the formula (I), the compound is shown in the specification,
representing a stability parameter of the system.
The invention is further improved in that: transmission method for calculating task flow by optimizing task flow needing to be calculated
Then under the condition of f (i, j) less than or equal to mu (i, j),
f (i, j) — f (j, i), i ≠ s or j ≠ t,
i is not equal to s or j is not equal to t; wherein f (i, j) · ci,jRepresenting the total network delay generated when the micro clouds i to j transmit the tasks, E representing a set of roadside micro cloud task transmission vector edges, f (i, j) representing the number (belt direction) of the tasks redirected from the roadside micro clouds i to j, f (j, i) representing the number (belt direction) of the tasks redirected from the roadside micro clouds i to jNumber of tasks redirected from roadside cloudlet j to i (tape direction), ci,jRepresenting edge sets of a traffic network G<i,j>S represents a virtual source node, t represents a virtual sink, VsRepresenting an overloaded collection of micro-clouds, VtRepresenting a lightly loaded set of micro-clouds, V ═ Vs∪VtAnd U { s, t } represents a roadside micro-cloud node set.
The invention is further improved in that: the total network delay is obtained by continuous iterative optimization.
Firstly, the average response time of each micro cloud under the condition of a certain task number is represented through a function, a specific value of the response time is found through dichotomy, the incoming load and the outgoing load of the micro clouds are ensured to be within a set threshold, if the average response time is smaller than the threshold, the micro clouds are in an overload state, if the average response time is larger than the threshold, the micro clouds are in a light negative state, and at the moment, the task amount on the micro clouds in the overload state can be redirected to the micro clouds in the light negative state through a network, so that the response time of the task amount in each micro cloud is infinitely close to the average response time; compared with the prior art, the method and the device can obviously reduce the maximum response time of the total micro-cloud tasks of the vehicle-mounted network and improve the resource utilization rate in the vehicle-mounted network.
Drawings
FIG. 1 is a schematic flow chart of a roadside micro-cloud load balancing optimization method according to the present invention;
FIG. 2 is a schematic diagram of a vehicle network model based on a micro cloud according to the present invention;
FIG. 3 is a schematic flow diagram of a task in the roadside micro cloud load balancing optimization method of the present invention;
FIG. 4 is a schematic view of a vector edge of nodes between micro clouds according to the present invention;
fig. 5 is a detailed flow diagram of the balancing process in the roadside cloudlet load balancing optimization method of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely illustrative of some, but not all, of the embodiments of the invention, and that the preferred embodiments of the invention are shown in the drawings. This invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, but rather should be construed as broadly as the present disclosure is set forth in order to provide a more thorough understanding thereof. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, in the embodiment of the present invention, a method for optimizing roadside cloudlet load balancing is provided, where the method includes the following steps S1: constructing a vehicle-mounted network system model based on micro-clouds arranged on the roadside; s2: under the condition that the number of tasks is set for each micro cloud, the average task response time of each micro cloud under the corresponding task is represented by using a function; s3: searching to obtain a numerical value of the average response time by using a dichotomy, and setting a threshold value for judging whether each clout has an overload condition; s4: if the micro cloud is overloaded, calculating the task flow from the overloaded micro cloud to the light load micro cloud meeting the condition by using a transmission method, and calculating the total network delay caused by redirecting the task flow; s5: and selecting the light-load micro-cloud of the optimal redirection flow according to the size of the total network delay, and ensuring that the response time of each micro-cloud under the condition of the total task number is close to the average response time.
Firstly, the average response time of each micro cloud under the condition of a certain task number is represented through a function, a specific value of the response time is found through dichotomy, the incoming load and the outgoing load of the micro clouds are ensured to be within a set threshold, if the average response time is smaller than the threshold, the micro clouds are in an overload state, if the average response time is larger than the threshold, the micro clouds are in a light negative state, and at the moment, the task amount on the micro clouds in the overload state can be redirected to the micro clouds in the light negative state through a network, so that the response time of the task amount in each micro cloud is infinitely close to the average response time; compared with the prior art, the method and the device can obviously reduce the maximum response time of the total micro-cloud tasks of the vehicle-mounted network and improve the resource utilization rate in the vehicle-mounted network.
Specifically, the roadside micro-cloud load balancing optimization method of the present invention is explained with reference to fig. 2 to 5 as follows:
referring to fig. 2, in the embodiment, it is assumed that the vehicle-mounted application dynamically transmits the task to a cloudlet closest to the vehicle, each vehicle may offload the task to an Access Point (AP) of a nearby cloudlet, and the cloudlet receiving the task may add the task to its own task processing queue or may resend the task to other cloudlets in the network; wherein, i represents a micro cloud at any position, the task average response time at the micro cloud i consists of two times: the queuing latency of tasks and the processing time of tasks, given the number of tasks of a cloudlet is λ, the function T can be usediRepresenting the mean response time of the task at the micro-cloud i, in particular, the function TiCan be driven by
It is shown that, among others,
in conjunction with fig. 3, assuming that the clouds are connected to each other and can communicate with each other, so that any one cloud with a high load can send its task stream to another cloud, in the embodiment of the present invention, f (i, j) is used to represent the number of tasks sent by cloud i to cloud j; and when i is not equal to j, the task flow number f (i, j) needs to meet the condition
And conditions
。
Referring to fig. 4, in the embodiment of the present invention, the vehicular network is represented by G, and u (i, j) represents an edge set in the network G<i，j>Is set to be phi, the size of the edge from the source node s to each overloaded micro-cloud node i is set to be phiiI.e. setting edge sets<s，j>Is equal to phiiSimilarly, set edge sets<j，t>Is equal to phij(ii) a Setting source nodes s to VsThe task transmission delay loss of the micro cloud node in (1) is 0, namely cs,jSimilarly, set V is set to 0tThe delay loss between the micro cloud node in (1) and the terminal sink is also 0, i.e. c j,t0; for collections<i，j>From the overloaded to the lightly loaded cloudlet node vector edge, u (i, j) ═ min { u (s, i), u (j, t) }, and c can be obtained as described abovei,j＝di,j。
With reference to fig. 5, the creation process of the traffic network G given the average response time of the task is described, specifically: after the traffic network G is created, the task routing problem from overloaded to lightly loaded cloudlines is transformed into the problem of finding the minimum delay maximum task traffic in the network G, with the objective being to optimize it to
And subject to the condition f (i, j) ≦ u (i, j),
f (i, j) ═ f (j, i), i ≠ s or j ≠ t and
i is not equal to s or j is not equal to t; in the formula, f (i, j) · ci,jRepresenting the total network delay generated when the micro clouds i to j transmit the tasks; wherein, the total network delay is obtained by continuous iterative optimization until the absolute value of the difference between the average response time of each micro cloud and the response time of each micro cloud after equalization is setWithin a fixed value theta, theta is a threshold value set according to actual conditions.
In the vehicle-mounted network established based on the micro cloud, the method provided by the invention can balance the workload among the plurality of micro clouds, and transfer some work of the micro cloud with large workload to some micro clouds with small workload for processing, thereby improving the efficiency of micro cloud processing.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing detailed description, or equivalent changes may be made in some of the features of the embodiments described above. All equivalent structures made by using the contents of the specification and the attached drawings of the invention can be directly or indirectly applied to other related technical fields, and are also within the protection scope of the patent of the invention.
Claims (4)
1. A method for optimizing roadside micro-cloud load balancing is characterized by comprising the following steps:
constructing a vehicle-mounted network system model based on micro-clouds arranged on the roadside;
under the condition that the number of tasks is set for each micro cloud, the average task response time of each micro cloud under the corresponding task is represented by using a function;
searching and obtaining the numerical value of the average response time by using a bisection method, and setting a threshold value for judging whether each clout has an overload condition;
if the micro cloud is overloaded, calculating the task flow from the overloaded micro cloud to the light load micro cloud meeting the condition by using a transmission method, and calculating the total network delay caused by redirecting the task flow;
and selecting the light-load micro-cloud of the optimal redirection flow according to the size of the total network delay, and ensuring that the response time of each micro-cloud under the condition of the total task number is close to the average response time.
2. A method of aligning roadside microfeatures as claimed in claim 1The cloud load balancing optimization method is characterized in that the number of tasks of each micro cloud is assumed to be lambda, and each cloud i has niA server, each server having a service rate muiThe function is TiThen can use the formula
To represent the average response time, wherein,
in the formula (I), the compound is shown in the specification,
representing a stability parameter of the system.
3. The method of claim 1, wherein computing the task traffic by the transport method is performed by optimizing the task traffic to be computed to be a load balancing optimization of the micro-clouds on the road-side
Then under the condition of f (i, j) less than or equal to mu (i, j),
f (i, j) — f (j, i), i ≠ s or j ≠ t,
i is not equal to s or j is not equal to t; wherein f (i, j) · ci,jRepresenting the total network delay generated when the micro clouds i to j transmit the tasks, E representing a set of roadside micro cloud task transmission vector edges, f (i, j) representing the number of tasks redirected from the roadside micro clouds i to j, f (j, i) representing the number of tasks redirected from the roadside micro clouds j to i, c (j, i) representing the number of tasks redirected from the roadside micro clouds j to ii,j represents the set of edges of the traffic network G<i,j>S represents a virtual source node, t represents a virtual sink, VsRepresenting an overloaded collection of micro-clouds, VtIndicating a lightnessMicro cloud set of loads, V ═ Vs∪VtAnd U { s, t } represents a roadside micro-cloud node set.
4. The method of claim 1, wherein the total network latency is obtained by continuously iterative optimization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810335686.8A CN109104455B (en) | 2018-04-16 | 2018-04-16 | Method for optimizing road edge micro-cloud load balance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810335686.8A CN109104455B (en) | 2018-04-16 | 2018-04-16 | Method for optimizing road edge micro-cloud load balance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109104455A CN109104455A (en) | 2018-12-28 |
| CN109104455B true CN109104455B (en) | 2021-06-22 |
Family
ID=64796729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810335686.8A Active CN109104455B (en) | 2018-04-16 | 2018-04-16 | Method for optimizing road edge micro-cloud load balance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109104455B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109639833B (en) * | 2019-01-25 | 2021-09-07 | 福建师范大学 | Task scheduling method based on wireless metropolitan area network micro-cloud load balancing |
| CN110445866B (en) * | 2019-08-12 | 2021-11-30 | 南京工业大学 | Task migration and cooperative load balancing method in mobile edge computing environment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129774A (en) * | 2011-04-06 | 2011-07-20 | 孙磊 | Intelligent traffic self-networking system with cloudlet function |
| CN102982408A (en) * | 2012-11-05 | 2013-03-20 | 中国电力科学研究院 | Large-scale electric car operation monitoring platform based on cloud computing |
| CN103456185A (en) * | 2013-08-27 | 2013-12-18 | 李德毅 | Relay navigation method for intelligent vehicle running in urban road |
| CN105788328A (en) * | 2016-04-25 | 2016-07-20 | 华为技术有限公司 | Road-side device or method for intelligent traffic |
| CN106131106A (en) * | 2016-06-07 | 2016-11-16 | 北京邮电大学 | A kind of thin cloud based on assembly, the network-building method of thin cloud and device |
| CN106251440A (en) * | 2016-07-28 | 2016-12-21 | 郝芊雨 | A kind of vehicle administrating system based on cloud computing |
| CN107196869A (en) * | 2017-07-14 | 2017-09-22 | 北京知道创宇信息技术有限公司 | The adaptive load balancing method, apparatus and system of Intrusion Detection based on host actual loading |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9529657B2 (en) * | 2014-02-07 | 2016-12-27 | Oracle International Corporation | Techniques for generating diagnostic identifiers to trace events and identifying related diagnostic information |
-
2018
- 2018-04-16 CN CN201810335686.8A patent/CN109104455B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129774A (en) * | 2011-04-06 | 2011-07-20 | 孙磊 | Intelligent traffic self-networking system with cloudlet function |
| CN102982408A (en) * | 2012-11-05 | 2013-03-20 | 中国电力科学研究院 | Large-scale electric car operation monitoring platform based on cloud computing |
| CN103456185A (en) * | 2013-08-27 | 2013-12-18 | 李德毅 | Relay navigation method for intelligent vehicle running in urban road |
| CN105788328A (en) * | 2016-04-25 | 2016-07-20 | 华为技术有限公司 | Road-side device or method for intelligent traffic |
| CN106131106A (en) * | 2016-06-07 | 2016-11-16 | 北京邮电大学 | A kind of thin cloud based on assembly, the network-building method of thin cloud and device |
| CN106251440A (en) * | 2016-07-28 | 2016-12-21 | 郝芊雨 | A kind of vehicle administrating system based on cloud computing |
| CN107196869A (en) * | 2017-07-14 | 2017-09-22 | 北京知道创宇信息技术有限公司 | The adaptive load balancing method, apparatus and system of Intrusion Detection based on host actual loading |
Non-Patent Citations (1)
| Title |
|---|
| Throughput maximization for online request admissions in mobile cloudlets;Xia Q等;《IEEE》;20140310;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109104455A (en) | 2018-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110198278B (en) | Lyapunov optimization method for vehicle networking cloud and edge joint task scheduling | |
| CN107995660B (en) | Joint task scheduling and resource allocation method supporting D2D-edge server unloading | |
| CN109639833B (en) | Task scheduling method based on wireless metropolitan area network micro-cloud load balancing | |
| CN111274035B (en) | Resource scheduling method and device in edge computing environment and computer equipment | |
| CN109831524B (en) | Load balancing processing method and device | |
| CN110109745A (en) | A kind of task cooperation on-line scheduling method for edge calculations environment | |
| Li et al. | Capacity-aware edge caching in fog computing networks | |
| CN110809275B (en) | Micro cloud node placement method based on wireless metropolitan area network | |
| CN113961264B (en) | Intelligent unloading algorithm and system for video monitoring cloud edge cooperation | |
| CN109104455B (en) | Method for optimizing road edge micro-cloud load balance | |
| CN110149401B (en) | Method and system for optimizing edge calculation task | |
| Li et al. | K-means based edge server deployment algorithm for edge computing environments | |
| CN111263401A (en) | Multi-user cooperative computing unloading method based on mobile edge computing | |
| Tanzil et al. | A distributed coalition game approach to femto-cloud formation | |
| CN112612553B (en) | Edge computing task unloading method based on container technology | |
| Shi et al. | Share-based edge computing paradigm with mobile-to-wired offloading computing | |
| CN113992678A (en) | Calculation migration method for offshore MEC load balancing and resource allocation joint optimization | |
| CN115396358A (en) | Route setting method, device and storage medium for computing power perception network | |
| Bute et al. | A collaborative task offloading scheme in vehicular edge computing | |
| CN113329432B (en) | Edge service arrangement method and system based on multi-objective optimization | |
| CN112235387B (en) | Multi-node cooperative computing unloading method based on energy consumption minimization | |
| CN115809148B (en) | Load balancing task scheduling method and device for edge computing | |
| Yan et al. | Fairness-aware data offloading of IoT applications enabled by heterogeneous UAVs | |
| CN108810856B (en) | M2M terminal service optimization control method | |
| Rasheed et al. | Hierarchical architecture for computational offloading in autonomous vehicle environment |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20181228 Assignee: Jiangsu Nanyou October Science Park Management Co.,Ltd. Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS Contract record no.: X2022980007683 Denomination of invention: A load balancing optimization method for roadside micro cloud Granted publication date: 20210622 License type: Common License Record date: 20220613 |
|
| EE01 | Entry into force of recordation of patent licensing contract |